mirror of
https://github.com/golang/go
synced 2024-11-26 01:47:58 -07:00
f243cf6016
Use float <-> int register moves without conversion instead of stores and loads to move float <-> int values like arm64 and mips64. goos: linux goarch: loong64 pkg: math cpu: Loongson-3A6000 @ 2500.00MHz │ bench.old │ bench.new │ │ sec/op │ sec/op vs base │ Acos 15.98n ± 0% 15.94n ± 0% -0.25% (p=0.000 n=20) Acosh 27.75n ± 0% 25.56n ± 0% -7.89% (p=0.000 n=20) Asin 15.85n ± 0% 15.76n ± 0% -0.57% (p=0.000 n=20) Asinh 39.79n ± 0% 37.69n ± 0% -5.28% (p=0.000 n=20) Atan 7.261n ± 0% 7.242n ± 0% -0.27% (p=0.000 n=20) Atanh 28.30n ± 0% 27.62n ± 0% -2.40% (p=0.000 n=20) Atan2 15.85n ± 0% 15.75n ± 0% -0.63% (p=0.000 n=20) Cbrt 27.02n ± 0% 21.08n ± 0% -21.98% (p=0.000 n=20) Ceil 2.830n ± 1% 2.896n ± 1% +2.31% (p=0.000 n=20) Copysign 0.8022n ± 0% 0.8004n ± 0% -0.22% (p=0.000 n=20) Cos 11.64n ± 0% 11.61n ± 0% -0.26% (p=0.000 n=20) Cosh 35.98n ± 0% 33.44n ± 0% -7.05% (p=0.000 n=20) Erf 10.09n ± 0% 10.08n ± 0% -0.10% (p=0.000 n=20) Erfc 11.40n ± 0% 11.35n ± 0% -0.44% (p=0.000 n=20) Erfinv 12.31n ± 0% 12.29n ± 0% -0.16% (p=0.000 n=20) Erfcinv 12.16n ± 0% 12.17n ± 0% +0.08% (p=0.000 n=20) Exp 28.41n ± 0% 26.44n ± 0% -6.95% (p=0.000 n=20) ExpGo 28.68n ± 0% 27.07n ± 0% -5.60% (p=0.000 n=20) Expm1 17.21n ± 0% 16.75n ± 0% -2.67% (p=0.000 n=20) Exp2 24.71n ± 0% 23.01n ± 0% -6.88% (p=0.000 n=20) Exp2Go 25.17n ± 0% 23.91n ± 0% -4.99% (p=0.000 n=20) Abs 0.8004n ± 0% 0.8004n ± 0% ~ (p=0.224 n=20) Dim 1.201n ± 0% 1.201n ± 0% ~ (p=1.000 n=20) ¹ Floor 2.848n ± 0% 2.859n ± 0% +0.39% (p=0.000 n=20) Max 3.074n ± 0% 3.071n ± 0% ~ (p=0.481 n=20) Min 3.179n ± 0% 3.176n ± 0% -0.09% (p=0.003 n=20) Mod 49.62n ± 0% 44.82n ± 0% -9.67% (p=0.000 n=20) Frexp 7.604n ± 0% 6.803n ± 0% -10.53% (p=0.000 n=20) Gamma 18.01n ± 0% 17.61n ± 0% -2.22% (p=0.000 n=20) Hypot 7.204n ± 0% 7.604n ± 0% +5.55% (p=0.000 n=20) HypotGo 7.204n ± 0% 7.604n ± 0% +5.56% (p=0.000 n=20) Ilogb 6.003n ± 0% 6.003n ± 0% ~ (p=0.407 n=20) J0 76.43n ± 0% 76.24n ± 0% -0.25% (p=0.000 n=20) J1 76.44n ± 0% 76.44n ± 0% ~ (p=1.000 n=20) Jn 168.2n ± 0% 168.5n ± 0% +0.18% (p=0.000 n=20) Ldexp 8.804n ± 0% 7.604n ± 