diff options
| author | Ben Shi <powerman1st@163.com> | 2018-08-23 02:08:15 +0000 |
|---|---|---|
| committer | Ben Shi <powerman1st@163.com> | 2018-08-25 02:39:49 +0000 |
| commit | e03220a594a1a4b7fa8c901eebddb9ea11ecbece (patch) | |
| tree | cb1a5a16e448d8b6f32640e03d4166853b02c0ff /src/cmd/compile/internal/x86 | |
| parent | 3bc34385faacbcbefb2b4abc0e280b709aab03c9 (diff) | |
| download | go-e03220a594a1a4b7fa8c901eebddb9ea11ecbece.tar.gz go-e03220a594a1a4b7fa8c901eebddb9ea11ecbece.zip | |
cmd/compile: optimize 386 code with FLDPI
FLDPI pushes the constant pi to 387's register stack, which is
more efficient than MOVSSconst/MOVSDconst.
1. This optimization reduces 0.3KB of the total size of pkg/linux_386
(exlcuding cmd/compile).
2. There is little regression in the go1 benchmark.
name old time/op new time/op delta
BinaryTree17-4 3.30s ± 3% 3.30s ± 2% ~ (p=0.759 n=40+39)
Fannkuch11-4 3.53s ± 1% 3.54s ± 1% ~ (p=0.168 n=40+40)
FmtFprintfEmpty-4 45.5ns ± 3% 45.6ns ± 3% ~ (p=0.553 n=40+40)
FmtFprintfString-4 78.4ns ± 3% 78.3ns ± 3% ~ (p=0.593 n=40+40)
FmtFprintfInt-4 88.8ns ± 2% 89.9ns ± 2% ~ (p=0.083 n=40+33)
FmtFprintfIntInt-4 140ns ± 4% 140ns ± 4% ~ (p=0.656 n=40+40)
FmtFprintfPrefixedInt-4 180ns ± 2% 181ns ± 3% +0.53% (p=0.050 n=40+40)
FmtFprintfFloat-4 408ns ± 4% 411ns ± 3% ~ (p=0.112 n=40+40)
FmtManyArgs-4 599ns ± 3% 602ns ± 3% ~ (p=0.784 n=40+40)
GobDecode-4 7.24ms ± 6% 7.30ms ± 5% ~ (p=0.171 n=40+40)
GobEncode-4 6.98ms ± 5% 6.89ms ± 8% ~ (p=0.107 n=40+40)
Gzip-4 396ms ± 4% 396ms ± 3% ~ (p=0.852 n=40+40)
Gunzip-4 41.3ms ± 3% 41.5ms ± 4% ~ (p=0.221 n=40+40)
HTTPClientServer-4 63.4µs ± 3% 63.4µs ± 2% ~ (p=0.895 n=39+40)
JSONEncode-4 17.5ms ± 2% 17.5ms ± 3% ~ (p=0.090 n=40+40)
JSONDecode-4 60.6ms ± 3% 60.1ms ± 4% ~ (p=0.184 n=40+40)
Mandelbrot200-4 7.80ms ± 3% 7.78ms ± 2% ~ (p=0.512 n=40+40)
GoParse-4 3.30ms ± 3% 3.28ms ± 2% -0.61% (p=0.034 n=40+40)
RegexpMatchEasy0_32-4 104ns ± 4% 103ns ± 4% ~ (p=0.118 n=40+40)
RegexpMatchEasy0_1K-4 850ns ± 2% 848ns ± 2% ~ (p=0.370 n=40+40)
RegexpMatchEasy1_32-4 112ns ± 4% 112ns ± 4% ~ (p=0.848 n=40+40)
RegexpMatchEasy1_1K-4 1.04µs ± 4% 1.03µs ± 4% ~ (p=0.333 n=40+40)
RegexpMatchMedium_32-4 132ns ± 4% 131ns ± 3% ~ (p=0.527 n=40+40)
RegexpMatchMedium_1K-4 43.4µs ± 3% 43.5µs ± 3% ~ (p=0.111 n=40+40)
RegexpMatchHard_32-4 2.24µs ± 4% 2.24µs ± 4% ~ (p=0.441 n=40+40)
