diff options
author | Russ Cox <rsc@golang.org> | 2014-10-28 21:50:16 -0400 |
---|---|---|
committer | Russ Cox <rsc@golang.org> | 2014-10-28 21:50:16 -0400 |
commit | b55791e2008703b33883e48e72a347ba07a65486 (patch) | |
tree | 2dc3ed44dc71a1aa6af2d9fbe331464408104d79 /src/runtime/memclr_amd64.s | |
parent | 87b4149b22feb9d8d52da1730b455e39436a3a8d (diff) | |
download | go-b55791e2008703b33883e48e72a347ba07a65486.tar.gz go-b55791e2008703b33883e48e72a347ba07a65486.zip |
[dev.power64] cmd/5a, cmd/6a, cmd/8a, cmd/9a: make labels function-scoped
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
Diffstat (limited to 'src/runtime/memclr_amd64.s')
-rw-r--r-- | src/runtime/memclr_amd64.s | 44 |
1 files changed, 22 insertions, 22 deletions
diff --git a/src/runtime/memclr_amd64.s b/src/runtime/memclr_amd64.s index 94a2c7f236..ec24f1db23 100644 --- a/src/runtime/memclr_amd64.s +++ b/src/runtime/memclr_amd64.s @@ -15,30 +15,30 @@ TEXT runtime·memclr(SB), NOSPLIT, $0-16 XORQ AX, AX // MOVOU seems always faster than REP STOSQ. -clr_tail: +tail: TESTQ BX, BX - JEQ clr_0 + JEQ _0 CMPQ BX, $2 - JBE clr_1or2 + JBE _1or2 CMPQ BX, $4 - JBE clr_3or4 + JBE _3or4 CMPQ BX, $8 - JBE clr_5through8 + JBE _5through8 CMPQ BX, $16 - JBE clr_9through16 + JBE _9through16 PXOR X0, X0 CMPQ BX, $32 - JBE clr_17through32 + JBE _17through32 CMPQ BX, $64 - JBE clr_33through64 + JBE _33through64 CMPQ BX, $128 - JBE clr_65through128 + JBE _65through128 CMPQ BX, $256 - JBE clr_129through256 + JBE _129through256 // TODO: use branch table and BSR to make this just a single dispatch // TODO: for really big clears, use MOVNTDQ. -clr_loop: +loop: MOVOU X0, 0(DI) MOVOU X0, 16(DI) MOVOU X0, 32(DI) @@ -58,38 +58,38 @@ clr_loop: SUBQ $256, BX ADDQ $256, DI CMPQ BX, $256 - JAE clr_loop - JMP clr_tail + JAE loop + JMP tail -clr_1or2: +_1or2: MOVB AX, (DI) MOVB AX, -1(DI)(BX*1) RET -clr_0: +_0: RET -clr_3or4: +_3or4: MOVW AX, (DI) MOVW AX, -2(DI)(BX*1) RET -clr_5through8: +_5through8: MOVL AX, (DI) MOVL AX, -4(DI)(BX*1) RET -clr_9through16: +_9through16: MOVQ AX, (DI) MOVQ AX, -8(DI)(BX*1) RET -clr_17through32: +_17through32: MOVOU X0, (DI) MOVOU X0, -16(DI)(BX*1) RET -clr_33through64: +_33through64: MOVOU X0, (DI) MOVOU X0, 16(DI) MOVOU X0, -32(DI)(BX*1) MOVOU X0, -16(DI)(BX*1) RET -clr_65through128: +_65through128: MOVOU X0, (DI) MOVOU X0, 16(DI) MOVOU X0, 32(DI) @@ -99,7 +99,7 @@ clr_65through128: MOVOU X0, -32(DI)(BX*1) MOVOU X0, -16(DI)(BX*1) RET -clr_129through256: +_129through256: MOVOU X0, (DI) MOVOU X0, 16(DI) MOVOU X0, 32(DI) |