0% -13.63% (p=0.000 n=20) Lgamma 19.01n ± 0% 19.01n ± 0% ~ (p=0.695 n=20) Log 19.38n ± 0% 19.12n ± 0% -1.34% (p=0.000 n=20) Logb 6.003n ± 0% 6.003n ± 0% ~ (p=1.000 n=20) Log1p 18.57n ± 0% 16.72n ± 0% -9.96% (p=0.000 n=20) Log10 20.67n ± 0% 20.45n ± 0% -1.06% (p=0.000 n=20) Log2 9.605n ± 0% 8.804n ± 0% -8.34% (p=0.000 n=20) Modf 4.402n ± 0% 4.402n ± 0% ~ (p=1.000 n=20) Nextafter32 7.204n ± 0% 5.603n ± 0% -22.22% (p=0.000 n=20) Nextafter64 6.803n ± 0% 6.003n ± 0% -11.76% (p=0.000 n=20) PowInt 39.62n ± 0% 37.22n ± 0% -6.06% (p=0.000 n=20) PowFrac 120.9n ± 0% 108.9n ± 0% -9.93% (p=0.000 n=20) Pow10Pos 1.601n ± 0% 1.601n ± 0% ~ (p=0.487 n=20) Pow10Neg 2.675n ± 0% 2.675n ± 0% ~ (p=1.000 n=20) Round 3.018n ± 0% 2.401n ± 0% -20.46% (p=0.000 n=20) RoundToEven 3.822n ± 0% 3.001n ± 0% -21.48% (p=0.000 n=20) Remainder 45.62n ± 0% 42.42n ± 0% -7.01% (p=0.000 n=20) Signbit 0.9075n ± 0% 0.8004n ± 0% -11.81% (p=0.000 n=20) Sin 12.65n ± 0% 12.65n ± 0% ~ (p=0.503 n=20) Sincos 14.81n ± 0% 14.60n ± 0% -1.42% (p=0.000 n=20) Sinh 36.75n ± 0% 35.11n ± 0% -4.46% (p=0.000 n=20) SqrtIndirect 1.201n ± 0% 1.201n ± 0% ~ (p=1.000 n=20) ¹ SqrtLatency 4.002n ± 0% 4.002n ± 0% ~ (p=1.000 n=20) SqrtIndirectLatency 4.002n ± 0% 4.002n ± 0% ~ (p=1.000 n=20) SqrtGoLatency 52.85n ± 0% 40.82n ± 0% -22.76% (p=0.000 n=20) SqrtPrime 887.4n ± 0% 887.4n ± 0% ~ (p=0.751 n=20) Tan 13.95n ± 0% 13.97n ± 0% +0.18% (p=0.000 n=20) Tanh 36.79n ± 0% 34.89n ± 0% -5.16% (p=0.000 n=20) Trunc 2.849n ± 0% 2.861n ± 0% +0.42% (p=0.000 n=20) Y0 77.44n ± 0% 77.64n ± 0% +0.26% (p=0.000 n=20) Y1 74.41n ± 0% 74.33n ± 0% -0.11% (p=0.000 n=20) Yn 158.7n ± 0% 159.0n ± 0% +0.19% (p=0.000 n=20) Float64bits 0.8774n ± 0% 0.4002n ± 0% -54.39% (p=0.000 n=20) Float64frombits 0.8042n ± 0% 0.4002n ± 0% -50.24% (p=0.000 n=20) Float32bits 1.1230n ± 0% 0.5336n ± 0% -52.48% (p=0.000 n=20) Float32frombits 1.0670n ± 0% 0.8004n ± 0% -24.99% (p=0.000 n=20) FMA 2.001n ± 0% 2.001n ± 0% ~ (p=0.605 n=20) geomean 10.87n 10.10n -7.15% ¹ all samples are equal goos: linux goarch: loong64 pkg: math cpu: Loongson-3A5000 @ 2500.00MHz │ bench.old │ bench.new │ │ sec/op │ sec/op vs base │ Acos 33.10n ± 0% 31.95n ± 2% -3.46% (p=0.000 