system/linux
system/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux synced 2024-10-14 23:39:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf tools changes and fixes for v6.5: 2nd batch

Browse source 
Build:
 
  - Allow to generate vmlinux.h from BTF using `make GEN_VMLINUX_H=1`
    and skip if the vmlinux has no BTF.
 
  - Replace deprecated clang -target xxx option by --target=xxx.
 
 perf record:
 
  - Print event attributes with well known type and config symbols in the
    debug output like below:
 
     # perf record -e cycles,cpu-clock -C0 -vv true
     <SNIP>
     ------------------------------------------------------------
     perf_event_attr:
       type                             0 (PERF_TYPE_HARDWARE)
       size                             136
       config                           0 (PERF_COUNT_HW_CPU_CYCLES)
       { sample_period, sample_freq }   4000
       sample_type                      IP|TID|TIME|CPU|PERIOD|IDENTIFIER
       read_format                      ID
       disabled                         1
       inherit                          1
       freq                             1
       sample_id_all                    1
       exclude_guest                    1
     ------------------------------------------------------------
     sys_perf_event_open: pid -1  cpu 0  group_fd -1  flags 0x8 = 5
     ------------------------------------------------------------
     perf_event_attr:
       type                             1 (PERF_TYPE_SOFTWARE)
       size                             136
       config                           0 (PERF_COUNT_SW_CPU_CLOCK)
       { sample_period, sample_freq }   4000
       sample_type                      IP|TID|TIME|CPU|PERIOD|IDENTIFIER
       read_format                      ID
       disabled                         1
       inherit                          1
       freq                             1
       sample_id_all                    1
       exclude_guest                    1
 
  - Update AMD IBS event error message since it now support per-process
    profiling but no priviledge filters.
 
     $ sudo perf record -e ibs_op//k -C 0
     Error:
     AMD IBS doesn't support privilege filtering. Try again without
     the privilege modifiers (like 'k') at the end.
 
 perf lock contention:
 
  - Support CSV style output using -x option
 
     $ sudo perf lock con -ab -x, sleep 1
     # output: contended, total wait, max wait, avg wait, type, caller
     19, 194232, 21415, 10222, spinlock, process_one_work+0x1f0
     15, 162748, 23843, 10849, rwsem:R, do_user_addr_fault+0x40e
     4, 86740, 23415, 21685, rwlock:R, ep_poll_callback+0x2d
     1, 84281, 84281, 84281, mutex, iwl_mvm_async_handlers_wk+0x135
     8, 67608, 27404, 8451, spinlock, __queue_work+0x174
     3, 58616, 31125, 19538, rwsem:W, do_mprotect_pkey+0xff
     3, 52953, 21172, 17651, rwlock:W, do_epoll_wait+0x248
     2, 30324, 19704, 15162, rwsem:R, do_madvise+0x3ad
     1, 24619, 24619, 24619, spinlock, rcu_core+0xd4
 
  - Add --output option to save the data to a file not to be interfered
    by other debug messages.
 
 Test:
 
  - Fix event parsing test on ARM where there's no raw PMU nor supports
    PERF_PMU_CAP_EXTENDED_HW_TYPE.
 
  - Update the lock contention test case for CSV output.
 
  - Fix a segfault in the daemon command test.
 
 Vendor events (JSON):
 
  - Add has_event() to check if the given event is available on system
    at runtime.  On Intel machines, some transaction events may not be
    present when TSC extensions are disabled.
 
  - Update Intel event metrics.
 
 Misc:
 
  - Sort symbols by name using an external array of pointers instead of
    a rbtree node in the symbol.  This will save 16-bytes or 24-bytes
    per symbol whether the sorting is actually requested or not.
 
  - Fix unwinding DWARF callstacks using libdw when --symfs option is
    used.
 
 Signed-off-by: Namhyung Kim <namhyung@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQSo2x5BnqMqsoHtzsmMstVUGiXMgwUCZKb4mwAKCRCMstVUGiXM
 g1QqAPwKZow/DhAzyN7KvzdNd+SojRGpUMl6RkVphY/9ntDqPAD+L3V5aXLTiC1L
 8kUzdpRX5VMjqdR9U7TycUOi4QU40QA=
 =dEF1
 -----END PGP SIGNATURE-----

Merge tag 'perf-tools-for-v6.5-2-2023-07-06' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next

Pull more perf tools updates from Namhyung Kim:
 "These are remaining changes and fixes for this cycle.

  Build:

   - Allow generating vmlinux.h from BTF using `make GEN_VMLINUX_H=1`
     and skip if the vmlinux has no BTF.

   - Replace deprecated clang -target xxx option by --target=xxx.

  perf record:

   - Print event attributes with well known type and config symbols in
     the debug output like below:

       # perf record -e cycles,cpu-clock -C0 -vv true
       <SNIP>
       ------------------------------------------------------------
       perf_event_attr:
         type                             0 (PERF_TYPE_HARDWARE)
         size                             136
         config                           0 (PERF_COUNT_HW_CPU_CYCLES)
         { sample_period, sample_freq }   4000
         sample_type                      IP|TID|TIME|CPU|PERIOD|IDENTIFIER
         read_format                      ID
         disabled                         1
         inherit                          1
         freq                             1
         sample_id_all                    1
         exclude_guest                    1
       ------------------------------------------------------------
       sys_perf_event_open: pid -1  cpu 0  group_fd -1  flags 0x8 = 5
       ------------------------------------------------------------
       perf_event_attr:
         type                             1 (PERF_TYPE_SOFTWARE)
         size                             136
         config                           0 (PERF_COUNT_SW_CPU_CLOCK)
         { sample_period, sample_freq }   4000
         sample_type                      IP|TID|TIME|CPU|PERIOD|IDENTIFIER
         read_format                      ID
         disabled                         1
         inherit                          1
         freq                             1
         sample_id_all                    1
         exclude_guest                    1

   - Update AMD IBS event error message since it now support per-process
     profiling but no priviledge filters.

       $ sudo perf record -e ibs_op//k -C 0
       Error:
       AMD IBS doesn't support privilege filtering. Try again without
       the privilege modifiers (like 'k') at the end.

  perf lock contention:

   - Support CSV style output using -x option

       $ sudo perf lock con -ab -x, sleep 1
       # output: contended, total wait, max wait, avg wait, type, caller
       19, 194232, 21415, 10222, spinlock, process_one_work+0x1f0
       15, 162748, 23843, 10849, rwsem:R, do_user_addr_fault+0x40e
       4, 86740, 23415, 21685, rwlock:R, ep_poll_callback+0x2d
       1, 84281, 84281, 84281, mutex, iwl_mvm_async_handlers_wk+0x135
       8, 67608, 27404, 8451, spinlock, __queue_work+0x174
       3, 58616, 31125, 19538, rwsem:W, do_mprotect_pkey+0xff
       3, 52953, 21172, 17651, rwlock:W, do_epoll_wait+0x248
       2, 30324, 19704, 15162, rwsem:R, do_madvise+0x3ad
       1, 24619, 24619, 24619, spinlock, rcu_core+0xd4

   - Add --output option to save the data to a file not to be interfered
     by other debug messages.

  Test:

   - Fix event parsing test on ARM where there's no raw PMU nor supports
     PERF_PMU_CAP_EXTENDED_HW_TYPE.

   - Update the lock contention test case for CSV output.

   - Fix a segfault in the daemon command test.

  Vendor events (JSON):

   - Add has_event() to check if the given event is available on system
     at runtime. On Intel machines, some transaction events may not be
     present when TSC extensions are disabled.

   - Update Intel event metrics.

  Misc:

   - Sort symbols by name using an external array of pointers instead of
     a rbtree node in the symbol. This will save 16-bytes or 24-bytes
     per symbol whether the sorting is actually requested or not.

   - Fix unwinding DWARF callstacks using libdw when --symfs option is
     used"

* tag 'perf-tools-for-v6.5-2-2023-07-06' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next: (38 commits)
  perf test: Fix event parsing test when PERF_PMU_CAP_EXTENDED_HW_TYPE isn't supported.
  perf test: Fix event parsing test on Arm
  perf evsel amd: Fix IBS error message
  perf: unwind: Fix symfs with libdw
  perf symbol: Fix uninitialized return value in symbols__find_by_name()
  perf test: Test perf lock contention CSV output
  perf lock contention: Add --output option
  perf lock contention: Add -x option for CSV style output
  perf lock: Remove stale comments
  perf vendor events intel: Update tigerlake to 1.13
  perf vendor events intel: Update skylakex to 1.31
  perf vendor events intel: Update skylake to 57
  perf vendor events intel: Update sapphirerapids to 1.14
  perf vendor events intel: Update icelakex to 1.21
  perf vendor events intel: Update icelake to 1.19
  perf vendor events intel: Update cascadelakex to 1.19
  perf vendor events intel: Update meteorlake to 1.03
  perf vendor events intel: Add rocketlake events/metrics
  perf vendor metrics intel: Make transaction metrics conditional
  perf jevents: Support for has_event function
  ...
This commit is contained in:
Linus Torvalds 2023-07-08 10:21:51 -07:00
parent ad8258e877 bcd981db12
commit c206353dfd
95 changed files with 9319 additions and 451 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
tools/perf/Documentation/perf-config.txt
View file

@ -669,7 +669,7 @@ llvm.*::
"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
"-Wno-unused-value -Wno-pointer-sign " \
"-working-directory $WORKING_DIR " \
"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
"-c \"$CLANG_SOURCE\" --target=bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
llvm.clang-opt::
Options passed to clang.

8
tools/perf/Documentation/perf-lock.txt
View file

@ -36,6 +36,9 @@ COMMON OPTIONS
--input=<file>::
Input file name. (default: perf.data unless stdin is a fifo)
--output=<file>::
Output file name for perf lock contention and report.
-v::
--verbose::
Be more verbose (show symbol address, etc).
@ -200,6 +203,11 @@ CONTENTION OPTIONS
Note that it matches the substring so 'rq' would match both 'raw_spin_rq_lock'
and 'irq_enter_rcu'.
-x::
--field-separator=<SEP>::
Show results using a CSV-style output to make it easy to import directly
into spreadsheets. Columns are separated by the string specified in SEP.
SEE ALSO
--------

17
tools/perf/Makefile.config
View file

@ -315,6 +315,9 @@ FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
FEATURE_CHECK_LDFLAGS-libaio = -lrt
FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl
FEATURE_CHECK_LDFLAGS-disassembler-init-styled = -lbfd -lopcodes -ldl
CORE_CFLAGS += -fno-omit-frame-pointer
CORE_CFLAGS += -ggdb3
CORE_CFLAGS += -funwind-tables
@ -344,8 +347,8 @@ ifneq ($(TCMALLOC),)
endif
ifeq ($(FEATURES_DUMP),)
# We will display at the end of this Makefile.config, using $(call feature_display_entries),
# as we may retry some feature detection here.
# We will display at the end of this Makefile.config, using $(call feature_display_entries)
# As we may retry some feature detection here, see the disassembler-four-args case, for instance
FEATURE_DISPLAY_DEFERRED := 1
include $(srctree)/tools/build/Makefile.feature
else
@ -680,6 +683,10 @@ ifdef BUILD_BPF_SKEL
CFLAGS += -DHAVE_BPF_SKEL
endif
ifndef GEN_VMLINUX_H
VMLINUX_H=$(src-perf)/util/bpf_skel/vmlinux/vmlinux.h
endif
dwarf-post-unwind := 1
dwarf-post-unwind-text := BUG
@ -903,9 +910,13 @@ ifdef BUILD_NONDISTRO
ifeq ($(feature-libbfd-liberty), 1)
EXTLIBS += -lbfd -lopcodes -liberty
FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -ldl
FEATURE_CHECK_LDFLAGS-disassembler-init-styled += -liberty -ldl
else
ifeq ($(feature-libbfd-liberty-z), 1)
EXTLIBS += -lbfd -lopcodes -liberty -lz
FEATURE_CHECK_LDFLAGS-disassembler-four-args += -liberty -lz -ldl
FEATURE_CHECK_LDFLAGS-disassembler-init-styled += -liberty -lz -ldl
endif
endif
$(call feature_check,disassembler-four-args)
@ -1329,6 +1340,6 @@ endif
# re-generate FEATURE-DUMP as we may have called feature_check, found out
# extra libraries to add to LDFLAGS of some other test and then redo those
# tests.
# tests, see the block about libbfd, disassembler-four-args, for instance.
$(shell rm -f $(FEATURE_DUMP_FILENAME))
$(foreach feat,$(FEATURE_TESTS),$(shell echo "$(call feature_assign,$(feat))" >> $(FEATURE_DUMP_FILENAME)))

45
tools/perf/Makefile.perf
View file

@ -132,6 +132,8 @@ include ../scripts/utilities.mak
# Define EXTRA_TESTS to enable building extra tests useful mainly to perf
# developers, such as:
# x86 instruction decoder - new instructions test
#
# Define GEN_VMLINUX_H to generate vmlinux.h from the BTF.
# As per kernel Makefile, avoid funny character set dependencies
unexport LC_ALL
@ -197,6 +199,7 @@ FLEX ?= flex
BISON ?= bison
STRIP = strip
AWK = awk
READELF ?= readelf
# include Makefile.config by default and rule out
# non-config cases
@ -1061,7 +1064,7 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_
ifdef BUILD_BPF_SKEL
BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool
# Get Clang's default includes on this system, as opposed to those seen by
# '-target bpf'. This fixes "missing" files on some architectures/distros,
# '--target=bpf'. This fixes "missing" files on some architectures/distros,
# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
#
# Use '-idirafter': Don't interfere with include mechanics except where the
@ -1084,8 +1087,44 @@ $(BPFTOOL): | $(SKEL_TMP_OUT)
$(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \
OUTPUT=$(SKEL_TMP_OUT)/ bootstrap
$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT)
$(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \
# Paths to search for a kernel to generate vmlinux.h from.
VMLINUX_BTF_ELF_PATHS ?= $(if $(O),$(O)/vmlinux) \
$(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \
../../vmlinux \
/boot/vmlinux-$(shell uname -r)
# Paths to BTF information.
VMLINUX_BTF_BTF_PATHS ?= /sys/kernel/btf/vmlinux
# Filter out kernels that don't exist or without a BTF section.
VMLINUX_BTF_ELF_ABSPATHS ?= $(abspath $(wildcard $(VMLINUX_BTF_ELF_PATHS)))
VMLINUX_BTF_PATHS ?= $(shell for file in $(VMLINUX_BTF_ELF_ABSPATHS); \
do \
if [ -f $$file ] && ($(READELF) -S "$$file" | grep -q .BTF); \
then \
echo "$$file"; \
fi; \
done) \
$(wildcard $(VMLINUX_BTF_BTF_PATHS))
# Select the first as the source of vmlinux.h.
VMLINUX_BTF ?= $(firstword $(VMLINUX_BTF_PATHS))
ifeq ($(VMLINUX_H),)
ifeq ($(VMLINUX_BTF),)
$(error Missing bpftool input for generating vmlinux.h)
endif
endif
$(SKEL_OUT)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL)
ifeq ($(VMLINUX_H),)
$(QUIET_GEN)$(BPFTOOL) btf dump file $< format c > $@
else
$(Q)cp "$(VMLINUX_H)" $@
endif
$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) $(SKEL_OUT)/vmlinux.h | $(SKEL_TMP_OUT)
$(QUIET_CLANG)$(CLANG) -g -O2 --target=bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \
-c $(filter util/bpf_skel/%.bpf.c,$^) -o $@
$(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL)

20
tools/perf/arch/x86/util/evsel.c
View file

@ -102,3 +102,23 @@ void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr)
}
}
}
int arch_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size)
{
if (!x86__is_amd_cpu())
return 0;
if (!evsel->core.attr.precise_ip &&
!(evsel->pmu_name && !strncmp(evsel->pmu_name, "ibs", 3)))
return 0;
/* More verbose IBS errors. */
if (evsel->core.attr.exclude_kernel || evsel->core.attr.exclude_user ||
evsel->core.attr.exclude_hv || evsel->core.attr.exclude_idle ||
evsel->core.attr.exclude_host || evsel->core.attr.exclude_guest) {
return scnprintf(msg, size, "AMD IBS doesn't support privilege filtering. Try "
"again without the privilege modifiers (like 'k') at the end.");
}
return 0;
}

2
tools/perf/builtin-daemon.c
View file

@ -1524,7 +1524,7 @@ int cmd_daemon(int argc, const char **argv)
if (argc) {
if (!strcmp(argv[0], "start"))
ret = __cmd_start(&__daemon, daemon_options, argc, argv);
if (!strcmp(argv[0], "signal"))
else if (!strcmp(argv[0], "signal"))
ret = __cmd_signal(&__daemon, daemon_options, argc, argv);
else if (!strcmp(argv[0], "stop"))
ret = __cmd_stop(&__daemon, daemon_options, argc, argv);

1
tools/perf/builtin-kallsyms.c
View file

@ -62,7 +62,6 @@ int cmd_kallsyms(int argc, const char **argv)
if (argc < 1)
usage_with_options(kallsyms_usage, options);
symbol_conf.sort_by_name = true;
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
if (symbol__init(NULL) < 0)
return -1;

