mirror of
https://github.com/golang/go
synced 2024-11-26 10:18:12 -07:00
1d20a362d0
Currently almost all math functions have the following pattern:
func Sin(x float64) float64
func sin(x float64) float64 {
// ... pure Go implementation ...
}
Architectures that implement a function in assembly provide the
assembly implementation directly as the exported function (e.g., Sin),
and architectures that don't implement it in assembly use a small stub
to jump back to the Go code, like:
TEXT ·Sin(SB), NOSPLIT, $0
JMP ·sin(SB)
However, most functions are not implemented in assembly on most
architectures, so this jump through assembly is a waste. It defeats
compiler optimizations like inlining. And, with regabi, it actually
adds a small but non-trivial overhead because the jump from assembly
back to Go must go through an ABI0->ABIInternal bridge function.
Hence, this CL reorganizes this structure across the entire package.
It now leans on inlining to achieve peak performance, but allows the
compiler to see all the way through the pure Go implementation.
Now, functions follow this pattern:
func Sin(x float64) float64 {
if haveArchSin {
return archSin(x)
}
return sin(x)
}
func sin(x float64) float64 {
// ... pure Go implementation ...
}
Architectures that have assembly implementations use build-tagged
files to set haveArchX to true an provide an archX implementation.
That implementation can also still call back into the Go
implementation (some of them do this).
Prior to this change, enabling ABI wrappers results in a geomean
slowdown of the math benchmarks of 8.77% (full results:
https://perf.golang.org/search?q=upload:20210415.6) and of the Tile38
benchmarks by ~4%. After this change, enabling ABI wrappers is
completely performance-neutral on Tile38 and all but one math
benchmark (full results:
https://perf.golang.org/search?q=upload:20210415.7). ABI wrappers slow
down SqrtIndirectLatency-12 by 2.09%, which makes sense because that
call must still go through an ABI wrapper.
With ABI wrappers disabled (which won't be an option on amd64 much
longer), on linux/amd64, this change is largely performance-neutral
and slightly improves the performance of a few benchmarks:
(Because there are so many benchmarks, I've applied the Šidák
correction to the alpha threshold. It makes relatively little
difference in which benchmarks are statistically significant.)
name old time/op new time/op delta
Acos-12 22.3ns ± 0% 18.8ns ± 1% -15.44% (p=0.000 n=18+16)
Acosh-12 28.2ns ± 0% 28.2ns ± 0% ~ (p=0.404 n=18+20)
Asin-12 18.1ns ± 0% 18.2ns ± 0% +0.20% (p=0.000 n=18+16)
Asinh-12 32.8ns ± 0% 32.9ns ± 1% ~ (p=0.891 n=18+20)
Atan-12 9.92ns ± 0% 9.90ns ± 1% -0.24% (p=0.000 n=17+16)
Atanh-12 27.7ns ± 0% 27.5ns ± 0% -0.72% (p=0.000 n=16+20)
Atan2-12 18.5ns ± 0% 18.4ns ± 0% -0.59% (p=0.000 n=19+19)
Cbrt-12 22.1ns ± 0% 22.1ns ± 0% ~ (p=0.804 n=16+17)
Ceil-12 0.84ns ± 0% 0.84ns ± 0% ~ (p=0.663 n=18+16)
Copysign-12 0.84ns ± 0% 0.84ns ± 0% ~ (p=0.762 n=16+19)
Cos-12 12.7ns ± 0% 12.7ns ± 1% ~ (p=0.145 n=19+18)
Cosh-12 22.2ns ± 0% 22.5ns ± 0% +1.60% (p=0.000 n=17+19)
Erf-12 11.1ns ± 1% 11.1ns ± 1% ~ (p=0.010 n=19+19)
Erfc-12 12.6ns ± 1% 12.7ns ± 0% ~ (p=0.066 n=19+15)
Erfinv-12 16.1ns ± 0% 16.1ns ± 0% ~ (p=0.462 n=17+20)
Erfcinv-12 16.0ns ± 1% 16.0ns ± 1% ~ (p=0.015 n=17+16)
Exp-12 16.3ns ± 0% 16.5ns ± 1% +1.25% (p=0.000 n=19+16)
ExpGo-12 36.2ns ± 1% 36.1ns ± 1% ~ (p=0.242 n=20+18)
Expm1-12 18.6ns ± 0% 18.7ns ± 0% +0.25% (p=0.000 n=16+19)
Exp2-12 34.7ns ± 0% 34.6ns ± 1% ~ (p=0.010 n=19+18)
Exp2Go-12 34.8ns ± 1% 34.8ns ± 1% ~ (p=0.372 n=19+19)
Abs-12 0.56ns ± 0% 0.56ns ± 0% ~ (p=0.766 n=18+16)
Dim-12 0.84ns ± 1% 0.84ns ± 1% ~ (p=0.167 n=17+19)
Floor-12 0.84ns ± 0% 0.84ns ± 0% ~ (p=0.993 n=18+16)
Max-12 3.35ns ± 0% 3.35ns ± 0% ~ (p=0.894 n=17+19)
Min-12 3.35ns ± 0% 3.36ns ± 1% ~ (p=0.214 n=18+18)
Mod-12 35.2ns ± 0% 34.7ns ± 0% -1.45% (p=0.000 n=18+17)
Frexp-12 5.31ns ± 0% 4.75ns ± 0% -10.51% (p=0.000 n=19+18)