RegexpMatchHard_1K-4 67.9µs ± 3% 68.0µs ± 3% ~ (p=0.095 n=40+40)
Revcomp-4 1.84s ± 2% 1.84s ± 2% ~ (p=0.677 n=40+40)
Template-4 68.4ms ± 3% 68.6ms ± 3% ~ (p=0.345 n=40+40)
TimeParse-4 433ns ± 3% 433ns ± 3% ~ (p=0.403 n=40+40)
TimeFormat-4 407ns ± 3% 406ns ± 3% ~ (p=0.900 n=40+40)
[Geo mean] 67.1µs 67.2µs +0.04%
name old speed new speed delta
GobDecode-4 106MB/s ± 5% 105MB/s ± 5% ~ (p=0.173 n=40+40)
GobEncode-4 110MB/s ± 5% 112MB/s ± 9% ~ (p=0.104 n=40+40)
Gzip-4 49.0MB/s ± 4% 49.1MB/s ± 4% ~ (p=0.836 n=40+40)
Gunzip-4 471MB/s ± 3% 468MB/s ± 4% ~ (p=0.218 n=40+40)
JSONEncode-4 111MB/s ± 2% 111MB/s ± 3% ~ (p=0.090 n=40+40)
JSONDecode-4 32.0MB/s ± 3% 32.3MB/s ± 4% ~ (p=0.194 n=40+40)
GoParse-4 17.6MB/s ± 3% 17.7MB/s ± 2% +0.62% (p=0.035 n=40+40)
RegexpMatchEasy0_32-4 307MB/s ± 4% 309MB/s ± 4% +0.70% (p=0.041 n=40+40)
RegexpMatchEasy0_1K-4 1.20GB/s ± 3% 1.21GB/s ± 2% ~ (p=0.353 n=40+40)
RegexpMatchEasy1_32-4 285MB/s ± 3% 284MB/s ± 4% ~ (p=0.384 n=40+40)
RegexpMatchEasy1_1K-4 988MB/s ± 4% 992MB/s ± 3% ~ (p=0.335 n=40+40)
RegexpMatchMedium_32-4 7.56MB/s ± 4% 7.57MB/s ± 4% ~ (p=0.314 n=40+40)
RegexpMatchMedium_1K-4 23.6MB/s ± 3% 23.6MB/s ± 3% ~ (p=0.107 n=40+40)
RegexpMatchHard_32-4 14.3MB/s ± 4% 14.3MB/s ± 4% ~ (p=0.429 n=40+40)
RegexpMatchHard_1K-4 15.1MB/s ± 3% 15.1MB/s ± 3% ~ (p=0.099 n=40+40)
Revcomp-4 138MB/s ± 2% 138MB/s ± 2% ~ (p=0.658 n=40+40)
Template-4 28.4MB/s ± 3% 28.3MB/s ± 3% ~ (p=0.331 n=40+40)
[Geo mean] 80.8MB/s 80.8MB/s +0.09%
Change-Id: I0cb715eead68ade097a302e7fb80ccbd1d1b511e
Reviewed-on: https://go-review.googlesource.com/130975
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Diffstat (limited to 'src/cmd/compile/internal/x86')
| -rw-r--r-- | src/cmd/compile/internal/x86/387.go | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/src/cmd/compile/internal/x86/387.go b/src/cmd/compile/internal/x86/387.go index ab3d30e76c..18838fb4ca 100644 --- a/src/cmd/compile/internal/x86/387.go +++ b/src/cmd/compile/internal/x86/387.go @@ -33,6 +33,11 @@ func ssaGenValue387(s *gc.SSAGenState, v *ssa.Value) { } else if iv == 0xbff0000000000000 { // -1.0 s.Prog(x86.AFLD1) s.Prog(x86.AFCHS) + } else if iv == 0x400921fb54442d18 { // +pi + s.Prog(x86.AFLDPI) + } else if iv == 0xc00921fb54442d18 { // -pi + s.Prog(x86.AFLDPI) + s.Prog(x86.AFCHS) } else { // others p := s.Prog(loadPush(v.Type)) p.From.Type = obj.TYPE_FCONST |