385
tools/perf/builtin-lock.c
View file

@ -27,6 +27,7 @@
#include "util/map.h"
#include "util/util.h"
#include <stdio.h>
#include <sys/types.h>
#include <sys/prctl.h>
#include <semaphore.h>
@ -65,6 +66,8 @@ static int max_stack_depth = CONTENTION_STACK_DEPTH;
static int stack_skip = CONTENTION_STACK_SKIP;
static int print_nr_entries = INT_MAX / 2;
static LIST_HEAD(callstack_filters);
static const char *output_name = NULL;
static FILE *lock_output;
struct callstack_filter {
struct list_head list;
@ -225,22 +228,28 @@ static void lock_stat_key_print_time(unsigned long long nsec, int len)
{ 0, NULL },
};
/* for CSV output */
if (len == 0) {
fprintf(lock_output, "%llu", nsec);
return;
}
for (int i = 0; table[i].unit; i++) {
if (nsec < table[i].base)
continue;
pr_info("%*.2f %s", len - 3, nsec / table[i].base, table[i].unit);
fprintf(lock_output, "%*.2f %s", len - 3, nsec / table[i].base, table[i].unit);
return;
}
pr_info("%*llu %s", len - 3, nsec, "ns");
fprintf(lock_output, "%*llu %s", len - 3, nsec, "ns");
}
#define PRINT_KEY(member) \
static void lock_stat_key_print_ ## member(struct lock_key *key, \
struct lock_stat *ls) \
{ \
pr_info("%*llu", key->len, (unsigned long long)ls->member); \
fprintf(lock_output, "%*llu", key->len, (unsigned long long)ls->member);\
}
#define PRINT_TIME(member) \
@ -1329,12 +1338,12 @@ static void print_bad_events(int bad, int total)
if (quiet || total == 0 || (broken == 0 && verbose <= 0))
return;
pr_info("\n=== output for debug ===\n\n");
pr_info("bad: %d, total: %d\n", bad, total);
pr_info("bad rate: %.2f %%\n", (double)bad / (double)total * 100);
pr_info("histogram of events caused bad sequence\n");
fprintf(lock_output, "\n=== output for debug ===\n\n");
fprintf(lock_output, "bad: %d, total: %d\n", bad, total);
fprintf(lock_output, "bad rate: %.2f %%\n", (double)bad / (double)total * 100);
fprintf(lock_output, "histogram of events caused bad sequence\n");
for (i = 0; i < BROKEN_MAX; i++)
pr_info(" %10s: %d\n", name[i], bad_hist[i]);
fprintf(lock_output, " %10s: %d\n", name[i], bad_hist[i]);
}
/* TODO: various way to print, coloring, nano or milli sec */
@ -1346,10 +1355,10 @@ static void print_result(void)
int bad, total, printed;
if (!quiet) {
pr_info("%20s ", "Name");
fprintf(lock_output, "%20s ", "Name");
list_for_each_entry(key, &lock_keys, list)
pr_info("%*s ", key->len, key->header);
pr_info("\n\n");
fprintf(lock_output, "%*s ", key->len, key->header);
fprintf(lock_output, "\n\n");
}
bad = total = printed = 0;
@ -1374,7 +1383,7 @@ static void print_result(void)
name = thread__comm_str(t);
}
pr_info("%20s ", name);
fprintf(lock_output, "%20s ", name);
} else {
strncpy(cut_name, st->name, 16);
cut_name[16] = '.';
@ -1382,14 +1391,14 @@ static void print_result(void)
cut_name[18] = '.';
cut_name[19] = '\0';
/* cut off name for saving output style */
pr_info("%20s ", cut_name);
fprintf(lock_output, "%20s ", cut_name);
}
list_for_each_entry(key, &lock_keys, list) {
key->print(key, st);
pr_info(" ");
fprintf(lock_output, " ");
}
pr_info("\n");
fprintf(lock_output, "\n");
if (++printed >= print_nr_entries)
break;
@ -1406,13 +1415,13 @@ static void dump_threads(void)
struct rb_node *node;
struct thread *t;
pr_info("%10s: comm\n", "Thread ID");
fprintf(lock_output, "%10s: comm\n", "Thread ID");
node = rb_first(&thread_stats);
while (node) {
st = container_of(node, struct thread_stat, rb);
t = perf_session__findnew(session, st->tid);
pr_info("%10d: %s\n", st->tid, thread__comm_str(t));
fprintf(lock_output, "%10d: %s\n", st->tid, thread__comm_str(t));
node = rb_next(node);
thread__put(t);
}
@ -1438,7 +1447,7 @@ static void dump_map(void)
unsigned int i;
struct lock_stat *st;
pr_info("Address of instance: name of class\n");
fprintf(lock_output, "Address of instance: name of class\n");
for (i = 0; i < LOCKHASH_SIZE; i++) {
hlist_for_each_entry(st, &lockhash_table[i], hash_entry) {
insert_to_result(st, compare_maps);
@ -1446,7 +1455,7 @@ static void dump_map(void)
}
while ((st = pop_from_result()))
pr_info(" %#llx: %s\n", (unsigned long long)st->addr, st->name);
fprintf(lock_output, " %#llx: %s\n", (unsigned long long)st->addr, st->name);
}
static int dump_info(void)
@ -1626,58 +1635,242 @@ static void sort_contention_result(void)
sort_result();
}
static void print_bpf_events(int total, struct lock_contention_fails *fails)
static void print_header_stdio(void)
{
struct lock_key *key;
list_for_each_entry(key, &lock_keys, list)
fprintf(lock_output, "%*s ", key->len, key->header);
switch (aggr_mode) {
case LOCK_AGGR_TASK:
fprintf(lock_output, " %10s %s\n\n", "pid",
show_lock_owner ? "owner" : "comm");
break;
case LOCK_AGGR_CALLER:
fprintf(lock_output, " %10s %s\n\n", "type", "caller");
break;
case LOCK_AGGR_ADDR:
fprintf(lock_output, " %16s %s\n\n", "address", "symbol");
break;
default:
break;
}
}
static void print_header_csv(const char *sep)
{
struct lock_key *key;
fprintf(lock_output, "# output: ");
list_for_each_entry(key, &lock_keys, list)
fprintf(lock_output, "%s%s ", key->header, sep);
switch (aggr_mode) {
case LOCK_AGGR_TASK:
fprintf(lock_output, "%s%s %s\n", "pid", sep,
show_lock_owner ? "owner" : "comm");
break;
case LOCK_AGGR_CALLER:
fprintf(lock_output, "%s%s %s", "type", sep, "caller");
if (verbose > 0)
fprintf(lock_output, "%s %s", sep, "stacktrace");
fprintf(lock_output, "\n");
break;
case LOCK_AGGR_ADDR:
fprintf(lock_output, "%s%s %s%s %s\n", "address", sep, "symbol", sep, "type");
break;
default:
break;
}
}
static void print_header(void)
{
if (!quiet) {
if (symbol_conf.field_sep)
print_header_csv(symbol_conf.field_sep);
else
print_header_stdio();
}
}
static void print_lock_stat_stdio(struct lock_contention *con, struct lock_stat *st)
{
struct lock_key *key;
struct thread *t;
int pid;
list_for_each_entry(key, &lock_keys, list) {
key->print(key, st);
fprintf(lock_output, " ");
}
switch (aggr_mode) {
case LOCK_AGGR_CALLER:
fprintf(lock_output, " %10s %s\n", get_type_str(st->flags), st->name);
break;
case LOCK_AGGR_TASK:
pid = st->addr;
t = perf_session__findnew(session, pid);
fprintf(lock_output, " %10d %s\n",
pid, pid == -1 ? "Unknown" : thread__comm_str(t));
break;
case LOCK_AGGR_ADDR:
fprintf(lock_output, " %016llx %s (%s)\n", (unsigned long long)st->addr,
st->name, get_type_name(st->flags));
break;
default:
break;
}
if (aggr_mode == LOCK_AGGR_CALLER && verbose > 0) {
struct map *kmap;
struct symbol *sym;
char buf[128];
u64 ip;
for (int i = 0; i < max_stack_depth; i++) {
if (!st->callstack || !st->callstack[i])
break;
ip = st->callstack[i];
sym = machine__find_kernel_symbol(con->machine, ip, &kmap);
get_symbol_name_offset(kmap, sym, ip, buf, sizeof(buf));
fprintf(lock_output, "\t\t\t%#lx %s\n", (unsigned long)ip, buf);
}
}
}
static void print_lock_stat_csv(struct lock_contention *con, struct lock_stat *st,
const char *sep)
{
struct lock_key *key;
struct thread *t;
int pid;
list_for_each_entry(key, &lock_keys, list) {
key->print(key, st);
fprintf(lock_output, "%s ", sep);
}
switch (aggr_mode) {
case LOCK_AGGR_CALLER:
fprintf(lock_output, "%s%s %s", get_type_str(st->flags), sep, st->name);
if (verbose <= 0)
fprintf(lock_output, "\n");
break;
case LOCK_AGGR_TASK:
pid = st->addr;
t = perf_session__findnew(session, pid);
fprintf(lock_output, "%d%s %s\n", pid, sep,
pid == -1 ? "Unknown" : thread__comm_str(t));
break;
case LOCK_AGGR_ADDR:
fprintf(lock_output, "%llx%s %s%s %s\n", (unsigned long long)st->addr, sep,
st->name, sep, get_type_name(st->flags));
break;
default:
break;
}
if (aggr_mode == LOCK_AGGR_CALLER && verbose > 0) {
struct map *kmap;
struct symbol *sym;
char buf[128];
u64 ip;
for (int i = 0; i < max_stack_depth; i++) {
if (!st->callstack || !st->callstack[i])
break;
ip = st->callstack[i];
sym = machine__find_kernel_symbol(con->machine, ip, &kmap);
get_symbol_name_offset(kmap, sym, ip, buf, sizeof(buf));
fprintf(lock_output, "%s %#lx %s", i ? ":" : sep, (unsigned long) ip, buf);
}
fprintf(lock_output, "\n");
}
}
static void print_lock_stat(struct lock_contention *con, struct lock_stat *st)
{
if (symbol_conf.field_sep)
print_lock_stat_csv(con, st, symbol_conf.field_sep);
else
print_lock_stat_stdio(con, st);
}
static void print_footer_stdio(int total, int bad, struct lock_contention_fails *fails)
{
/* Output for debug, this have to be removed */
int broken = fails->task + fails->stack + fails->time + fails->data;
if (!use_bpf)
print_bad_events(bad, total);
if (quiet || total == 0 || (broken == 0 && verbose <= 0))
return;
total += broken;
pr_info("\n=== output for debug ===\n\n");
pr_info("bad: %d, total: %d\n", broken, total);
pr_info("bad rate: %.2f %%\n", (double)broken / (double)total * 100);
fprintf(lock_output, "\n=== output for debug ===\n\n");
fprintf(lock_output, "bad: %d, total: %d\n", broken, total);
fprintf(lock_output, "bad rate: %.2f %%\n", 100.0 * broken / total);
pr_info("histogram of failure reasons\n");
pr_info(" %10s: %d\n", "task", fails->task);
pr_info(" %10s: %d\n", "stack", fails->stack);
pr_info(" %10s: %d\n", "time", fails->time);
pr_info(" %10s: %d\n", "data", fails->data);
fprintf(lock_output, "histogram of failure reasons\n");
fprintf(lock_output, " %10s: %d\n", "task", fails->task);
fprintf(lock_output, " %10s: %d\n", "stack", fails->stack);
fprintf(lock_output, " %10s: %d\n", "time", fails->time);
fprintf(lock_output, " %10s: %d\n", "data", fails->data);
}
static void print_footer_csv(int total, int bad, struct lock_contention_fails *fails,
const char *sep)
{
/* Output for debug, this have to be removed */
if (use_bpf)
bad = fails->task + fails->stack + fails->time + fails->data;
if (quiet || total == 0 || (bad == 0 && verbose <= 0))
return;
total += bad;
fprintf(lock_output, "# debug: total=%d%s bad=%d", total, sep, bad);
if (use_bpf) {
fprintf(lock_output, "%s bad_%s=%d", sep, "task", fails->task);
fprintf(lock_output, "%s bad_%s=%d", sep, "stack", fails->stack);
fprintf(lock_output, "%s bad_%s=%d", sep, "time", fails->time);
fprintf(lock_output, "%s bad_%s=%d", sep, "data", fails->data);
} else {
int i;
const char *name[4] = { "acquire", "acquired", "contended", "release" };
for (i = 0; i < BROKEN_MAX; i++)
fprintf(lock_output, "%s bad_%s=%d", sep, name[i], bad_hist[i]);
}
fprintf(lock_output, "\n");
}
static void print_footer(int total, int bad, struct lock_contention_fails *fails)
{
if (symbol_conf.field_sep)
print_footer_csv(total, bad, fails, symbol_conf.field_sep);
else
print_footer_stdio(total, bad, fails);
}
static void print_contention_result(struct lock_contention *con)
{
struct lock_stat *st;
struct lock_key *key;
int bad, total, printed;
if (!quiet) {
list_for_each_entry(key, &lock_keys, list)
pr_info("%*s ", key->len, key->header);
switch (aggr_mode) {
case LOCK_AGGR_TASK:
pr_info(" %10s %s\n\n", "pid",
show_lock_owner ? "owner" : "comm");
break;
case LOCK_AGGR_CALLER:
pr_info(" %10s %s\n\n", "type", "caller");
break;
case LOCK_AGGR_ADDR:
pr_info(" %16s %s\n\n", "address", "symbol");
break;
default:
break;
}
}
if (!quiet)
print_header();
bad = total = printed = 0;
while ((st = pop_from_result())) {
struct thread *t;
int pid;
total += use_bpf ? st->nr_contended : 1;
if (st->broken)
bad++;
@ -1685,45 +1878,7 @@ static void print_contention_result(struct lock_contention *con)
if (!st->wait_time_total)
continue;
list_for_each_entry(key, &lock_keys, list) {
key->print(key, st);
pr_info(" ");
}
switch (aggr_mode) {
case LOCK_AGGR_CALLER:
pr_info(" %10s %s\n", get_type_str(st->flags), st->name);
break;
case LOCK_AGGR_TASK:
pid = st->addr;
t = perf_session__findnew(session, pid);
pr_info(" %10d %s\n",
pid, pid == -1 ? "Unknown" : thread__comm_str(t));
break;
case LOCK_AGGR_ADDR:
pr_info(" %016llx %s (%s)\n", (unsigned long long)st->addr,
st->name, get_type_name(st->flags));
break;
default:
break;
}
if (aggr_mode == LOCK_AGGR_CALLER && verbose > 0) {
struct map *kmap;
struct symbol *sym;
char buf[128];
u64 ip;
for (int i = 0; i < max_stack_depth; i++) {
if (!st->callstack || !st->callstack[i])
break;
ip = st->callstack[i];
sym = machine__find_kernel_symbol(con->machine, ip, &kmap);
get_symbol_name_offset(kmap, sym, ip, buf, sizeof(buf));
pr_info("\t\t\t%#lx %s\n", (unsigned long)ip, buf);
}
}
print_lock_stat(con, st);
if (++printed >= print_nr_entries)
break;
@ -1740,10 +1895,7 @@ static void print_contention_result(struct lock_contention *con)
/* some entries are collected but hidden by the callstack filter */
total += con->nr_filtered;
if (use_bpf)
print_bpf_events(total, &con->fails);
else
print_bad_events(bad, total);
print_footer(total, bad, &con->fails);
}
static bool force;
@ -1773,8 +1925,6 @@ static int __cmd_report(bool display_info)
return PTR_ERR(session);
}
/* for lock function check */
symbol_conf.sort_by_name = true;
symbol_conf.allow_aliases = true;
symbol__init(&session->header.env);
@ -1849,6 +1999,16 @@ static int check_lock_contention_options(const struct option *options,
return -1;
}
if (symbol_conf.field_sep) {
if (strstr(symbol_conf.field_sep, ":") || /* part of type flags */
strstr(symbol_conf.field_sep, "+") || /* part of caller offset */
strstr(symbol_conf.field_sep, ".")) { /* can be in a symbol name */
pr_err("Cannot use the separator that is already used\n");
parse_options_usage(usage, options, "x", 1);
return -1;
}
}
if (show_lock_owner)
show_thread_stats = true;
@ -1903,8 +2063,6 @@ static int __cmd_contention(int argc, const char **argv)
if (con.aggr_mode == LOCK_AGGR_CALLER)
con.save_callstack = true;
/* for lock function check */
symbol_conf.sort_by_name = true;
symbol_conf.allow_aliases = true;
symbol__init(&session->header.env);
@ -1966,6 +2124,15 @@ static int __cmd_contention(int argc, const char **argv)
if (select_key(true))
goto out_delete;
if (symbol_conf.field_sep) {
int i;
struct lock_key *keys = contention_keys;
/* do not align output in CSV format */
for (i = 0; keys[i].name; i++)
keys[i].len = 0;
}
if (use_bpf) {
lock_contention_start();
if (argc)
@ -2264,10 +2431,29 @@ static int parse_call_stack(const struct option *opt __maybe_unused, const char
return ret;
}
static int parse_output(const struct option *opt __maybe_unused, const char *str,
int unset __maybe_unused)
{
const char **name = (const char **)opt->value;
if (str == NULL)
return -1;
lock_output = fopen(str, "w");
if (lock_output == NULL) {
pr_err("Cannot open %s\n", str);
return -1;
}
*name = str;
return 0;
}
int cmd_lock(int argc, const char **argv)
{
const struct option lock_options[] = {
OPT_STRING('i', "input", &input_name, "file", "input file name"),
OPT_CALLBACK(0, "output", &output_name, "file", "output file name", parse_output),
OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"),
OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
@ -2334,6 +2520,8 @@ int cmd_lock(int argc, const char **argv)
OPT_CALLBACK('S', "callstack-filter", NULL, "NAMES",
"Filter specific function in the callstack", parse_call_stack),
OPT_BOOLEAN('o', "lock-owner", &show_lock_owner, "show lock owners instead of waiters"),
OPT_STRING_NOEMPTY('x', "field-separator", &symbol_conf.field_sep, "separator",
"print result in CSV format with custom separator"),
OPT_PARENT(lock_options)
};
@ -2365,6 +2553,7 @@ int cmd_lock(int argc, const char **argv)
for (i = 0; i < LOCKHASH_SIZE; i++)
INIT_HLIST_HEAD(lockhash_table + i);
lock_output = stderr;
argc = parse_options_subcommand(argc, argv, lock_options, lock_subcommands,
lock_usage, PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc)

1
tools/perf/builtin-report.c
View file

@ -1676,7 +1676,6 @@ int cmd_report(int argc, const char **argv)
* See symbol__browser_index.
*/
symbol_conf.priv_size += sizeof(u32);
symbol_conf.sort_by_name = true;
}
annotation_config__init(&report.annotation_opts);
}

8
tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
View file

@ -92,28 +92,28 @@
},
{
"BriefDescription": "Percentage of cycles in aborted transactions.",
"MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles",
"MetricExpr": "(max(cycles\\-t - cycles\\-ct, 0) / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_aborted_cycles",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of elisions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@",
"MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_elision",
"ScaleUnit": "1cycles / elision"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of transactions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@",
"MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_transaction",
"ScaleUnit": "1cycles / transaction"
},
{
"BriefDescription": "Percentage of cycles within a transaction region.",
"MetricExpr": "cpu@cycles\\-t@ / cycles",
"MetricExpr": "(cycles\\-t / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_transactional_cycles",
"ScaleUnit": "100%"

8
tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
View file

@ -1830,28 +1830,28 @@
},
{
"BriefDescription": "Percentage of cycles in aborted transactions.",
"MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles",
"MetricExpr": "(max(cycles\\-t - cycles\\-ct, 0) / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_aborted_cycles",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of elisions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@",
"MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_elision",
"ScaleUnit": "1cycles / elision"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of transactions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@",
"MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_transaction",
"ScaleUnit": "1cycles / transaction"
},
{
"BriefDescription": "Percentage of cycles within a transaction region.",
"MetricExpr": "cpu@cycles\\-t@ / cycles",
"MetricExpr": "(cycles\\-t / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_transactional_cycles",
"ScaleUnit": "100%"

43
tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json
View file

@ -7,6 +7,14 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to ILD_STALL.LCP]",
"EventCode": "0x87",
"EventName": "DECODE.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to ILD_STALL.LCP]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches",
"EventCode": "0xAB",
@ -245,27 +253,34 @@
"UMask": "0x2"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_STALL",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.DSB_CYCLES_OK]",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
"PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop [This event is alias to IDQ.DSB_CYCLES_ANY]",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_ANY]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
@ -296,6 +311,24 @@
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop [This event is alias to IDQ.ALL_DSB_CYCLES_ANY_UOPS]",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_ANY_UOPS]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
"PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"EventCode": "0x79",

17
tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json
View file

@ -361,10 +361,10 @@
"UMask": "0x1"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to DECODE.LCP]",
"EventCode": "0x87",
"EventName": "ILD_STALL.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to DECODE.LCP]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
@ -488,11 +488,11 @@
"UMask": "0x1"
},
{
"BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
"BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder. [This event is alias to LSD.CYCLES_OK]",
"CounterMask": "4",
"EventCode": "0xA8",
"EventName": "LSD.CYCLES_4_UOPS",
"PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
"PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector). [This event is alias to LSD.CYCLES_OK]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
@ -505,6 +505,15 @@
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder. [This event is alias to LSD.CYCLES_4_UOPS]",
"CounterMask": "4",
"EventCode": "0xA8",
"EventName": "LSD.CYCLES_OK",
"PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector). [This event is alias to LSD.CYCLES_4_UOPS]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of Uops delivered by the LSD.",
"EventCode": "0xA8",

2
tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json
View file

@ -6606,7 +6606,7 @@
"EventCode": "0x52",
"EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS",
"PerPkg": "1",
"PublicDescription": "ad and bl messages were actually slotted into the same flit in paralle",
"PublicDescription": "ad and bl messages were actually slotted into the same flit in parallel",
"UMask": "0x8",
"Unit": "M3UPI"
},

2
tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json
View file

@ -2735,7 +2735,7 @@
"EventCode": "0x81",
"EventName": "UNC_M_WPQ_OCCUPANCY",
"PerPkg": "1",
"PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts?",
"PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.",
"Unit": "iMC"
},
{

8
tools/perf/pmu-events/arch/x86/icelake/cache.json
View file

@ -155,18 +155,18 @@
"UMask": "0x21"
},
{
"BriefDescription": "All requests that miss L2 cache. This event is not supported on ICL and ICX products, only supported on RKL products.",
"BriefDescription": "This event is deprecated.",
"Deprecated": "1",
"EventCode": "0x24",
"EventName": "L2_RQSTS.MISS",
"PublicDescription": "Counts all requests that miss L2 cache. This event is not supported on ICL and ICX products, only supported on RKL products.",
"SampleAfterValue": "200003",
"UMask": "0x3f"
},
{
"BriefDescription": "All L2 requests. This event is not supported on ICL and ICX products, only supported on RKL products.",
"BriefDescription": "This event is deprecated.",
"Deprecated": "1",
"EventCode": "0x24",
"EventName": "L2_RQSTS.REFERENCES",
"PublicDescription": "Counts all L2 requests. This event is not supported on ICL and ICX products, only supported on RKL products.",
"SampleAfterValue": "200003",
"UMask": "0xff"
},

32
tools/perf/pmu-events/arch/x86/icelake/frontend.json
View file

@ -7,6 +7,14 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to ILD_STALL.LCP]",
"EventCode": "0x87",
"EventName": "DECODE.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to ILD_STALL.LCP]",
"SampleAfterValue": "500009",
"UMask": "0x1"
},
{
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE transitions count.",
"CounterMask": "1",
@ -213,10 +221,10 @@
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_DATA.STALLS]",
"EventCode": "0x80",
"EventName": "ICACHE_16B.IFDATA_STALL",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_DATA.STALLS]",
"SampleAfterValue": "500009",
"UMask": "0x4"
},
@ -237,10 +245,26 @@
"UMask": "0x2"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_STALL",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_16B.IFDATA_STALL]",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALLS",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_16B.IFDATA_STALL]",
"SampleAfterValue": "500009",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
"SampleAfterValue": "200003",
"UMask": "0x4"
},

8
tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
View file

@ -1516,28 +1516,28 @@
},
{
"BriefDescription": "Percentage of cycles in aborted transactions.",
"MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles",
"MetricExpr": "(max(cycles\\-t - cycles\\-ct, 0) / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_aborted_cycles",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of elisions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@",
"MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_elision",
"ScaleUnit": "1cycles / elision"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of transactions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@",
"MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_transaction",
"ScaleUnit": "1cycles / transaction"
},
{
"BriefDescription": "Percentage of cycles within a transaction region.",
"MetricExpr": "cpu@cycles\\-t@ / cycles",
"MetricExpr": "(cycles\\-t / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_transactional_cycles",
"ScaleUnit": "100%"

6
tools/perf/pmu-events/arch/x86/icelake/pipeline.json
View file

@ -318,10 +318,10 @@
"UMask": "0x40"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to DECODE.LCP]",
"EventCode": "0x87",
"EventName": "ILD_STALL.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to DECODE.LCP]",
"SampleAfterValue": "500009",
"UMask": "0x1"
},
@ -556,7 +556,7 @@
"BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions",
"EventCode": "0xa4",
"EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
"PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by branch mispredictions. This event estimates number of operations that were issued but not retired from the specualtive path as well as the out-of-order engine recovery past a branch misprediction.",
"PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by branch mispredictions. This event estimates number of operations that were issued but not retired from the speculative path as well as the out-of-order engine recovery past a branch misprediction.",
"SampleAfterValue": "10000003",
"UMask": "0x8"
},

32
tools/perf/pmu-events/arch/x86/icelakex/frontend.json
View file

@ -7,6 +7,14 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to ILD_STALL.LCP]",
"EventCode": "0x87",
"EventName": "DECODE.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to ILD_STALL.LCP]",
"SampleAfterValue": "500009",
"UMask": "0x1"
},
{
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE transitions count.",
"CounterMask": "1",
@ -213,10 +221,10 @@
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_DATA.STALLS]",
"EventCode": "0x80",
"EventName": "ICACHE_16B.IFDATA_STALL",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_DATA.STALLS]",
"SampleAfterValue": "500009",
"UMask": "0x4"
},
@ -237,10 +245,26 @@
"UMask": "0x2"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_STALL",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_16B.IFDATA_STALL]",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALLS",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_16B.IFDATA_STALL]",
"SampleAfterValue": "500009",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
"SampleAfterValue": "200003",
"UMask": "0x4"
},

8
tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
View file

@ -1812,28 +1812,28 @@
},
{
"BriefDescription": "Percentage of cycles in aborted transactions.",
"MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles",
"MetricExpr": "(max(cycles\\-t - cycles\\-ct, 0) / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_aborted_cycles",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of elisions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@",
"MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_elision",
"ScaleUnit": "1cycles / elision"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of transactions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@",
"MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_transaction",
"ScaleUnit": "1cycles / transaction"
},
{
"BriefDescription": "Percentage of cycles within a transaction region.",
"MetricExpr": "cpu@cycles\\-t@ / cycles",
"MetricExpr": "(cycles\\-t / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_transactional_cycles",
"ScaleUnit": "100%"

4
tools/perf/pmu-events/arch/x86/icelakex/pipeline.json
View file

@ -318,10 +318,10 @@
"UMask": "0x40"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to DECODE.LCP]",
"EventCode": "0x87",
"EventName": "ILD_STALL.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to DECODE.LCP]",
"SampleAfterValue": "500009",
"UMask": "0x1"
},