Gamma-12 14.8ns ± 0% 16.2ns ± 1% +9.21% (p=0.000 n=20+19)
Hypot-12 6.16ns ± 0% 6.17ns ± 0% +0.26% (p=0.000 n=19+20)
HypotGo-12 7.79ns ± 1% 7.78ns ± 0% ~ (p=0.497 n=18+17)
Ilogb-12 4.47ns ± 0% 4.47ns ± 0% ~ (p=0.167 n=19+19)
J0-12 76.0ns ± 0% 76.3ns ± 0% +0.35% (p=0.000 n=19+18)
J1-12 76.8ns ± 1% 75.9ns ± 0% -1.14% (p=0.000 n=18+18)
Jn-12 167ns ± 1% 168ns ± 1% ~ (p=0.038 n=18+18)
Ldexp-12 6.98ns ± 0% 6.43ns ± 0% -7.97% (p=0.000 n=17+18)
Lgamma-12 15.9ns ± 0% 16.0ns ± 1% ~ (p=0.011 n=20+17)
Log-12 13.3ns ± 0% 13.4ns ± 1% +0.37% (p=0.000 n=15+18)
Logb-12 4.75ns ± 0% 4.75ns ± 0% ~ (p=0.831 n=16+18)
Log1p-12 19.5ns ± 0% 19.5ns ± 1% ~ (p=0.851 n=18+17)
Log10-12 15.9ns ± 0% 14.0ns ± 0% -11.92% (p=0.000 n=17+16)
Log2-12 7.88ns ± 1% 8.01ns ± 0% +1.72% (p=0.000 n=20+20)
Modf-12 4.75ns ± 0% 4.34ns ± 0% -8.66% (p=0.000 n=19+17)
Nextafter32-12 5.31ns ± 0% 5.31ns ± 0% ~ (p=0.389 n=17+18)
Nextafter64-12 5.03ns ± 1% 5.03ns ± 0% ~ (p=0.774 n=17+18)
PowInt-12 29.9ns ± 0% 28.5ns ± 0% -4.69% (p=0.000 n=18+19)
PowFrac-12 91.0ns ± 0% 91.1ns ± 0% ~ (p=0.029 n=19+19)
Pow10Pos-12 1.12ns ± 0% 1.12ns ± 0% ~ (p=0.363 n=20+20)
Pow10Neg-12 3.90ns ± 0% 3.90ns ± 0% ~ (p=0.921 n=17+18)
Round-12 2.31ns ± 0% 2.31ns ± 1% ~ (p=0.390 n=18+18)
RoundToEven-12 0.84ns ± 0% 0.84ns ± 0% ~ (p=0.280 n=18+19)
Remainder-12 31.6ns ± 0% 29.6ns ± 0% -6.16% (p=0.000 n=18+17)
Signbit-12 0.56ns ± 0% 0.56ns ± 0% ~ (p=0.385 n=19+18)
Sin-12 12.5ns ± 0% 12.5ns ± 0% ~ (p=0.080 n=18+18)
Sincos-12 16.4ns ± 2% 16.4ns ± 2% ~ (p=0.253 n=20+19)
Sinh-12 26.1ns ± 0% 26.1ns ± 0% +0.18% (p=0.000 n=17+19)
SqrtIndirect-12 3.91ns ± 0% 3.90ns ± 0% ~ (p=0.133 n=19+19)
SqrtLatency-12 2.79ns ± 0% 2.79ns ± 0% ~ (p=0.226 n=16+19)
SqrtIndirectLatency-12 6.68ns ± 0% 6.37ns ± 2% -4.66% (p=0.000 n=17+20)
SqrtGoLatency-12 49.4ns ± 0% 49.4ns ± 0% ~ (p=0.289 n=18+16)
SqrtPrime-12 3.18µs ± 0% 3.18µs ± 0% ~ (p=0.084 n=17+18)
Tan-12 13.8ns ± 0% 13.9ns ± 2% ~ (p=0.292 n=19+20)
Tanh-12 25.4ns ± 0% 25.4ns ± 0% ~ (p=0.101 n=17+17)
Trunc-12 0.84ns ± 0% 0.84ns ± 0% ~ (p=0.765 n=18+16)
Y0-12 75.8ns ± 0% 75.9ns ± 1% ~ (p=0.805 n=16+18)
Y1-12 76.3ns ± 0% 75.3ns ± 1% -1.34% (p=0.000 n=19+17)
Yn-12 164ns ± 0% 164ns ± 2% ~ (p=0.356 n=18+20)
Float64bits-12 0.56ns ± 0% 0.56ns ± 0% ~ (p=0.383 n=18+18)
Float64frombits-12 0.56ns ± 0% 0.56ns ± 0% ~ (p=0.066 n=18+19)
Float32bits-12 0.56ns ± 0% 0.56ns ± 0% ~ (p=0.889 n=16+19)
Float32frombits-12 0.56ns ± 0% 0.56ns ± 0% ~ (p=0.007 n=18+19)
FMA-12 23.9ns ± 0% 24.0ns ± 0% +0.31% (p=0.000 n=16+17)
[Geo mean] 9.86ns 9.77ns -0.87%
(https://perf.golang.org/search?q=upload:20210415.5)
For #40724.
Change-Id: I44fbba2a17be930ec9daeb0a8222f55cd50555a0
Reviewed-on: https://go-review.googlesource.com/c/go/+/310331
Trust: Austin Clements <austin@google.com>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
469 lines
12 KiB
ArmAsm
469 lines
12 KiB
ArmAsm
// Copyright 2016 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.
|
|
|
|
#include "textflag.h"
|
|
|
|
TEXT ·archLog10(SB), NOSPLIT, $0
|
|
MOVD ·log10vectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·log10TrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·log10vectorfacility+0x00(SB), R1
|
|
MOVD $·log10(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·log10(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·log10vectorfacility+0x00(SB), R1
|
|
MOVD $·log10Asm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·log10Asm(SB)
|
|
|
|
GLOBL ·log10vectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·log10vectorfacility+0x00(SB)/8, $·log10TrampolineSetup(SB)
|
|
|
|
TEXT ·archCos(SB), NOSPLIT, $0
|
|
MOVD ·cosvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·cosTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·cosvectorfacility+0x00(SB), R1
|
|
MOVD $·cos(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·cos(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·cosvectorfacility+0x00(SB), R1
|
|
