about summary refs log tree commit diff
path: root/sysdeps/i386
Commit message (Collapse)AuthorAgeFilesLines
* Fix whitespacesUlrich Drepper2011-10-122-10/+10
|
* Optimized memchr, memrchr, rawmemchr for x86-32Liubov Dmitrieva2011-10-1211-1/+2639
|
* Optimize libmUlrich Drepper2011-10-1246-149/+179
| | | | | libm is now somewhat integrated with gcc's -ffinite-math-only option and lots of the wrapper functions have been optimized.
* Don't call ifunc functions in trace modeAndreas Schwab2011-10-051-11/+16
|
* Avoid macro clash between <sys/select.h> and <linux/posix_types.h>Andreas Schwab2011-09-131-3/+3
|
* Remove --wth-tls option, TLS support is requiredUlrich Drepper2011-09-112-10/+5
|
* Remove support for !USE___THREADUlrich Drepper2011-09-101-24/+16
|
* Fix jn precisionPetr Baudis2011-09-091-4/+50
|
* Fix up x86-32 section names for Atom codeLiubov Dmitrieva2011-09-076-9/+6
|
* Move Atom-optimized code out of the way and togetherUlrich Drepper2011-09-064-5/+7
|
* Fix whitespacesUlrich Drepper2011-09-052-2/+0
|
* Optimized strchr and strrchr with SSE2 on x86-32Liubov Dmitrieva2011-09-057-1/+1656
|
* Fix whitespacesUlrich Drepper2011-09-053-4/+1
|
* Add x86-32 optimized wcscmpUlrich Drepper2011-09-054-1/+1075
|
* rtld, i386: Fix cfi directive in audit trampoline codeJiri Olsa2011-08-291-2/+2
| | | | | | | | | | | _dl_runtime_profile function has wrong cfi directive when rewinding stack back for the pltexit path. Only 8 bytes - 2 'pop edx' instructions from the pltentry-only code should be rewinded back. With attached patch, I'm able to rewind stack correctly throught the rtld code from audit library callback.
* Fix spurious nop at start of __strspn_ia32Andreas Schwab2011-08-231-2/+2
|
* More warning patrol, in dead code (sigh).Roland McGrath2011-08-141-5/+13
|
* Fix whitespacesUlrich Drepper2011-08-042-2/+0
|
* Improve x86-32 strcat functions with SSE2/SSSE3Liubov Dmitrieva2011-08-0410-317/+2314
|
* Fix inline strncat/strncmp on x86Andreas Schwab2011-08-041-8/+8
|
* Never use -mpreferred-stack-boundary=2 on i386, now disallowed by GCC.Roland McGrath2011-07-161-1/+4
|
* Quash a warning in strstr-c.c built for static.Roland McGrath2011-07-141-0/+2
|
* Fix unwind info in 32bit SSE2/SSSE3 strncpyH.J. Lu2011-06-252-1/+5
|
* Optimized st{r,p}{,n}cpy for SSE2/SSSE3 on x86-32H.J. Lu2011-06-2414-1/+6542
|
* Add an elf_ifunc_invoke interface so that architectures can implementDavid S. Miller2011-06-201-1/+8
| | | | the ifunc resolver calls however they wish.
* Remove doubled words.Jim Meyering2011-04-221-2/+2
|
* Fix static linking with checking x86/x86-64 memcpy.Mike Frysinger2011-04-172-2/+2
|
* Fix memory leak in TLS of loaded objects.Ulrich Drepper2011-04-101-1/+4
|
* Regenerate.Ulrich Drepper2011-03-101-12/+90
|
* AVX audit test failures with gcc 4.6H.J. Lu2011-02-022-332/+433
|
* Fix alignment in x86 destructor calls.Ulrich Drepper2011-01-121-0/+1
|
* Clean up some bits/select.h headers.Ulrich Drepper2011-01-091-25/+8
|
* Remove `.ctors' and `.dtors' output sectionsH.J. Lu2010-12-241-0/+2
|
* Make PowerPC64 default to nonexecutable stackRyan S. Arnold2010-12-191-1/+7
|
* Undo accidental checkin.Ulrich Drepper2010-12-141-25/+30
|
* Fix -D_FORTIFY_SOURCE memmove and bcopJakub Jelinek2010-12-091-30/+25
|
* Remove dead code from x86-32 SSSE3 strncmp.H.J. Lu2010-12-011-8/+1
|
* Relax libm tests for x86-32.Ulrich Drepper2010-11-301-2/+2
|
* Fix warnings in __bswap_16.Ulrich Drepper2010-11-101-7/+8
|
* 32bit memset-sse2.S fails with uneven cache sizeUlrich Drepper2010-11-051-0/+4
| | | | | | | | | 32bit memset-sse2.S assumes cache size is multiple of 128 bytes. If it isn't true, memset-sse2.S will fail. For example, a processor can have 24576 KB L3 cache and 20 cores. That is 2516582 byte per core. Half of it is 1258291, which isn't helpful for vector instructions. This patch rounds cache sizes to multiple of 256 bytes and adds "raw" cache sizes.
* Provide FP_FAST_FMA{,F,L} definitions for x86/x86-64.Ulrich Drepper2010-10-191-1/+15
|
* Implement fmal, some fma bugfixesJakub Jelinek2010-10-153-94/+0
|
* Implement accurate fma.Jakub Jelinek2010-10-132-5/+3
|
* Correct implementation of fmaf.Jakub Jelinek2010-10-113-3/+5
|
* Add missing i686/multiarch/Makefile bit for shared x86_64 code.Roland McGrath2010-08-271-0/+1
|
* Fixup x86 after x86-64 varshift change.Ulrich Drepper2010-08-272-1/+1
|
* Unroll 32bit SSE strlen and handle slow bsfH.J. Lu2010-08-254-80/+480
|
* Clean up SSE variable shiftsRichard Henderson2010-08-243-1/+3
|
* Fix ifunc thunk for strspn on x86 in static libcAndreas Schwab2010-08-191-2/+2
|
* Add -fno-asynchronous-unwind-tables to initfini.s for i386H.J. Lu2010-08-151-0/+4
|