2
tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json
View file

@ -9311,7 +9311,7 @@
"EventCode": "0x50",
"EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS",
"PerPkg": "1",
"PublicDescription": "Message Held : Parallel Success : ad and bl messages were actually slotted into the same flit in paralle",
"PublicDescription": "Message Held : Parallel Success : ad and bl messages were actually slotted into the same flit in parallel",
"UMask": "0x8",
"Unit": "M3UPI"
},

17
tools/perf/pmu-events/arch/x86/mapfile.csv
View file

@ -5,7 +5,7 @@ GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core
GenuineIntel-6-(3D|47),v28,broadwell,core
GenuineIntel-6-56,v10,broadwellde,core
GenuineIntel-6-4F,v21,broadwellx,core
GenuineIntel-6-55-[56789ABCDEF],v1.18,cascadelakex,core
GenuineIntel-6-55-[56789ABCDEF],v1.19,cascadelakex,core
GenuineIntel-6-9[6C],v1.04,elkhartlake,core
GenuineIntel-6-5[CF],v13,goldmont,core
GenuineIntel-6-7A,v1.01,goldmontplus,core
@ -13,23 +13,24 @@ GenuineIntel-6-B6,v1.00,grandridge,core
GenuineIntel-6-A[DE],v1.01,graniterapids,core
GenuineIntel-6-(3C|45|46),v33,haswell,core
GenuineIntel-6-3F,v27,haswellx,core
GenuineIntel-6-(7D|7E|A7),v1.18,icelake,core
GenuineIntel-6-6[AC],v1.20,icelakex,core
GenuineIntel-6-7[DE],v1.19,icelake,core
GenuineIntel-6-6[AC],v1.21,icelakex,core
GenuineIntel-6-3A,v24,ivybridge,core
GenuineIntel-6-3E,v23,ivytown,core
GenuineIntel-6-2D,v23,jaketown,core
GenuineIntel-6-(57|85),v10,knightslanding,core
GenuineIntel-6-A[AC],v1.01,meteorlake,core
GenuineIntel-6-A[AC],v1.03,meteorlake,core
GenuineIntel-6-1[AEF],v3,nehalemep,core
GenuineIntel-6-2E,v3,nehalemex,core
GenuineIntel-6-A7,v1.01,rocketlake,core
GenuineIntel-6-2A,v19,sandybridge,core
GenuineIntel-6-(8F|CF),v1.13,sapphirerapids,core
GenuineIntel-6-(8F|CF),v1.14,sapphirerapids,core
GenuineIntel-6-AF,v1.00,sierraforest,core
GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core
GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v56,skylake,core
GenuineIntel-6-55-[01234],v1.30,skylakex,core
GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v57,skylake,core
GenuineIntel-6-55-[01234],v1.31,skylakex,core
GenuineIntel-6-86,v1.21,snowridgex,core
GenuineIntel-6-8[CD],v1.12,tigerlake,core
GenuineIntel-6-8[CD],v1.13,tigerlake,core
GenuineIntel-6-2C,v4,westmereep-dp,core
GenuineIntel-6-25,v3,westmereep-sp,core
GenuineIntel-6-2F,v3,westmereex,core

1 Family-model Version Filename EventType
5 GenuineIntel-6-(3D|47) v28 broadwell core
6 GenuineIntel-6-56 v10 broadwellde core
7 GenuineIntel-6-4F v21 broadwellx core
8 GenuineIntel-6-55-[56789ABCDEF] v1.18 v1.19 cascadelakex core
9 GenuineIntel-6-9[6C] v1.04 elkhartlake core
10 GenuineIntel-6-5[CF] v13 goldmont core
11 GenuineIntel-6-7A v1.01 goldmontplus core
13 GenuineIntel-6-A[DE] v1.01 graniterapids core
14 GenuineIntel-6-(3C|45|46) v33 haswell core
15 GenuineIntel-6-3F v27 haswellx core
16 GenuineIntel-6-(7D|7E|A7) GenuineIntel-6-7[DE] v1.18 v1.19 icelake core
17 GenuineIntel-6-6[AC] v1.20 v1.21 icelakex core
18 GenuineIntel-6-3A v24 ivybridge core
19 GenuineIntel-6-3E v23 ivytown core
20 GenuineIntel-6-2D v23 jaketown core
21 GenuineIntel-6-(57|85) v10 knightslanding core
22 GenuineIntel-6-A[AC] v1.01 v1.03 meteorlake core
23 GenuineIntel-6-1[AEF] v3 nehalemep core
24 GenuineIntel-6-2E v3 nehalemex core
25 GenuineIntel-6-A7 v1.01 rocketlake core
26 GenuineIntel-6-2A v19 sandybridge core
27 GenuineIntel-6-(8F|CF) v1.13 v1.14 sapphirerapids core
28 GenuineIntel-6-AF v1.00 sierraforest core
29 GenuineIntel-6-(37|4A|4C|4D|5A) v15 silvermont core
30 GenuineIntel-6-(4E|5E|8E|9E|A5|A6) v56 v57 skylake core
31 GenuineIntel-6-55-[01234] v1.30 v1.31 skylakex core
32 GenuineIntel-6-86 v1.21 snowridgex core
33 GenuineIntel-6-8[CD] v1.12 v1.13 tigerlake core
34 GenuineIntel-6-2C v4 westmereep-dp core
35 GenuineIntel-6-25 v3 westmereep-sp core
36 GenuineIntel-6-2F v3 westmereex core

811
tools/perf/pmu-events/arch/x86/meteorlake/cache.json
View file

@ -1,4 +1,114 @@
[
{
"BriefDescription": "L1D.HWPF_MISS",
"EventCode": "0x51",
"EventName": "L1D.HWPF_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of cache lines replaced in L1 data cache.",
"EventCode": "0x51",
"EventName": "L1D.REPLACEMENT",
"PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.FB_FULL",
"PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability.",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
"PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of L1D misses that are outstanding",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.PENDING",
"PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles with L1D load Misses outstanding.",
"CounterMask": "1",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.PENDING_CYCLES",
"PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2 cache lines filling L2",
"EventCode": "0x25",
"EventName": "L2_LINES_IN.ALL",
"PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
"SampleAfterValue": "100003",
"UMask": "0x1f",
"Unit": "cpu_core"
},
{
"BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.",
"EventCode": "0x26",
"EventName": "L2_LINES_OUT.NON_SILENT",
"PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.",
"EventCode": "0x26",
"EventName": "L2_LINES_OUT.SILENT",
"PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
"SampleAfterValue": "200003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES]",
"EventCode": "0x24",
"EventName": "L2_REQUEST.ALL",
"PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]",
"SampleAfterValue": "200003",
"UMask": "0xff",
"Unit": "cpu_core"
},
{
"BriefDescription": "All requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]",
"EventCode": "0x24",
"EventName": "L2_REQUEST.HIT",
"PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]",
"SampleAfterValue": "200003",
"UMask": "0xdf",
"Unit": "cpu_core"
},
{
"BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]",
"EventCode": "0x24",
"EventName": "L2_REQUEST.MISS",
"PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
"SampleAfterValue": "200003",
"UMask": "0x3f",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2 code requests",
"EventCode": "0x24",
@ -17,6 +127,139 @@
"UMask": "0xe1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Demand requests that miss L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_DEMAND_MISS",
"PublicDescription": "Counts demand requests that miss L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0x27",
"Unit": "cpu_core"
},
{
"BriefDescription": "Demand requests to L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
"PublicDescription": "Counts demand requests to L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0xe7",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2_RQSTS.ALL_HWPF",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_HWPF",
"SampleAfterValue": "200003",
"UMask": "0xf0",
"Unit": "cpu_core"
},
{
"BriefDescription": "RFO requests to L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_RFO",
"PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
"SampleAfterValue": "200003",
"UMask": "0xe2",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2 cache hits when fetching instructions, code reads.",
"EventCode": "0x24",
"EventName": "L2_RQSTS.CODE_RD_HIT",
"PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
"SampleAfterValue": "200003",
"UMask": "0xc4",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2 cache misses when fetching instructions",
"EventCode": "0x24",
"EventName": "L2_RQSTS.CODE_RD_MISS",
"PublicDescription": "Counts L2 cache misses when fetching instructions.",
"SampleAfterValue": "200003",
"UMask": "0x24",
"Unit": "cpu_core"
},
{
"BriefDescription": "Demand Data Read requests that hit L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
"PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0xc1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Demand Data Read miss L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
"PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
"SampleAfterValue": "200003",
"UMask": "0x21",
"Unit": "cpu_core"
},
{
"BriefDescription": "All requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]",
"EventCode": "0x24",
"EventName": "L2_RQSTS.HIT",
"PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]",
"SampleAfterValue": "200003",
"UMask": "0xdf",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2_RQSTS.HWPF_MISS",
"EventCode": "0x24",
"EventName": "L2_RQSTS.HWPF_MISS",
"SampleAfterValue": "200003",
"UMask": "0x30",
"Unit": "cpu_core"
},
{
"BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_REQUEST.MISS]",
"EventCode": "0x24",
"EventName": "L2_RQSTS.MISS",
"PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
"SampleAfterValue": "200003",
"UMask": "0x3f",
"Unit": "cpu_core"
},
{
"BriefDescription": "All accesses to L2 cache [This event is alias to L2_REQUEST.ALL]",
"EventCode": "0x24",
"EventName": "L2_RQSTS.REFERENCES",
"PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]",
"SampleAfterValue": "200003",
"UMask": "0xff",
"Unit": "cpu_core"
},
{
"BriefDescription": "RFO requests that hit L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.RFO_HIT",
"PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0xc2",
"Unit": "cpu_core"
},
{
"BriefDescription": "RFO requests that miss L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.RFO_MISS",
"PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0x22",
"Unit": "cpu_core"
},
{
"BriefDescription": "L2 writebacks that access L2 cache",
"EventCode": "0x23",
"EventName": "L2_TRANS.L2_WB",
"PublicDescription": "Counts L2 writebacks that access L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0x40",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.",
"EventCode": "0x2e",
@ -53,6 +296,72 @@
"UMask": "0x4f",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an instruction cache or TLB miss.",
"EventCode": "0x35",
"EventName": "MEM_BOUND_STALLS_IFETCH.ALL",
"SampleAfterValue": "1000003",
"UMask": "0x6f",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which hit in the L2 cache.",
"EventCode": "0x35",
"EventName": "MEM_BOUND_STALLS_IFETCH.L2_HIT",
"PublicDescription": "Counts the number of cycles the core is stalled due to an instruction cache or Translation Lookaside Buffer (TLB) miss which hit in the L2 cache.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which hit in the LLC.",
"EventCode": "0x35",
"EventName": "MEM_BOUND_STALLS_IFETCH.LLC_HIT",
"SampleAfterValue": "1000003",
"UMask": "0x6",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which missed all the caches.",
"EventCode": "0x35",
"EventName": "MEM_BOUND_STALLS_IFETCH.LLC_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x68",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an L1 demand load miss.",
"EventCode": "0x34",
"EventName": "MEM_BOUND_STALLS_LOAD.ALL",
"SampleAfterValue": "1000003",
"UMask": "0x6f",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which hit in the L2 cache.",
"EventCode": "0x34",
"EventName": "MEM_BOUND_STALLS_LOAD.L2_HIT",
"PublicDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 cache.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC.",
"EventCode": "0x34",
"EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT",
"SampleAfterValue": "1000003",
"UMask": "0x6",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.",
"EventCode": "0x34",
"EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x68",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Retired load instructions.",
"Data_LA": "1",
@ -75,6 +384,352 @@
"UMask": "0x82",
"Unit": "cpu_core"
},
{
"BriefDescription": "All retired memory instructions.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ANY",
"PEBS": "1",
"PublicDescription": "Counts all retired memory instructions - loads and stores.",
"SampleAfterValue": "1000003",
"UMask": "0x83",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions with locked access.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.LOCK_LOADS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with locked access.",
"SampleAfterValue": "100007",
"UMask": "0x21",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions that split across a cacheline boundary.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
"SampleAfterValue": "100003",
"UMask": "0x41",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired store instructions that split across a cacheline boundary.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.SPLIT_STORES",
"PEBS": "1",
"PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
"SampleAfterValue": "100003",
"UMask": "0x42",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions that hit the STLB.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS",
"PEBS": "1",
"PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x9",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired store instructions that hit the STLB.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_HIT_STORES",
"PEBS": "1",
"PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0xa",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions that miss the STLB.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
"PEBS": "1",
"PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x11",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired store instructions that miss the STLB.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
"PEBS": "1",
"PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x12",
"Unit": "cpu_core"
},
{
"BriefDescription": "Completed demand load uops that miss the L1 d-cache.",
"EventCode": "0x43",
"EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY",
"PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)",
"SampleAfterValue": "1000003",
"UMask": "0xfd",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
"SampleAfterValue": "20011",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
"SampleAfterValue": "20011",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
"SampleAfterValue": "20011",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
"SampleAfterValue": "20011",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram",
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
"PEBS": "1",
"PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
"SampleAfterValue": "100007",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.",
"Data_LA": "1",
"EventCode": "0xd4",
"EventName": "MEM_LOAD_MISC_RETIRED.UC",
"PEBS": "1",
"PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
"SampleAfterValue": "100007",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.FB_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
"SampleAfterValue": "100007",
"UMask": "0x40",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions with L1 cache hits as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L1_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions missed L1 cache as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L1_MISS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
"SampleAfterValue": "200003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions with L2 cache hits as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L2_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions missed L2 cache as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L2_MISS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
"SampleAfterValue": "100021",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions with L3 cache hits as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L3_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
"SampleAfterValue": "100021",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired load instructions missed L3 cache as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L3_MISS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
"SampleAfterValue": "50021",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in DRAM",
"EventCode": "0xd4",
"EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LOCAL_DRAM",
"PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of load ops retired that hit the L1 data cache.",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of load ops retired that miss in the L1 data cache.",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x40",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of load ops retired that hit in the L2 cache.",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of load ops retired that miss in the L2 cache.",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x80",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of load ops retired that hit in the L3 cache.",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x1c",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of loads that hit in a write combining buffer (WCB), excluding the first load that caused the WCB to allocate.",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x20",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.",
"EventCode": "0x04",
"EventName": "MEM_SCHEDULER_BLOCK.ALL",
"SampleAfterValue": "20003",
"UMask": "0x7",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that uops are blocked due to a load buffer full condition.",
"EventCode": "0x04",
"EventName": "MEM_SCHEDULER_BLOCK.LD_BUF",
"SampleAfterValue": "20003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that uops are blocked due to an RSV full condition.",
"EventCode": "0x04",
"EventName": "MEM_SCHEDULER_BLOCK.RSV",
"SampleAfterValue": "20003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that uops are blocked due to a store buffer full condition.",
"EventCode": "0x04",
"EventName": "MEM_SCHEDULER_BLOCK.ST_BUF",
"SampleAfterValue": "20003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of load ops retired.",
"Data_LA": "1",
@ -95,6 +750,18 @@
"UMask": "0x82",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024",
"MSRIndex": "0x3F6",
"MSRValue": "0x400",
"PEBS": "2",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Data_LA": "1",
@ -119,6 +786,18 @@
"UMask": "0x5",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048",
"MSRIndex": "0x3F6",
"MSRValue": "0x800",
"PEBS": "2",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
"Data_LA": "1",
@ -191,6 +870,46 @@
"UMask": "0x5",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of load uops retired that performed one or more locks",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x21",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of memory uops retired that were splits.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.SPLIT",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x43",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of retired split load uops.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x41",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of retired split store uops.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x42",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES",
"Data_LA": "1",
@ -200,5 +919,97 @@
"SampleAfterValue": "1000003",
"UMask": "0x6",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Retired memory uops for any access",
"EventCode": "0xe5",
"EventName": "MEM_UOP_RETIRED.ANY",
"PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
"SampleAfterValue": "1000003",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified.",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x8003C0001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified.",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0002",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Any memory transaction that reached the SQ.",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
"PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..",
"SampleAfterValue": "100003",
"UMask": "0x80",
"Unit": "cpu_core"
},
{
"BriefDescription": "Demand and prefetch data reads",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.DATA_RD",
"PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Demand Data Read requests sent to uncore",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
"PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
"PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.",
"EventCode": "0x2c",
"EventName": "SQ_MISC.BUS_LOCK",
"PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to an icache miss",
"EventCode": "0x71",
"EventName": "TOPDOWN_FE_BOUND.ICACHE",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_atom"
}
]

143
tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json Normal file
View file

@ -0,0 +1,143 @@
[
{
"BriefDescription": "This event counts the cycles the floating point divider is busy.",
"CounterMask": "1",
"EventCode": "0xb0",
"EventName": "ARITH.FPDIV_ACTIVE",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts all microcode FP assists.",
"EventCode": "0xc1",
"EventName": "ASSISTS.FP",
"PublicDescription": "Counts all microcode Floating Point assists.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "ASSISTS.SSE_AVX_MIX",
"EventCode": "0xc1",
"EventName": "ASSISTS.SSE_AVX_MIX",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "FP_ARITH_DISPATCHED.PORT_0",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.PORT_0",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "FP_ARITH_DISPATCHED.PORT_1",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.PORT_1",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x18",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "1000003",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of any Vector retired FP arithmetic instructions",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.VECTOR",
"PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "1000003",
"UMask": "0xfc",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of floating point operations retired that required microcode assist.",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.FP_ASSIST",
"PublicDescription": "Counts the number of floating point operations retired that required microcode assist, which is not a reflection of the number of FP operations, instructions or uops.",
"SampleAfterValue": "20003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of floating point divide uops retired (x87 and sse, including x87 sqrt).",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.FPDIV",
"PEBS": "1",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_atom"
}
]

410
tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
View file

@ -1,4 +1,259 @@
[
{
"BriefDescription": "Counts the total number of BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"PublicDescription": "Counts the total number of BACLEARS, which occur when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
"SampleAfterValue": "200003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Clears due to Unknown Branches.",
"EventCode": "0x60",
"EventName": "BACLEARS.ANY",
"PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"EventCode": "0x87",
"EventName": "DECODE.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
"SampleAfterValue": "500009",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles the Microcode Sequencer is busy.",
"EventCode": "0x87",
"EventName": "DECODE.MS_BUSY",
"SampleAfterValue": "500009",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "DSB-to-MITE switch true penalty cycles.",
"EventCode": "0x61",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired ANT branches",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ANY_ANT",
"MSRIndex": "0x3F7",
"MSRValue": "0x9",
"PEBS": "1",
"PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Retired Instructions who experienced iTLB true miss.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x14",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x12",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x600106",
"PEBS": "1",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"MSRValue": "0x608006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"MSRValue": "0x601006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"MSRValue": "0x600206",
"PEBS": "1",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"MSRValue": "0x610006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x100206",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"MSRValue": "0x602006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
"MSRIndex": "0x3F7",
"MSRValue": "0x600406",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"MSRValue": "0x620006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"MSRValue": "0x604006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"MSRValue": "0x600806",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Mispredicted Retired ANT branches",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.MISP_ANT",
"MSRIndex": "0x3F7",
"MSRValue": "0x9",
"PEBS": "1",
"PublicDescription": "ANT retired branches that got just mispredicted",
"SampleAfterValue": "100007",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "FRONTEND_RETIRED.MS_FLOWS",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.MS_FLOWS",
"MSRIndex": "0x3F7",
"MSRValue": "0x8",
"PEBS": "1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
"MSRIndex": "0x3F7",
"MSRValue": "0x17",
"PEBS": "1",
"SampleAfterValue": "100007",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.",
"EventCode": "0x80",
@ -15,6 +270,131 @@
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALLS",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
"SampleAfterValue": "500009",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "ICACHE_DATA.STALL_PERIODS",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALL_PERIODS",
"SampleAfterValue": "500009",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.HIT",
"PublicDescription": "Counts instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.",
"SampleAfterValue": "200003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles DSB is delivering optimal number of Uops",
"CounterMask": "6",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_ANY",
"PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles MITE is delivering optimal number of Uops",
"CounterMask": "6",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_OK",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES_ANY",
"PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Number of switches from DSB or MITE to the MS",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
"PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "1000003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.",
"EventCode": "0x9c",
@ -23,5 +403,35 @@
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled",
"CounterMask": "6",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled",
"CounterMask": "1",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
"PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
}
]

142
tools/perf/pmu-events/arch/x86/meteorlake/memory.json
View file

@ -1,4 +1,100 @@
[
{
"BriefDescription": "Cycles while L3 cache miss demand load is outstanding.",
"CounterMask": "2",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
"CounterMask": "6",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x6",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to any number of reasons, including an L1 miss, WCB full, pagewalk, store address block or store data block, on a load that retires.",
"EventCode": "0x05",
"EventName": "LD_HEAD.ANY_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0xff",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a core bound stall including a store address match, a DTLB miss or a page walk that detains the load from retiring.",
"EventCode": "0x05",
"EventName": "LD_HEAD.L1_BOUND_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0xf4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DL1 miss.",
"EventCode": "0x05",
"EventName": "LD_HEAD.L1_MISS_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0x81",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases.",
"EventCode": "0x05",
"EventName": "LD_HEAD.OTHER_AT_RET",
"PublicDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases such as pipeline conflicts, fences, etc.",
"SampleAfterValue": "1000003",
"UMask": "0xc0",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a pagewalk.",
"EventCode": "0x05",
"EventName": "LD_HEAD.PGWALK_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0xa0",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a store address match.",
"EventCode": "0x05",
"EventName": "LD_HEAD.ST_ADDR_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0x84",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
"CounterMask": "3",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x3",
"Unit": "cpu_core"
},
{
"BriefDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding.",
"CounterMask": "5",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
"PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
"SampleAfterValue": "1000003",
"UMask": "0x5",
"Unit": "cpu_core"
},
{
"BriefDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding.",
"CounterMask": "9",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
"PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
"SampleAfterValue": "1000003",
"UMask": "0x9",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
"Data_LA": "1",
@ -115,43 +211,29 @@
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"BriefDescription": "Counts misaligned loads that are 4K page splits.",
"EventCode": "0x13",
"EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x2",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00002",
"SampleAfterValue": "100003",
"UMask": "0x1",
"BriefDescription": "Counts misaligned stores that are 4K page splits.",
"EventCode": "0x13",
"EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
"PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00002",
"BriefDescription": "Counts demand data read requests that miss the L3 cache.",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
"SampleAfterValue": "100003",
"UMask": "0x1",
"UMask": "0x10",
"Unit": "cpu_core"
}
]