MOVD $·cosAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·cosAsm(SB)
|
|
|
|
GLOBL ·cosvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·cosvectorfacility+0x00(SB)/8, $·cosTrampolineSetup(SB)
|
|
|
|
TEXT ·archCosh(SB), NOSPLIT, $0
|
|
MOVD ·coshvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·coshTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·coshvectorfacility+0x00(SB), R1
|
|
MOVD $·cosh(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·cosh(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·coshvectorfacility+0x00(SB), R1
|
|
MOVD $·coshAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·coshAsm(SB)
|
|
|
|
GLOBL ·coshvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·coshvectorfacility+0x00(SB)/8, $·coshTrampolineSetup(SB)
|
|
|
|
TEXT ·archSin(SB), NOSPLIT, $0
|
|
MOVD ·sinvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·sinTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·sinvectorfacility+0x00(SB), R1
|
|
MOVD $·sin(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·sin(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·sinvectorfacility+0x00(SB), R1
|
|
MOVD $·sinAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·sinAsm(SB)
|
|
|
|
GLOBL ·sinvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·sinvectorfacility+0x00(SB)/8, $·sinTrampolineSetup(SB)
|
|
|
|
TEXT ·archSinh(SB), NOSPLIT, $0
|
|
MOVD ·sinhvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·sinhTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·sinhvectorfacility+0x00(SB), R1
|
|
MOVD $·sinh(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·sinh(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·sinhvectorfacility+0x00(SB), R1
|
|
MOVD $·sinhAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·sinhAsm(SB)
|
|
|
|
GLOBL ·sinhvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·sinhvectorfacility+0x00(SB)/8, $·sinhTrampolineSetup(SB)
|
|
|
|
TEXT ·archTanh(SB), NOSPLIT, $0
|
|
MOVD ·tanhvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·tanhTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·tanhvectorfacility+0x00(SB), R1
|
|
MOVD $·tanh(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·tanh(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·tanhvectorfacility+0x00(SB), R1
|
|
MOVD $·tanhAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·tanhAsm(SB)
|
|
|
|
GLOBL ·tanhvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·tanhvectorfacility+0x00(SB)/8, $·tanhTrampolineSetup(SB)
|
|
|
|
TEXT ·archLog1p(SB), NOSPLIT, $0
|
|
MOVD ·log1pvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·log1pTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·log1pvectorfacility+0x00(SB), R1
|
|
MOVD $·log1p(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·log1p(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·log1pvectorfacility+0x00(SB), R1
|
|
MOVD $·log1pAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·log1pAsm(SB)
|
|
|
|
GLOBL ·log1pvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·log1pvectorfacility+0x00(SB)/8, $·log1pTrampolineSetup(SB)
|
|
|
|
TEXT ·archAtanh(SB), NOSPLIT, $0
|
|
MOVD ·atanhvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·atanhTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·atanhvectorfacility+0x00(SB), R1
|
|
MOVD $·atanh(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·atanh(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·atanhvectorfacility+0x00(SB), R1
|
|
MOVD $·atanhAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·atanhAsm(SB)
|
|
|
|
GLOBL ·atanhvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·atanhvectorfacility+0x00(SB)/8, $·atanhTrampolineSetup(SB)
|
|
|
|
TEXT ·archAcos(SB), NOSPLIT, $0
|
|
MOVD ·acosvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·acosTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·acosvectorfacility+0x00(SB), R1
|
|
