mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-23 05:20:06 +00:00
bc3753638a
On powerpc32 hard-float, older processors (ones where fcfid is not available for 32-bit code), GCC generates conversions from integers to floating point that wrongly convert integer 0 to -0 instead of +0 in FE_DOWNWARD mode. This in turn results in logb and a few other functions wrongly returning -0 when they should return +0. This patch works around this issue in glibc as I proposed in <https://sourceware.org/ml/libc-alpha/2015-09/msg00728.html>, so that the affected functions can be correct and the affected tests pass in the absence of a GCC fix for this longstanding issue (GCC bug 67771 - if fixed, of course we can put in GCC version conditionals, and eventually phase out the workarounds). A new macro FIX_INT_FP_CONVERT_ZERO is added in a new sysdeps header fix-int-fp-convert-zero.h, and the powerpc32/fpu version of that header defines the macro based on the results of a configure test for whether such conversions use the fcfid instruction. Tested for x86_64 (that installed stripped shared libraries are unchanged by the patch) and powerpc (that HAVE_PPC_FCFID comes out to 0 as expected and that the relevant tests are fixed). Also tested a build with GCC configured for -mcpu=power4 and verified that HAVE_PPC_FCFID comes out to 1 in that case. There are still some other issues to fix to get test-float and test-double passing cleanly for older powerpc32 processors (apart from the need for an ulps regeneration for powerpc). (test-ldouble will be harder to get passing cleanly, but with a combination of selected fixes to ldbl-128ibm code that don't involve significant performance issues, allowing spurious underflow and inexact exceptions for that format, and lots of XFAILing for the default case of unpatched libgcc, it should be doable.) [BZ #887] [BZ #19049] [BZ #19050] * sysdeps/generic/fix-int-fp-convert-zero.h: New file. * sysdeps/ieee754/dbl-64/e_log10.c: Include <fix-int-fp-convert-zero.h>. (__ieee754_log10): Adjust signs as needed if FIX_INT_FP_CONVERT_ZERO. * sysdeps/ieee754/dbl-64/e_log2.c: Include <fix-int-fp-convert-zero.h>. (__ieee754_log2): Adjust signs as needed if FIX_INT_FP_CONVERT_ZERO. * sysdeps/ieee754/dbl-64/s_erf.c: Include <fix-int-fp-convert-zero.h>. (__erfc): Adjust signs as needed if FIX_INT_FP_CONVERT_ZERO. * sysdeps/ieee754/dbl-64/s_logb.c: Include <fix-int-fp-convert-zero.h>. (__logb): Adjust signs as needed if FIX_INT_FP_CONVERT_ZERO. * sysdeps/ieee754/flt-32/e_log10f.c: Include <fix-int-fp-convert-zero.h>. (__ieee754_log10f): Adjust signs as needed if FIX_INT_FP_CONVERT_ZERO. * sysdeps/ieee754/flt-32/e_log2f.c: Include <fix-int-fp-convert-zero.h>. (__ieee754_log2f): Adjust signs as needed if FIX_INT_FP_CONVERT_ZERO. * sysdeps/ieee754/flt-32/s_erff.c: Include <fix-int-fp-convert-zero.h>. (__erfcf): Adjust signs as needed if FIX_INT_FP_CONVERT_ZERO. * sysdeps/ieee754/flt-32/s_logbf.c: Include <fix-int-fp-convert-zero.h>. (__logbf): Adjust signs as needed if FIX_INT_FP_CONVERT_ZERO. * sysdeps/ieee754/ldbl-128ibm/s_erfl.c: Include <fix-int-fp-convert-zero.h>. (__erfcl): Adjust signs as needed if FIX_INT_FP_CONVERT_ZERO. * sysdeps/ieee754/ldbl-128ibm/s_logbl.c: Include <fix-int-fp-convert-zero.h>. (__logbl): Adjust signs as needed if FIX_INT_FP_CONVERT_ZERO. * sysdeps/powerpc/powerpc32/fpu/configure.ac: New file. * sysdeps/powerpc/powerpc32/fpu/configure: New generated file. * sysdeps/powerpc/powerpc32/fpu/fix-int-fp-convert-zero.h: New file. * config.h.in [_LIBC] (HAVE_PPC_FCFID): New macro.