59
tools/perf/pmu-events/arch/x86/meteorlake/other.json
View file

@ -1,41 +1,50 @@
[
{
"BriefDescription": "Counts demand data reads that have any type of response.",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand data reads that have any type of response.",
"BriefDescription": "Counts streaming stores that have any type of response.",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
"EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10001",
"MSRValue": "0x10800",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10002",
"BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
"EventCode": "0xa5",
"EventName": "RS.EMPTY",
"PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
"SampleAfterValue": "1000003",
"UMask": "0x7",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0xa5",
"EventName": "RS.EMPTY_COUNT",
"Invert": "1",
"PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
"SampleAfterValue": "100003",
"UMask": "0x1",
"UMask": "0x7",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
"EventCode": "0x75",
"EventName": "SERIALIZATION.C01_MS_SCB",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10002",
"SampleAfterValue": "100003",
"BriefDescription": "Cycles the uncore cannot take further requests",
"CounterMask": "1",
"EventCode": "0x2d",
"EventName": "XQ.FULL_CYCLES",
"PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
}

1121
tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
View file

File diff suppressed because it is too large Load diff

18
tools/perf/pmu-events/arch/x86/meteorlake/uncore-cache.json Normal file
View file

@ -0,0 +1,18 @@
[
{
"BriefDescription": "Number of all entries allocated. Includes also retries.",
"EventCode": "0x35",
"EventName": "UNC_HAC_CBO_TOR_ALLOCATION.ALL",
"PerPkg": "1",
"UMask": "0x8",
"Unit": "HAC_CBO"
},
{
"BriefDescription": "Asserted on coherent DRD + DRdPref allocations into the queue. Cacheable only",
"EventCode": "0x35",
"EventName": "UNC_HAC_CBO_TOR_ALLOCATION.DRD",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "HAC_CBO"
}
]

42
tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json Normal file
View file

@ -0,0 +1,42 @@
[
{
"BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches",
"EventCode": "0x81",
"EventName": "UNC_HAC_ARB_REQ_TRK_REQUEST.DRD",
"PerPkg": "1",
"UMask": "0x2",
"Unit": "HAC_ARB"
},
{
"BriefDescription": "Number of all CMI transactions",
"EventCode": "0x8a",
"EventName": "UNC_HAC_ARB_TRANSACTIONS.ALL",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "HAC_ARB"
},
{
"BriefDescription": "Number of all CMI reads",
"EventCode": "0x8a",
"EventName": "UNC_HAC_ARB_TRANSACTIONS.READS",
"PerPkg": "1",
"UMask": "0x2",
"Unit": "HAC_ARB"
},
{
"BriefDescription": "Number of all CMI writes not including Mflush",
"EventCode": "0x8a",
"EventName": "UNC_HAC_ARB_TRANSACTIONS.WRITES",
"PerPkg": "1",
"UMask": "0x4",
"Unit": "HAC_ARB"
},
{
"BriefDescription": "Total number of all outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
"EventCode": "0x81",
"EventName": "UNC_HAC_ARB_TRK_REQUESTS.ALL",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "HAC_ARB"
}
]

126
tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json Normal file
View file

@ -0,0 +1,126 @@
[
{
"BriefDescription": "Counts every CAS read command sent from the Memory Controller 0 to DRAM (sum of all channels).",
"EventCode": "0xff",
"EventName": "UNC_MC0_RDCAS_COUNT_FREERUN",
"PerPkg": "1",
"PublicDescription": "Counts every CAS read command sent from the Memory Controller 0 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data.",
"UMask": "0x20",
"Unit": "imc_free_running_0"
},
{
"BriefDescription": "Counts every read and write request entering the Memory Controller 0.",
"EventCode": "0xff",
"EventName": "UNC_MC0_TOTAL_REQCOUNT_FREERUN",
"PerPkg": "1",
"PublicDescription": "Counts every read and write request entering the Memory Controller 0 (sum of all channels). All requests are counted as one, whether they are 32B or 64B Read/Write or partial/full line writes. Some write requests to the same address may merge to a single write command to DRAM. Therefore, the total request count may be higher than total DRAM BW.",
"UMask": "0x10",
"Unit": "imc_free_running_0"
},
{
"BriefDescription": "Counts every CAS write command sent from the Memory Controller 0 to DRAM (sum of all channels).",
"EventCode": "0xff",
"EventName": "UNC_MC0_WRCAS_COUNT_FREERUN",
"PerPkg": "1",
"PublicDescription": "Counts every CAS write command sent from the Memory Controller 0 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data.",
"UMask": "0x30",
"Unit": "imc_free_running_0"
},
{
"BriefDescription": "Counts every CAS read command sent from the Memory Controller 1 to DRAM (sum of all channels).",
"EventCode": "0xff",
"EventName": "UNC_MC1_RDCAS_COUNT_FREERUN",
"PerPkg": "1",
"PublicDescription": "Counts every CAS read command sent from the Memory Controller 1 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data.",
"UMask": "0x20",
"Unit": "imc_free_running_1"
},
{
"BriefDescription": "Counts every read and write request entering the Memory Controller 1.",
"EventCode": "0xff",
"EventName": "UNC_MC1_TOTAL_REQCOUNT_FREERUN",
"PerPkg": "1",
"PublicDescription": "Counts every read and write request entering the Memory Controller 1 (sum of all channels). All requests are counted as one, whether they are 32B or 64B Read/Write or partial/full line writes. Some write requests to the same address may merge to a single write command to DRAM. Therefore, the total request count may be higher than total DRAM BW.",
"UMask": "0x10",
"Unit": "imc_free_running_1"
},
{
"BriefDescription": "Counts every CAS write command sent from the Memory Controller 1 to DRAM (sum of all channels).",
"EventCode": "0xff",
"EventName": "UNC_MC1_WRCAS_COUNT_FREERUN",
"PerPkg": "1",
"PublicDescription": "Counts every CAS write command sent from the Memory Controller 1 to DRAM (sum of all channels). Each CAS commands can be for 32B or 64B of data.",
"UMask": "0x30",
"Unit": "imc_free_running_1"
},
{
"BriefDescription": "ACT command for a read request sent to DRAM",
"EventCode": "0x24",
"EventName": "UNC_M_ACT_COUNT_RD",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "ACT command sent to DRAM",
"EventCode": "0x26",
"EventName": "UNC_M_ACT_COUNT_TOTAL",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "ACT command for a write request sent to DRAM",
"EventCode": "0x25",
"EventName": "UNC_M_ACT_COUNT_WR",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Read CAS command sent to DRAM",
"EventCode": "0x22",
"EventName": "UNC_M_CAS_COUNT_RD",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Write CAS command sent to DRAM",
"EventCode": "0x23",
"EventName": "UNC_M_CAS_COUNT_WR",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "PRE command sent to DRAM due to page table idle timer expiration",
"EventCode": "0x28",
"EventName": "UNC_M_PRE_COUNT_IDLE",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "PRE command sent to DRAM for a read/write request",
"EventCode": "0x27",
"EventName": "UNC_M_PRE_COUNT_PAGE_MISS",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Number of bytes read from DRAM, in 32B chunks. Counter increments by 1 after receiving 32B chunk data.",
"EventCode": "0x3A",
"EventName": "UNC_M_RD_DATA",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Total number of read and write byte transfers to/from DRAM, in 32B chunks. Counter increments by 1 after sending or receiving 32B chunk data.",
"EventCode": "0x3C",
"EventName": "UNC_M_TOTAL_DATA",
"PerPkg": "1",
"Unit": "iMC"
},
{
"BriefDescription": "Number of bytes written to DRAM, in 32B chunks. Counter increments by 1 after sending 32B chunk data.",
"EventCode": "0x3B",
"EventName": "UNC_M_WR_DATA",
"PerPkg": "1",
"Unit": "iMC"
}
]

257
tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json
View file

@ -1,4 +1,39 @@
[
{
"BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"SampleAfterValue": "200003",
"UMask": "0x20",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Loads that miss the DTLB and hit the STLB.",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.",
"CounterMask": "1",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks completed due to load DTLB misses.",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"SampleAfterValue": "200003",
"UMask": "0xe",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
"EventCode": "0x12",
@ -8,6 +43,95 @@
"UMask": "0xe",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 1G page.",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 2M or 4M page.",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.",
"SampleAfterValue": "200003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 4K page.",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle.",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.",
"SampleAfterValue": "200003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of first level TLB misses but second level hits due to stores that did not start a page walk. Accounts for all pages sizes. Will result in a DTLB write from STLB.",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"SampleAfterValue": "2000003",
"UMask": "0x20",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Stores that miss the DTLB and hit the STLB.",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.",
"CounterMask": "1",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 1G page.",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"SampleAfterValue": "2000003",
"UMask": "0xe",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
"EventCode": "0x13",
@ -17,6 +141,86 @@
"UMask": "0xe",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 1G page.",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x8",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 4K page.",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle.",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.",
"SampleAfterValue": "200003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks initiated by a instruction fetch that missed the first and second level TLBs.",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.MISS_CAUSED_WALK",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of first level TLB misses but second level hits due to an instruction fetch that did not start a page walk. Account for all pages sizes. Will result in an ITLB write from STLB.",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT",
"SampleAfterValue": "2000003",
"UMask": "0x20",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.STLB_HIT",
"PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x20",
"Unit": "cpu_core"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.",
"CounterMask": "1",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.",
"EventCode": "0x85",
@ -34,5 +238,58 @@
"SampleAfterValue": "100003",
"UMask": "0xe",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 2M or 4M page.",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.",
"SampleAfterValue": "2000003",
"UMask": "0x4",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4",
"Unit": "cpu_core"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of page walks outstanding for iside in PMH every cycle.",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for iside in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals. Walks could be counted by edge detecting on this event, but would count restarted suspended walks.",
"SampleAfterValue": "200003",
"UMask": "0x10",
"Unit": "cpu_atom"
},
{
"BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10",
"Unit": "cpu_core"
},
{
"BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DTLB miss.",
"EventCode": "0x05",
"EventName": "LD_HEAD.DTLB_MISS_AT_RET",
"SampleAfterValue": "1000003",
"UMask": "0x90",
"Unit": "cpu_atom"
}
]

894
tools/perf/pmu-events/arch/x86/rocketlake/cache.json Normal file
View file

@ -0,0 +1,894 @@
[
{
"BriefDescription": "Counts the number of cache lines replaced in L1 data cache.",
"EventCode": "0x51",
"EventName": "L1D.REPLACEMENT",
"PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.FB_FULL",
"PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability.",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
"PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.L2_STALL",
"PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of L1D misses that are outstanding",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.PENDING",
"PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles with L1D load Misses outstanding.",
"CounterMask": "1",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.PENDING_CYCLES",
"PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "L2 cache lines filling L2",
"EventCode": "0xF1",
"EventName": "L2_LINES_IN.ALL",
"PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
"SampleAfterValue": "100003",
"UMask": "0x1f"
},
{
"BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.",
"EventCode": "0xF2",
"EventName": "L2_LINES_OUT.NON_SILENT",
"PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.",
"EventCode": "0xF2",
"EventName": "L2_LINES_OUT.SILENT",
"PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses",
"EventCode": "0xf2",
"EventName": "L2_LINES_OUT.USELESS_HWPF",
"PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "L2 code requests",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_CODE_RD",
"PublicDescription": "Counts the total number of L2 code requests.",
"SampleAfterValue": "200003",
"UMask": "0xe4"
},
{
"BriefDescription": "Demand Data Read requests",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
"PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.",
"SampleAfterValue": "200003",
"UMask": "0xe1"
},
{
"BriefDescription": "Demand requests that miss L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_DEMAND_MISS",
"PublicDescription": "Counts demand requests that miss L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0x27"
},
{
"BriefDescription": "Demand requests to L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
"PublicDescription": "Counts demand requests to L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0xe7"
},
{
"BriefDescription": "RFO requests to L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_RFO",
"PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
"SampleAfterValue": "200003",
"UMask": "0xe2"
},
{
"BriefDescription": "L2 cache hits when fetching instructions, code reads.",
"EventCode": "0x24",
"EventName": "L2_RQSTS.CODE_RD_HIT",
"PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
"SampleAfterValue": "200003",
"UMask": "0xc4"
},
{
"BriefDescription": "L2 cache misses when fetching instructions",
"EventCode": "0x24",
"EventName": "L2_RQSTS.CODE_RD_MISS",
"PublicDescription": "Counts L2 cache misses when fetching instructions.",
"SampleAfterValue": "200003",
"UMask": "0x24"
},
{
"BriefDescription": "Demand Data Read requests that hit L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
"PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0xc1"
},
{
"BriefDescription": "Demand Data Read miss L2, no rejects",
"EventCode": "0x24",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
"PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.",
"SampleAfterValue": "200003",
"UMask": "0x21"
},
{
"BriefDescription": "All requests that miss L2 cache.",
"EventCode": "0x24",
"EventName": "L2_RQSTS.MISS",
"PublicDescription": "Counts all requests that miss L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0x3f"
},
{
"BriefDescription": "All L2 requests.",
"EventCode": "0x24",
"EventName": "L2_RQSTS.REFERENCES",
"PublicDescription": "Counts all L2 requests.",
"SampleAfterValue": "200003",
"UMask": "0xff"
},
{
"BriefDescription": "RFO requests that hit L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.RFO_HIT",
"PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0xc2"
},
{
"BriefDescription": "RFO requests that miss L2 cache",
"EventCode": "0x24",
"EventName": "L2_RQSTS.RFO_MISS",
"PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0x22"
},
{
"BriefDescription": "SW prefetch requests that hit L2 cache.",
"EventCode": "0x24",
"EventName": "L2_RQSTS.SWPF_HIT",
"PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
"SampleAfterValue": "200003",
"UMask": "0xc8"
},
{
"BriefDescription": "SW prefetch requests that miss L2 cache.",
"EventCode": "0x24",
"EventName": "L2_RQSTS.SWPF_MISS",
"PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
"SampleAfterValue": "200003",
"UMask": "0x28"
},
{
"BriefDescription": "L2 writebacks that access L2 cache",
"EventCode": "0xF0",
"EventName": "L2_TRANS.L2_WB",
"PublicDescription": "Counts L2 writebacks that access L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0x40"
},
{
"BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)",
"EventCode": "0x2e",
"EventName": "LONGEST_LAT_CACHE.MISS",
"PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
"SampleAfterValue": "100003",
"UMask": "0x41"
},
{
"BriefDescription": "Retired load instructions.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ALL_LOADS",
"PEBS": "1",
"PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
"SampleAfterValue": "1000003",
"UMask": "0x81"
},
{
"BriefDescription": "Retired store instructions.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ALL_STORES",
"PEBS": "1",
"PublicDescription": "Counts all retired store instructions.",
"SampleAfterValue": "1000003",
"UMask": "0x82"
},
{
"BriefDescription": "All retired memory instructions.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ANY",
"PEBS": "1",
"PublicDescription": "Counts all retired memory instructions - loads and stores.",
"SampleAfterValue": "1000003",
"UMask": "0x83"
},
{
"BriefDescription": "Retired load instructions with locked access.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.LOCK_LOADS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with locked access.",
"SampleAfterValue": "100007",
"UMask": "0x21"
},
{
"BriefDescription": "Retired load instructions that split across a cacheline boundary.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
"SampleAfterValue": "100003",
"UMask": "0x41"
},
{
"BriefDescription": "Retired store instructions that split across a cacheline boundary.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.SPLIT_STORES",
"PEBS": "1",
"PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
"SampleAfterValue": "100003",
"UMask": "0x42"
},
{
"BriefDescription": "Retired load instructions that miss the STLB.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
"PEBS": "1",
"PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x11"
},
{
"BriefDescription": "Retired store instructions that miss the STLB.",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
"PEBS": "1",
"PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x12"
},
{
"BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
"SampleAfterValue": "20011",
"UMask": "0x2"
},
{
"BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
"SampleAfterValue": "20011",
"UMask": "0x4"
},
{
"BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
"PEBS": "1",
"PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
"SampleAfterValue": "20011",
"UMask": "0x1"
},
{
"BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Retired instructions with at least 1 uncacheable load or Bus Lock.",
"Data_LA": "1",
"EventCode": "0xd4",
"EventName": "MEM_LOAD_MISC_RETIRED.UC",
"PEBS": "1",
"PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
"SampleAfterValue": "100007",
"UMask": "0x4"
},
{
"BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.FB_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
"SampleAfterValue": "100007",
"UMask": "0x40"
},
{
"BriefDescription": "Retired load instructions with L1 cache hits as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L1_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Retired load instructions missed L1 cache as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L1_MISS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
"SampleAfterValue": "200003",
"UMask": "0x8"
},
{
"BriefDescription": "Retired load instructions with L2 cache hits as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L2_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Retired load instructions missed L2 cache as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L2_MISS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
"SampleAfterValue": "100021",
"UMask": "0x10"
},
{
"BriefDescription": "Retired load instructions with L3 cache hits as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L3_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
"SampleAfterValue": "100021",
"UMask": "0x4"
},
{
"BriefDescription": "Retired load instructions missed L3 cache as data sources",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L3_MISS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
"SampleAfterValue": "50021",
"UMask": "0x20"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was sent or not.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT.ANY",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FC03C0004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x4003C0004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x2003C0004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1003C0004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a cacheline in the L3 where a snoop was sent.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_SENT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1E003C0004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was sent or not.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.ANY",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FC03C0001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x4003C0001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x2003C0001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1003C0001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop was sent.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_SENT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1E003C0001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_HIT.ANY",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FC03C0002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x4003C0002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x2003C0002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1003C0002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop was sent.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_SENT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1E003C0002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit a cacheline in the L3 where a snoop was sent or not.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT.ANY",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FC03C0400",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT.SNOOP_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x2003C0400",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT.SNOOP_NOT_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1003C0400",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent or not.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.ANY",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FC03C0010",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0010",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x4003C0010",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x2003C0010",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1003C0010",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_SENT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1E003C0010",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent or not.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.L3_HIT.ANY",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FC03C0020",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0020",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x4003C0020",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x2003C0020",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1003C0020",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that hit a cacheline in the L3 where a snoop was sent.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_SENT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1E003C0020",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetches to the L3 only that hit a cacheline in the L3 where a snoop was sent or not.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L3.L3_HIT.ANY",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FC03C2380",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that hit a cacheline in the L3 where a snoop hit in another core, data forwarding is not required.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.L3_HIT.SNOOP_HIT_NO_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x4003C8000",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that hit a cacheline in the L3 where a snoop was sent but no other cores had the data.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.L3_HIT.SNOOP_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x2003C8000",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that hit a cacheline in the L3 where a snoop was not needed to satisfy the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.L3_HIT.SNOOP_NOT_NEEDED",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1003C8000",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that hit a cacheline in the L3 where a snoop was sent.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.L3_HIT.SNOOP_SENT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x1E003C8000",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts streaming stores that hit a cacheline in the L3 where a snoop was sent or not.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.STREAMING_WR.L3_HIT.ANY",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FC03C0800",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Demand and prefetch data reads",
"EventCode": "0xB0",
"EventName": "OFFCORE_REQUESTS.ALL_DATA_RD",
"PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts memory transactions sent to the uncore.",
"EventCode": "0xB0",
"EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
"PublicDescription": "Counts memory transactions sent to the uncore including requests initiated by the core, all L3 prefetches, reads resulting from page walks, and snoop responses.",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Demand Data Read requests sent to uncore",
"EventCode": "0xb0",
"EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
"PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM",
"EventCode": "0xb0",
"EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
"PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "For every cycle, increments by the number of outstanding data read requests pending.",
"EventCode": "0x60",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
"PublicDescription": "For every cycle, increments by the number of outstanding data read requests pending. Data read requests include cacheable demand reads and L2 prefetches, but do not include RFOs, code reads or prefetches to the L3. Reads due to page walks resulting from any request type will also be counted. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles where at least 1 outstanding data read request is pending.",
"CounterMask": "1",
"EventCode": "0x60",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
"PublicDescription": "Cycles where at least 1 outstanding data read request is pending. Data read requests include cacheable demand reads and L2 prefetches, but do not include RFOs, code reads or prefetches to the L3. Reads due to page walks resulting from any request type will also be counted. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles where at least 1 outstanding Demand RFO request is pending.",
"CounterMask": "1",
"EventCode": "0x60",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
"PublicDescription": "Cycles where at least 1 outstanding Demand RFO request is pending. RFOs are initiated by a core as part of a data store operation. Demand RFO requests include RFOs, locks, and ItoM transactions. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.",
"EventCode": "0x60",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
"PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Store Read transactions pending for off-core. Highly correlated.",
"EventCode": "0x60",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
"PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.",
"EventCode": "0xF4",
"EventName": "SQ_MISC.BUS_LOCK",
"PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Cycles the queue waiting for offcore responses is full.",
"EventCode": "0xf4",
"EventName": "SQ_MISC.SQ_FULL",
"PublicDescription": "Counts the cycles for which the thread is active and the queue waiting for responses from the uncore cannot take any more entries.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of PREFETCHNTA instructions executed.",
"EventCode": "0x32",
"EventName": "SW_PREFETCH_ACCESS.NTA",
"PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of PREFETCHW instructions executed.",
"EventCode": "0x32",
"EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
"PublicDescription": "Counts the number of PREFETCHW instructions executed.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of PREFETCHT0 instructions executed.",
"EventCode": "0x32",
"EventName": "SW_PREFETCH_ACCESS.T0",
"PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.",
"EventCode": "0x32",
"EventName": "SW_PREFETCH_ACCESS.T1_T2",
"PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
"SampleAfterValue": "100003",
"UMask": "0x4"
}
]

105
tools/perf/pmu-events/arch/x86/rocketlake/floating-point.json Normal file
View file

@ -0,0 +1,105 @@
[
{
"BriefDescription": "Counts all microcode FP assists.",
"EventCode": "0xc1",
"EventName": "ASSISTS.FP",
"PublicDescription": "Counts all microcode Floating Point assists.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x18"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
"PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.8_FLOPS",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x60"
},
{
"BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "1000003",
"UMask": "0x3"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of any Vector retired FP arithmetic instructions",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.VECTOR",
"SampleAfterValue": "1000003",
"UMask": "0xfc"
}
]