MOVD $·acos(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·acos(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·acosvectorfacility+0x00(SB), R1
|
|
MOVD $·acosAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·acosAsm(SB)
|
|
|
|
GLOBL ·acosvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·acosvectorfacility+0x00(SB)/8, $·acosTrampolineSetup(SB)
|
|
|
|
TEXT ·archAsin(SB), NOSPLIT, $0
|
|
MOVD ·asinvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·asinTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·asinvectorfacility+0x00(SB), R1
|
|
MOVD $·asin(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·asin(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·asinvectorfacility+0x00(SB), R1
|
|
MOVD $·asinAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·asinAsm(SB)
|
|
|
|
GLOBL ·asinvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·asinvectorfacility+0x00(SB)/8, $·asinTrampolineSetup(SB)
|
|
|
|
TEXT ·archAsinh(SB), NOSPLIT, $0
|
|
MOVD ·asinhvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·asinhTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·asinhvectorfacility+0x00(SB), R1
|
|
MOVD $·asinh(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·asinh(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·asinhvectorfacility+0x00(SB), R1
|
|
MOVD $·asinhAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·asinhAsm(SB)
|
|
|
|
GLOBL ·asinhvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·asinhvectorfacility+0x00(SB)/8, $·asinhTrampolineSetup(SB)
|
|
|
|
TEXT ·archAcosh(SB), NOSPLIT, $0
|
|
MOVD ·acoshvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·acoshTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·acoshvectorfacility+0x00(SB), R1
|
|
MOVD $·acosh(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·acosh(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·acoshvectorfacility+0x00(SB), R1
|
|
MOVD $·acoshAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·acoshAsm(SB)
|
|
|
|
GLOBL ·acoshvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·acoshvectorfacility+0x00(SB)/8, $·acoshTrampolineSetup(SB)
|
|
|
|
TEXT ·archErf(SB), NOSPLIT, $0
|
|
MOVD ·erfvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·erfTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·erfvectorfacility+0x00(SB), R1
|
|
MOVD $·erf(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·erf(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·erfvectorfacility+0x00(SB), R1
|
|
MOVD $·erfAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·erfAsm(SB)
|
|
|
|
GLOBL ·erfvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·erfvectorfacility+0x00(SB)/8, $·erfTrampolineSetup(SB)
|
|
|
|
TEXT ·archErfc(SB), NOSPLIT, $0
|
|
MOVD ·erfcvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·erfcTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·erfcvectorfacility+0x00(SB), R1
|
|
MOVD $·erfc(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·erfc(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·erfcvectorfacility+0x00(SB), R1
|
|
MOVD $·erfcAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·erfcAsm(SB)
|
|
|
|
GLOBL ·erfcvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·erfcvectorfacility+0x00(SB)/8, $·erfcTrampolineSetup(SB)
|
|
|
|
TEXT ·archAtan(SB), NOSPLIT, $0
|
|
MOVD ·atanvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·atanTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·atanvectorfacility+0x00(SB), R1
|
|
MOVD $·atan(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·atan(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·atanvectorfacility+0x00(SB), R1
|
|
MOVD $·atanAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·atanAsm(SB)
|
|
|
|
GLOBL ·atanvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·atanvectorfacility+0x00(SB)/8, $·atanTrampolineSetup(SB)
|
|
|
|
TEXT ·archAtan2(SB), NOSPLIT, $0
|
|
MOVD ·atan2vectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·atan2TrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·atan2vectorfacility+0x00(SB), R1