87 lines
2.3 KiB
C
87 lines
2.3 KiB
C
/* e_logf.c -- float version of e_log.c.
|
|
* Conversion to float by Ian Lance Taylor, Cygnus Support, ian@cygnus.com.
|
|
* adapted for log2 by Ulrich Drepper <drepper@cygnus.com>
|
|
*/
|
|
|
|
/*
|
|
* ====================================================
|
|
* Copyright (C) 1993 by Sun Microsystems, Inc. All rights reserved.
|
|
*
|
|
* Developed at SunPro, a Sun Microsystems, Inc. business.
|
|
* Permission to use, copy, modify, and distribute this
|
|
* software is freely granted, provided that this notice
|
|
* is preserved.
|
|
* ====================================================
|
|
*/
|
|
|
|
|
|
#include <math.h>
|
|
#include <math_private.h>
|
|
#include <fix-int-fp-convert-zero.h>
|
|
|
|
static const float
|
|
ln2 = 0.69314718055994530942,
|
|
two25 = 3.355443200e+07, /* 0x4c000000 */
|
|
Lg1 = 6.6666668653e-01, /* 3F2AAAAB */
|
|
Lg2 = 4.0000000596e-01, /* 3ECCCCCD */
|
|
Lg3 = 2.8571429849e-01, /* 3E924925 */
|
|
Lg4 = 2.2222198546e-01, /* 3E638E29 */
|
|
Lg5 = 1.8183572590e-01, /* 3E3A3325 */
|
|
Lg6 = 1.5313838422e-01, /* 3E1CD04F */
|
|
Lg7 = 1.4798198640e-01; /* 3E178897 */
|
|
|
|
static const float zero = 0.0;
|
|
|
|
float
|
|
__ieee754_log2f(float x)
|
|
{
|
|
float hfsq,f,s,z,R,w,t1,t2,dk;
|
|
int32_t k,ix,i,j;
|
|
|
|
GET_FLOAT_WORD(ix,x);
|
|
|
|
k=0;
|
|
if (ix < 0x00800000) { /* x < 2**-126 */
|
|
if (__builtin_expect((ix&0x7fffffff)==0, 0))
|
|
return -two25/(x-x); /* log(+-0)=-inf */
|
|
if (__builtin_expect(ix<0, 0))
|
|
return (x-x)/(x-x); /* log(-#) = NaN */
|
|
k -= 25; x *= two25; /* subnormal number, scale up x */
|
|
GET_FLOAT_WORD(ix,x);
|
|
}
|
|
if (__builtin_expect(ix >= 0x7f800000, 0)) return x+x;
|
|
k += (ix>>23)-127;
|
|
ix &= 0x007fffff;
|
|
i = (ix+(0x95f64<<3))&0x800000;
|
|
SET_FLOAT_WORD(x,ix|(i^0x3f800000)); /* normalize x or x/2 */
|
|
k += (i>>23);
|
|
dk = (float)k;
|
|
f = x-(float)1.0;
|
|
if((0x007fffff&(15+ix))<16) { /* |f| < 2**-20 */
|
|
if(f==zero)
|
|
{
|
|
if (FIX_INT_FP_CONVERT_ZERO && dk == 0.0f)
|
|
dk = 0.0f;
|
|
return dk;
|
|
}
|
|
R = f*f*((float)0.5-(float)0.33333333333333333*f);
|
|
return dk-(R-f)/ln2;
|
|
}
|
|
s = f/((float)2.0+f);
|
|
z = s*s;
|
|
i = ix-(0x6147a<<3);
|
|
w = z*z;
|
|
j = (0x6b851<<3)-ix;
|
|
t1= w*(Lg2+w*(Lg4+w*Lg6));
|
|
t2= z*(Lg1+w*(Lg3+w*(Lg5+w*Lg7)));
|
|
i |= j;
|
|
R = t2+t1;
|
|
if(i>0) {
|
|
hfsq=(float)0.5*f*f;
|
|
return dk-((hfsq-(s*(hfsq+R)))-f)/ln2;
|
|
} else {
|
|
return dk-((s*(f-R))-f)/ln2;
|
|
}
|
|
}
|
|
strong_alias (__ieee754_log2f, __log2f_finite)
|