go/test/codegen/bits.go
Ben Shi c6bf9a8109 cmd/compile: optimize AMD64's bit wise operation
Currently "arr[idx] |= 0x80" is compiled to MOVLload->BTSL->MOVLstore.
And this CL optimizes it to a single BTSLconstmodify. Other bit wise
operations with a direct memory operand are also implemented.

1. The size of the executable bin/go decreases about 4KB, and the total size
of pkg/linux_amd64 (excluding cmd/compile) decreases about 0.6KB.

2. There a little improvement in the go1 benchmark test (excluding noise).
name                     old time/op    new time/op    delta
BinaryTree17-4              2.66s ± 4%     2.66s ± 3%    ~     (p=0.596 n=49+49)
Fannkuch11-4                2.38s ± 2%     2.32s ± 2%  -2.69%  (p=0.000 n=50+50)
FmtFprintfEmpty-4          42.7ns ± 4%    43.2ns ± 7%  +1.31%  (p=0.009 n=50+50)
FmtFprintfString-4         71.0ns ± 5%    72.0ns ± 3%  +1.33%  (p=0.000 n=50+50)
FmtFprintfInt-4            80.7ns ± 4%    80.6ns ± 3%    ~     (p=0.931 n=50+50)
FmtFprintfIntInt-4          125ns ± 3%     126ns ± 4%    ~     (p=0.051 n=50+50)
FmtFprintfPrefixedInt-4     158ns ± 1%     142ns ± 3%  -9.84%  (p=0.000 n=36+50)
FmtFprintfFloat-4           215ns ± 4%     212ns ± 4%  -1.23%  (p=0.002 n=50+50)
FmtManyArgs-4               519ns ± 3%     510ns ± 3%  -1.77%  (p=0.000 n=50+50)
GobDecode-4                6.49ms ± 6%    6.52ms ± 5%    ~     (p=0.866 n=50+50)
GobEncode-4                5.93ms ± 8%    6.01ms ± 7%    ~     (p=0.076 n=50+50)
Gzip-4                      222ms ± 4%     224ms ± 8%  +0.80%  (p=0.001 n=50+50)
Gunzip-4                   36.6ms ± 5%    36.4ms ± 4%    ~     (p=0.093 n=50+50)
HTTPClientServer-4         59.1µs ± 1%    58.9µs ± 2%  -0.24%  (p=0.039 n=49+48)
JSONEncode-4               9.23ms ± 4%    9.21ms ± 5%    ~     (p=0.244 n=50+50)
JSONDecode-4               48.8ms ± 4%    48.7ms ± 4%    ~     (p=0.653 n=50+50)
Mandelbrot200-4            3.81ms ± 4%    3.80ms ± 3%    ~     (p=0.834 n=50+50)
GoParse-4                  3.20ms ± 5%    3.19ms ± 5%    ~     (p=0.494 n=50+50)
RegexpMatchEasy0_32-4      78.1ns ± 2%    77.4ns ± 3%  -0.86%  (p=0.005 n=50+50)
RegexpMatchEasy0_1K-4       233ns ± 3%     233ns ± 3%    ~     (p=0.074 n=50+50)
RegexpMatchEasy1_32-4      74.2ns ± 3%    73.4ns ± 3%  -1.06%  (p=0.000 n=50+50)
RegexpMatchEasy1_1K-4       369ns ± 2%     364ns ± 4%  -1.41%  (p=0.000 n=36+50)
RegexpMatchMedium_32-4      109ns ± 4%     107ns ± 3%  -2.06%  (p=0.001 n=50+50)
RegexpMatchMedium_1K-4     31.5µs ± 3%    30.8µs ± 3%  -2.20%  (p=0.000 n=50+50)
RegexpMatchHard_32-4       1.57µs ± 3%    1.56µs ± 2%  -0.57%  (p=0.016 n=50+50)
RegexpMatchHard_1K-4       47.4µs ± 4%    47.0µs ± 3%  -0.82%  (p=0.008 n=50+50)
Revcomp-4                   414ms ± 7%     412ms ± 7%    ~     (p=0.285 n=50+50)
Template-4                 64.3ms ± 4%    62.7ms ± 3%  -2.44%  (p=0.000 n=50+50)
TimeParse-4                 316ns ± 3%     313ns ± 3%    ~     (p=0.122 n=50+50)
TimeFormat-4                291ns ± 3%     293ns ± 3%  +0.80%  (p=0.001 n=50+50)
[Geo mean]                 46.5µs         46.2µs       -0.81%