n=20) Acosh 58.38n ± 0% 50.44n ± 0% -13.60% (p=0.000 n=20) Asin 32.70n ± 0% 31.94n ± 0% -2.32% (p=0.000 n=20) Asinh 57.65n ± 0% 50.83n ± 0% -11.82% (p=0.000 n=20) Atan 14.21n ± 0% 14.21n ± 0% ~ (p=0.501 n=20) Atanh 60.86n ± 0% 54.44n ± 0% -10.56% (p=0.000 n=20) Atan2 32.02n ± 0% 34.02n ± 0% +6.25% (p=0.000 n=20) Cbrt 55.58n ± 0% 40.64n ± 0% -26.88% (p=0.000 n=20) Ceil 9.566n ± 0% 9.566n ± 0% ~ (p=0.463 n=20) Copysign 0.8005n ± 0% 0.8005n ± 0% ~ (p=0.806 n=20) Cos 18.02n ± 0% 18.02n ± 0% ~ (p=0.191 n=20) Cosh 64.44n ± 0% 65.64n ± 0% +1.86% (p=0.000 n=20) Erf 16.15n ± 0% 16.16n ± 0% ~ (p=0.770 n=20) Erfc 18.71n ± 0% 18.83n ± 0% +0.61% (p=0.000 n=20) Erfinv 19.33n ± 0% 19.34n ± 0% ~ (p=0.513 n=20) Erfcinv 18.90n ± 0% 19.78n ± 0% +4.63% (p=0.000 n=20) Exp 50.04n ± 0% 49.66n ± 0% -0.75% (p=0.000 n=20) ExpGo 50.03n ± 0% 50.03n ± 0% ~ (p=0.723 n=20) Expm1 28.41n ± 0% 28.27n ± 0% -0.49% (p=0.000 n=20) Exp2 50.08n ± 0% 51.23n ± 0% +2.31% (p=0.000 n=20) Exp2Go 49.77n ± 0% 49.89n ± 0% +0.24% (p=0.000 n=20) Abs 0.8009n ± 0% 0.8006n ± 0% ~ (p=0.317 n=20) Dim 1.987n ± 0% 1.993n ± 0% +0.28% (p=0.001 n=20) Floor 8.543n ± 0% 8.548n ± 0% ~ (p=0.509 n=20) Max 6.670n ± 0% 6.672n ± 0% ~ (p=0.335 n=20) Min 6.694n ± 0% 6.694n ± 0% ~ (p=0.459 n=20) Mod 56.44n ± 0% 53.23n ± 0% -5.70% (p=0.000 n=20) Frexp 8.409n ± 0% 7.606n ± 0% -9.55% (p=0.000 n=20) Gamma 35.64n ± 0% 35.23n ± 0% -1.15% (p=0.000 n=20) Hypot 11.21n ± 0% 10.61n ± 0% -5.31% (p=0.000 n=20) HypotGo 11.50n ± 0% 11.01n ± 0% -4.30% (p=0.000 n=20) Ilogb 7.606n ± 0% 6.804n ± 0% -10.54% (p=0.000 n=20) J0 125.3n ± 0% 126.5n ± 0% +0.96% (p=0.000 n=20) J1 124.9n ± 0% 125.3n ± 0% +0.32% (p=0.000 n=20) Jn 264.3n ± 0% 265.9n ± 0% +0.61% (p=0.000 n=20) Ldexp 9.606n ± 0% 9.204n ± 0% -4.19% (p=0.000 n=20) Lgamma 38.82n ± 0% 38.85n ± 0% +0.06% (p=0.019 n=20) Log 38.44n ± 0% 28.04n ± 0% -27.06% (p=0.000 n=20) Logb 8.405n ± 0% 7.605n ± 0% -9.52% (p=0.000 n=20) Log1p 31.62n ± 0% 27.11n ± 0% -14.26% (p=0.000 n=20) Log10 38.83n ± 0% 28.42n ± 0% -26.81% (p=0.000 n=20) Log2 11.21n ± 0% 10.41n ± 0% -7.14% (p=0.000 n=20) Modf 5.204n ± 0% 5.205n ± 0% ~ (p=0.983 n=20) Nextafter32 8.809n ± 0% 7.208n ± 