-
Ben Shi authored
This CL adds more combinations of two consequtive MOVBload/MOVBstore to a unique MOVWload/MOVWstore. 1. The size of the go executable decreases about 4KB, and the total size of pkg/linux_386 (excluding cmd/compile) decreases about 1.5KB. 2. There is no regression in the go1 benchmark result, excluding noise. name old time/op new time/op delta BinaryTree17-4 3.28s ± 2% 3.29s ± 2% ~ (p=0.151 n=40+40) Fannkuch11-4 3.52s ± 1% 3.51s ± 1% -0.28% (p=0.002 n=40+40) FmtFprintfEmpty-4 45.4ns ± 4% 45.0ns ± 4% -0.89% (p=0.019 n=40+40) FmtFprintfString-4 81.9ns ± 7% 81.3ns ± 1% ~ (p=0.660 n=40+25) FmtFprintfInt-4 91.9ns ± 9% 91.4ns ± 9% ~ (p=0.249 n=40+40) FmtFprintfIntInt-4 143ns ± 4% 143ns ± 4% ~ (p=0.760 n=40+40) FmtFprintfPrefixedInt-4 184ns ± 3% 183ns ± 4% ~ (p=0.485 n=40+40) FmtFprintfFloat-4 408ns ± 3% 409ns ± 3% ~ (p=0.961 n=40+40) FmtManyArgs-4 597ns ± 4% 602ns ± 3% ~ (p=0.413 n=40+40) GobDecode-4 7.13ms ± 6% 7.14ms ± 6% ~ (p=0.859 n=40+40) GobEncode-4 6.86ms ± 9% 6.94ms ± 7% ~ (p=0.162 n=40+40) Gzip-4 395ms ± 4% 396ms ± 3% ~ (p=0.099 n=40+40) Gunzip-4 40.9ms ± 4% 41.1ms ± 3% ~ (p=0.064 n=40+40) HTTPClientServer-4 63.6µs ± 2% 63.6µs ± 3% ~ (p=0.832 n=36+39) JSONEncode-4 16.1ms ± 3% 15.8ms ± 3% -1.60% (p=0.001 n=40+40) JSONDecode-4 61.0ms ± 3% 61.5ms ± 4% ~ (p=0.065 n=40+40) Mandelbrot200-4 5.16ms ± 3% 5.18ms ± 3% ~ (p=0.056 n=40+40) GoParse-4 3.25ms ± 2% 3.23ms ± 3% ~ (p=0.727 n=40+40) RegexpMatchEasy0_32-4 90.2ns ± 3% 89.3ns ± 6% -0.98% (p=0.002 n=40+40) RegexpMatchEasy0_1K-4 812ns ± 3% 815ns ± 3% ~ (p=0.309 n=40+40) RegexpMatchEasy1_32-4 103ns ± 6% 103ns ± 5% ~ (p=0.680 n=40+40) RegexpMatchEasy1_1K-4 1.01µs ± 4% 1.02µs ± 3% ~ (p=0.326 n=40+33) RegexpMatchMedium_32-4 120ns ± 4% 120ns ± 5% ~ (p=0.834 n=40+40) RegexpMatchMedium_1K-4 40.1µs ± 3% 39.5µs ± 4% -1.35% (p=0.000 n=40+40) RegexpMatchHard_32-4 2.27µs ± 6% 2.23µs ± 4% -1.67% (p=0.011 n=40+40) RegexpMatchHard_1K-4 67.2µs ± 3% 67.2µs ± 3% ~ (p=0.149 n=40+40) Revcomp-4 1.84s ± 2% 1.86s ± 3% +0.70% (p=0.020 n=40+40) Template-4 69.0ms ± 4% 69.8ms ± 3% +1.20% (p=0.003 n=40+40) TimeParse-4 438ns ± 3% 439ns ± 4% ~ (p=0.650 n=40+40) TimeFormat-4 412ns ± 3% 412ns ± 3% ~ (p=0.888 n=40+40) [Geo mean] 65.2µs 65.2µs -0.04% name old speed new speed delta GobDecode-4 108MB/s ± 6% 108MB/s ± 6% ~ (p=0.855 n=40+40) GobEncode-4 112MB/s ± 9% 111MB/s ± 8% ~ (p=0.159 n=40+40) Gzip-4 49.2MB/s ± 4% 49.1MB/s ± 3% ~ (p=0.102 n=40+40) Gunzip-4 474MB/s ± 3% 472MB/s ± 3% ~ (p=0.063 n=40+40) JSONEncode-4 121MB/s ± 3% 123MB/s ± 3% +1.62% (p=0.001 n=40+40) JSONDecode-4 31.9MB/s ± 3% 31.6MB/s ± 4% ~ (p=0.070 n=40+40) GoParse-4 17.9MB/s ± 2% 17.9MB/s ± 3% ~ (p=0.696 n=40+40) RegexpMatchEasy0_32-4 355MB/s ± 3% 358MB/s ± 5% +0.99% (p=0.002 n=40+40) RegexpMatchEasy0_1K-4 1.26GB/s ± 3% 1.26GB/s ± 3% ~ (p=0.381 n=40+40) RegexpMatchEasy1_32-4 310MB/s ± 5% 310MB/s ± 4% ~ (p=0.655 n=40+40) RegexpMatchEasy1_1K-4 1.01GB/s ± 4% 1.01GB/s ± 3% ~ (p=0.351 n=40+33) RegexpMatchMedium_32-4 8.32MB/s ± 4% 8.34MB/s ± 5% ~ (p=0.696 n=40+40) RegexpMatchMedium_1K-4 25.6MB/s ± 3% 25.9MB/s ± 4% +1.36% (p=0.000 n=40+40) RegexpMatchHard_32-4 14.1MB/s ± 6% 14.3MB/s ± 4% +1.64% (p=0.011 n=40+40) RegexpMatchHard_1K-4 15.2MB/s ± 3% 15.2MB/s ± 3% ~ (p=0.147 n=40+40) Revcomp-4 138MB/s ± 2% 137MB/s ± 3% -0.70% (p=0.021 n=40+40) Template-4 28.1MB/s ± 4% 27.8MB/s ± 3% -1.19% (p=0.003 n=40+40) [Geo mean] 83.7MB/s 83.7MB/s +0.03% Change-Id: I2a2b3a942b5c45467491515d201179fd192e65c9 Reviewed-on: https://go-review.googlesource.com/c/141650 Run-TryBot: Ben Shi <powerman1st@163.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by:
Keith Randall <khr@golang.org>
4b78fe57
