mirror of
https://github.com/golang/go
synced 2024-11-20 03:34:40 -07:00
b55791e200
I removed support for jumping between functions years ago, as part of doing the instruction layout for each function separately. Given that, it makes sense to treat labels as function-scoped. This lets each function have its own 'loop' label, for example. Makes the assembly much cleaner and removes the last reason anyone would reach for the 123(PC) form instead. Note that this is on the dev.power64 branch, but it changes all the assemblers. The change will ship in Go 1.5 (perhaps after being ported into the new assembler). Came up as part of CL 167730043. LGTM=r R=r CC=austin, dave, golang-codereviews, minux https://golang.org/cl/159670043
131 lines
2.2 KiB
ArmAsm
131 lines
2.2 KiB
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.
|
|
|
|
// +build !plan9
|
|
|
|
#include "textflag.h"
|
|
|
|
// NOTE: Windows externalthreadhandler expects memclr to preserve DX.
|
|
|
|
// 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
|
|
|
|
// MOVOU seems always faster than REP STOSL.
|
|
tail:
|
|
TESTL BX, BX
|
|
JEQ _0
|
|
CMPL BX, $2
|
|
JBE _1or2
|
|
CMPL BX, $4
|
|
JBE _3or4
|
|
CMPL BX, $8
|
|
JBE _5through8
|
|
CMPL BX, $16
|
|
JBE _9through16
|
|
TESTL $0x4000000, runtime·cpuid_edx(SB) // check for sse2
|
|
JEQ nosse2
|
|
PXOR X0, X0
|
|
CMPL BX, $32
|
|
JBE _17through32
|
|
CMPL BX, $64
|
|
JBE _33through64
|
|
CMPL BX, $128
|
|
JBE _65through128
|
|
CMPL BX, $256
|
|
JBE _129through256
|
|
// TODO: use branch table and BSR to make this just a single dispatch
|
|
|
|
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)
|
|
SUBL $256, BX
|
|
ADDL $256, DI
|
|
CMPL BX, $256
|
|
JAE loop
|
|
JMP tail
|
|
|
|
_1or2:
|
|
MOVB AX, (DI)
|
|
MOVB AX, -1(DI)(BX*1)
|
|
RET
|
|
_0:
|
|
RET
|
|
_3or4:
|
|
MOVW AX, (DI)
|
|
MOVW AX, -2(DI)(BX*1)
|
|
RET
|
|
_5through8:
|
|
MOVL AX, (DI)
|
|
MOVL AX, -4(DI)(BX*1)
|
|
RET
|
|
_9through16:
|
|
MOVL AX, (DI)
|
|
MOVL AX, 4(DI)
|
|
MOVL AX, -8(DI)(BX*1)
|
|
MOVL AX, -4(DI)(BX*1)
|
|
RET
|
|
_17through32:
|
|
MOVOU X0, (DI)
|
|
MOVOU X0, -16(DI)(BX*1)
|
|
RET
|
|
_33through64:
|
|
MOVOU X0, (DI)
|
|
MOVOU X0, 16(DI)
|
|
MOVOU X0, -32(DI)(BX*1)
|
|
MOVOU X0, -16(DI)(BX*1)
|
|
RET
|
|
_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
|
|
_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
|
|
nosse2:
|
|
MOVL BX, CX
|
|
SHRL $2, CX
|
|
REP
|
|
STOSL
|
|
ANDL $3, BX
|
|
JNE tail
|
|
RET
|