diff options
author | Josh Bleecher Snyder <josharian@gmail.com> | 2021-02-26 09:16:56 -0800 |
---|---|---|
committer | Robert Griesemer <gri@golang.org> | 2021-03-05 06:15:22 +0000 |
commit | 60b500dc6c78a793775a7dff4eb8c656734a54c8 (patch) | |
tree | cbde03a9c3857581ebc9b3ef723e2b429ea8b737 /src/math | |
parent | f0b6d3753f57bf37487b127f968920743c401ed9 (diff) | |
download | go-60b500dc6c78a793775a7dff4eb8c656734a54c8.tar.gz go-60b500dc6c78a793775a7dff4eb8c656734a54c8.zip |
math/big: remove bounds checks for shrVU_g inner loop
Make explicit a shrVU_g precondition.
Replace i with i+1 throughout the loop.
The resulting loop is functionally identical,
but the compiler can do better BCE without the i-1 slice offset.
Benchmarks results on amd64 with -tags=math_big_pure_go.
name old time/op new time/op delta
NonZeroShifts/1/shrVU-8 4.55ns ± 2% 4.45ns ± 3% -2.27% (p=0.000 n=28+30)
NonZeroShifts/1/shlVU-8 4.07ns ± 1% 4.13ns ± 4% +1.55% (p=0.000 n=26+29)
NonZeroShifts/2/shrVU-8 6.12ns ± 1% 5.55ns ± 1% -9.30% (p=0.000 n=28+28)
NonZeroShifts/2/shlVU-8 5.65ns ± 3% 5.70ns ± 2% +0.92% (p=0.008 n=30+29)
NonZeroShifts/3/shrVU-8 7.58ns ± 2% 6.79ns ± 2% -10.46% (p=0.000 n=28+28)
NonZeroShifts/3/shlVU-8 6.62ns ± 2% 6.69ns ± 1% +1.07% (p=0.000 n=29+28)
NonZeroShifts/4/shrVU-8 9.02ns ± 1% 7.79ns ± 2% -13.59% (p=0.000 n=27+30)
NonZeroShifts/4/shlVU-8 7.74ns ± 1% 7.82ns ± 1% +0.92% (p=0.000 n=26+28)
NonZeroShifts/5/shrVU-8 10.6ns ± 1% 8.9ns ± 3% -16.31% (p=0.000 n=25+29)
NonZeroShifts/5/shlVU-8 8.59ns ± 1% 8.68ns ± 1% +1.13% (p=0.000 n=27+29)
NonZeroShifts/10/shrVU-8 18.2ns ± 2% 14.4ns ± 1% -20.96% (p=0.000 n=27+28)
NonZeroShifts/10/shlVU-8 14.1ns ± 1% 14.1ns ± 1% +0.46% (p=0.001 n=26+28)
NonZeroShifts/100/shrVU-8 161ns ± 2% 118ns ± 1% -26.83% (p=0.000 n=29+30)
NonZeroShifts/100/shlVU-8 119ns ± 2% 120ns ± 2% +0.92% (p=0.000 n=29+29)
NonZeroShifts/1000/shrVU-8 1.54µs ± 1% 1.10µs ± 1% -28.63% (p=0.000 n=29+29)
NonZeroShifts/1000/shlVU-8 1.10µs ± 1% 1.10µs ± 2% ~ (p=0.701 n=28+29)
NonZeroShifts/10000/shrVU-8 15.3µs ± 2% 10.9µs ± 1% -28.68% (p=0.000 n=28+28)
NonZeroShifts/10000/shlVU-8 10.9µs ± 2% 10.9µs ± 2% -0.57% (p=0.003 n=26+29)
NonZeroShifts/100000/shrVU-8 154µs ± 1% 111µs ± 2% -28.04% (p=0.000 n=27+28)
NonZeroShifts/100000/shlVU-8 113µs ± 2% 113µs ± 2% ~ (p=0.790 n=30+30)
Change-Id: Ib6a621ee7c88b27f0f18121fb2cba3606c40c9b0
Reviewed-on: https://go-review.googlesource.com/c/go/+/297049
Trust: Josh Bleecher Snyder <josharian@gmail.com>
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
TryBot-Result: Go Bot <gobot@golang.org>
Reviewed-by: Robert Griesemer <gri@golang.org>
Diffstat (limited to 'src/math')
-rw-r--r-- | src/math/big/arith.go | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/src/math/big/arith.go b/src/math/big/arith.go index 750ce8aa39..e1947936d4 100644 --- a/src/math/big/arith.go +++ b/src/math/big/arith.go @@ -170,12 +170,16 @@ func shrVU_g(z, x []Word, s uint) (c Word) { if len(z) == 0 { return } + if len(x) != len(z) { + // This is an invariant guaranteed by the caller. + panic("len(x) != len(z)") + } s &= _W - 1 // hint to the compiler that shifts by s don't need guard code ŝ := _W - s ŝ &= _W - 1 // ditto c = x[0] << ŝ - for i := 0; i < len(z)-1; i++ { - z[i] = x[i]>>s | x[i+1]<<ŝ + for i := 1; i < len(z); i++ { + z[i-1] = x[i-1]>>s | x[i]<<ŝ } z[len(z)-1] = x[len(z)-1] >> s return |