377
tools/perf/pmu-events/arch/x86/rocketlake/frontend.json Normal file
View file

@ -0,0 +1,377 @@
[
{
"BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
"EventCode": "0xe6",
"EventName": "BACLEARS.ANY",
"PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to ILD_STALL.LCP]",
"EventCode": "0x87",
"EventName": "DECODE.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to ILD_STALL.LCP]",
"SampleAfterValue": "500009",
"UMask": "0x1"
},
{
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE transitions count.",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0xab",
"EventName": "DSB2MITE_SWITCHES.COUNT",
"PublicDescription": "Counts the number of Decode Stream Buffer (DSB a.k.a. Uop Cache)-to-MITE speculative transitions.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "DSB-to-MITE switch true penalty cycles.",
"EventCode": "0xab",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Retired Instructions who experienced DSB miss.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x1",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced a critical DSB miss.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
"PEBS": "1",
"PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced iTLB true miss.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x14",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x12",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L2_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x13",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x500106",
"PEBS": "1",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"MSRValue": "0x508006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"MSRValue": "0x501006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"MSRValue": "0x500206",
"PEBS": "1",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"MSRValue": "0x510006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x100206",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"MSRValue": "0x502006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
"MSRIndex": "0x3F7",
"MSRValue": "0x500406",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"MSRValue": "0x520006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"MSRValue": "0x504006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"MSRValue": "0x500806",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x15",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_DATA.STALLS]",
"EventCode": "0x80",
"EventName": "ICACHE_16B.IFDATA_STALL",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_DATA.STALLS]",
"SampleAfterValue": "500009",
"UMask": "0x4"
},
{
"BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_HIT",
"PublicDescription": "Counts instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_MISS",
"PublicDescription": "Counts instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_STALL",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_16B.IFDATA_STALL]",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALLS",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_16B.IFDATA_STALL]",
"SampleAfterValue": "500009",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles DSB is delivering optimal number of Uops",
"CounterMask": "5",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_ANY",
"PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles MITE is delivering optimal number of Uops",
"CounterMask": "5",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_OK",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES_ANY",
"PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
"SampleAfterValue": "2000003",
"UMask": "0x30"
},
{
"BriefDescription": "Number of switches from DSB or MITE to the MS",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_SWITCHES",
"PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
"SampleAfterValue": "100003",
"UMask": "0x30"
},
{
"BriefDescription": "Uops delivered to IDQ while MS is busy",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
"SampleAfterValue": "100003",
"UMask": "0x30"
},
{
"BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled",
"CounterMask": "5",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled",
"CounterMask": "1",
"EventCode": "0x9C",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
"PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
}
]

394
tools/perf/pmu-events/arch/x86/rocketlake/memory.json Normal file
View file

@ -0,0 +1,394 @@
[
{
"BriefDescription": "Cycles while L3 cache miss demand load is outstanding.",
"CounterMask": "2",
"EventCode": "0xA3",
"EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
"CounterMask": "6",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x6"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED",
"PublicDescription": "Counts the number of times HLE abort was triggered.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_EVENTS",
"PublicDescription": "Counts the number of times an HLE execution aborted due to unfriendly events (such as interrupts).",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_MEM",
"PublicDescription": "Counts the number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
"PublicDescription": "Counts the number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of times an HLE execution successfully committed",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.COMMIT",
"PublicDescription": "Counts the number of times HLE commit succeeded.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an HLE execution started.",
"EventCode": "0xc8",
"EventName": "HLE_RETIRED.START",
"PublicDescription": "Counts the number of times we entered an HLE region. Does not count nested transactions.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of machine clears due to memory ordering conflicts.",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
"PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "1009",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
"PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "20011",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
"PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "503",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
"PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
"PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
"PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "101",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
"PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "2003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
"PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "50021",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that was not supplied by the L3 cache.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that was not supplied by the L3 cache.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that was not supplied by the L3 cache.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that was not supplied by the L3 cache.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00400",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that was not supplied by the L3 cache.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00010",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that was not supplied by the L3 cache.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00020",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that was not supplied by the L3 cache.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC08000",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts streaming stores that was not supplied by the L3 cache.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.STREAMING_WR.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FFFC00800",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data read requests that miss the L3 cache.",
"EventCode": "0xb0",
"EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Cycles where at least one demand data read request known to have missed the L3 cache is pending.",
"CounterMask": "1",
"EventCode": "0x60",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
"PublicDescription": "Cycles where at least one demand data read request known to have missed the L3 cache is pending. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known to have missed the L3 cache.",
"SampleAfterValue": "1000003",
"UMask": "0x10"
},
{
"BriefDescription": "Number of times an RTM execution aborted.",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED",
"PublicDescription": "Counts the number of times RTM abort was triggered.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_EVENTS",
"PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEM",
"PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
"PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
"PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of times an RTM execution successfully committed",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.COMMIT",
"PublicDescription": "Counts the number of times RTM commit succeeded.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an RTM execution started.",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.START",
"PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed inside a transactional region",
"EventCode": "0x5d",
"EventName": "TX_EXEC.MISC2",
"PublicDescription": "Counts Unfriendly TSX abort triggered by a vzeroupper instruction.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an instruction execution caused the transactional nest count supported to be exceeded",
"EventCode": "0x5d",
"EventName": "TX_EXEC.MISC3",
"PublicDescription": "Counts Unfriendly TSX abort triggered by a nest count that is too deep.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_READ",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CONFLICT",
"PublicDescription": "Counts the number of times a TSX line had a cache conflict.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH",
"PublicDescription": "Counts the number of times a TSX Abort was triggered due to release/commit but data and address mismatch.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY",
"PublicDescription": "Counts the number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT",
"PublicDescription": "Counts the number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK",
"PublicDescription": "Counts the number of times a TSX Abort was triggered due to a non-release/commit store to lock.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.",
"EventCode": "0x54",
"EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL",
"PublicDescription": "Counts the number of times we could not allocate Lock Buffer.",
"SampleAfterValue": "100003",
"UMask": "0x40"
}
]

113
tools/perf/pmu-events/arch/x86/rocketlake/metricgroups.json Normal file
View file

@ -0,0 +1,113 @@
{
"Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
"TopdownL1": "Metrics for top-down breakdown at level 1",
"TopdownL2": "Metrics for top-down breakdown at level 2",
"TopdownL3": "Metrics for top-down breakdown at level 3",
"TopdownL4": "Metrics for top-down breakdown at level 4",
"TopdownL5": "Metrics for top-down breakdown at level 5",
"TopdownL6": "Metrics for top-down breakdown at level 6",
"tma_L1_group": "Metrics for top-down breakdown at level 1",
"tma_L2_group": "Metrics for top-down breakdown at level 2",
"tma_L3_group": "Metrics for top-down breakdown at level 3",
"tma_L4_group": "Metrics for top-down breakdown at level 4",
"tma_L5_group": "Metrics for top-down breakdown at level 5",
"tma_L6_group": "Metrics for top-down breakdown at level 6",
"tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category",
"tma_backend_bound_group": "Metrics contributing to tma_backend_bound category",
"tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
"tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
"tma_core_bound_group": "Metrics contributing to tma_core_bound category",
"tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
"tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
"tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
"tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category",
"tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category",
"tma_fp_arith_group": "Metrics contributing to tma_fp_arith category",
"tma_fp_vector_group": "Metrics contributing to tma_fp_vector category",
"tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category",
"tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category",
"tma_issue2P": "Metrics related by the issue $issue2P",
"tma_issueBC": "Metrics related by the issue $issueBC",
"tma_issueBM": "Metrics related by the issue $issueBM",
"tma_issueBW": "Metrics related by the issue $issueBW",
"tma_issueD0": "Metrics related by the issue $issueD0",
"tma_issueFB": "Metrics related by the issue $issueFB",
"tma_issueFL": "Metrics related by the issue $issueFL",
"tma_issueL1": "Metrics related by the issue $issueL1",
"tma_issueLat": "Metrics related by the issue $issueLat",
"tma_issueMC": "Metrics related by the issue $issueMC",
"tma_issueMS": "Metrics related by the issue $issueMS",
"tma_issueMV": "Metrics related by the issue $issueMV",
"tma_issueRFO": "Metrics related by the issue $issueRFO",
"tma_issueSL": "Metrics related by the issue $issueSL",
"tma_issueSO": "Metrics related by the issue $issueSO",
"tma_issueSmSt": "Metrics related by the issue $issueSmSt",
"tma_issueSpSt": "Metrics related by the issue $issueSpSt",
"tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
"tma_issueTLB": "Metrics related by the issue $issueTLB",
"tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
"tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
"tma_light_operations_group": "Metrics contributing to tma_light_operations category",
"tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category",
"tma_mem_latency_group": "Metrics contributing to tma_mem_latency category",
"tma_memory_bound_group": "Metrics contributing to tma_memory_bound category",
"tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category",
"tma_mite_group": "Metrics contributing to tma_mite category",
"tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category",
"tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category",
"tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category",
"tma_retiring_group": "Metrics contributing to tma_retiring category",
"tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category",
"tma_store_bound_group": "Metrics contributing to tma_store_bound category",
"tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category"
}

242
tools/perf/pmu-events/arch/x86/rocketlake/other.json Normal file
View file

@ -0,0 +1,242 @@
[
{
"BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.",
"EventCode": "0x28",
"EventName": "CORE_POWER.LVL0_TURBO_LICENSE",
"PublicDescription": "Counts Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.",
"SampleAfterValue": "200003",
"UMask": "0x7"
},
{
"BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule.",
"EventCode": "0x28",
"EventName": "CORE_POWER.LVL1_TURBO_LICENSE",
"PublicDescription": "Counts Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.",
"SampleAfterValue": "200003",
"UMask": "0x18"
},
{
"BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.",
"EventCode": "0x28",
"EventName": "CORE_POWER.LVL2_TURBO_LICENSE",
"PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchtecture). This includes high current AVX 512-bit instructions.",
"SampleAfterValue": "200003",
"UMask": "0x20"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that have any type of response.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that have any type of response.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10400",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000400",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts L1 data cache prefetch requests and software prefetches (except PREFETCHW) that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L1D_AND_SWPF.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000400",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that have any type of response.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10010",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000010",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch data reads (which bring data to L2) that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000010",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that have any type of response.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10020",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000020",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts hardware prefetch RFOs (which bring data to L2) that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000020",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that have any type of response.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x18000",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184008000",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts miscellaneous requests, such as I/O and un-cacheable accesses that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.OTHER.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184008000",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts streaming stores that have any type of response.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10800",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts streaming stores that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.STREAMING_WR.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000800",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts streaming stores that DRAM supplied the request.",
"EventCode": "0xB7, 0xBB",
"EventName": "OCR.STREAMING_WR.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x184000800",
"SampleAfterValue": "100003",
"UMask": "0x1"
}
]

801
tools/perf/pmu-events/arch/x86/rocketlake/pipeline.json Normal file
View file

@ -0,0 +1,801 @@
[
{
"BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.",
"CounterMask": "1",
"EventCode": "0x14",
"EventName": "ARITH.DIVIDER_ACTIVE",
"PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
"SampleAfterValue": "1000003",
"UMask": "0x9"
},
{
"BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.",
"EventCode": "0xc1",
"EventName": "ASSISTS.ANY",
"PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware Examples include AD (page Access Dirty), FP and AVX related assists.",
"SampleAfterValue": "100003",
"UMask": "0x7"
},
{
"BriefDescription": "All branch instructions retired.",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.ALL_BRANCHES",
"PEBS": "1",
"PublicDescription": "Counts all branch instructions retired.",
"SampleAfterValue": "400009"
},
{
"BriefDescription": "Conditional branch instructions retired.",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND",
"PEBS": "1",
"PublicDescription": "Counts conditional branch instructions retired.",
"SampleAfterValue": "400009",
"UMask": "0x11"
},
{
"BriefDescription": "Not taken branch instructions retired.",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND_NTAKEN",
"PEBS": "1",
"PublicDescription": "Counts not taken branch instructions retired.",
"SampleAfterValue": "400009",
"UMask": "0x10"
},
{
"BriefDescription": "Taken conditional branch instructions retired.",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.COND_TAKEN",
"PEBS": "1",
"PublicDescription": "Counts taken conditional branch instructions retired.",
"SampleAfterValue": "400009",
"UMask": "0x1"
},
{
"BriefDescription": "Far branch instructions retired.",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.FAR_BRANCH",
"PEBS": "1",
"PublicDescription": "Counts far branch instructions retired.",
"SampleAfterValue": "100007",
"UMask": "0x40"
},
{
"BriefDescription": "Indirect near branch instructions retired (excluding returns)",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.INDIRECT",
"PEBS": "1",
"PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Direct and indirect near call instructions retired.",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_CALL",
"PEBS": "1",
"PublicDescription": "Counts both direct and indirect near call instructions retired.",
"SampleAfterValue": "100007",
"UMask": "0x2"
},
{
"BriefDescription": "Return instructions retired.",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_RETURN",
"PEBS": "1",
"PublicDescription": "Counts return instructions retired.",
"SampleAfterValue": "100007",
"UMask": "0x8"
},
{
"BriefDescription": "Taken branch instructions retired.",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.NEAR_TAKEN",
"PEBS": "1",
"PublicDescription": "Counts taken branch instructions retired.",
"SampleAfterValue": "400009",
"UMask": "0x20"
},
{
"BriefDescription": "All mispredicted branch instructions retired.",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
"PEBS": "1",
"PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
"SampleAfterValue": "50021"
},
{
"BriefDescription": "Mispredicted conditional branch instructions retired.",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND",
"PEBS": "1",
"PublicDescription": "Counts mispredicted conditional branch instructions retired.",
"SampleAfterValue": "50021",
"UMask": "0x11"
},
{
"BriefDescription": "Mispredicted non-taken conditional branch instructions retired.",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND_NTAKEN",
"PEBS": "1",
"PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
"SampleAfterValue": "50021",
"UMask": "0x10"
},
{
"BriefDescription": "number of branch instructions retired that were mispredicted and taken.",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.COND_TAKEN",
"PEBS": "1",
"PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
"SampleAfterValue": "50021",
"UMask": "0x1"
},
{
"BriefDescription": "All miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT",
"PEBS": "1",
"PublicDescription": "Counts all miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).",
"SampleAfterValue": "50021",
"UMask": "0x80"
},
{
"BriefDescription": "Mispredicted indirect CALL instructions retired.",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
"PEBS": "1",
"PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
"SampleAfterValue": "50021",
"UMask": "0x2"
},
{
"BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
"PEBS": "1",
"PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
"SampleAfterValue": "50021",
"UMask": "0x20"
},
{
"BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.RET",
"PEBS": "1",
"PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
"SampleAfterValue": "50021",
"UMask": "0x8"
},
{
"BriefDescription": "Cycle counts are evenly distributed between active threads in the Core.",
"EventCode": "0xec",
"EventName": "CPU_CLK_UNHALTED.DISTRIBUTED",
"PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
"EventCode": "0x3C",
"EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
"PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.",
"SampleAfterValue": "25003",
"UMask": "0x2"
},
{
"BriefDescription": "Core crystal clock cycles. Cycle counts are evenly distributed between active threads in the Core.",
"EventCode": "0x3c",
"EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED",
"PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Reference cycles when the core is not in halt state.",
"EventName": "CPU_CLK_UNHALTED.REF_TSC",
"PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
"SampleAfterValue": "2000003",
"UMask": "0x3"
},
{
"BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
"EventCode": "0x3C",
"EventName": "CPU_CLK_UNHALTED.REF_XCLK",
"PublicDescription": "Counts core crystal clock cycles when the thread is unhalted.",
"SampleAfterValue": "25003",
"UMask": "0x1"
},
{
"BriefDescription": "Core cycles when the thread is not in halt state",
"EventName": "CPU_CLK_UNHALTED.THREAD",
"PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Thread cycles when thread is not in halt state",
"EventCode": "0x3C",
"EventName": "CPU_CLK_UNHALTED.THREAD_P",
"PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
"SampleAfterValue": "2000003"
},
{
"BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
"CounterMask": "8",
"EventCode": "0xA3",
"EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
"CounterMask": "1",
"EventCode": "0xA3",
"EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles while memory subsystem has an outstanding load.",
"CounterMask": "16",
"EventCode": "0xA3",
"EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
"SampleAfterValue": "1000003",
"UMask": "0x10"
},
{
"BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
"CounterMask": "12",
"EventCode": "0xA3",
"EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
"SampleAfterValue": "1000003",
"UMask": "0xc"
},
{
"BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
"CounterMask": "5",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x5"
},
{
"BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
"CounterMask": "20",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
"SampleAfterValue": "1000003",
"UMask": "0x14"
},
{
"BriefDescription": "Total execution stalls.",
"CounterMask": "4",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
"PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
"PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
"PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.",
"EventCode": "0xa6",
"EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
"PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Cycles where the Store Buffer was full and no loads caused an execution stall.",
"CounterMask": "2",
"EventCode": "0xA6",
"EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
"PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.",
"SampleAfterValue": "1000003",
"UMask": "0x40"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to DECODE.LCP]",
"EventCode": "0x87",
"EventName": "ILD_STALL.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to DECODE.LCP]",
"SampleAfterValue": "500009",
"UMask": "0x1"
},
{
"BriefDescription": "Instruction decoders utilized in a cycle",
"EventCode": "0x55",
"EventName": "INST_DECODED.DECODERS",
"PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
"EventName": "INST_RETIRED.ANY",
"PEBS": "1",
"PublicDescription": "Counts the number of instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of instructions retired. General Counter - architectural event",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.ANY_P",
"PEBS": "1",
"PublicDescription": "Counts the number of instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
"SampleAfterValue": "2000003"
},
{
"BriefDescription": "Number of all retired NOP instructions.",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.NOP",
"PEBS": "1",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Precise instruction retired event with a reduced effect of PEBS shadow in IP distribution",
"EventName": "INST_RETIRED.PREC_DIST",
"PEBS": "1",
"PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled. Use on Fixed Counter 0.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles without actually retired instructions.",
"CounterMask": "1",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.STALL_CYCLES",
"Invert": "1",
"PublicDescription": "This event counts cycles without actually retired instructions.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.",
"CounterMask": "1",
"EventCode": "0x0D",
"EventName": "INT_MISC.ALL_RECOVERY_CYCLES",
"PublicDescription": "Counts cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.",
"SampleAfterValue": "2000003",
"UMask": "0x3"
},
{
"BriefDescription": "Clears speculative count",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x0D",
"EventName": "INT_MISC.CLEARS_COUNT",
"PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
"SampleAfterValue": "500009",
"UMask": "0x1"
},
{
"BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
"EventCode": "0x0d",
"EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
"PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
"SampleAfterValue": "500009",
"UMask": "0x80"
},
{
"BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread",
"EventCode": "0x0D",
"EventName": "INT_MISC.RECOVERY_CYCLES",
"PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
"SampleAfterValue": "500009",
"UMask": "0x1"
},
{
"BriefDescription": "TMA slots where uops got dropped",
"EventCode": "0x0d",
"EventName": "INT_MISC.UOP_DROPPING",
"PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons",
"SampleAfterValue": "1000003",
"UMask": "0x10"
},
{
"BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.NO_SR",
"PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.",
"EventCode": "0x03",
"EventName": "LD_BLOCKS.STORE_FORWARD",
"PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "False dependencies due to partial compare on address.",
"EventCode": "0x07",
"EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
"PublicDescription": "Counts the number of times a load got blocked due to false dependencies due to partial compare on address.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts the number of demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.",
"EventCode": "0x4c",
"EventName": "LOAD_HIT_PREFETCH.SWPF",
"PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
"CounterMask": "1",
"EventCode": "0xA8",
"EventName": "LSD.CYCLES_ACTIVE",
"PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles optimal number of Uops delivered by the LSD, but did not come from the decoder.",
"CounterMask": "5",
"EventCode": "0xa8",
"EventName": "LSD.CYCLES_OK",
"PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of Uops delivered by the LSD.",
"EventCode": "0xa8",
"EventName": "LSD.UOPS",
"PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of machine clears (nukes) of any type.",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.COUNT",
"PublicDescription": "Counts the number of machine clears (nukes) of any type.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Self-modifying code (SMC) detected.",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.SMC",
"PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Increments whenever there is an update to the LBR array.",
"EventCode": "0xcc",
"EventName": "MISC_RETIRED.LBR_INSERTS",
"PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR to be enabled properly.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of retired PAUSE instructions. This event is not supported on first SKL and KBL products.",
"EventCode": "0xcc",
"EventName": "MISC_RETIRED.PAUSE_INST",
"PublicDescription": "Counts number of retired PAUSE instructions. This event is not supported on first SKL and KBL products.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
"EventCode": "0xa2",
"EventName": "RESOURCE_STALLS.SB",
"PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.",
"EventCode": "0xa2",
"EventName": "RESOURCE_STALLS.SCOREBOARD",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
"EventCode": "0x5e",
"EventName": "RS_EVENTS.EMPTY_CYCLES",
"PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into stravation periods (e.g. branch mispredictions or i-cache misses)",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x5E",
"EventName": "RS_EVENTS.EMPTY_END",
"Invert": "1",
"PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "TMA slots where no uops were being issued due to lack of back-end resources.",
"EventCode": "0xa4",
"EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
"PublicDescription": "Counts the number of Top-down Microarchitecture Analysis (TMA) method's slots where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.",
"SampleAfterValue": "10000003",
"UMask": "0x2"
},
{
"BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions",
"EventCode": "0xa4",
"EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
"PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by branch mispredictions. This event estimates number of operations that were issued but not retired from the speculative path as well as the out-of-order engine recovery past a branch misprediction.",
"SampleAfterValue": "10000003",
"UMask": "0x8"
},
{
"BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event",
"EventName": "TOPDOWN.SLOTS",
"PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).",
"SampleAfterValue": "10000003",
"UMask": "0x4"
},
{
"BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event",
"EventCode": "0xa4",
"EventName": "TOPDOWN.SLOTS_P",
"PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.",
"SampleAfterValue": "10000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of uops decoded out of instructions exclusively fetched by decoder 0",
"EventCode": "0x56",
"EventName": "UOPS_DECODED.DEC0",
"PublicDescription": "Uops exclusively fetched by decoder 0",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of uops executed on port 0",
"EventCode": "0xa1",
"EventName": "UOPS_DISPATCHED.PORT_0",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of uops executed on port 1",
"EventCode": "0xa1",
"EventName": "UOPS_DISPATCHED.PORT_1",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of uops executed on port 2 and 3",
"EventCode": "0xa1",
"EventName": "UOPS_DISPATCHED.PORT_2_3",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 2 and 3.",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of uops executed on port 4 and 9",
"EventCode": "0xa1",
"EventName": "UOPS_DISPATCHED.PORT_4_9",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 5 and 9.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Number of uops executed on port 5",
"EventCode": "0xa1",
"EventName": "UOPS_DISPATCHED.PORT_5",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.",
"SampleAfterValue": "2000003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of uops executed on port 6",
"EventCode": "0xa1",
"EventName": "UOPS_DISPATCHED.PORT_6",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.",
"SampleAfterValue": "2000003",
"UMask": "0x40"
},
{
"BriefDescription": "Number of uops executed on port 7 and 8",
"EventCode": "0xa1",
"EventName": "UOPS_DISPATCHED.PORT_7_8",
"PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 7 and 8.",
"SampleAfterValue": "2000003",
"UMask": "0x80"
},
{
"BriefDescription": "Number of uops executed on the core.",
"EventCode": "0xB1",
"EventName": "UOPS_EXECUTED.CORE",
"PublicDescription": "Counts the number of uops executed from any thread.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
"CounterMask": "1",
"EventCode": "0xB1",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
"PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
"CounterMask": "2",
"EventCode": "0xB1",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
"PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
"CounterMask": "3",
"EventCode": "0xB1",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
"PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
"CounterMask": "4",
"EventCode": "0xB1",
"EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
"PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles where at least 1 uop was executed per-thread",
"CounterMask": "1",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CYCLES_GE_1",
"PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where at least 2 uops were executed per-thread",
"CounterMask": "2",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CYCLES_GE_2",
"PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where at least 3 uops were executed per-thread",
"CounterMask": "3",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CYCLES_GE_3",
"PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where at least 4 uops were executed per-thread",
"CounterMask": "4",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.CYCLES_GE_4",
"PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
"CounterMask": "1",
"EventCode": "0xB1",
"EventName": "UOPS_EXECUTED.STALL_CYCLES",
"Invert": "1",
"PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
"EventCode": "0xb1",
"EventName": "UOPS_EXECUTED.THREAD",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts the number of x87 uops dispatched.",
"EventCode": "0xB1",
"EventName": "UOPS_EXECUTED.X87",
"PublicDescription": "Counts the number of x87 uops executed.",
"SampleAfterValue": "2000003",
"UMask": "0x10"
},
{
"BriefDescription": "Uops that RAT issues to RS",
"EventCode": "0x0e",
"EventName": "UOPS_ISSUED.ANY",
"PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when RAT does not issue Uops to RS for the thread",
"CounterMask": "1",
"EventCode": "0x0E",
"EventName": "UOPS_ISSUED.STALL_CYCLES",
"Invert": "1",
"PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
"EventCode": "0x0e",
"EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
"PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to 'Mixing Intel AVX and Intel SSE Code' section of the Optimization Guide.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Retirement slots used.",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.SLOTS",
"PublicDescription": "Counts the retirement slots used each cycle.",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles without actually retired uops.",
"CounterMask": "1",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.STALL_CYCLES",
"Invert": "1",
"PublicDescription": "This event counts cycles without actually retired uops.",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles with less than 10 actually retired uops.",
"CounterMask": "10",
"EventCode": "0xc2",
"EventName": "UOPS_RETIRED.TOTAL_CYCLES",
"Invert": "1",
"PublicDescription": "Counts the number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
"SampleAfterValue": "1000003",
"UMask": "0x2"
}
]

