1
0
mirror of https://github.com/golang/go synced 2024-10-04 08:31:22 -06:00
go/src/pkg/runtime/memclr_plan9_386.s
Josh Bleecher Snyder bc9e160443 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 06:21:08 -07:00

52 lines
828 B
ArmAsm

// 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.
#include "../../cmd/ld/textflag.h"
// void runtime·memclr(void*, uintptr)
TEXT runtime·memclr(SB), NOSPLIT, $0-8
MOVL ptr+0(FP), DI
MOVL n+4(FP), BX
XORL AX, AX
clr_tail:
TESTL BX, BX
JEQ clr_0
CMPL BX, $2
JBE clr_1or2
CMPL BX, $4
JBE clr_3or4
CMPL BX, $8
JBE clr_5through8
CMPL BX, $16
JBE clr_9through16
MOVL BX, CX
SHRL $2, CX
REP
STOSL
ANDL $3, BX
JNE clr_tail
RET
clr_1or2:
MOVB AX, (DI)
MOVB AX, -1(DI)(BX*1)
RET
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:
MOVL AX, (DI)
MOVL AX, 4(DI)
MOVL AX, -8(DI)(BX*1)
MOVL AX, -4(DI)(BX*1)
RET