summaryrefslogtreecommitdiff
path: root/sysdeps
AgeCommit message (Collapse)AuthorFilesLines
2013-12-18Remove use of SSE4.2 functions for strstr on i686Andreas Schwab6-49/+2
The SSE4.2 have been removed from x86_64 by commit 584b18eb. This patch fixes the build on i686, which attempts to use the removed files.
2013-12-17Remove unused files from sysdeps/unix/bsd/bsd4.4/bits/.Joseph Myers2-452/+0
2013-12-17Remove various unused files from sysdeps/unix/bsd/.Joseph Myers27-1534/+0
2013-12-17Remove __FAVOR_BSD.Joseph Myers2-75/+78
2013-12-17Update powerpc-fpu ULPs.Adhemerval Zanella1-2/+380
2013-12-17Fix dbl-64 hypot spurious underflows (bug 16314).Joseph Myers1-1/+1
2013-12-17Fix hypot handling of subnormals (bug 16316, bug 16330).Joseph Myers3-0/+33
2013-12-17Make soft-float sh use soft-fp fma/fmaf.Kaz Kojima4-0/+66
2013-12-16Move tests of atan2, hypot and pow from libm-test.inc to auto-libm-test-in.Joseph Myers2-0/+273
2013-12-16Minor code cleanup in s_sin.cSiddhesh Poyarekar1-20/+13
- Remove redundant mynumber union definitions - Clean up a clumsy ternary operator - Rename TAYLOR_SINCOS to TAYLOR_SIN since we're only expanding the sin Taylor series in it.
2013-12-16Update file name in x86_64 ifunc listAllan McRae1-1/+1
File name update missed in commit 584b18eb.
2013-12-14Add strstr with unaligned loads. Fixes bug 12100.Ondřej Bílka8-494/+415
A sse42 version of strstr used pcmpistr instruction which is quite ineffective. A faster way is look for pairs of characters which is uses sse2, is faster than pcmpistr and for real strings a pairs we look for are relatively rare. For linear time complexity we use buy or rent technique which switches to two-way algorithm when superlinear behaviour is detected.
2013-12-14Move sysdeps/sh/sh4/fpu/bits/fenv.h to sysdeps/sh/bits/.Kaz Kojima1-0/+0
2013-12-13PowerPC: multiarch hypot/hypotf for PowerPC64Adhemerval Zanella7-1/+158
2013-12-13PowerPC: multiarch modf/modff for PowerPC64Adhemerval Zanella7-2/+173
2013-12-13PowerPC: multiarch logb/logbl/logbf for PowerPC64Adhemerval Zanella10-1/+244
2013-12-13PowerPC: multiarch isinf/isinff for PowerPC64Adhemerval Zanella6-2/+178
2013-12-13PowerPC: multiarch finite/finitef for PowerPC64Adhemerval Zanella6-2/+186
2013-12-13PowerPC: multiarch llrint/lrint for PowerPC64Adhemerval Zanella5-1/+122
2013-12-13PowerPC: multiarch copysign/copysignf for PowerPC64Adhemerval Zanella5-2/+155
2013-12-13PowerPC: multiarch trunc/truncf for PowerPC64Adhemerval Zanella7-1/+188
2013-12-13PowerPC: multiarch round/roundf for PowerPC64Adhemerval Zanella7-1/+188
2013-12-13PowerPC: multiarch floor/floorf for PowerPC64Adhemerval Zanella7-1/+190
2013-12-13PowerPC: multiarch ceil/ceilf for PowerPC64Adhemerval Zanella7-1/+188
2013-12-13PowerPC: multiarch llround/lround for PowerPC64Adhemerval Zanella6-1/+155
2013-12-13PowerPC: multiarch isnan/isnanf for PowerPC64Adhemerval Zanella8-0/+264
2013-12-13PowerPC: Adjust multiarch Implies for PowerPC64Adhemerval Zanella6-2/+5
This patch adds Implies files on multiarch folder for POWER chips so multirach is enabled when building with --with-cpu and powerN option.
2013-12-13PowerPC: Cleaning up uneeded sqrt routinesAdhemerval Zanella4-202/+0
For PPC64, all the wrappers at sysdeps are superfluous: they are basically the same implementation from math/w_sqrt.c with the '#ifdef _IEEE_LIBM'. And the power4 version just force the 'fsqrt' instruction utilization with an inline assembly, which is already handled by math_private.h __ieee754_sqrt implementation.
2013-12-13PowerPC: multiarch stpcpy for PowerPC64Adhemerval Zanella5-1/+130
2013-12-13PowerPC: multiarch strcpy for PowerPC64Adhemerval Zanella5-1/+123
2013-12-13PowerPC: multiarch wordcopy for PowerPC64Adhemerval Zanella5-1/+146
2013-12-13PowerPC: multiarch wcscpy for PowerPC64.Adhemerval Zanella6-1/+106
2013-12-13PowerPC: multiarch wcsrchr for PowerPC64Adhemerval Zanella6-1/+107
2013-12-13PowerPC: multiarch wcschr for PowerPC64Adhemerval Zanella6-1/+109
2013-12-13PowerPC: multiarch strchrnul for PowerPC64Adhemerval Zanella5-1/+105
2013-12-13PowerPC: multiarch strchr for PowerPC64Adhemerval Zanella6-1/+143
2013-12-13PowerPC: multiarch strncmp for PowerPC64Adhemerval Zanella6-1/+169
2013-12-13PowerPC: multiarch strncasecmp for PowerPC64Adhemerval Zanella6-1/+152
2013-12-13PowerPC: multiarch strcasecmp for PowerPC64Adhemerval Zanella6-1/+182
2013-12-13PowerPC: multiarch strnlen for PowerPC64Adhemerval Zanella5-1/+104
2013-12-13PowerPC: multiarch strlen for PowerPC64Adhemerval Zanella5-1/+120
2013-12-13PowerPC: multiarch rawmemchr for PowerPC64Adhemerval Zanella5-1/+102
2013-12-13PowerPC: multiarch memrchr for PowerPC64Adhemerval Zanella5-1/+107
2013-12-13PowerPC: multiarch memchr for PowerPC64Adhemerval Zanella5-1/+107
2013-12-13PowerPC: multiarch mempcpy for PowerPC64Adhemerval Zanella5-1/+109
2013-12-13PowerPC: multiarch memset/bzero for PowerPC64Adhemerval Zanella16-1/+385
2013-12-13PowerPC: multirach memcmp for PowerPC64Adhemerval Zanella6-1/+166
2013-12-13PowerPC: multiarch memcpy for PowerPC64Adhemerval Zanella10-0/+379
2013-12-13PowerPC: Adjust multiarch Implies for PowerPC64Adhemerval Zanella21-15/+13
This patch adds Implies files on multiarch folder for POWER chips so multirach is enabled when building with --with-cpu and powerN option.
2013-12-13Use $$ver instead of $ver.Kaz Kojima1-2/+2
generated by cgit v1.2.3 (git 2.39.1) at 2025-06-20 11:34:02 +0000