1571
tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json Normal file
View file

File diff suppressed because it is too large Load diff

74
tools/perf/pmu-events/arch/x86/rocketlake/uncore-interconnect.json Normal file
View file

@ -0,0 +1,74 @@
[
{
"BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, etc.",
"EventCode": "0x84",
"EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "ARB"
},
{
"BriefDescription": "Each cycle counts number of any coherent request at memory controller that were issued by any core. This event is not supported on ICL products but is supported on RKL products.",
"EventCode": "0x85",
"EventName": "UNC_ARB_DAT_OCCUPANCY.ALL",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "ARB"
},
{
"BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core. This event is not supported on ICL products but is supported on RKL products.",
"EventCode": "0x85",
"EventName": "UNC_ARB_DAT_OCCUPANCY.RD",
"PerPkg": "1",
"UMask": "0x2",
"Unit": "ARB"
},
{
"BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.",
"EventCode": "0x80",
"EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD",
"PerPkg": "1",
"UMask": "0x2",
"Unit": "ARB"
},
{
"BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches",
"EventCode": "0x81",
"EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD",
"PerPkg": "1",
"UMask": "0x2",
"Unit": "ARB"
},
{
"BriefDescription": "Each cycle counts number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from its allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic. This event is not supported on ICL products but is supported on RKL products.",
"EventCode": "0x80",
"EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "ARB"
},
{
"BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.",
"EventCode": "0x80",
"EventName": "UNC_ARB_TRK_OCCUPANCY.RD",
"PerPkg": "1",
"UMask": "0x2",
"Unit": "ARB"
},
{
"BriefDescription": "Total number of all outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
"EventCode": "0x81",
"EventName": "UNC_ARB_TRK_REQUESTS.ALL",
"PerPkg": "1",
"UMask": "0x1",
"Unit": "ARB"
},
{
"BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.",
"EventCode": "0x81",
"EventName": "UNC_ARB_TRK_REQUESTS.RD",
"PerPkg": "1",
"UMask": "0x2",
"Unit": "ARB"
}
]

9
tools/perf/pmu-events/arch/x86/rocketlake/uncore-other.json Normal file
View file

@ -0,0 +1,9 @@
[
{
"BriefDescription": "UNC_CLOCK.SOCKET",
"EventCode": "0xff",
"EventName": "UNC_CLOCK.SOCKET",
"PerPkg": "1",
"Unit": "CLOCK"
}
]

165
tools/perf/pmu-events/arch/x86/rocketlake/virtual-memory.json Normal file
View file

@ -0,0 +1,165 @@
[
{
"BriefDescription": "Loads that miss the DTLB and hit the STLB.",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.",
"CounterMask": "1",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 4K page.",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.",
"EventCode": "0x08",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Stores that miss the DTLB and hit the STLB.",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.",
"CounterMask": "1",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 4K page.",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.",
"EventCode": "0x49",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.STLB_HIT",
"PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.",
"CounterMask": "1",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.",
"EventCode": "0x85",
"EventName": "ITLB_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "DTLB flush attempts of the thread-specific entries",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.DTLB_THREAD",
"PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "STLB flush attempts",
"EventCode": "0xBD",
"EventName": "TLB_FLUSH.STLB_ANY",
"PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).",
"SampleAfterValue": "100007",
"UMask": "0x20"
}
]

2
tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
View file

@ -706,7 +706,7 @@
"BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions",
"EventCode": "0xa4",
"EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
"PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of specualtive operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.",
"PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.",
"SampleAfterValue": "10000003",
"UMask": "0x8"
},

8
tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
View file

@ -1938,28 +1938,28 @@
},
{
"BriefDescription": "Percentage of cycles in aborted transactions.",
"MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles",
"MetricExpr": "(max(cycles\\-t - cycles\\-ct, 0) / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_aborted_cycles",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of elisions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@",
"MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_elision",
"ScaleUnit": "1cycles / elision"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of transactions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@",
"MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_transaction",
"ScaleUnit": "1cycles / transaction"
},
{
"BriefDescription": "Percentage of cycles within a transaction region.",
"MetricExpr": "cpu@cycles\\-t@ / cycles",
"MetricExpr": "(cycles\\-t / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_transactional_cycles",
"ScaleUnit": "100%"

308
tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json
View file

@ -3156,6 +3156,23 @@
"UMask": "0xc88ffd01",
"Unit": "CHA"
},
{
"BriefDescription": "All requests issued from IA cores to CXL accelerator memory regions that hit the LLC.",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c0018101",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_INSERTS.IA_HIT_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c0008101",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts; DRd hits from local IA",
"EventCode": "0x35",
@ -3371,6 +3388,23 @@
"UMask": "0xc80f7e01",
"Unit": "CHA"
},
{
"BriefDescription": "All requests issued from IA cores to CXL accelerator memory regions that miss the LLC.",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c0018201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c0008201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts for DRd misses from local IA",
"EventCode": "0x35",
@ -3397,6 +3431,23 @@
"UMask": "0xc837fe01",
"Unit": "CHA"
},
{
"BriefDescription": "DRds issued from an IA core which miss the L3 and target memory in a CXL type 2 memory expander card.",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c8178201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8168201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts for DRds issued by IA Cores targeting DDR Mem that Missed the LLC",
"EventCode": "0x35",
@ -3442,6 +3493,15 @@
"UMask": "0xc827fe01",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8268201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts; DRd Opt Pref misses from local IA",
"EventCode": "0x35",
@ -3451,6 +3511,15 @@
"UMask": "0xc8a7fe01",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8a68201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts for DRds issued by iA Cores targeting PMM Mem that Missed the LLC",
"EventCode": "0x35",
@ -3469,6 +3538,23 @@
"UMask": "0xc897fe01",
"Unit": "CHA"
},
{
"BriefDescription": "L2 data prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c8978201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8968201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC",
"EventCode": "0x35",
@ -3603,6 +3689,23 @@
"UMask": "0xccd7fe01",
"Unit": "CHA"
},
{
"BriefDescription": "LLC data prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10ccd78201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10ccd68201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts; LLCPrefRFO misses from local IA",
"EventCode": "0x35",
@ -3612,6 +3715,23 @@
"UMask": "0xccc7fe01",
"Unit": "CHA"
},
{
"BriefDescription": "L2 RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c8878201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8868201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally",
"EventCode": "0x35",
@ -3701,6 +3821,23 @@
"UMask": "0x10c8038201",
"Unit": "CHA"
},
{
"BriefDescription": "RFOs issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c8078201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8068201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts RFO misses from local IA",
"EventCode": "0x35",
@ -3719,6 +3856,23 @@
"UMask": "0xc887fe01",
"Unit": "CHA"
},
{
"BriefDescription": "LLC RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10ccc78201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10ccc68201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Inserts; RFO prefetch misses from local IA",
"EventCode": "0x35",
@ -4427,6 +4581,23 @@
"UMask": "0xc88ffd01",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy for All requests issued from IA cores to CXL accelerator memory regions that hit the LLC.",
"EventCode": "0x36",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c0018101",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c0008101",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy; DRd hits from local IA",
"EventCode": "0x36",
@ -4644,6 +4815,23 @@
"UMask": "0xc80f7e01",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy for All requests issued from IA cores to CXL accelerator memory regions that miss the LLC.",
"EventCode": "0x36",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c0018201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c0008201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy for DRd misses from local IA",
"EventCode": "0x36",
@ -4672,6 +4860,23 @@
"UMask": "0xc837fe01",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy for DRds and equivalent opcodes issued from an IA core which miss the L3 and target memory in a CXL type 2 memory expander card.",
"EventCode": "0x36",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c8178201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8168201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy for DRds issued by iA Cores targeting DDR Mem that Missed the LLC",
"EventCode": "0x36",
@ -4717,6 +4922,15 @@
"UMask": "0xc827fe01",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8268201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy; DRd Opt Pref misses from local IA",
"EventCode": "0x36",
@ -4726,6 +4940,15 @@
"UMask": "0xc8a7fe01",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8a68201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy for DRds issued by iA Cores targeting PMM Mem that Missed the LLC",
"EventCode": "0x36",
@ -4744,6 +4967,23 @@
"UMask": "0xc897fe01",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy for L2 data prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.",
"EventCode": "0x36",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c8978201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8968201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC",
"EventCode": "0x36",
@ -4878,6 +5118,23 @@
"UMask": "0xccd7fe01",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy for LLC data prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.",
"EventCode": "0x36",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10ccd78201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10ccd68201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy; LLCPrefRFO misses from local IA",
"EventCode": "0x36",
@ -4887,6 +5144,23 @@
"UMask": "0xccc7fe01",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy for L2 RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.",
"EventCode": "0x36",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c8878201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8868201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally",
"EventCode": "0x36",
@ -4976,6 +5250,23 @@
"UMask": "0x10c8038201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy for RFOs issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.",
"EventCode": "0x36",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10c8078201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10c8068201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy; RFO misses from local IA",
"EventCode": "0x36",
@ -4994,6 +5285,23 @@
"UMask": "0xc887fe01",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy for LLC RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.",
"EventCode": "0x36",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_CXL_ACC",
"PerPkg": "1",
"UMask": "0x10ccc78201",
"Unit": "CHA"
},
{
"BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_CXL_ACC_LOCAL",
"EventCode": "0x35",
"EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_CXL_ACC_LOCAL",
"PerPkg": "1",
"PortMask": "0x000",
"UMask": "0x10ccc68201",
"Unit": "CHA"
},
{
"BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA",
"EventCode": "0x36",

2
tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json
View file

@ -3326,7 +3326,7 @@
"EventCode": "0x50",
"EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS",
"PerPkg": "1",
"PublicDescription": "Message Held : Parallel Success : ad and bl messages were actually slotted into the same flit in paralle",
"PublicDescription": "Message Held : Parallel Success : ad and bl messages were actually slotted into the same flit in parallel",
"UMask": "0x8",
"Unit": "M3UPI"
},

43
tools/perf/pmu-events/arch/x86/skylake/frontend.json
View file

@ -7,6 +7,14 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to ILD_STALL.LCP]",
"EventCode": "0x87",
"EventName": "DECODE.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to ILD_STALL.LCP]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches",
"EventCode": "0xAB",
@ -245,27 +253,34 @@
"UMask": "0x2"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_STALL",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.DSB_CYCLES_OK]",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
"PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop [This event is alias to IDQ.DSB_CYCLES_ANY]",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_ANY]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
@ -296,6 +311,24 @@
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop [This event is alias to IDQ.ALL_DSB_CYCLES_ANY_UOPS]",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_ANY_UOPS]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
"PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"EventCode": "0x79",

17
tools/perf/pmu-events/arch/x86/skylake/pipeline.json
View file

@ -352,10 +352,10 @@
"UMask": "0x1"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to DECODE.LCP]",
"EventCode": "0x87",
"EventName": "ILD_STALL.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to DECODE.LCP]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
@ -479,11 +479,11 @@
"UMask": "0x1"
},
{
"BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
"BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder. [This event is alias to LSD.CYCLES_OK]",
"CounterMask": "4",
"EventCode": "0xA8",
"EventName": "LSD.CYCLES_4_UOPS",
"PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
"PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector). [This event is alias to LSD.CYCLES_OK]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
@ -496,6 +496,15 @@
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder. [This event is alias to LSD.CYCLES_4_UOPS]",
"CounterMask": "4",
"EventCode": "0xA8",
"EventName": "LSD.CYCLES_OK",
"PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector). [This event is alias to LSD.CYCLES_4_UOPS]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of Uops delivered by the LSD.",
"EventCode": "0xA8",

8
tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
View file

@ -1466,28 +1466,28 @@
},
{
"BriefDescription": "Percentage of cycles in aborted transactions.",
"MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles",
"MetricExpr": "(max(cycles\\-t - cycles\\-ct, 0) / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_aborted_cycles",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of elisions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@",
"MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_elision",
"ScaleUnit": "1cycles / elision"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of transactions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@",
"MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_transaction",
"ScaleUnit": "1cycles / transaction"
},
{
"BriefDescription": "Percentage of cycles within a transaction region.",
"MetricExpr": "cpu@cycles\\-t@ / cycles",
"MetricExpr": "(cycles\\-t / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_transactional_cycles",
"ScaleUnit": "100%"

43
tools/perf/pmu-events/arch/x86/skylakex/frontend.json
View file

@ -7,6 +7,14 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to ILD_STALL.LCP]",
"EventCode": "0x87",
"EventName": "DECODE.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to ILD_STALL.LCP]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches",
"EventCode": "0xAB",
@ -245,27 +253,34 @@
"UMask": "0x2"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_STALL",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.DSB_CYCLES_OK]",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
"PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
"PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop [This event is alias to IDQ.DSB_CYCLES_ANY]",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_ANY]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
@ -296,6 +311,24 @@
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop [This event is alias to IDQ.ALL_DSB_CYCLES_ANY_UOPS]",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_ANY_UOPS]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
"CounterMask": "4",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_OK",
"PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
"SampleAfterValue": "2000003",
"UMask": "0x18"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"EventCode": "0x79",

17
tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
View file

@ -361,10 +361,10 @@
"UMask": "0x1"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to DECODE.LCP]",
"EventCode": "0x87",
"EventName": "ILD_STALL.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to DECODE.LCP]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
@ -488,11 +488,11 @@
"UMask": "0x1"
},
{
"BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
"BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder. [This event is alias to LSD.CYCLES_OK]",
"CounterMask": "4",
"EventCode": "0xA8",
"EventName": "LSD.CYCLES_4_UOPS",
"PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
"PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector). [This event is alias to LSD.CYCLES_OK]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
@ -505,6 +505,15 @@
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder. [This event is alias to LSD.CYCLES_4_UOPS]",
"CounterMask": "4",
"EventCode": "0xA8",
"EventName": "LSD.CYCLES_OK",
"PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector). [This event is alias to LSD.CYCLES_4_UOPS]",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of Uops delivered by the LSD.",
"EventCode": "0xA8",

8
tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
View file

@ -1774,28 +1774,28 @@
},
{
"BriefDescription": "Percentage of cycles in aborted transactions.",
"MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles",
"MetricExpr": "(max(cycles\\-t - cycles\\-ct, 0) / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_aborted_cycles",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of elisions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@",
"MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_elision",
"ScaleUnit": "1cycles / elision"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of transactions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@",
"MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_transaction",
"ScaleUnit": "1cycles / transaction"
},
{
"BriefDescription": "Percentage of cycles within a transaction region.",
"MetricExpr": "cpu@cycles\\-t@ / cycles",
"MetricExpr": "(cycles\\-t / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_transactional_cycles",
"ScaleUnit": "100%"

2
tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json
View file

@ -6504,7 +6504,7 @@
"EventCode": "0x52",
"EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS",
"PerPkg": "1",
"PublicDescription": "ad and bl messages were actually slotted into the same flit in paralle",
"PublicDescription": "ad and bl messages were actually slotted into the same flit in parallel",
"UMask": "0x8",
"Unit": "M3UPI"
},

2
tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json
View file

@ -1952,7 +1952,7 @@
"EventCode": "0x81",
"EventName": "UNC_M_WPQ_OCCUPANCY",
"PerPkg": "1",
"PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts?",
"PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.",
"Unit": "iMC"
},
{

32
tools/perf/pmu-events/arch/x86/tigerlake/frontend.json
View file

@ -7,6 +7,14 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to ILD_STALL.LCP]",
"EventCode": "0x87",
"EventName": "DECODE.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to ILD_STALL.LCP]",
"SampleAfterValue": "500009",
"UMask": "0x1"
},
{
"BriefDescription": "Decode Stream Buffer (DSB)-to-MITE transitions count.",
"CounterMask": "1",
@ -213,10 +221,10 @@
"UMask": "0x1"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_DATA.STALLS]",
"EventCode": "0x80",
"EventName": "ICACHE_16B.IFDATA_STALL",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_DATA.STALLS]",
"SampleAfterValue": "500009",
"UMask": "0x4"
},
@ -237,10 +245,26 @@
"UMask": "0x2"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
"EventCode": "0x83",
"EventName": "ICACHE_64B.IFTAG_STALL",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_16B.IFDATA_STALL]",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALLS",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_16B.IFDATA_STALL]",
"SampleAfterValue": "500009",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]",
"SampleAfterValue": "200003",
"UMask": "0x4"
},

6
tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json
View file

@ -335,10 +335,10 @@
"UMask": "0x80"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to DECODE.LCP]",
"EventCode": "0x87",
"EventName": "ILD_STALL.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to DECODE.LCP]",
"SampleAfterValue": "500009",
"UMask": "0x1"
},
@ -564,7 +564,7 @@
"BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions",
"EventCode": "0xa4",
"EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
"PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by branch mispredictions. This event estimates number of operations that were issued but not retired from the specualtive path as well as the out-of-order engine recovery past a branch misprediction.",
"PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by branch mispredictions. This event estimates number of operations that were issued but not retired from the speculative path as well as the out-of-order engine recovery past a branch misprediction.",
"SampleAfterValue": "10000003",
"UMask": "0x8"
},

8
tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
View file

@ -1530,28 +1530,28 @@
},
{
"BriefDescription": "Percentage of cycles in aborted transactions.",
"MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles",
"MetricExpr": "(max(cycles\\-t - cycles\\-ct, 0) / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_aborted_cycles",
"ScaleUnit": "100%"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of elisions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@",
"MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_elision",
"ScaleUnit": "1cycles / elision"
},
{
"BriefDescription": "Number of cycles within a transaction divided by the number of transactions.",
"MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@",
"MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_cycles_per_transaction",
"ScaleUnit": "1cycles / transaction"
},
{
"BriefDescription": "Percentage of cycles within a transaction region.",
"MetricExpr": "cpu@cycles\\-t@ / cycles",
"MetricExpr": "(cycles\\-t / cycles if has_event(cycles\\-t) else 0)",
"MetricGroup": "transaction",
"MetricName": "tsx_transactional_cycles",
"ScaleUnit": "100%"

8
tools/perf/pmu-events/metric.py
View file

@ -408,6 +408,12 @@ def source_count(event: Event) -> Function:
return Function('source_count', event)
def has_event(event: Event) -> Function:
# pylint: disable=redefined-builtin
# pylint: disable=invalid-name
return Function('has_event', event)
class Metric:
"""An individual metric that will specifiable on the perf command line."""
groups: Set[str]
@ -539,7 +545,7 @@ def ParsePerfJson(orig: str) -> Expression:
r'Event(r"\1")', py)
py = re.sub(r'#Event\(r"([^"]*)"\)', r'Literal("#\1")', py)
py = re.sub(r'([0-9]+)Event\(r"(e[0-9]+)"\)', r'\1\2', py)
keywords = ['if', 'else', 'min', 'max', 'd_ratio', 'source_count']
keywords = ['if', 'else', 'min', 'max', 'd_ratio', 'source_count', 'has_event']
for kw in keywords:
py = re.sub(rf'Event\(r"{kw}"\)', kw, py)

