1
0
mirror of https://github.com/golang/go synced 2024-11-13 20:00:23 -07:00
go/src/math/cbrt.go
Bill O'Farrell 88672de7af math: use SIMD to accelerate additional scalar math functions on s390x
As necessary, math functions were structured to use stubs, so that they can
be accelerated with assembly on any platform.

Technique used was minimax polynomial approximation using tables of
polynomial coefficients, with argument range reduction.

Benchmark         New     Old     Speedup
BenchmarkAcos     12.2    47.5    3.89
BenchmarkAcosh    18.5    56.2    3.04
BenchmarkAsin     13.1    40.6    3.10
BenchmarkAsinh    19.4    62.8    3.24
BenchmarkAtan     10.1    23      2.28
BenchmarkAtanh    19.1    53.2    2.79
BenchmarkAtan2    16.5    33.9    2.05
BenchmarkCbrt     14.8    58      3.92
BenchmarkErf      10.8    20.1    1.86
BenchmarkErfc     11.2    23.5    2.10
BenchmarkExp      8.77    53.8    6.13
BenchmarkExpm1    10.1    38.3    3.79
BenchmarkLog      13.1    40.1    3.06
BenchmarkLog1p    12.7    38.3    3.02
BenchmarkPowInt   31.7    40.5    1.28
BenchmarkPowFrac  33.1    141     4.26
BenchmarkTan      11.5    30      2.61

Accuracy was tested against a high precision
reference function to determine maximum error.
Note: ulperr is error in "units in the last place"

       max
      ulperr
Acos  1.15
Acosh 1.07
Asin  2.22
Asinh 1.72
Atan  1.41
Atanh 3.00
Atan2 1.45
Cbrt  1.18
Erf   1.29
Erfc  4.82
Exp   1.00
Expm1 2.26
Log   0.94
Log1p 2.39
Tan   3.14

Pow will have 99.99% correctly rounded results with reasonable inputs
producing numeric (non Inf or NaN) results

Change-Id: I850e8cf7b70426e8b54ec49d74acd4cddc8c6cb2
Reviewed-on: https://go-review.googlesource.com/38585
Reviewed-by: Michael Munday <munday@ca.ibm.com>
Run-TryBot: Michael Munday <munday@ca.ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
2017-05-08 19:52:30 +00:00

80 lines
2.2 KiB
Go

// Copyright 2009 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 math
// The go code is a modified version of the original C code from
// http://www.netlib.org/fdlibm/s_cbrt.c and came with this notice.
//
// ====================================================
// Copyright (C) 1993 by Sun Microsystems, Inc. All rights reserved.
//
// Developed at SunSoft, a Sun Microsystems, Inc. business.
// Permission to use, copy, modify, and distribute this
// software is freely granted, provided that this notice
// is preserved.
// ====================================================
// Cbrt returns the cube root of x.
//
// Special cases are:
// Cbrt(±0) = ±0
// Cbrt(±Inf) = ±Inf
// Cbrt(NaN) = NaN
func Cbrt(x float64) float64
func cbrt(x float64) float64 {
const (
B1 = 715094163 // (682-0.03306235651)*2**20
B2 = 696219795 // (664-0.03306235651)*2**20
C = 5.42857142857142815906e-01 // 19/35 = 0x3FE15F15F15F15F1
D = -7.05306122448979611050e-01 // -864/1225 = 0xBFE691DE2532C834
E = 1.41428571428571436819e+00 // 99/70 = 0x3FF6A0EA0EA0EA0F
F = 1.60714285714285720630e+00 // 45/28 = 0x3FF9B6DB6DB6DB6E
G = 3.57142857142857150787e-01 // 5/14 = 0x3FD6DB6DB6DB6DB7
SmallestNormal = 2.22507385850720138309e-308 // 2**-1022 = 0x0010000000000000
)
// special cases
switch {
case x == 0 || IsNaN(x) || IsInf(x, 0):
return x
}
sign := false
if x < 0 {
x = -x
sign = true
}
// rough cbrt to 5 bits
t := Float64frombits(Float64bits(x)/3 + B1<<32)
if x < SmallestNormal {
// subnormal number
t = float64(1 << 54) // set t= 2**54
t *= x
t = Float64frombits(Float64bits(t)/3 + B2<<32)
}
// new cbrt to 23 bits
r := t * t / x
s := C + r*t
t *= G + F/(s+E+D/s)
// chop to 22 bits, make larger than cbrt(x)
t = Float64frombits(Float64bits(t)&(0xFFFFFFFFC<<28) + 1<<30)
// one step newton iteration to 53 bits with error less than 0.667ulps
s = t * t // t*t is exact
r = x / s
w := t + t
r = (r - t) / (w + r) // r-s is exact
t = t + t*r
// restore the sign bit
if sign {
t = -t
}
return t
}