mirror of
https://github.com/golang/go
synced 2024-09-25 03:10:12 -06:00
crypto/sha1: Optimise FUNC1 with alternate formulation
According to Wikipedia: http://en.wikipedia.org/wiki/SHA-1 there is an alternate formulation for the FUNC1 transform, namely f1 = d xor (b and (c xor d)) instead of f1 = (b and c) or ((not b) and d) This reduces the instruction count of FUNC1 from 6 to 4 and makes about 5% speed improvement on amd64 and suprisingly 17% on 386. amd64 Intel(R) Core(TM) i7 CPU Q 820 @ 1.73GHz: benchmark old ns/op new ns/op delta BenchmarkHash8Bytes 506 499 -1.38% BenchmarkHash1K 3099 2961 -4.45% BenchmarkHash8K 22292 21243 -4.71% benchmark old MB/s new MB/s speedup BenchmarkHash8Bytes 15.80 16.00 1.01x BenchmarkHash1K 330.40 345.82 1.05x BenchmarkHash8K 367.48 385.63 1.05x i386 Intel(R) Core(TM) i7 CPU Q 820 @ 1.73GHz: benchmark old ns/op new ns/op delta BenchmarkHash8Bytes 647 615 -4.95% BenchmarkHash1K 3673 3161 -13.94% BenchmarkHash8K 26141 22374 -14.41% benchmark old MB/s new MB/s speedup BenchmarkHash8Bytes 12.35 13.01 1.05x BenchmarkHash1K 278.74 323.94 1.16x BenchmarkHash8K 313.37 366.13 1.17x The improvements on an Intel(R) Core(TM) i7-4770K CPU @ 3.50GHz were almost identical. R=golang-dev, r, hanwen CC=golang-dev, rsc https://golang.org/cl/19910043
This commit is contained in:
parent
e5902fc70f
commit
107d18299c
@ -46,12 +46,10 @@
|
||||
ADDL DI, e
|
||||
|
||||
#define FUNC1(a, b, c, d, e) \
|
||||
MOVL b, SI; \
|
||||
ANDL c, SI; \
|
||||
MOVL b, DI; \
|
||||
NOTL DI; \
|
||||
ANDL d, DI; \
|
||||
ORL SI, DI
|
||||
MOVL d, DI; \
|
||||
XORL c, DI; \
|
||||
ANDL b, DI; \
|
||||
XORL d, DI
|
||||
|
||||
#define FUNC2(a, b, c, d, e) \
|
||||
MOVL b, DI; \
|
||||
|
@ -34,12 +34,10 @@
|
||||
MOVL R10, (((index)&0xf)*4)(SP)
|
||||
|
||||
#define FUNC1(a, b, c, d, e) \
|
||||
MOVL b, R8; \
|
||||
ANDL c, R8; \
|
||||
MOVL b, R9; \
|
||||
NOTL R9; \
|
||||
ANDL d, R9; \
|
||||
ORL R8, R9
|
||||
MOVL d, R9; \
|
||||
XORL c, R9; \
|
||||
ANDL b, R9; \
|
||||
XORL d, R9
|
||||
|
||||
#define FUNC2(a, b, c, d, e) \
|
||||
MOVL b, R9; \
|
||||
|
Loading…
Reference in New Issue
Block a user