1
tools/perf/tests/builtin-test.c
View file

@ -542,7 +542,6 @@ int cmd_test(int argc, const char **argv)
return run_workload(workload, argc, argv);
symbol_conf.priv_size = sizeof(int);
symbol_conf.sort_by_name = true;
symbol_conf.try_vmlinux_path = true;
if (symbol__init(NULL) < 0)

4
tools/perf/tests/expr.c
View file

@ -254,6 +254,10 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
TEST_ASSERT_VAL("source count", hashmap__size(ctx->ids) == 1);
TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1", &val_ptr));
/* has_event returns 1 when an event exists. */
expr__add_id_val(ctx, strdup("cycles"), 2);
ret = test(ctx, "has_event(cycles)", 1);
expr__ctx_free(ctx);
return 0;

4
tools/perf/tests/make
View file

@ -70,6 +70,8 @@ make_python_perf_so := $(python_perf_so)
make_debug := DEBUG=1
make_nondistro := BUILD_NONDISTRO=1
make_extra_tests := EXTRA_TESTS=1
make_bpf_skel := BUILD_BPF_SKEL=1
make_gen_vmlinux_h := BUILD_BPF_SKEL=1 GEN_VMLINUX_H=1
make_no_libperl := NO_LIBPERL=1
make_no_libpython := NO_LIBPYTHON=1
make_no_scripts := NO_LIBPYTHON=1 NO_LIBPERL=1
@ -137,6 +139,8 @@ endif
run += make_python_perf_so
run += make_debug
run += make_nondistro
run += make_build_bpf_skel
run += make_gen_vmlinux_h
run += make_no_libperl
run += make_no_libpython
run += make_no_scripts

100
tools/perf/tests/parse-events.c
View file

@ -20,6 +20,20 @@
#define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
static int num_core_entries(void)
{
/*
* If the kernel supports extended type, expect events to be
* opened once for each core PMU type. Otherwise fall back to the legacy
* behavior of opening only one event even though there are multiple
* PMUs
*/
if (perf_pmus__supports_extended_type())
return perf_pmus__num_core_pmus();
return 1;
}
static bool test_config(const struct evsel *evsel, __u64 expected_config)
{
__u32 type = evsel->core.attr.type;
@ -108,10 +122,21 @@ static int test__checkevent_raw(struct evlist *evlist)
TEST_ASSERT_VAL("wrong number of entries", 0 != evlist->core.nr_entries);
perf_evlist__for_each_evsel(&evlist->core, evsel) {
struct perf_pmu *pmu = NULL;
struct perf_pmu *pmu __maybe_unused = NULL;
bool type_matched = false;
TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, 0x1a));
TEST_ASSERT_VAL("event not parsed as raw type",
evsel->attr.type == PERF_TYPE_RAW);
#if defined(__aarch64__)
/*
* Arm doesn't have a real raw type PMU in sysfs, so raw events
* would never match any PMU. However, RAW events on Arm will
* always successfully open on the first available core PMU
* so no need to test for a matching type here.
*/
type_matched = raw_type_match = true;
#else
while ((pmu = perf_pmus__scan(pmu)) != NULL) {
if (pmu->type == evsel->attr.type) {
TEST_ASSERT_VAL("PMU type expected once", !type_matched);
@ -120,6 +145,7 @@ static int test__checkevent_raw(struct evlist *evlist)
raw_type_match = true;
}
}
#endif
TEST_ASSERT_VAL("No PMU found for type", type_matched);
}
TEST_ASSERT_VAL("Raw PMU not matched", raw_type_match);
@ -327,7 +353,7 @@ static int test__checkevent_symbolic_name_modifier(struct evlist *evlist)
struct perf_evsel *evsel;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == perf_pmus__num_core_pmus());
evlist->core.nr_entries == num_core_entries());
perf_evlist__for_each_entry(&evlist->core, evsel) {
TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
@ -830,11 +856,11 @@ static int test__group1(struct evlist *evlist)
struct evsel *evsel, *leader;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (perf_pmus__num_core_pmus() * 2));
evlist->core.nr_entries == (num_core_entries() * 2));
TEST_ASSERT_VAL("wrong number of groups",
evlist__nr_groups(evlist) == perf_pmus__num_core_pmus());
evlist__nr_groups(evlist) == num_core_entries());
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* instructions:k */
evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -873,7 +899,7 @@ static int test__group2(struct evlist *evlist)
struct evsel *evsel, *leader = NULL;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (2 * perf_pmus__num_core_pmus() + 1));
evlist->core.nr_entries == (2 * num_core_entries() + 1));
/*
* TODO: Currently the software event won't be grouped with the hardware
* event except for 1 PMU.
@ -1039,11 +1065,11 @@ static int test__group4(struct evlist *evlist __maybe_unused)
struct evsel *evsel, *leader;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (perf_pmus__num_core_pmus() * 2));
evlist->core.nr_entries == (num_core_entries() * 2));
TEST_ASSERT_VAL("wrong number of groups",
perf_pmus__num_core_pmus() == evlist__nr_groups(evlist));
num_core_entries() == evlist__nr_groups(evlist));
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* cycles:u + p */
evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1084,11 +1110,11 @@ static int test__group5(struct evlist *evlist __maybe_unused)
struct evsel *evsel = NULL, *leader;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (5 * perf_pmus__num_core_pmus()));
evlist->core.nr_entries == (5 * num_core_entries()));
TEST_ASSERT_VAL("wrong number of groups",
evlist__nr_groups(evlist) == (2 * perf_pmus__num_core_pmus()));
evlist__nr_groups(evlist) == (2 * num_core_entries()));
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* cycles + G */
evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1119,7 +1145,7 @@ static int test__group5(struct evlist *evlist __maybe_unused)
TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
TEST_ASSERT_VAL("wrong sample_read", !evsel->sample_read);
}
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* cycles:G */
evsel = leader = evsel__next(evsel);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1149,7 +1175,7 @@ static int test__group5(struct evlist *evlist __maybe_unused)
TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
TEST_ASSERT_VAL("wrong group_idx", evsel__group_idx(evsel) == 1);
}
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* cycles */
evsel = evsel__next(evsel);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1170,11 +1196,11 @@ static int test__group_gh1(struct evlist *evlist)
struct evsel *evsel = NULL, *leader;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (2 * perf_pmus__num_core_pmus()));
evlist->core.nr_entries == (2 * num_core_entries()));
TEST_ASSERT_VAL("wrong number of groups",
evlist__nr_groups(evlist) == perf_pmus__num_core_pmus());
evlist__nr_groups(evlist) == num_core_entries());
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* cycles + :H group modifier */
evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1211,11 +1237,11 @@ static int test__group_gh2(struct evlist *evlist)
struct evsel *evsel = NULL, *leader;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (2 * perf_pmus__num_core_pmus()));
evlist->core.nr_entries == (2 * num_core_entries()));
TEST_ASSERT_VAL("wrong number of groups",
evlist__nr_groups(evlist) == perf_pmus__num_core_pmus());
evlist__nr_groups(evlist) == num_core_entries());
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* cycles + :G group modifier */
evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1252,11 +1278,11 @@ static int test__group_gh3(struct evlist *evlist)
struct evsel *evsel = NULL, *leader;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (2 * perf_pmus__num_core_pmus()));
evlist->core.nr_entries == (2 * num_core_entries()));
TEST_ASSERT_VAL("wrong number of groups",
evlist__nr_groups(evlist) == perf_pmus__num_core_pmus());
evlist__nr_groups(evlist) == num_core_entries());
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* cycles:G + :u group modifier */
evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1293,11 +1319,11 @@ static int test__group_gh4(struct evlist *evlist)
struct evsel *evsel = NULL, *leader;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (2 * perf_pmus__num_core_pmus()));
evlist->core.nr_entries == (2 * num_core_entries()));
TEST_ASSERT_VAL("wrong number of groups",
evlist__nr_groups(evlist) == perf_pmus__num_core_pmus());
evlist__nr_groups(evlist) == num_core_entries());
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* cycles:G + :uG group modifier */
evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1334,9 +1360,9 @@ static int test__leader_sample1(struct evlist *evlist)
struct evsel *evsel = NULL, *leader;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (3 * perf_pmus__num_core_pmus()));
evlist->core.nr_entries == (3 * num_core_entries()));
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* cycles - sampling group leader */
evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1386,9 +1412,9 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused)
struct evsel *evsel = NULL, *leader;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (2 * perf_pmus__num_core_pmus()));
evlist->core.nr_entries == (2 * num_core_entries()));
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* instructions - sampling group leader */
evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1425,9 +1451,9 @@ static int test__checkevent_pinned_modifier(struct evlist *evlist)
struct evsel *evsel = NULL;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == perf_pmus__num_core_pmus());
evlist->core.nr_entries == num_core_entries());
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
evsel = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
@ -1443,9 +1469,9 @@ static int test__pinned_group(struct evlist *evlist)
struct evsel *evsel = NULL, *leader;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (3 * perf_pmus__num_core_pmus()));
evlist->core.nr_entries == (3 * num_core_entries()));
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* cycles - group leader */
evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1488,9 +1514,9 @@ static int test__exclusive_group(struct evlist *evlist)
struct evsel *evsel = NULL, *leader;
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (3 * perf_pmus__num_core_pmus()));
evlist->core.nr_entries == 3 * num_core_entries());
for (int i = 0; i < perf_pmus__num_core_pmus(); i++) {
for (int i = 0; i < num_core_entries(); i++) {
/* cycles - group leader */
evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel));
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
@ -1562,7 +1588,7 @@ static int test__checkevent_precise_max_modifier(struct evlist *evlist)
struct evsel *evsel = evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries",
evlist->core.nr_entries == (1 + perf_pmus__num_core_pmus()));
evlist->core.nr_entries == 1 + num_core_entries());
TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type);
TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_SW_TASK_CLOCK));
return TEST_OK;

3
tools/perf/tests/pe-file-parsing.c
View file

@ -34,6 +34,7 @@ static int run_dir(const char *d)
struct dso *dso;
struct symbol *sym;
int ret;
size_t idx;
scnprintf(filename, PATH_MAX, "%s/pe-file.exe", d);
ret = filename__read_build_id(filename, &bid);
@ -61,7 +62,7 @@ static int run_dir(const char *d)
TEST_ASSERT_VAL("Failed to load symbols", ret == 0);
dso__sort_by_name(dso);
sym = dso__find_symbol_by_name(dso, "main");
sym = dso__find_symbol_by_name(dso, "main", &idx);
TEST_ASSERT_VAL("Failed to find main", sym);
dso__delete(dso);

36
tools/perf/tests/shell/lock_contention.sh
View file

@ -233,6 +233,41 @@ test_aggr_task_stack_filter()
fi
}
test_csv_output()
{
echo "Testing perf lock contention CSV output"
perf lock contention -i ${perfdata} -E 1 -x , --output ${result}
# count the number of commas in the header
# it should have 5: contended, total-wait, max-wait, avg-wait, type, caller
header=$(grep "# output:" ${result} | tr -d -c , | wc -c)
if [ "${header}" != "5" ]; then
echo "[Fail] Recorded result does not have enough output columns: ${header} != 5"
err=1
exit
fi
# count the number of commas in the output
output=$(grep -v "^#" ${result} | tr -d -c , | wc -c)
if [ "${header}" != "${output}" ]; then
echo "[Fail] Recorded result does not match the number of commas: ${header} != ${output}"
err=1
exit
fi
if ! perf lock con -b true > /dev/null 2>&1 ; then
echo "[Skip] No BPF support"
return
fi
# the perf lock contention output goes to the stderr
perf lock con -a -b -E 1 -x , --output ${result} -- perf bench sched messaging > /dev/null 2>&1
output=$(grep -v "^#" ${result} | tr -d -c , | wc -c)
if [ "${header}" != "${output}" ]; then
echo "[Fail] BPF result does not match the number of commas: ${header} != ${output}"
err=1
exit
fi
}
check
test_record
@ -244,5 +279,6 @@ test_type_filter
test_lock_filter
test_stack_filter
test_aggr_task_stack_filter
test_csv_output
exit ${err}

1
tools/perf/util/bpf_skel/.gitignore vendored
View file

@ -1,3 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
.tmp
*.skel.h
vmlinux.h

2
tools/perf/util/bpf_skel/lock_contention.bpf.c
View file

@ -416,8 +416,6 @@ int contention_end(u64 *ctx)
return 0;
}
struct rq {};
extern struct rq runqueues __ksym;
struct rq___old {

10
tools/perf/util/bpf_skel/vmlinux.h → tools/perf/util/bpf_skel/vmlinux/vmlinux.h
View file

@ -171,4 +171,14 @@ struct bpf_perf_event_data_kern {
struct perf_sample_data *data;
struct perf_event *event;
} __attribute__((preserve_access_index));
/*
* If 'struct rq' isn't defined for lock_contention.bpf.c, for the sake of
* rq___old and rq___new, then the type for the 'runqueue' variable ends up
* being a forward declaration (BTF_KIND_FWD) while the kernel has it defined
* (BTF_KIND_STRUCT). The definition appears in vmlinux.h rather than
* lock_contention.bpf.c for consistency with a generated vmlinux.h.
*/
struct rq {};
#endif // __VMLINUX_H

7
tools/perf/util/dso.c
View file

@ -1320,7 +1320,9 @@ struct dso *dso__new_id(const char *name, struct dso_id *id)
dso->id = *id;
dso__set_long_name_id(dso, dso->name, id, false);
dso__set_short_name(dso, dso->name, false);
dso->symbols = dso->symbol_names = RB_ROOT_CACHED;
dso->symbols = RB_ROOT_CACHED;
dso->symbol_names = NULL;
dso->symbol_names_len = 0;
dso->data.cache = RB_ROOT;
dso->inlined_nodes = RB_ROOT_CACHED;
dso->srclines = RB_ROOT_CACHED;
@ -1364,7 +1366,8 @@ void dso__delete(struct dso *dso)
inlines__tree_delete(&dso->inlined_nodes);
srcline__tree_delete(&dso->srclines);
symbols__delete(&dso->symbols);
dso->symbol_names_len = 0;
zfree(&dso->symbol_names);
if (dso->short_name_allocated) {
zfree((char **)&dso->short_name);
dso->short_name_allocated = false;

3
tools/perf/util/dso.h
View file

@ -150,7 +150,8 @@ struct dso {
struct rb_node rb_node; /* rbtree node sorted by long name */
struct rb_root *root; /* root of rbtree that rb_node is in */
struct rb_root_cached symbols;
struct rb_root_cached symbol_names;
struct symbol **symbol_names;
size_t symbol_names_len;
struct rb_root_cached inlined_nodes;
struct rb_root_cached srclines;
struct {

7
tools/perf/util/event.c
View file

@ -581,15 +581,14 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
maps__zput(al->maps);
map__zput(al->map);
thread__zput(al->thread);
al->thread = thread__get(thread);
al->addr = addr;
al->cpumode = cpumode;
al->filtered = 0;
if (machine == NULL) {
al->map = NULL;
if (machine == NULL)
return NULL;
}
if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
al->level = 'k';
@ -605,7 +604,6 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
al->level = 'u';
} else {
al->level = 'H';
al->map = NULL;
if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
cpumode == PERF_RECORD_MISC_GUEST_KERNEL) &&
@ -619,7 +617,6 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
return NULL;
}
al->maps = maps__get(maps);
al->thread = thread__get(thread);
al->map = map__get(maps__find(maps, al->addr));
if (al->map != NULL) {
/*

30
tools/perf/util/evsel.c
View file

@ -2924,25 +2924,19 @@ static bool find_process(const char *name)
return ret ? false : true;
}
static bool is_amd(const char *arch, const char *cpuid)
int __weak arch_evsel__open_strerror(struct evsel *evsel __maybe_unused,
char *msg __maybe_unused,
size_t size __maybe_unused)
{
return arch && !strcmp("x86", arch) && cpuid && strstarts(cpuid, "AuthenticAMD");
}
static bool is_amd_ibs(struct evsel *evsel)
{
return evsel->core.attr.precise_ip
|| (evsel->pmu_name && !strncmp(evsel->pmu_name, "ibs", 3));
return 0;
}
int evsel__open_strerror(struct evsel *evsel, struct target *target,
int err, char *msg, size_t size)
{
struct perf_env *env = evsel__env(evsel);
const char *arch = perf_env__arch(env);
const char *cpuid = perf_env__cpuid(env);
char sbuf[STRERR_BUFSIZE];
int printed = 0, enforced = 0;
int ret;
switch (err) {
case EPERM:
@ -3044,16 +3038,6 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
return scnprintf(msg, size,
"Invalid event (%s) in per-thread mode, enable system wide with '-a'.",
evsel__name(evsel));
if (is_amd(arch, cpuid)) {
if (is_amd_ibs(evsel)) {
if (evsel->core.attr.exclude_kernel)
return scnprintf(msg, size,
"AMD IBS can't exclude kernel events. Try running at a higher privilege level.");
if (!evsel->core.system_wide)
return scnprintf(msg, size,
"AMD IBS may only be available in system-wide/per-cpu mode. Try using -a, or -C and workload affinity");
}
}
break;
case ENODATA:
@ -3063,6 +3047,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
break;
}
ret = arch_evsel__open_strerror(evsel, msg, size);
if (ret)
return ret;
return scnprintf(msg, size,
"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
"/bin/dmesg | grep -i perf may provide additional information.\n",

1
tools/perf/util/evsel.h
View file

@ -311,6 +311,7 @@ void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier);
void arch_evsel__set_sample_weight(struct evsel *evsel);
void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr);
int arch_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size);
int evsel__set_filter(struct evsel *evsel, const char *filter);
int evsel__append_tp_filter(struct evsel *evsel, const char *filter);

21
tools/perf/util/expr.c
View file

@ -8,6 +8,7 @@
#include "cpumap.h"
#include "cputopo.h"
#include "debug.h"
#include "evlist.h"
#include "expr.h"
#include "expr-bison.h"
#include "expr-flex.h"
@ -474,3 +475,23 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx
pr_debug2("literal: %s = %f\n", literal, result);
return result;
}
/* Does the event 'id' parse? Determine via ctx->ids if possible. */
double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id)
{
struct evlist *tmp;
double ret;
if (hashmap__find(ctx->ids, id, /*value=*/NULL))
return 1.0;
if (!compute_ids)
return 0.0;
tmp = evlist__new();
if (!tmp)
return NAN;
ret = parse_event(tmp, id) ? 0 : 1;
evlist__delete(tmp);
return ret;
}

1
tools/perf/util/expr.h
View file

@ -54,5 +54,6 @@ int expr__find_ids(const char *expr, const char *one,
double expr_id_data__value(const struct expr_id_data *data);
double expr_id_data__source_count(const struct expr_id_data *data);
double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx);
double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id);
#endif

1
tools/perf/util/expr.l
View file

@ -113,6 +113,7 @@ min { return MIN; }
if { return IF; }
else { return ELSE; }
source_count { return SOURCE_COUNT; }
has_event { return HAS_EVENT; }
{literal} { return literal(yyscanner, sctx); }
{number} { return value(yyscanner); }
{symbol} { return str(yyscanner, ID, sctx->runtime); }

8
tools/perf/util/expr.y
View file

@ -37,7 +37,7 @@
} ids;
}
%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT EXPR_ERROR
%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT HAS_EVENT EXPR_ERROR
%left MIN MAX IF
%left '|'
%left '^'
@ -199,6 +199,12 @@ expr: NUMBER
}
| ID { $$ = handle_id(ctx, $1, compute_ids, /*source_count=*/false); }
| SOURCE_COUNT '(' ID ')' { $$ = handle_id(ctx, $3, compute_ids, /*source_count=*/true); }
| HAS_EVENT '(' ID ')'
{
$$.val = expr__has_event(ctx, compute_ids, $3);
$$.ids = NULL;
free($3);
}
| expr '|' expr
{
if (is_const($1.val) && is_const($3.val)) {

4
tools/perf/util/llvm-utils.c
View file

@ -25,7 +25,7 @@
"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
"-Wno-unused-value -Wno-pointer-sign " \
"-working-directory $WORKING_DIR " \
"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -g -O2 -o - $LLVM_OPTIONS_PIPE"
"-c \"$CLANG_SOURCE\" --target=bpf $CLANG_EMIT_LLVM -g -O2 -o - $LLVM_OPTIONS_PIPE"
struct llvm_param llvm_param = {
.clang_path = "clang",
@ -569,7 +569,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
pr_err("ERROR:\tunable to compile %s\n", path);
pr_err("Hint:\tCheck error message shown above.\n");
pr_err("Hint:\tYou can also pre-compile it into .o using:\n");
pr_err(" \t\tclang -target bpf -O2 -c %s\n", path);
pr_err(" \t\tclang --target=bpf -O2 -c %s\n", path);
pr_err(" \twith proper -I and -D options.\n");
goto errout;
}

14
tools/perf/util/map.c
View file

@ -390,7 +390,7 @@ struct symbol *map__find_symbol(struct map *map, u64 addr)
return dso__find_symbol(map__dso(map), addr);
}
struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
struct symbol *map__find_symbol_by_name_idx(struct map *map, const char *name, size_t *idx)
{
struct dso *dso;
@ -398,10 +398,16 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
return NULL;
dso = map__dso(map);
if (!dso__sorted_by_name(dso))
dso__sort_by_name(dso);
dso__sort_by_name(dso);
return dso__find_symbol_by_name(dso, name);
return dso__find_symbol_by_name(dso, name, idx);
}
struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
{
size_t idx;
return map__find_symbol_by_name_idx(map, name, &idx);
}
struct map *map__clone(struct map *from)