0% -18.18% (p=0.000 n=20) Nextafter64 8.405n ± 0% 8.406n ± 0% +0.01% (p=0.007 n=20) PowInt 48.83n ± 0% 44.78n ± 0% -8.28% (p=0.000 n=20) PowFrac 146.9n ± 0% 142.1n ± 0% -3.23% (p=0.000 n=20) Pow10Pos 2.334n ± 0% 2.333n ± 0% ~ (p=0.110 n=20) Pow10Neg 4.803n ± 0% 4.803n ± 0% ~ (p=0.130 n=20) Round 4.816n ± 0% 3.819n ± 0% -20.70% (p=0.000 n=20) RoundToEven 5.735n ± 0% 5.204n ± 0% -9.26% (p=0.000 n=20) Remainder 52.05n ± 0% 49.64n ± 0% -4.63% (p=0.000 n=20) Signbit 1.201n ± 0% 1.001n ± 0% -16.65% (p=0.000 n=20) Sin 20.63n ± 0% 20.64n ± 0% +0.05% (p=0.040 n=20) Sincos 23.82n ± 0% 24.62n ± 0% +3.36% (p=0.000 n=20) Sinh 71.25n ± 0% 68.44n ± 0% -3.94% (p=0.000 n=20) SqrtIndirect 2.001n ± 0% 2.001n ± 0% ~ (p=0.182 n=20) SqrtLatency 4.003n ± 0% 4.003n ± 0% ~ (p=0.754 n=20) SqrtIndirectLatency 4.003n ± 0% 4.003n ± 0% ~ (p=0.773 n=20) SqrtGoLatency 60.84n ± 0% 81.26n ± 0% +33.56% (p=0.000 n=20) SqrtPrime 1.791µ ± 0% 1.791µ ± 0% ~ (p=0.784 n=20) Tan 27.22n ± 0% 27.22n ± 0% ~ (p=0.819 n=20) Tanh 70.88n ± 0% 69.04n ± 0% -2.60% (p=0.000 n=20) Trunc 8.543n ± 0% 8.543n ± 0% ~ (p=0.784 n=20) Y0 122.9n ± 0% 122.9n ± 0% ~ (p=0.559 n=20) Y1 123.3n ± 0% 121.7n ± 0% -1.30% (p=0.000 n=20) Yn 263.0n ± 0% 262.6n ± 0% -0.15% (p=0.000 n=20) Float64bits 1.2010n ± 0% 0.6004n ± 0% -50.01% (p=0.000 n=20) Float64frombits 1.2010n ± 0% 0.6004n ± 0% -50.01% (p=0.000 n=20) Float32bits 1.7010n ± 0% 0.8005n ± 0% -52.94% (p=0.000 n=20) Float32frombits 1.5010n ± 0% 0.8005n ± 0% -46.67% (p=0.000 n=20) FMA 2.001n ± 0% 2.001n ± 0% ~ (p=0.238 n=20) geomean 17.41n 16.15n -7.19% Change-Id: I0a0c263af2f07203eab1782e69c706f20c689d8d Reviewed-on: https://go-review.googlesource.com/c/go/+/604737 Auto-Submit: Tim King <taking@google.com> LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com> Reviewed-by: Dmitri Shuralyov <dmitshur@google.com> Reviewed-by: Meidan Li <limeidan@loongson.cn> Reviewed-by: Tim King <taking@google.com> Reviewed-by: abner chenc <chenguoqi@loongson.cn>
260 lines
6.4 KiB
Go
260 lines
6.4 KiB
Go
// asmcheck
|
|
|
|
// Copyright 2018 The Go Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style
|
|
// license that can be found in the LICENSE file.