|
|
MOVD $·atan2(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·atan2(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·atan2vectorfacility+0x00(SB), R1
|
|
MOVD $·atan2Asm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·atan2Asm(SB)
|
|
|
|
GLOBL ·atan2vectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·atan2vectorfacility+0x00(SB)/8, $·atan2TrampolineSetup(SB)
|
|
|
|
TEXT ·archCbrt(SB), NOSPLIT, $0
|
|
MOVD ·cbrtvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·cbrtTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·cbrtvectorfacility+0x00(SB), R1
|
|
MOVD $·cbrt(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·cbrt(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·cbrtvectorfacility+0x00(SB), R1
|
|
MOVD $·cbrtAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·cbrtAsm(SB)
|
|
|
|
GLOBL ·cbrtvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·cbrtvectorfacility+0x00(SB)/8, $·cbrtTrampolineSetup(SB)
|
|
|
|
TEXT ·archLog(SB), NOSPLIT, $0
|
|
MOVD ·logvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·logTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·logvectorfacility+0x00(SB), R1
|
|
MOVD $·log(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·log(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·logvectorfacility+0x00(SB), R1
|
|
MOVD $·logAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·logAsm(SB)
|
|
|
|
GLOBL ·logvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·logvectorfacility+0x00(SB)/8, $·logTrampolineSetup(SB)
|
|
|
|
TEXT ·archTan(SB), NOSPLIT, $0
|
|
MOVD ·tanvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·tanTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·tanvectorfacility+0x00(SB), R1
|
|
MOVD $·tan(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·tan(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·tanvectorfacility+0x00(SB), R1
|
|
MOVD $·tanAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·tanAsm(SB)
|
|
|
|
GLOBL ·tanvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·tanvectorfacility+0x00(SB)/8, $·tanTrampolineSetup(SB)
|
|
|
|
TEXT ·archExp(SB), NOSPLIT, $0
|
|
MOVD ·expvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·expTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·expvectorfacility+0x00(SB), R1
|
|
MOVD $·exp(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·exp(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·expvectorfacility+0x00(SB), R1
|
|
MOVD $·expAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·expAsm(SB)
|
|
|
|
GLOBL ·expvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·expvectorfacility+0x00(SB)/8, $·expTrampolineSetup(SB)
|
|
|
|
TEXT ·archExpm1(SB), NOSPLIT, $0
|
|
MOVD ·expm1vectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·expm1TrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·expm1vectorfacility+0x00(SB), R1
|
|
MOVD $·expm1(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·expm1(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·expm1vectorfacility+0x00(SB), R1
|
|
MOVD $·expm1Asm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·expm1Asm(SB)
|
|
|
|
GLOBL ·expm1vectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·expm1vectorfacility+0x00(SB)/8, $·expm1TrampolineSetup(SB)
|
|
|
|
TEXT ·archPow(SB), NOSPLIT, $0
|
|
MOVD ·powvectorfacility+0x00(SB), R1
|
|
BR (R1)
|
|
|
|
TEXT ·powTrampolineSetup(SB), NOSPLIT, $0
|
|
MOVB ·hasVX(SB), R1
|
|
CMPBEQ R1, $1, vectorimpl // vectorfacility = 1, vector supported
|
|
MOVD $·powvectorfacility+0x00(SB), R1
|
|
MOVD $·pow(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·pow(SB)
|
|
|
|
vectorimpl:
|
|
MOVD $·powvectorfacility+0x00(SB), R1
|
|
MOVD $·powAsm(SB), R2
|
|
MOVD R2, 0(R1)
|
|
BR ·powAsm(SB)
|
|
|
|
GLOBL ·powvectorfacility+0x00(SB), NOPTR, $8
|
|
DATA ·powvectorfacility+0x00(SB)/8, $·powTrampolineSetup(SB)
|
|
|