70 lines
1.4 KiB
ArmAsm
70 lines
1.4 KiB
ArmAsm
// Atomics and carry-extending multi-word arithmetic: exchange,
|
|
// compare-exchange, exchange-add, ADCX/ADOX and the CRC-32 accumulator
|
|
// family. Every result is folded back so no instruction is dead.
|
|
|
|
#include "textflag.h"
|
|
|
|
// func xchg(p *uint64, v uint64) uint64
|
|
TEXT ·xchg(SB), NOSPLIT, $0-24
|
|
MOVQ p+0(FP), AX
|
|
MOVQ v+8(FP), BX
|
|
XCHGQ BX, (AX)
|
|
XCHGQ BX, CX
|
|
XCHGL BX, CX
|
|
XCHGW BX, CX
|
|
XCHGB BL, CL
|
|
MOVQ AX, ret+16(FP)
|
|
RET
|
|
|
|
// func cmpxchg(p *uint64, old, new uint64) uint8
|
|
TEXT ·cmpxchg(SB), NOSPLIT, $0-25
|
|
MOVQ p+0(FP), AX
|
|
MOVQ old+8(FP), BX
|
|
MOVQ new+16(FP), CX
|
|
CMPXCHGQ CX, (AX)
|
|
CMPXCHGL CX, BX
|
|
CMPXCHGW CX, BX
|
|
CMPXCHGB CL, BL
|
|
SETEQ AL
|
|
MOVB AL, ret+24(FP)
|
|
RET
|
|
|
|
// func xadd(p *uint64, v uint64) uint64
|
|
TEXT ·xadd(SB), NOSPLIT, $0-24
|
|
MOVQ p+0(FP), AX
|
|
MOVQ v+8(FP), BX
|
|
XADDQ BX, (AX)
|
|
XADDL BX, CX
|
|
XADDW BX, CX
|
|
XADDB BL, CL
|
|
MOVQ AX, ret+16(FP)
|
|
RET
|
|
|
|
// func adcx_adox(lo, hi, x, y uint64) uint64
|
|
TEXT ·adcx_adox(SB), NOSPLIT, $0-40
|
|
MOVQ lo+0(FP), AX
|
|
MOVQ hi+8(FP), DX
|
|
MOVQ x+16(FP), BX
|
|
MOVQ y+24(FP), CX
|
|
ADCXQ BX, AX
|
|
ADOXQ CX, DX
|
|
ADCXL BX, AX
|
|
ADOXL CX, DX
|
|
XORQ BX, BX
|
|
ADCXQ BX, AX
|
|
MOVQ AX, ret+32(FP)
|
|
RET
|
|
|
|
// func crc32(crc uint32, p *byte, n int) uint32
|
|
TEXT ·crc32(SB), NOSPLIT, $0-28
|
|
MOVL crc+0(FP), AX
|
|
MOVQ p+8(FP), SI
|
|
MOVQ n+16(FP), CX
|
|
CRC32B (SI), AX
|
|
CRC32Q (SI), CX
|
|
CRC32L (SI), AX
|
|
MOVW (SI), DX
|
|
CRC32W DX, AX
|
|
MOVL AX, ret+24(FP)
|
|
RET
|