]> Cypherpunks repositories - gostls13.git/commit
cmd/compile: use prove pass to detect Ctz of non-zero values
authorJosh Bleecher Snyder <josharian@gmail.com>
Wed, 25 Apr 2018 18:52:06 +0000 (11:52 -0700)
committerJosh Bleecher Snyder <josharian@gmail.com>
Thu, 26 Apr 2018 18:22:28 +0000 (18:22 +0000)
commitd9a50a6531860b43e552656e2990b87e36c8e440
tree24b5455af66a4a26f9effaeae4153f1b4d89a0e2
parentadbb6ec903fc135dac2c7a141fa13273d414acaf
cmd/compile: use prove pass to detect Ctz of non-zero values

On amd64, Ctz must include special handling of zeros.
But the prove pass has enough information to detect whether the input
is non-zero, allowing a more efficient lowering.

Introduce new CtzNonZero ops to capture and use this information.

Benchmark code:

func BenchmarkVisitBits(b *testing.B) {
b.Run("8", func(b *testing.B) {
for i := 0; i < b.N; i++ {
x := uint8(0xff)
for x != 0 {
sink = bits.TrailingZeros8(x)
x &= x - 1
}
}
})

    // and similarly so for 16, 32, 64
}

name            old time/op  new time/op  delta
VisitBits/8-8   7.27ns ± 4%  5.58ns ± 4%  -23.35%  (p=0.000 n=28+26)
VisitBits/16-8  14.7ns ± 7%  10.5ns ± 4%  -28.43%  (p=0.000 n=30+28)
VisitBits/32-8  27.6ns ± 8%  19.3ns ± 3%  -30.14%  (p=0.000 n=30+26)
VisitBits/64-8  44.0ns ±11%  38.0ns ± 5%  -13.48%  (p=0.000 n=30+30)

Fixes #25077

Change-Id: Ie6e5bd86baf39ee8a4ca7cadcf56d934e047f957
Reviewed-on: https://go-review.googlesource.com/109358
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
19 files changed:
src/cmd/compile/internal/ssa/gen/AMD64.rules
src/cmd/compile/internal/ssa/gen/ARM.rules
src/cmd/compile/internal/ssa/gen/ARM64.rules
src/cmd/compile/internal/ssa/gen/MIPS.rules
src/cmd/compile/internal/ssa/gen/PPC64.rules
src/cmd/compile/internal/ssa/gen/S390X.rules
src/cmd/compile/internal/ssa/gen/dec64.rules
src/cmd/compile/internal/ssa/gen/genericOps.go
src/cmd/compile/internal/ssa/opGen.go
src/cmd/compile/internal/ssa/prove.go
src/cmd/compile/internal/ssa/rewriteAMD64.go
src/cmd/compile/internal/ssa/rewriteARM.go
src/cmd/compile/internal/ssa/rewriteARM64.go
src/cmd/compile/internal/ssa/rewriteMIPS.go
src/cmd/compile/internal/ssa/rewritePPC64.go
src/cmd/compile/internal/ssa/rewriteS390X.go
src/cmd/compile/internal/ssa/rewritedec64.go
test/codegen/mathbits.go
test/run.go