cmd/compile: optimize math.Float64(32)bits and math.Float64(32)frombits on arm64

Use float <-> int register moves without conversion instead of stores
and loads to move float <-> int values.

Math package benchmark results.
name                 old time/op  new time/op  delta
Acosh                 153ns ± 0%   147ns ± 0%   -3.92%  (p=0.000 n=10+10)
Asinh                 183ns ± 0%   177ns ± 0%   -3.28%  (p=0.000 n=10+10)
Atanh                 157ns ± 0%   155ns ± 0%   -1.27%  (p=0.000 n=10+10)
Atan2                 118ns ± 0%   117ns ± 1%   -0.59%  (p=0.003 n=10+10)
Cbrt                  119ns ± 0%   114ns ± 0%   -4.20%  (p=0.000 n=10+10)
Copysign             7.51ns ± 0%  6.51ns ± 0%  -13.32%  (p=0.000 n=9+10)
Cos                  73.1ns ± 0%  70.6ns ± 0%   -3.42%  (p=0.000 n=10+10)
Cosh                  119ns ± 0%   121ns ± 0%   +1.68%  (p=0.000 n=10+9)
ExpGo                 154ns ± 0%   149ns ± 0%   -3.05%  (p=0.000 n=9+10)
Expm1                 101ns ± 0%    99ns ± 0%   -1.88%  (p=0.000 n=10+10)
Exp2Go                150ns ± 0%   146ns ± 0%   -2.67%  (p=0.000 n=10+10)
Abs                  7.01ns ± 0%  6.01ns ± 0%  -14.27%  (p=0.000 n=10+9)
Mod                   234ns ± 0%   212ns ± 0%   -9.40%  (p=0.000 n=9+10)
Frexp                34.5ns ± 0%  30.0ns ± 0%  -13.04%  (p=0.000 n=10+10)
Gamma                 112ns ± 0%   111ns ± 0%   -0.89%  (p=0.000 n=10+10)
Hypot                73.6ns ± 0%  68.6ns ± 0%   -6.79%  (p=0.000 n=10+10)
HypotGo              77.1ns ± 0%  72.1ns ± 0%   -6.49%  (p=0.000 n=10+10)
Ilogb                31.0ns ± 0%  28.0ns ± 0%   -9.68%  (p=0.000 n=10+10)
J0                    437ns ± 0%   434ns ± 0%   -0.62%  (p=0.000 n=10+10)
J1                    433ns ± 0%   431ns ± 0%   -0.46%  (p=0.000 n=10+10)
Jn                    927ns ± 0%   922ns ± 0%   -0.54%  (p=0.000 n=10+10)
Ldexp                41.5ns ± 0%  37.0ns ± 0%  -10.84%  (p=0.000 n=9+10)
Log                   124ns ± 0%   118ns ± 0%   -4.84%  (p=0.000 n=10+9)
Logb                 34.0ns ± 0%  32.0ns ± 0%   -5.88%  (p=0.000 n=10+10)
Log1p                 110ns ± 0%   108ns ± 0%   -1.82%  (p=0.000 n=10+10)
Log10                 136ns ± 0%   132ns ± 0%   -2.94%  (p=0.000 n=10+10)
Log2                 51.6ns ± 0%  47.1ns ± 0%   -8.72%  (p=0.000 n=10+10)
Nextafter32          33.0ns ± 0%  30.5ns ± 0%   -7.58%  (p=0.000 n=10+10)
Nextafter64          29.0ns ± 0%  26.5ns ± 0%   -8.62%  (p=0.000 n=10+10)
PowInt                169ns ± 0%   160ns ± 0%   -5.33%  (p=0.000 n=10+10)
PowFrac               375ns ± 0%   361ns ± 0%   -3.73%  (p=0.000 n=10+10)
RoundToEven          14.0ns ± 0%  12.5ns ± 0%  -10.71%  (p=0.000 n=10+10)
Remainder             206ns ± 0%   192ns ± 0%   -6.80%  (p=0.000 n=10+9)
Signbit              6.01ns ± 0%  5.51ns ± 0%   -8.32%  (p=0.000 n=10+9)
Sin                  70.1ns ± 0%  69.6ns ± 0%   -0.71%  (p=0.000 n=10+10)
Sincos               99.1ns ± 0%  99.6ns ± 0%   +0.50%  (p=0.000 n=9+10)
SqrtGoLatency         178ns ± 0%   146ns ± 0%  -17.70%  (p=0.000 n=8+10)
SqrtPrime            9.19µs ± 0%  9.20µs ± 0%   +0.01%  (p=0.000 n=9+9)
Tanh                  125ns ± 1%   127ns ± 0%   +1.36%  (p=0.000 n=10+10)
Y0                    428ns ± 0%   426ns ± 0%   -0.47%  (p=0.000 n=10+10)
Y1                    431ns ± 0%   429ns ± 0%   -0.46%  (p=0.000 n=10+9)
Yn                    906ns ± 0%   901ns ± 0%   -0.55%  (p=0.000 n=10+10)
Float64bits          4.50ns ± 0%  3.50ns ± 0%  -22.22%  (p=0.000 n=10+10)
Float64frombits      4.00ns ± 0%  3.50ns ± 0%  -12.50%  (p=0.000 n=10+9)
Float32bits          4.50ns ± 0%  3.50ns ± 0%  -22.22%  (p=0.002 n=8+10)
Float32frombits      4.00ns ± 0%  3.50ns ± 0%  -12.50%  (p=0.000 n=10+10)

Change-Id: Iba829e15d5624962fe0c699139ea783efeefabc2
Reviewed-on: https://go-review.googlesource.com/129715
Reviewed-by: Cherry Zhang <cherryyz@google.com>
Run-TryBot: Cherry Zhang <cherryyz@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
This commit is contained in:
fanzha02 2018-07-16 04:45:25 +00:00 committed by Cherry Zhang
parent e57f24ab39
commit a19a83c8ef
7 changed files with 256 additions and 11 deletions

View file

@ -92,21 +92,25 @@ func copysign(a, b, c float64) {
func fromFloat64(f64 float64) uint64 {
// amd64:"MOVQ\tX.*, [^X].*"
// arm64:"FMOVD\tF.*, R.*"
return math.Float64bits(f64+1) + 1
}
func fromFloat32(f32 float32) uint32 {
// amd64:"MOVL\tX.*, [^X].*"
// arm64:"FMOVS\tF.*, R.*"
return math.Float32bits(f32+1) + 1
}
func toFloat64(u64 uint64) float64 {
// amd64:"MOVQ\t[^X].*, X.*"
// arm64:"FMOVD\tR.*, F.*"
return math.Float64frombits(u64+1) + 1
}
func toFloat32(u32 uint32) float32 {
// amd64:"MOVL\t[^X].*, X.*"
// arm64:"FMOVS\tR.*, F.*"
return math.Float32frombits(u32+1) + 1
}
@ -132,6 +136,7 @@ func constantConvert32(x float32) float32 {
// amd64:"MOVSS\t[$]f32.3f800000\\(SB\\)"
// s390x:"FMOVS\t[$]f32.3f800000\\(SB\\)"
// ppc64le:"FMOVS\t[$]f32.3f800000\\(SB\\)"
// arm64:"FMOVS\t[$]\\(1.0\\)"
if x > math.Float32frombits(0x3f800000) {
return -x
}
@ -142,6 +147,7 @@ func constantConvertInt32(x uint32) uint32 {
// amd64:-"MOVSS"
// s390x:-"FMOVS"
// ppc64le:-"FMOVS"
// arm64:-"FMOVS"
if x > math.Float32bits(1) {
return -x
}