go/test/codegen/bits.go
Jake Ciolek 732f6fa9d5 cmd/compile: use ANDL for small immediates
We can rewrite ANDQ with an immediate fitting in 32bit with an ANDL, which is shorter to encode.

Looking at Go binary itself, before the change there was:

ANDL: 2337
ANDQ: 4476

After the change:

ANDL: 3790
ANDQ: 3024

So we got rid of 1452 ANDQs

This makes the Linux x86_64 binary 0.03% smaller.

There seems to be an impact on performance.

Intel Cascade Lake benchmarks (with perflock):

name                     old time/op    new time/op    delta
BinaryTree17-8              1.91s ± 1%     1.89s ± 1%  -1.22%  (p=0.000 n=21+18)
Fannkuch11-8                2.34s ± 0%     2.34s ± 0%    ~     (p=0.052 n=20+20)
FmtFprintfEmpty-8          27.7ns ± 1%    27.4ns ± 3%    ~     (p=0.497 n=21+21)
FmtFprintfString-8         53.2ns ± 0%    51.5ns ± 0%  -3.21%  (p=0.000 n=20+19)
FmtFprintfInt-8            57.3ns ± 0%    55.7ns ± 0%  -2.89%  (p=0.000 n=19+19)
FmtFprintfIntInt-8         92.3ns ± 0%    88.4ns ± 1%  -4.23%  (p=0.000 n=20+21)
FmtFprintfPrefixedInt-8     103ns ± 0%     103ns ± 0%  +0.23%  (p=0.000 n=20+21)
FmtFprintfFloat-8           147ns ± 0%     148ns ± 0%  +0.75%  (p=0.000 n=20+21)
FmtManyArgs-8               384ns ± 0%     381ns ± 0%  -0.63%  (p=0.000 n=21+21)
GobDecode-8                3.86ms ± 1%    3.88ms ± 1%  +0.52%  (p=0.000 n=20+21)
GobEncode-8                2.77ms ± 1%    2.77ms ± 0%    ~     (p=0.078 n=21+21)
Gzip-8                      168ms ± 1%     168ms ± 0%  +0.24%  (p=0.000 n=20+20)
Gunzip-8                   25.1ms ± 0%    24.3ms ± 0%  -3.03%  (p=0.000 n=21+21)
HTTPClientServer-8         61.4µs ± 8%    59.1µs ±10%    ~     (p=0.088 n=20+21)
JSONEncode-8               6.86ms ± 0%    6.70ms ± 0%  -2.29%  (p=0.000 n=20+19)
JSONDecode-8               30.8ms ± 1%    30.6ms ± 1%  -0.82%  (p=0.000 n=20+20)
Mandelbrot200-8            3.85ms ± 0%    3.85ms ± 0%    ~     (p=0.191 n=16+17)
GoParse-8                  2.61ms ± 2%    2.60ms ± 1%    ~     (p=0.561 n=21+20)
RegexpMatchEasy0_32-8      48.5ns ± 2%    45.9ns ± 3%  -5.26%  (p=0.000 n=20+21)
RegexpMatchEasy0_1K-8       139ns ± 0%     139ns ± 0%  +0.27%  (p=0.000 n=18+20)
RegexpMatchEasy1_32-8      41.3ns ± 0%    42.1ns ± 4%  +1.95%  (p=0.000 n=17+21)
RegexpMatchEasy1_1K-8       216ns ± 2%     216ns ± 0%  +0.17%  (p=0.020 n=21+19)
RegexpMatchMedium_32-8      790ns ± 7%     803ns ± 8%    ~     (p=0.178 n=21+21)
RegexpMatchMedium_1K-8     23.5µs ± 5%    23.7µs ± 5%    ~     (p=0.421 n=21+21)
RegexpMatchHard_32-8       1.09µs ± 1%    1.09µs ± 1%  -0.53%  (p=0.000 n=19+18)
RegexpMatchHard_1K-8       33.0µs ± 0%    33.0µs ± 0%    ~     (p=0.610 n=21+20)
Revcomp-8                   348ms ± 0%     353ms ± 0%  +1.38%  (p=0.000 n=17+18)
Template-8                 42.0ms ± 1%    41.9ms ± 1%  -0.30%  (p=0.049 n=20+20)
TimeParse-8                 185ns ± 0%     185ns ± 0%    ~     (p=0.387 n=20+18)
TimeFormat-8                237ns ± 1%     241ns ± 1%  +1.57%  (p=0.000 n=21+21)
[Geo mean]                 35.4µs         35.2µs       -0.66%

