mirror of
https://github.com/python/cpython
synced 2024-07-21 18:25:47 +00:00
This is my patch:
[ 1005891 ] support --with-tsc on PPC plus a trivial change to settscdump's docstring and a Misc/NEWS entry.
This commit is contained in:
parent
d459f536c5
commit
800ba2375a
|
@ -57,6 +57,9 @@ Tools/Demos
|
|||
Build
|
||||
-----
|
||||
|
||||
- The --with-tsc flag to configure to enable VM profiling with the
|
||||
processor's timestamp counter now works on PPC platforms.
|
||||
|
||||
C API
|
||||
-----
|
||||
|
||||
|
|
|
@ -227,3 +227,28 @@ When this symbol is defined, the ceval mainloop and helper functions
|
|||
count the number of function calls made. It keeps detailed statistics
|
||||
about what kind of object was called and whether the call hit any of
|
||||
the special fast paths in the code.
|
||||
|
||||
---------------------------------------------------------------------------
|
||||
WITH_TSC introduced for Python 2.4
|
||||
|
||||
Super-lowlevel profiling of the interpreter. When enabled, the sys
|
||||
module grows a new function:
|
||||
|
||||
settscdump(bool)
|
||||
If true, tell the Python interpreter to dump VM measurements to
|
||||
stderr. If false, turn off dump. The measurements are based on the
|
||||
processor's time-stamp counter.
|
||||
|
||||
This build option requires a small amount of platform specific code.
|
||||
Currently this code is present for linux/x86 and any PowerPC platform
|
||||
that uses GCC (i.e. OS X and linux/ppc).
|
||||
|
||||
On the PowerPC the rate at which the time base register is incremented
|
||||
is not defined by the architecture specification, so you'll need to
|
||||
find the manual for your specific processor. For the 750CX, 750CXe,
|
||||
750FX (all sold as the G3) we find:
|
||||
|
||||
The time base counter is clocked at a frequency that is
|
||||
one-fourth that of the bus clock.
|
||||
|
||||
This build is enabled by the --with-tsc flag to configure.
|
||||
|
|
|
@ -17,10 +17,38 @@
|
|||
#include <ctype.h>
|
||||
|
||||
#ifdef WITH_TSC
|
||||
#include <asm/msr.h>
|
||||
|
||||
typedef unsigned long long uint64;
|
||||
|
||||
#if defined(__ppc__) /* <- Don't know if this is the correct symbol; this
|
||||
section should work for GCC on any PowerPC platform,
|
||||
irrespective of OS. POWER? Who knows :-) */
|
||||
|
||||
#define rdtscll(var) ppc_getcounter(&var)
|
||||
|
||||
static void
|
||||
ppc_getcounter(uint64 *v)
|
||||
{
|
||||
register unsigned long tbu, tb, tbu2;
|
||||
|
||||
loop:
|
||||
asm volatile ("mftbu %0" : "=r" (tbu) );
|
||||
asm volatile ("mftb %0" : "=r" (tb) );
|
||||
asm volatile ("mftbu %0" : "=r" (tbu2));
|
||||
if (__builtin_expect(tbu != tbu2, 0)) goto loop;
|
||||
|
||||
/* The slightly peculiar way of writing the next lines is
|
||||
compiled better by GCC than any other way I tried. */
|
||||
((long*)(v))[0] = tbu;
|
||||
((long*)(v))[1] = tb;
|
||||
}
|
||||
|
||||
#else /* this section is for linux/x86 */
|
||||
|
||||
#include <asm/msr.h>
|
||||
|
||||
#endif
|
||||
|
||||
void dump_tsc(int opcode, int ticked, uint64 inst0, uint64 inst1,
|
||||
uint64 loop0, uint64 loop1, uint64 intr0, uint64 intr1)
|
||||
{
|
||||
|
@ -34,6 +62,7 @@ void dump_tsc(int opcode, int ticked, uint64 inst0, uint64 inst1,
|
|||
fprintf(stderr, "opcode=%03d t=%d inst=%06lld loop=%06lld\n",
|
||||
opcode, ticked, inst, loop);
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
/* Turn this on if your compiler chokes on the big switch: */
|
||||
|
@ -545,6 +574,9 @@ PyEval_EvalFrame(PyFrameObject *f)
|
|||
rdtscll(inst1);
|
||||
rdtscll(loop0);
|
||||
rdtscll(loop1);
|
||||
|
||||
/* shut up the compiler */
|
||||
opcode = 0;
|
||||
#endif
|
||||
|
||||
/* Code access macros */
|
||||
|
|
|
@ -465,7 +465,7 @@ PyDoc_STRVAR(settscdump_doc,
|
|||
\n\
|
||||
If true, tell the Python interpreter to dump VM measurements to\n\
|
||||
stderr. If false, turn off dump. The measurements are based on the\n\
|
||||
Pentium time-stamp counter."
|
||||
processor's time-stamp counter."
|
||||
);
|
||||
#endif /* TSC */
|
||||
|
||||
|
|
Loading…
Reference in a new issue