|
|
|
|
package codegen
|
|
|
|
import "math"
|
|
|
|
var sink64 [8]float64
|
|
|
|
func approx(x float64) {
|
|
// amd64/v2:-".*x86HasSSE41" amd64/v3:-".*x86HasSSE41"
|
|
// amd64:"ROUNDSD\t[$]2"
|
|
// s390x:"FIDBR\t[$]6"
|
|
// arm64:"FRINTPD"
|
|
// ppc64x:"FRIP"
|
|
// wasm:"F64Ceil"
|
|
sink64[0] = math.Ceil(x)
|
|
|
|
// amd64/v2:-".*x86HasSSE41" amd64/v3:-".*x86HasSSE41"
|
|
// amd64:"ROUNDSD\t[$]1"
|
|
// s390x:"FIDBR\t[$]7"
|
|
// arm64:"FRINTMD"
|
|
// ppc64x:"FRIM"
|
|
// wasm:"F64Floor"
|
|
sink64[1] = math.Floor(x)
|
|
|
|
// s390x:"FIDBR\t[$]1"
|
|
// arm64:"FRINTAD"
|
|
// ppc64x:"FRIN"
|
|
sink64[2] = math.Round(x)
|
|
|
|
// amd64/v2:-".*x86HasSSE41" amd64/v3:-".*x86HasSSE41"
|
|
// amd64:"ROUNDSD\t[$]3"
|
|
// s390x:"FIDBR\t[$]5"
|
|
// arm64:"FRINTZD"
|
|
// ppc64x:"FRIZ"
|
|
// wasm:"F64Trunc"
|
|
sink64[3] = math.Trunc(x)
|
|
|
|
// amd64/v2:-".*x86HasSSE41" amd64/v3:-".*x86HasSSE41"
|
|
// amd64:"ROUNDSD\t[$]0"
|
|
// s390x:"FIDBR\t[$]4"
|
|
// arm64:"FRINTND"
|
|
// wasm:"F64Nearest"
|
|
sink64[4] = math.RoundToEven(x)
|
|
}
|
|
|
|
func sqrt(x float64) float64 {
|
|
// amd64:"SQRTSD"
|
|
// 386/sse2:"SQRTSD" 386/softfloat:-"SQRTD"
|
|
// arm64:"FSQRTD"
|
|
// arm/7:"SQRTD"
|
|
// mips/hardfloat:"SQRTD" mips/softfloat:-"SQRTD"
|
|
// mips64/hardfloat:"SQRTD" mips64/softfloat:-"SQRTD"
|
|
// wasm:"F64Sqrt"
|
|
// ppc64x:"FSQRT"
|
|
// riscv64: "FSQRTD"
|
|
return math.Sqrt(x)
|
|
}
|
|
|
|
func sqrt32(x float32) float32 {
|
|
// amd64:"SQRTSS"
|
|
// 386/sse2:"SQRTSS" 386/softfloat:-"SQRTS"
|
|
// arm64:"FSQRTS"
|
|
// arm/7:"SQRTF"
|
|
// mips/hardfloat:"SQRTF" mips/softfloat:-"SQRTF"
|
|
// mips64/hardfloat:"SQRTF" mips64/softfloat:-"SQRTF"
|
|
// wasm:"F32Sqrt"
|
|
// ppc64x:"FSQRTS"
|
|
// riscv64: "FSQRTS"
|
|
return float32(math.Sqrt(float64(x)))
|
|
}
|
|
|
|
// Check that it's using integer registers
|
|
func abs(x, y float64) {
|
|
// amd64:"BTRQ\t[$]63"
|
|
// arm64:"FABSD\t"
|
|
// s390x:"LPDFR\t",-"MOVD\t" (no integer load/store)
|
|
// ppc64x:"FABS\t"
|
|
// riscv64:"FABSD\t"
|
|
// wasm:"F64Abs"
|
|
// arm/6:"ABSD\t"
|
|
// mips64/hardfloat:"ABSD\t"
|
|
// mips/hardfloat:"ABSD\t"
|
|
sink64[0] = math.Abs(x)
|
|
|
|
// amd64:"BTRQ\t[$]63","PXOR" (TODO: this should be BTSQ)
|
|
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
|
|
// ppc64x:"FNABS\t"
|
|
sink64[1] = -math.Abs(y)
|
|
}
|
|
|
|