name                     old speed      new speed      delta
GobDecode-4               118MB/s ± 6%   118MB/s ± 5%    ~     (p=0.863 n=50+50)
GobEncode-4               130MB/s ± 9%   128MB/s ± 8%    ~     (p=0.076 n=50+50)
Gzip-4                   87.4MB/s ± 4%  86.8MB/s ± 7%  -0.78%  (p=0.002 n=50+50)
Gunzip-4                  531MB/s ± 5%   533MB/s ± 4%    ~     (p=0.093 n=50+50)
JSONEncode-4              210MB/s ± 4%   211MB/s ± 5%    ~     (p=0.247 n=50+50)
JSONDecode-4             39.8MB/s ± 4%  39.9MB/s ± 4%    ~     (p=0.654 n=50+50)
GoParse-4                18.1MB/s ± 5%  18.2MB/s ± 5%    ~     (p=0.493 n=50+50)
RegexpMatchEasy0_32-4     410MB/s ± 2%   413MB/s ± 3%  +0.86%  (p=0.004 n=50+50)
RegexpMatchEasy0_1K-4    4.39GB/s ± 3%  4.38GB/s ± 3%    ~     (p=0.063 n=50+50)
RegexpMatchEasy1_32-4     432MB/s ± 3%   436MB/s ± 3%  +1.07%  (p=0.000 n=50+50)
RegexpMatchEasy1_1K-4    2.77GB/s ± 2%  2.81GB/s ± 4%  +1.46%  (p=0.000 n=36+50)
RegexpMatchMedium_32-4   9.16MB/s ± 3%  9.35MB/s ± 4%  +2.09%  (p=0.001 n=50+50)
RegexpMatchMedium_1K-4   32.5MB/s ± 3%  33.2MB/s ± 3%  +2.25%  (p=0.000 n=50+50)
RegexpMatchHard_32-4     20.4MB/s ± 3%  20.5MB/s ± 2%  +0.56%  (p=0.017 n=50+50)
RegexpMatchHard_1K-4     21.6MB/s ± 4%  21.8MB/s ± 3%  +0.83%  (p=0.008 n=50+50)
Revcomp-4                 613MB/s ± 4%   618MB/s ± 7%    ~     (p=0.152 n=48+50)
Template-4               30.2MB/s ± 4%  30.9MB/s ± 3%  +2.49%  (p=0.000 n=50+50)
[Geo mean]                127MB/s        128MB/s       +0.64%

Change-Id: If405198283855d75697f66cf894b2bef458f620e
Reviewed-on: https://go-review.googlesource.com/135422
Reviewed-by: Keith Randall <khr@golang.org>
2018-09-19 03:00:58 +00:00