name                     old speed      new speed      delta
GobDecode-8               199MB/s ± 1%   198MB/s ± 1%  -0.52%  (p=0.000 n=20+21)
GobEncode-8               277MB/s ± 1%   277MB/s ± 0%    ~     (p=0.075 n=21+21)
Gzip-8                    116MB/s ± 1%   115MB/s ± 0%  -0.25%  (p=0.000 n=20+20)
Gunzip-8                  773MB/s ± 0%   797MB/s ± 0%  +3.12%  (p=0.000 n=21+21)
JSONEncode-8              283MB/s ± 0%   290MB/s ± 0%  +2.35%  (p=0.000 n=20+19)
JSONDecode-8             63.0MB/s ± 1%  63.5MB/s ± 1%  +0.82%  (p=0.000 n=20+20)
GoParse-8                22.2MB/s ± 2%  22.3MB/s ± 1%    ~     (p=0.539 n=21+20)
RegexpMatchEasy0_32-8     660MB/s ± 2%   697MB/s ± 3%  +5.57%  (p=0.000 n=20+21)
RegexpMatchEasy0_1K-8    7.36GB/s ± 0%  7.34GB/s ± 0%  -0.26%  (p=0.000 n=18+20)
RegexpMatchEasy1_32-8     775MB/s ± 0%   761MB/s ± 4%  -1.88%  (p=0.000 n=17+21)
RegexpMatchEasy1_1K-8    4.74GB/s ± 2%  4.74GB/s ± 0%  -0.18%  (p=0.020 n=21+19)
RegexpMatchMedium_32-8   40.6MB/s ± 7%  39.9MB/s ± 9%    ~     (p=0.191 n=21+21)
RegexpMatchMedium_1K-8   43.7MB/s ± 5%  43.2MB/s ± 5%    ~     (p=0.435 n=21+21)
RegexpMatchHard_32-8     29.3MB/s ± 1%  29.4MB/s ± 1%  +0.53%  (p=0.000 n=19+18)
RegexpMatchHard_1K-8     31.0MB/s ± 0%  31.0MB/s ± 0%    ~     (p=0.572 n=21+20)
Revcomp-8                 730MB/s ± 0%   720MB/s ± 0%  -1.36%  (p=0.000 n=17+18)
Template-8               46.2MB/s ± 1%  46.3MB/s ± 1%  +0.30%  (p=0.041 n=20+20)
[Geo mean]                204MB/s        205MB/s       +0.30%

Change-Id: Iac75d0ec184a515ce0e65e19559d5fe2e9840514
Reviewed-on: https://go-review.googlesource.com/c/go/+/354970
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
Trust: Josh Bleecher Snyder <josharian@gmail.com>
Trust: Keith Randall <khr@golang.org>
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
TryBot-Result: Go Bot <gobot@golang.org>
2021-10-12 22:02:39 +00:00

366 lines
6 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
import "math/bits"
/************************************
* 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 and shifted constant sources
func bitOpOnMem(a []uint32, b, c, d uint32) {
// amd64:`ANDL\s[$]200,\s\([A-Z][A-Z0-9]+\)`
a[0] &= 200
// amd64:`ORL\s[$]220,\s4\([A-Z][A-Z0-9]+\)`
a[1] |= 220
// amd64:`XORL\s[$]240,\s8\([A-Z][A-Z0-9]+\)`
a[2] ^= 240
}
func bitcheckMostNegative(b uint8) bool {
// amd64:"TESTB"
return b&0x80 == 0x80
}
// 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, z uint32, a []uint32, n, m uint64) uint64 {
// arm64:`EON\t`,-`EOR`,-`MVN`
a[0] = x ^ (y ^ 0xffffffff)
// arm64:`EON\t`,-`EOR`,-`MVN`
a[1] = ^(y ^ z)
// arm64:`EON\t`,-`XOR`
a[2] = x ^ ^z
// arm64:`EON\t`,-`EOR`,-`MVN`
return n ^ (m ^ 0xffffffffffffffff)
}
func op_orn(x, y uint32) uint32 {
// arm64:`ORN\t`,-`ORR`
return x | ^y
}
// check bitsets
func bitSetPowerOf2Test(x int) bool {
// amd64:"BTL\t[$]3"
return x&8 == 8
}
func bitSetTest(x int) bool {
// amd64:"ANDL\t[$]9, AX"
// amd64:"CMPQ\tAX, [$]9"
return x&9 == 9
}
// mask contiguous one bits
func cont1Mask64U(x uint64) uint64 {
// s390x:"RISBGZ\t[$]16, [$]47, [$]0,"
return x & 0x0000ffffffff0000
}
// mask contiguous zero bits
func cont0Mask64U(x uint64) uint64 {
// s390x:"RISBGZ\t[$]48, [$]15, [$]0,"
return x & 0xffff00000000ffff
}
func issue44228a(a []int64, i int) bool {
// amd64: "BTQ", -"SHL"
return a[i>>6]&(1<<(i&63)) != 0
}
func issue44228b(a []int32, i int) bool {
// amd64: "BTL", -"SHL"
return a[i>>5]&(1<<(i&31)) != 0
}
func issue48467(x, y uint64) uint64 {
// arm64: -"NEG"
d, borrow := bits.Sub64(x, y, 0)
return x - d&(-borrow)
}