// Check that it's using integer registers
|
|
func abs32(x float32) float32 {
|
|
// s390x:"LPDFR",-"LDEBR",-"LEDBR" (no float64 conversion)
|
|
return float32(math.Abs(float64(x)))
|
|
}
|
|
|
|
// Check that it's using integer registers
|
|
func copysign(a, b, c float64) {
|
|
// amd64:"BTRQ\t[$]63","ANDQ","ORQ"
|
|
// s390x:"CPSDR",-"MOVD" (no integer load/store)
|
|
// ppc64x:"FCPSGN"
|
|
// riscv64:"FSGNJD"
|
|
// wasm:"F64Copysign"
|
|
sink64[0] = math.Copysign(a, b)
|
|
|
|
// amd64:"BTSQ\t[$]63"
|
|
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
|
|
// ppc64x:"FCPSGN"
|
|
// riscv64:"FSGNJD"
|
|
// arm64:"ORR", -"AND"
|
|
sink64[1] = math.Copysign(c, -1)
|
|
|
|
// Like math.Copysign(c, -1), but with integer operations. Useful
|
|
// for platforms that have a copysign opcode to see if it's detected.
|
|
// s390x:"LNDFR\t",-"MOVD\t" (no integer load/store)
|
|
sink64[2] = math.Float64frombits(math.Float64bits(a) | 1<<63)
|
|
|
|
// amd64:"ANDQ","ORQ"
|
|
// s390x:"CPSDR\t",-"MOVD\t" (no integer load/store)
|
|
// ppc64x:"FCPSGN"
|
|
// riscv64:"FSGNJD"
|
|
sink64[3] = math.Copysign(-1, c)
|
|
}
|
|
|
|
func fma(x, y, z float64) float64 {
|
|
// amd64/v3:-".*x86HasFMA"
|
|
// amd64:"VFMADD231SD"
|
|
// arm/6:"FMULAD"
|
|
// arm64:"FMADDD"
|
|
// s390x:"FMADD"
|
|
// ppc64x:"FMADD"
|
|
// riscv64:"FMADDD"
|
|
return math.FMA(x, y, z)
|
|
}
|
|
|
|
func fms(x, y, z float64) float64 {
|
|
// riscv64:"FMSUBD"
|
|
return math.FMA(x, y, -z)
|
|
}
|
|
|
|
func fnms(x, y, z float64) float64 {
|
|
// riscv64:"FNMSUBD",-"FNMADDD"
|
|
return math.FMA(-x, y, z)
|
|
}
|
|
|
|
func fnma(x, y, z float64) float64 {
|
|
// riscv64:"FNMADDD",-"FNMSUBD"
|
|
return math.FMA(x, -y, -z)
|
|
}
|
|
|
|
func fromFloat64(f64 float64) uint64 {
|
|
// amd64:"MOVQ\tX.*, [^X].*"
|
|
// arm64:"FMOVD\tF.*, R.*"
|
|
// loong64:"MOVV\tF.*, R.*"
|
|
// ppc64x:"MFVSRD"
|
|
// mips64/hardfloat:"MOVV\tF.*, R.*"
|
|
return math.Float64bits(f64+1) + 1
|
|
}
|
|
|
|
func fromFloat32(f32 float32) uint32 {
|
|
// amd64:"MOVL\tX.*, [^X].*"
|
|
// arm64:"FMOVS\tF.*, R.*"
|
|
// loong64:"MOVW\tF.*, R.*"
|
|
// mips64/hardfloat:"MOVW\tF.*, R.*"
|
|
return math.Float32bits(f32+1) + 1
|
|
}
|
|
|
|
func toFloat64(u64 uint64) float64 {
|
|
// amd64:"MOVQ\t[^X].*, X.*"
|
|
// arm64:"FMOVD\tR.*, F.*"
|
|
// loong64:"MOVV\tR.*, F.*"
|
|
// ppc64x:"MTVSRD"
|
|