12
tools/perf/util/map.h
View file

@ -148,16 +148,17 @@ struct thread;
* @map: the 'struct map *' in which symbols are iterated
* @sym_name: the symbol name
* @pos: the 'struct symbol *' to use as a loop cursor
* @idx: the cursor index in the symbol names array
*/
#define __map__for_each_symbol_by_name(map, sym_name, pos) \
for (pos = map__find_symbol_by_name(map, sym_name); \
#define __map__for_each_symbol_by_name(map, sym_name, pos, idx) \
for (pos = map__find_symbol_by_name_idx(map, sym_name, &idx); \
pos && \
!symbol__match_symbol_name(pos->name, sym_name, \
SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); \
pos = symbol__next_by_name(pos))
pos = dso__next_symbol_by_name(map__dso(map), &idx))
#define map__for_each_symbol_by_name(map, sym_name, pos) \
__map__for_each_symbol_by_name(map, sym_name, (pos))
#define map__for_each_symbol_by_name(map, sym_name, pos, idx) \
__map__for_each_symbol_by_name(map, sym_name, (pos), idx)
void map__init(struct map *map,
u64 start, u64 end, u64 pgoff, struct dso *dso);
@ -202,6 +203,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
int map__load(struct map *map);
struct symbol *map__find_symbol(struct map *map, u64 addr);
struct symbol *map__find_symbol_by_name(struct map *map, const char *name);
struct symbol *map__find_symbol_by_name_idx(struct map *map, const char *name, size_t *idx);
void map__fixup_start(struct map *map);
void map__fixup_end(struct map *map);

186
tools/perf/util/perf_event_attr_fprintf.c
View file

@ -1,11 +1,13 @@
// SPDX-License-Identifier: GPL-2.0
#include <inttypes.h>
#include <stdio.h>
#include <stdlib.h>
#include <stdbool.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/perf_event.h>
#include "util/evsel_fprintf.h"
#include "trace-event.h"
struct bit_names {
int bit;
@ -71,6 +73,170 @@ static void __p_read_format(char *buf, size_t size, u64 value)
__p_bits(buf, size, value, bits);
}
#define ENUM_ID_TO_STR_CASE(x) case x: return (#x);
static const char *stringify_perf_type_id(u64 value)
{
switch (value) {
ENUM_ID_TO_STR_CASE(PERF_TYPE_HARDWARE)
ENUM_ID_TO_STR_CASE(PERF_TYPE_SOFTWARE)
ENUM_ID_TO_STR_CASE(PERF_TYPE_TRACEPOINT)
ENUM_ID_TO_STR_CASE(PERF_TYPE_HW_CACHE)
ENUM_ID_TO_STR_CASE(PERF_TYPE_RAW)
ENUM_ID_TO_STR_CASE(PERF_TYPE_BREAKPOINT)
default:
return NULL;
}
}
static const char *stringify_perf_hw_id(u64 value)
{
switch (value) {
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CPU_CYCLES)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_INSTRUCTIONS)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_REFERENCES)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_MISSES)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_BRANCH_MISSES)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_BUS_CYCLES)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_STALLED_CYCLES_FRONTEND)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_STALLED_CYCLES_BACKEND)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_REF_CPU_CYCLES)
default:
return NULL;
}
}
static const char *stringify_perf_hw_cache_id(u64 value)
{
switch (value) {
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_L1D)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_L1I)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_LL)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_DTLB)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_ITLB)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_BPU)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_NODE)
default:
return NULL;
}
}
static const char *stringify_perf_hw_cache_op_id(u64 value)
{
switch (value) {
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_OP_READ)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_OP_WRITE)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_OP_PREFETCH)
default:
return NULL;
}
}
static const char *stringify_perf_hw_cache_op_result_id(u64 value)
{
switch (value) {
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_RESULT_ACCESS)
ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_RESULT_MISS)
default:
return NULL;
}
}
static const char *stringify_perf_sw_id(u64 value)
{
switch (value) {
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_CPU_CLOCK)
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_TASK_CLOCK)
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_PAGE_FAULTS)
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_CONTEXT_SWITCHES)
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_CPU_MIGRATIONS)
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_PAGE_FAULTS_MIN)
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_PAGE_FAULTS_MAJ)
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_ALIGNMENT_FAULTS)
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_EMULATION_FAULTS)
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_DUMMY)
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_BPF_OUTPUT)
ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_CGROUP_SWITCHES)
default:
return NULL;
}
}
#undef ENUM_ID_TO_STR_CASE
#define PRINT_ID(_s, _f) \
do { \
const char *__s = _s; \
if (__s == NULL) \
snprintf(buf, size, _f, value); \
else \
snprintf(buf, size, _f" (%s)", value, __s); \
} while (0)
#define print_id_unsigned(_s) PRINT_ID(_s, "%"PRIu64)
#define print_id_hex(_s) PRINT_ID(_s, "%#"PRIx64)
static void __p_type_id(char *buf, size_t size, u64 value)
{
print_id_unsigned(stringify_perf_type_id(value));
}
static void __p_config_hw_id(char *buf, size_t size, u64 value)
{
print_id_hex(stringify_perf_hw_id(value));
}
static void __p_config_sw_id(char *buf, size_t size, u64 value)
{
print_id_hex(stringify_perf_sw_id(value));
}
static void __p_config_hw_cache_id(char *buf, size_t size, u64 value)
{
const char *hw_cache_str = stringify_perf_hw_cache_id(value & 0xff);
const char *hw_cache_op_str =
stringify_perf_hw_cache_op_id((value & 0xff00) >> 8);
const char *hw_cache_op_result_str =
stringify_perf_hw_cache_op_result_id((value & 0xff0000) >> 16);
if (hw_cache_str == NULL || hw_cache_op_str == NULL ||
hw_cache_op_result_str == NULL) {
snprintf(buf, size, "%#"PRIx64, value);
} else {
snprintf(buf, size, "%#"PRIx64" (%s | %s | %s)", value,
hw_cache_op_result_str, hw_cache_op_str, hw_cache_str);
}
}
#ifdef HAVE_LIBTRACEEVENT
static void __p_config_tracepoint_id(char *buf, size_t size, u64 value)
{
char *str = tracepoint_id_to_name(value);
print_id_hex(str);
free(str);
}
#endif
static void __p_config_id(char *buf, size_t size, u32 type, u64 value)
{
switch (type) {
case PERF_TYPE_HARDWARE:
return __p_config_hw_id(buf, size, value);
case PERF_TYPE_SOFTWARE:
return __p_config_sw_id(buf, size, value);
case PERF_TYPE_HW_CACHE:
return __p_config_hw_cache_id(buf, size, value);
case PERF_TYPE_TRACEPOINT:
#ifdef HAVE_LIBTRACEEVENT
return __p_config_tracepoint_id(buf, size, value);
#endif
case PERF_TYPE_RAW:
case PERF_TYPE_BREAKPOINT:
default:
snprintf(buf, size, "%#"PRIx64, value);
return;
}
}
#define BUF_SIZE 1024
#define p_hex(val) snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
@ -79,16 +245,18 @@ static void __p_read_format(char *buf, size_t size, u64 value)
#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val)
#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
#define p_read_format(val) __p_read_format(buf, BUF_SIZE, val)
#define p_type_id(val) __p_type_id(buf, BUF_SIZE, val)
#define p_config_id(val) __p_config_id(buf, BUF_SIZE, attr->type, val)
#define PRINT_ATTRn(_n, _f, _p) \
#define PRINT_ATTRn(_n, _f, _p, _a) \
do { \
if (attr->_f) { \
if (_a || attr->_f) { \
_p(attr->_f); \
ret += attr__fprintf(fp, _n, buf, priv);\
} \
} while (0)
#define PRINT_ATTRf(_f, _p) PRINT_ATTRn(#_f, _f, _p)
#define PRINT_ATTRf(_f, _p) PRINT_ATTRn(#_f, _f, _p, false)
int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
attr__fprintf_f attr__fprintf, void *priv)
@ -96,10 +264,10 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
char buf[BUF_SIZE];
int ret = 0;
PRINT_ATTRf(type, p_unsigned);
PRINT_ATTRn("type", type, p_type_id, true);
PRINT_ATTRf(size, p_unsigned);
PRINT_ATTRf(config, p_hex);
PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
PRINT_ATTRn("config", config, p_config_id, true);
PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned, false);
PRINT_ATTRf(sample_type, p_sample_type);
PRINT_ATTRf(read_format, p_read_format);
@ -141,10 +309,10 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
PRINT_ATTRf(remove_on_exec, p_unsigned);
PRINT_ATTRf(sigtrap, p_unsigned);
PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned, false);
PRINT_ATTRf(bp_type, p_unsigned);
PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex, false);
PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex, false);
PRINT_ATTRf(branch_sample_type, p_branch_sample_type);
PRINT_ATTRf(sample_regs_user, p_hex);
PRINT_ATTRf(sample_stack_user, p_unsigned);

27
tools/perf/util/pmu.c
View file

@ -928,6 +928,31 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
return NULL;
}
/* Creates the PMU when sysfs scanning fails. */
struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus)
{
struct perf_pmu *pmu = zalloc(sizeof(*pmu));
if (!pmu)
return NULL;
pmu->name = strdup("cpu");
if (!pmu->name) {
free(pmu);
return NULL;
}
pmu->is_core = true;
pmu->type = PERF_TYPE_RAW;
pmu->cpus = cpu_map__online();
INIT_LIST_HEAD(&pmu->format);
INIT_LIST_HEAD(&pmu->aliases);
INIT_LIST_HEAD(&pmu->caps);
list_add_tail(&pmu->list, core_pmus);
return pmu;
}
void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu)
{
struct perf_pmu_format *format;
@ -1427,7 +1452,7 @@ bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu)
bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu)
{
return pmu->is_core && perf_pmus__num_core_pmus() == 1;
return !pmu->is_core || perf_pmus__num_core_pmus() == 1;
}
bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name)

1
tools/perf/util/pmu.h
View file

@ -286,6 +286,7 @@ int perf_pmu__event_source_devices_fd(void);
int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags);
struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name);
struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
void perf_pmu__delete(struct perf_pmu *pmu);
#endif /* __PMU_H */

7
tools/perf/util/pmus.c
View file

@ -153,7 +153,12 @@ static void pmu_read_sysfs(bool core_only)
closedir(dir);
if (core_only) {
read_sysfs_core_pmus = true;
if (!list_empty(&core_pmus))
read_sysfs_core_pmus = true;
else {
if (perf_pmu__create_placeholder_core_pmu(&core_pmus))
read_sysfs_core_pmus = true;
}
} else {
read_sysfs_core_pmus = true;
read_sysfs_all_pmus = true;

16
tools/perf/util/probe-event.c
View file

@ -74,7 +74,6 @@ int init_probe_symbol_maps(bool user_only)
{
int ret;
symbol_conf.sort_by_name = true;
symbol_conf.allow_aliases = true;
ret = symbol__init(NULL);
if (ret < 0) {
@ -382,6 +381,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
struct symbol *sym;
u64 address = 0;
int ret = -ENOENT;
size_t idx;
/* This can work only for function-name based one */
if (!pp->function || pp->file)
@ -392,7 +392,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
return -EINVAL;
/* Find the address of given function */
map__for_each_symbol_by_name(map, pp->function, sym) {
map__for_each_symbol_by_name(map, pp->function, sym, idx) {
if (uprobes) {
address = sym->start;
if (sym->type == STT_GNU_IFUNC)
@ -3738,7 +3738,6 @@ int del_perf_probe_events(struct strfilter *filter)
int show_available_funcs(const char *target, struct nsinfo *nsi,
struct strfilter *_filter, bool user)
{
struct rb_node *nd;
struct map *map;
struct dso *dso;
int ret;
@ -3767,17 +3766,16 @@ int show_available_funcs(const char *target, struct nsinfo *nsi,
goto end;
}
dso = map__dso(map);
if (!dso__sorted_by_name(dso))
dso__sort_by_name(dso);
dso__sort_by_name(dso);
/* Show all (filtered) symbols */
setup_pager();
for (nd = rb_first_cached(&dso->symbol_names); nd; nd = rb_next(nd)) {
struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
for (size_t i = 0; i < dso->symbol_names_len; i++) {
struct symbol *pos = dso->symbol_names[i];
if (strfilter__compare(_filter, pos->sym.name))
printf("%s\n", pos->sym.name);
if (strfilter__compare(_filter, pos->name))
printf("%s\n", pos->name);
}
end:
map__put(map);

8
tools/perf/util/python.c
View file

@ -123,6 +123,14 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp,
return 0;
}
/*
* Add this one here not to drag util/trace-event-info.c
*/
char *tracepoint_id_to_name(u64 config)
{
return NULL;
}
/*
* XXX: All these evsel destructors need some better mechanism, like a linked
* list of destructors registered when the relevant code indeed is used instead

140
tools/perf/util/symbol.c
View file

@ -440,38 +440,35 @@ static struct symbol *symbols__next(struct symbol *sym)
return NULL;
}
static void symbols__insert_by_name(struct rb_root_cached *symbols, struct symbol *sym)
static int symbols__sort_name_cmp(const void *vlhs, const void *vrhs)
{
struct rb_node **p = &symbols->rb_root.rb_node;
struct rb_node *parent = NULL;
struct symbol_name_rb_node *symn, *s;
bool leftmost = true;
const struct symbol *lhs = *((const struct symbol **)vlhs);
const struct symbol *rhs = *((const struct symbol **)vrhs);
symn = container_of(sym, struct symbol_name_rb_node, sym);
while (*p != NULL) {
parent = *p;
s = rb_entry(parent, struct symbol_name_rb_node, rb_node);
if (strcmp(sym->name, s->sym.name) < 0)
p = &(*p)->rb_left;
else {
p = &(*p)->rb_right;
leftmost = false;
}
}
rb_link_node(&symn->rb_node, parent, p);
rb_insert_color_cached(&symn->rb_node, symbols, leftmost);
return strcmp(lhs->name, rhs->name);
}
static void symbols__sort_by_name(struct rb_root_cached *symbols,
struct rb_root_cached *source)
static struct symbol **symbols__sort_by_name(struct rb_root_cached *source, size_t *len)
{
struct rb_node *nd;
struct symbol **result;
size_t i = 0, size = 0;
for (nd = rb_first_cached(source); nd; nd = rb_next(nd))
size++;
result = malloc(sizeof(*result) * size);
if (!result)
return NULL;
for (nd = rb_first_cached(source); nd; nd = rb_next(nd)) {
struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
symbols__insert_by_name(symbols, pos);
result[i++] = pos;
}
qsort(result, size, sizeof(*result), symbols__sort_name_cmp);
*len = size;
return result;
}
int symbol__match_symbol_name(const char *name, const char *str,
@ -491,48 +488,53 @@ int symbol__match_symbol_name(const char *name, const char *str,
return arch__compare_symbol_names(name, str);
}
static struct symbol *symbols__find_by_name(struct rb_root_cached *symbols,
static struct symbol *symbols__find_by_name(struct symbol *symbols[],
size_t symbols_len,
const char *name,
enum symbol_tag_include includes)
enum symbol_tag_include includes,
size_t *found_idx)
{
struct rb_node *n;
struct symbol_name_rb_node *s = NULL;
size_t i, lower = 0, upper = symbols_len;
struct symbol *s = NULL;
if (symbols == NULL)
if (found_idx)
*found_idx = SIZE_MAX;
if (!symbols_len)
return NULL;
n = symbols->rb_root.rb_node;
while (n) {
while (lower < upper) {
int cmp;
s = rb_entry(n, struct symbol_name_rb_node, rb_node);
cmp = symbol__match_symbol_name(s->sym.name, name, includes);
i = (lower + upper) / 2;
cmp = symbol__match_symbol_name(symbols[i]->name, name, includes);
if (cmp > 0)
n = n->rb_left;
upper = i;
else if (cmp < 0)
n = n->rb_right;
else
lower = i + 1;
else {
if (found_idx)
*found_idx = i;
s = symbols[i];
break;
}
if (n == NULL)
return NULL;
if (includes != SYMBOL_TAG_INCLUDE__DEFAULT_ONLY)
/* return first symbol that has same name (if any) */
for (n = rb_prev(n); n; n = rb_prev(n)) {
struct symbol_name_rb_node *tmp;
tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
if (arch__compare_symbol_names(tmp->sym.name, s->sym.name))
break;
s = tmp;
}
}
if (s && includes != SYMBOL_TAG_INCLUDE__DEFAULT_ONLY) {
/* return first symbol that has same name (if any) */
for (; i > 0; i--) {
struct symbol *tmp = symbols[i - 1];
return &s->sym;
if (!arch__compare_symbol_names(tmp->name, s->name)) {
if (found_idx)
*found_idx = i - 1;
s = tmp;
} else
break;
}
}
assert(!found_idx || !s || s == symbols[*found_idx]);
return s;
}
void dso__reset_find_symbol_cache(struct dso *dso)
@ -590,31 +592,41 @@ struct symbol *dso__next_symbol(struct symbol *sym)
return symbols__next(sym);
}
struct symbol *symbol__next_by_name(struct symbol *sym)
struct symbol *dso__next_symbol_by_name(struct dso *dso, size_t *idx)
{
struct symbol_name_rb_node *s = container_of(sym, struct symbol_name_rb_node, sym);
struct rb_node *n = rb_next(&s->rb_node);
if (*idx + 1 >= dso->symbol_names_len)
return NULL;
return n ? &rb_entry(n, struct symbol_name_rb_node, rb_node)->sym : NULL;
++*idx;
return dso->symbol_names[*idx];
}
/*
* Returns first symbol that matched with @name.
*/
struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name)
struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name, size_t *idx)
{
struct symbol *s = symbols__find_by_name(&dso->symbol_names, name,
SYMBOL_TAG_INCLUDE__NONE);
struct symbol *s = symbols__find_by_name(dso->symbol_names, dso->symbol_names_len,
name, SYMBOL_TAG_INCLUDE__NONE, idx);
if (!s)
s = symbols__find_by_name(&dso->symbol_names, name,
SYMBOL_TAG_INCLUDE__DEFAULT_ONLY);
s = symbols__find_by_name(dso->symbol_names, dso->symbol_names_len,
name, SYMBOL_TAG_INCLUDE__DEFAULT_ONLY, idx);
return s;
}
void dso__sort_by_name(struct dso *dso)
{
dso__set_sorted_by_name(dso);
return symbols__sort_by_name(&dso->symbol_names, &dso->symbols);
mutex_lock(&dso->lock);
if (!dso__sorted_by_name(dso)) {
size_t len;
dso->symbol_names = symbols__sort_by_name(&dso->symbols, &len);
if (dso->symbol_names) {
dso->symbol_names_len = len;
dso__set_sorted_by_name(dso);
}
}
mutex_unlock(&dso->lock);
}
/*
@ -2656,10 +2668,6 @@ int symbol__init(struct perf_env *env)
symbol__elf_init();
if (symbol_conf.sort_by_name)
symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
sizeof(struct symbol));
if (symbol_conf.try_vmlinux_path && vmlinux_path__init(env) < 0)
return -1;

12
tools/perf/util/symbol.h
View file

@ -43,8 +43,7 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
/**
* A symtab entry. When allocated this may be preceded by an annotation (see
* symbol__annotation), a browser_index (see symbol__browser_index) and rb_node
* to sort by name (see struct symbol_name_rb_node).
* symbol__annotation) and/or a browser_index (see symbol__browser_index).
*/
struct symbol {
struct rb_node rb_node;
@ -95,11 +94,6 @@ static inline size_t symbol__size(const struct symbol *sym)
struct strlist;
struct intlist;
struct symbol_name_rb_node {
struct rb_node rb_node;
struct symbol sym;
};
static inline int __symbol__join_symfs(char *bf, size_t size, const char *path)
{
return path__join(bf, size, symbol_conf.symfs, path);
@ -136,9 +130,9 @@ void dso__delete_symbol(struct dso *dso,
struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
struct symbol *dso__find_symbol_nocache(struct dso *dso, u64 addr);
struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);
struct symbol *symbol__next_by_name(struct symbol *sym);
struct symbol *dso__next_symbol_by_name(struct dso *dso, size_t *idx);
struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name, size_t *idx);
struct symbol *dso__first_symbol(struct dso *dso);
struct symbol *dso__last_symbol(struct dso *dso);

1
tools/perf/util/symbol_conf.h
View file

@ -18,7 +18,6 @@ struct symbol_conf {
show_kernel_path,
use_modules,
allow_aliases,
sort_by_name,
show_nr_samples,
show_total_period,
use_callchain,

10
tools/perf/util/symbol_fprintf.c
View file

@ -63,13 +63,11 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso,
FILE *fp)
{
size_t ret = 0;
struct rb_node *nd;
struct symbol_name_rb_node *pos;
for (nd = rb_first_cached(&dso->symbol_names); nd; nd = rb_next(nd)) {
pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
ret += fprintf(fp, "%s\n", pos->sym.name);
for (size_t i = 0; i < dso->symbol_names_len; i++) {
struct symbol *pos = dso->symbol_names[i];
ret += fprintf(fp, "%s\n", pos->name);
}
return ret;
}

12
tools/perf/util/trace-event-info.c
View file

@ -466,6 +466,18 @@ static struct tracepoint_path *tracepoint_id_to_path(u64 config)
return NULL;
}
char *tracepoint_id_to_name(u64 config)
{
struct tracepoint_path *path = tracepoint_id_to_path(config);
char *buf = NULL;
if (path && asprintf(&buf, "%s:%s", path->system, path->name) < 0)
buf = NULL;
put_tracepoints_path(path);
return buf;
}
static struct tracepoint_path *tracepoint_name_to_path(const char *name)
{
struct tracepoint_path *path = zalloc(sizeof(*path));

6
tools/perf/util/trace-event.h
View file

@ -62,6 +62,12 @@ unsigned long long eval_flag(const char *flag);
int read_tracing_data(int fd, struct list_head *pattrs);
/*
* Return the tracepoint name in the format "subsystem:event_name",
* callers should free the returned string.
*/
char *tracepoint_id_to_name(u64 config);
struct tracing_data {
/* size is only valid if temp is 'true' */
ssize_t size;

8
tools/perf/util/unwind-libdw.c
View file

@ -66,9 +66,13 @@ static int __report_module(struct addr_location *al, u64 ip,
mod = 0;
}
if (!mod)
mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1,
if (!mod) {
char filename[PATH_MAX];
__symbol__join_symfs(filename, sizeof(filename), dso->long_name);
mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
map__start(al->map) - map__pgoff(al->map), false);
}
if (!mod) {
char filename[PATH_MAX];