317 lines
5 KiB
Go

// asmcheck
// Copyright 2018 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package codegen
/************************************
* 64-bit instructions
************************************/
func bitcheck64_constleft(a uint64) (n int) {
// amd64:"BTQ\t[$]63"
if a&(1<<63) != 0 {
return 1
}
// amd64:"BTQ\t[$]60"
if a&(1<<60) != 0 {
return 1
}
// amd64:"BTL\t[$]0"
if a&(1<<0) != 0 {
return 1
}
return 0
}
func bitcheck64_constright(a [8]uint64) (n int) {
// amd64:"BTQ\t[$]63"
if (a[0]>>63)&1 != 0 {
return 1
}
// amd64:"BTQ\t[$]63"
if a[1]>>63 != 0 {
return 1
}
// amd64:"BTQ\t[$]63"
if a[2]>>63 == 0 {
return 1
}
// amd64:"BTQ\t[$]60"
if (a[3]>>60)&1 == 0 {
return 1
}
// amd64:"BTL\t[$]1"
if (a[4]>>1)&1 == 0 {
return 1
}
// amd64:"BTL\t[$]0"
if (a[5]>>0)&1 == 0 {
return 1
}
// amd64:"BTL\t[$]7"
if (a[6]>>5)&4 == 0 {
return 1
}
return 0
}
func bitcheck64_var(a, b uint64) (n int) {
// amd64:"BTQ"
if a&(1<<(b&63)) != 0 {
return 1
}
// amd64:"BTQ",-"BT.\t[$]0"
if (b>>(a&63))&1 != 0 {
return 1
}
return 0
}
func bitcheck64_mask(a uint64) (n int) {
// amd64:"BTQ\t[$]63"
if a&0x8000000000000000 != 0 {
return 1
}
// amd64:"BTQ\t[$]59"
if a&0x800000000000000 != 0 {
return 1
}
// amd64:"BTL\t[$]0"
if a&0x1 != 0 {
return 1
}
return 0
}
func biton64(a, b uint64) (n uint64) {
// amd64:"BTSQ"
n += b | (1 << (a & 63))
// amd64:"BTSQ\t[$]63"
n += a | (1 << 63)
// amd64:"BTSQ\t[$]60"
n += a | (1 << 60)
// amd64:"ORQ\t[$]1"
n += a | (1 << 0)
return n
}
func bitoff64(a, b uint64) (n uint64) {
// amd64:"BTRQ"
n += b &^ (1 << (a & 63))
// amd64:"BTRQ\t[$]63"
n += a &^ (1 << 63)
// amd64:"BTRQ\t[$]60"
n += a &^ (1 << 60)
// amd64:"ANDQ\t[$]-2"
n += a &^ (1 << 0)
return n
}
func bitcompl64(a, b uint64) (n uint64) {
// amd64:"BTCQ"
n += b ^ (1 << (a & 63))
// amd64:"BTCQ\t[$]63"
n += a ^ (1 << 63)
// amd64:"BTCQ\t[$]60"
n += a ^ (1 << 60)
// amd64:"XORQ\t[$]1"
n += a ^ (1 << 0)
return n
}
/************************************
* 32-bit instructions
************************************/
func bitcheck32_constleft(a uint32) (n int) {
// amd64:"BTL\t[$]31"
if a&(1<<31) != 0 {
return 1
}
// amd64:"BTL\t[$]28"
if a&(1<<28) != 0 {
return 1
}
// amd64:"BTL\t[$]0"
if a&(1<<0) != 0 {
return 1
}
return 0
}
func bitcheck32_constright(a [8]uint32) (n int) {
// amd64:"BTL\t[$]31"
if (a[0]>>31)&1 != 0 {
return 1
}
// amd64:"BTL\t[$]31"
if a[1]>>31 != 0 {
return 1
}
// amd64:"BTL\t[$]31"
if a[2]>>31 == 0 {
return 1
}
// amd64:"BTL\t[$]28"
if (a[3]>>28)&1 == 0 {
return 1
}
// amd64:"BTL\t[$]1"
if (a[4]>>1)&1 == 0 {
return 1
}
// amd64:"BTL\t[$]0"
if (a[5]>>0)&1 == 0 {
return 1
}
// amd64:"BTL\t[$]7"
if (a[6]>>5)&4 == 0 {
return 1
}
return 0
}
func bitcheck32_var(a, b uint32) (n int) {
// amd64:"BTL"
if a&(1<<(b&31)) != 0 {
return 1
}
// amd64:"BTL",-"BT.\t[$]0"
if (b>>(a&31))&1 != 0 {
return 1
}
return 0
}
func bitcheck32_mask(a uint32) (n int) {
// amd64:"BTL\t[$]31"
if a&0x80000000 != 0 {
return 1
}
// amd64:"BTL\t[$]27"
if a&0x8000000 != 0 {
return 1
}
// amd64:"BTL\t[$]0"
if a&0x1 != 0 {
return 1
}
return 0
}
func biton32(a, b uint32) (n uint32) {
// amd64:"BTSL"
n += b | (1 << (a & 31))
// amd64:"BTSL\t[$]31"
n += a | (1 << 31)
// amd64:"BTSL\t[$]28"
n += a | (1 << 28)
// amd64:"ORL\t[$]1"
n += a | (1 << 0)
return n
}
func bitoff32(a, b uint32) (n uint32) {
// amd64:"BTRL"
n += b &^ (1 << (a & 31))
// amd64:"BTRL\t[$]31"
n += a &^ (1 << 31)
// amd64:"BTRL\t[$]28"
n += a &^ (1 << 28)
// amd64:"ANDL\t[$]-2"
n += a &^ (1 << 0)
return n
}
func bitcompl32(a, b uint32) (n uint32) {
// amd64:"BTCL"
n += b ^ (1 << (a & 31))
// amd64:"BTCL\t[$]31"
n += a ^ (1 << 31)
// amd64:"BTCL\t[$]28"
n += a ^ (1 << 28)
// amd64:"XORL\t[$]1"
n += a ^ (1 << 0)
return n
}
// check direct operation on memory with constant source
func bitOpOnMem(a []uint32) {
// amd64:`ANDL\s[$]200,\s\([A-Z]+\)`
a[0] &= 200
// amd64:`ORL\s[$]220,\s4\([A-Z]+\)`
a[1] |= 220
// amd64:`XORL\s[$]240,\s8\([A-Z]+\)`
a[2] ^= 240
// amd64:`BTRL\s[$]15,\s12\([A-Z]+\)`,-`ANDL`
a[3] &= 0xffff7fff
// amd64:`BTSL\s[$]14,\s16\([A-Z]+\)`,-`ORL`
a[4] |= 0x4000
// amd64:`BTCL\s[$]13,\s20\([A-Z]+\)`,-`XORL`
a[5] ^= 0x2000
}
// Check AND masking on arm64 (Issue #19857)
func and_mask_1(a uint64) uint64 {
// arm64:`AND\t`
return a & ((1 << 63) - 1)
}
func and_mask_2(a uint64) uint64 {
// arm64:`AND\t`
return a & (1 << 63)
}
func and_mask_3(a, b uint32) (uint32, uint32) {
// arm/7:`BIC`,-`AND`
a &= 0xffffaaaa
// arm/7:`BFC`,-`AND`,-`BIC`
b &= 0xffc003ff
return a, b
}
// Check generation of arm64 BIC/EON/ORN instructions
func op_bic(x, y uint32) uint32 {
// arm64:`BIC\t`,-`AND`
return x &^ y
}
func op_eon(x, y uint32) uint32 {
// arm64:`EON\t`,-`XOR`
return x ^ ^y
}
func op_orn(x, y uint32) uint32 {
// arm64:`ORN\t`,-`ORR`
return x | ^y
}