// mips64/hardfloat:"MOVV\tR.*, F.*"
|
|
return math.Float64frombits(u64+1) + 1
|
|
}
|
|
|
|
func toFloat32(u32 uint32) float32 {
|
|
// amd64:"MOVL\t[^X].*, X.*"
|
|
// arm64:"FMOVS\tR.*, F.*"
|
|
// loong64:"MOVW\tR.*, F.*"
|
|
// mips64/hardfloat:"MOVW\tR.*, F.*"
|
|
return math.Float32frombits(u32+1) + 1
|
|
}
|
|
|
|
// Test that comparisons with constants converted to float
|
|
// are evaluated at compile-time
|
|
|
|
func constantCheck64() bool {
|
|
// amd64:"(MOVB\t[$]0)|(XORL\t[A-Z][A-Z0-9]+, [A-Z][A-Z0-9]+)",-"FCMP",-"MOVB\t[$]1"
|
|
// s390x:"MOV(B|BZ|D)\t[$]0,",-"FCMPU",-"MOV(B|BZ|D)\t[$]1,"
|
|
return 0.5 == float64(uint32(1)) || 1.5 > float64(uint64(1<<63))
|
|
}
|
|
|
|
func constantCheck32() bool {
|
|
// amd64:"MOV(B|L)\t[$]1",-"FCMP",-"MOV(B|L)\t[$]0"
|
|
// s390x:"MOV(B|BZ|D)\t[$]1,",-"FCMPU",-"MOV(B|BZ|D)\t[$]0,"
|
|
return float32(0.5) <= float32(int64(1)) && float32(1.5) >= float32(int32(-1<<31))
|
|
}
|
|
|
|
// Test that integer constants are converted to floating point constants
|
|
// at compile-time
|
|
|
|
func constantConvert32(x float32) float32 {
|
|
// amd64:"MOVSS\t[$]f32.3f800000\\(SB\\)"
|
|
// s390x:"FMOVS\t[$]f32.3f800000\\(SB\\)"
|
|
// ppc64x/power8:"FMOVS\t[$]f32.3f800000\\(SB\\)"
|
|
// ppc64x/power9:"FMOVS\t[$]f32.3f800000\\(SB\\)"
|
|
// ppc64x/power10:"XXSPLTIDP\t[$]1065353216, VS0"
|
|
// arm64:"FMOVS\t[$]\\(1.0\\)"
|
|
if x > math.Float32frombits(0x3f800000) {
|
|
return -x
|
|
}
|
|
return x
|
|
}
|
|
|
|
func constantConvertInt32(x uint32) uint32 {
|
|
// amd64:-"MOVSS"
|
|
// s390x:-"FMOVS"
|
|
// ppc64x:-"FMOVS"
|
|
// arm64:-"FMOVS"
|
|
if x > math.Float32bits(1) {
|
|
return -x
|
|
}
|
|
return x
|
|
}
|
|
|
|
func nanGenerate64() float64 {
|
|
// Test to make sure we don't generate a NaN while constant propagating.
|
|
// See issue 36400.
|
|
zero := 0.0
|
|
// amd64:-"DIVSD"
|
|
inf := 1 / zero // +inf. We can constant propagate this one.
|
|
negone := -1.0
|
|
|
|
// amd64:"DIVSD"
|
|
z0 := zero / zero
|
|
// amd64:"MULSD"
|
|
z1 := zero * inf
|
|
// amd64:"SQRTSD"
|
|
z2 := math.Sqrt(negone)
|
|
return z0 + z1 + z2
|
|
}
|
|
|
|
func nanGenerate32() float32 {
|
|
zero := float32(0.0)
|
|
// amd64:-"DIVSS"
|
|
inf := 1 / zero // +inf. We can constant propagate this one.
|
|
|
|
// amd64:"DIVSS"
|
|
z0 := zero / zero
|
|
// amd64:"MULSS"
|
|
z1 := zero * inf
|
|
return z0 + z1
|
|
}
|