qbit/go
1
0
Fork 0
mirror of https://github.com/golang/go synced 2024-11-19 14:44:40 -07:00
Code Releases Activity
d16a2ad09b
go/src/pkg/runtime/memclr_amd64.s

118 lines
2.1 KiB
ArmAsm
Raw Normal View History

runtime: faster memclr on x86. Use explicit SSE writes instead of REP STOSQ. benchmark old ns/op new ns/op delta BenchmarkMemclr5 22 5 -73.62% BenchmarkMemclr16 27 5 -78.49% BenchmarkMemclr64 28 6 -76.43% BenchmarkMemclr256 34 8 -74.94% BenchmarkMemclr4096 112 84 -24.73% BenchmarkMemclr65536 1902 1920 +0.95% LGTM=dvyukov R=golang-codereviews, dvyukov CC=golang-codereviews https://golang.org/cl/60090044
2014-02-06 18:43:22 -07:00
// Copyright 2014 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.
runtime: use unoptimized memmove and memclr on Plan 9 On Plan 9, the kernel disallows the use of floating point instructions while handling a note. Previously, we worked around this by using a simple loop in place of memmove. When I added that work-around, I verified that all paths from the note handler didn't end up calling memmove. Now that memclr is using SSE instructions, the same process will have to be done again. Instead of doing that, however, this CL just punts and uses unoptimized functions everywhere on Plan 9. LGTM=rsc R=rsc, 0intro CC=golang-codereviews https://golang.org/cl/73830044
2014-03-12 19:12:25 -06:00
// +build !plan9
runtime: faster memclr on x86. Use explicit SSE writes instead of REP STOSQ. benchmark old ns/op new ns/op delta BenchmarkMemclr5 22 5 -73.62% BenchmarkMemclr16 27 5 -78.49% BenchmarkMemclr64 28 6 -76.43% BenchmarkMemclr256 34 8 -74.94% BenchmarkMemclr4096 112 84 -24.73% BenchmarkMemclr65536 1902 1920 +0.95% LGTM=dvyukov R=golang-codereviews, dvyukov CC=golang-codereviews https://golang.org/cl/60090044
2014-02-06 18:43:22 -07:00
#include "../../cmd/ld/textflag.h"
// void runtime·memclr(void*, uintptr)
TEXT runtime·memclr(SB), NOSPLIT, $0-16
MOVQ ptr+0(FP), DI
MOVQ n+8(FP), BX
XORQ AX, AX
// MOVOU seems always faster than REP STOSQ.
clr_tail:
TESTQ BX, BX
JEQ clr_0
CMPQ BX, $2
JBE clr_1or2
CMPQ BX, $4
JBE clr_3or4
CMPQ BX, $8
JBE clr_5through8
CMPQ BX, $16
JBE clr_9through16
PXOR X0, X0
CMPQ BX, $32
JBE clr_17through32
CMPQ BX, $64
JBE clr_33through64
CMPQ BX, $128
JBE clr_65through128
CMPQ BX, $256
JBE clr_129through256
// TODO: use branch table and BSR to make this just a single dispatch
// TODO: for really big clears, use MOVNTDQ.
clr_loop:
MOVOU X0, 0(DI)
MOVOU X0, 16(DI)
MOVOU X0, 32(DI)
MOVOU X0, 48(DI)
MOVOU X0, 64(DI)
MOVOU X0, 80(DI)
MOVOU X0, 96(DI)
MOVOU X0, 112(DI)
MOVOU X0, 128(DI)
MOVOU X0, 144(DI)
MOVOU X0, 160(DI)
MOVOU X0, 176(DI)
MOVOU X0, 192(DI)
MOVOU X0, 208(DI)
MOVOU X0, 224(DI)
MOVOU X0, 240(DI)
SUBQ $256, BX
ADDQ $256, DI
CMPQ BX, $256
JAE clr_loop
JMP clr_tail
clr_1or2:
MOVB AX, (DI)
MOVB AX, -1(DI)(BX*1)
runtime: prevent pointless jmp in amd64 and 386 memmove 6a and 8a rearrange memmove such that the fallthrough from move_1or2 to move_0 ends up being a JMP to a RET. Insert an explicit RET to prevent such silliness. Do the same for memclr as prophylaxis. benchmark old ns/op new ns/op delta BenchmarkMemmove1 4.59 4.13 -10.02% BenchmarkMemmove2 4.58 4.13 -9.83% LGTM=khr R=golang-codereviews, dvyukov, minux, ruiu, bradfitz, khr CC=golang-codereviews https://golang.org/cl/120930043
2014-08-01 07:21:08 -06:00
RET
runtime: faster memclr on x86. Use explicit SSE writes instead of REP STOSQ. benchmark old ns/op new ns/op delta BenchmarkMemclr5 22 5 -73.62% BenchmarkMemclr16 27 5 -78.49% BenchmarkMemclr64 28 6 -76.43% BenchmarkMemclr256 34 8 -74.94% BenchmarkMemclr4096 112 84 -24.73% BenchmarkMemclr65536 1902 1920 +0.95% LGTM=dvyukov R=golang-codereviews, dvyukov CC=golang-codereviews https://golang.org/cl/60090044
2014-02-06 18:43:22 -07:00
clr_0:
RET
clr_3or4:
MOVW AX, (DI)
MOVW AX, -2(DI)(BX*1)
RET
clr_5through8:
MOVL AX, (DI)
MOVL AX, -4(DI)(BX*1)
RET
clr_9through16:
MOVQ AX, (DI)
MOVQ AX, -8(DI)(BX*1)
RET
clr_17through32:
MOVOU X0, (DI)
MOVOU X0, -16(DI)(BX*1)
RET
clr_33through64:
MOVOU X0, (DI)
MOVOU X0, 16(DI)
MOVOU X0, -32(DI)(BX*1)
MOVOU X0, -16(DI)(BX*1)
RET
clr_65through128:
MOVOU X0, (DI)
MOVOU X0, 16(DI)
MOVOU X0, 32(DI)
MOVOU X0, 48(DI)
MOVOU X0, -64(DI)(BX*1)
MOVOU X0, -48(DI)(BX*1)
MOVOU X0, -32(DI)(BX*1)
MOVOU X0, -16(DI)(BX*1)
RET
clr_129through256:
MOVOU X0, (DI)
MOVOU X0, 16(DI)
MOVOU X0, 32(DI)
MOVOU X0, 48(DI)
MOVOU X0, 64(DI)
MOVOU X0, 80(DI)
MOVOU X0, 96(DI)
MOVOU X0, 112(DI)
MOVOU X0, -128(DI)(BX*1)
MOVOU X0, -112(DI)(BX*1)
MOVOU X0, -96(DI)(BX*1)
MOVOU X0, -80(DI)(BX*1)
MOVOU X0, -64(DI)(BX*1)
MOVOU X0, -48(DI)(BX*1)
MOVOU X0, -32(DI)(BX*1)
MOVOU X0, -16(DI)(BX*1)
RET
Copy Permalink