Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Fix minor CFI problem in regular x86-64 trampoline | Ulrich Drepper | 2011-08-20 | 1 | -1/+2 |
| | |||||
* | Fix CFI info in x86-64 trampolines for non-AVX code | Ulrich Drepper | 2011-08-20 | 2 | -11/+19 |
| | |||||
* | Minor optimization of popcount in l10nflist | Ulrich Drepper | 2011-08-11 | 1 | -0/+13 |
| | |||||
* | Fix inline strncat/strncmp on x86 | Andreas Schwab | 2011-08-04 | 1 | -1/+1 |
| | |||||
* | One more typo in AVX test | Ulrich Drepper | 2011-07-23 | 1 | -2/+2 |
| | |||||
* | Merge branch 'master' of ssh://sourceware.org/git/glibc | Ulrich Drepper | 2011-07-23 | 2 | -29/+27 |
|\ | | | | | | | | | Conflicts: ChangeLog | ||||
| * | Fix overflow bug is optimized strncat for x86-64 | Ulrich Drepper | 2011-07-21 | 2 | -29/+27 |
| | | |||||
* | | One more change to XSAVE patch | Ulrich Drepper | 2011-07-22 | 1 | -2/+4 |
| | | |||||
* | | Fix AVX check | Andreas Schwab | 2011-07-22 | 1 | -6/+15 |
|/ | |||||
* | Fix check for AVX enablement | Ulrich Drepper | 2011-07-20 | 1 | -5/+12 |
| | | | | | The AVX bit is set if the CPU supports AVX. But this doesn't mean the kernel does. Add checks according to Intel's documentation. | ||||
* | Force :a_x86_64_ymm to be 16-byte aligned | Ulrich Drepper | 2011-07-20 | 1 | -3/+4 |
| | |||||
* | Fix whitespaces | Ulrich Drepper | 2011-07-19 | 4 | -12/+9 |
| | |||||
* | Improve 64 bit strcat functions with SSE2/SSSE3 | Liubov Dmitrieva | 2011-07-19 | 15 | -318/+1486 |
| | |||||
* | Rebuild configure scripts | Ulrich Drepper | 2011-07-06 | 1 | -1/+1 |
| | |||||
* | Improved st{r,p}{,n}cpy for SSE2 and SSSE3 on x86-64 | H.J. Lu | 2011-06-24 | 10 | -1838/+5488 |
| | |||||
* | Optimized st{r,p}{,n}cpy for SSE2/SSSE3 on x86-32 | H.J. Lu | 2011-06-24 | 2 | -3/+14 |
| | |||||
* | Add an elf_ifunc_invoke interface so that architectures can implement | David S. Miller | 2011-06-20 | 1 | -1/+8 |
| | | | | the ifunc resolver calls however they wish. | ||||
* | Assume Intel Core i3/i5/i7 processor if AVX is available | H.J. Lu | 2011-06-03 | 1 | -0/+7 |
| | |||||
* | Fix typo in x86-64 powl | H.J. Lu | 2011-05-18 | 1 | -2/+2 |
| | |||||
* | Fix static linking with checking x86/x86-64 memcpy. | Mike Frysinger | 2011-04-17 | 2 | -2/+2 |
| | |||||
* | Fix memory leak in TLS of loaded objects. | Ulrich Drepper | 2011-04-10 | 1 | -1/+4 |
| | |||||
* | Fix typo in cache information table for x86-{32,64}. | Ulrich Drepper | 2011-04-03 | 1 | -1/+1 |
| | |||||
* | Work around old buggy program which cannot cope with memcpy semantics. | H.J. Lu | 2011-04-01 | 5 | -5/+58 |
| | |||||
* | Last change caused infinite loops because of missing loop increment. | Ulrich Drepper | 2011-03-22 | 1 | -0/+2 |
| | |||||
* | Handle page boundaries in x86 SSE4.2 strncmp. | H.J. Lu | 2011-03-21 | 1 | -15/+30 |
| | |||||
* | Implement x86 cpuid handling of leaf4 for cache information. | Ulrich Drepper | 2011-03-20 | 1 | -0/+49 |
| | |||||
* | Enable SSE2 memset for AMD'supcoming Orochi processor. | Harsha Jagasia | 2011-03-04 | 3 | -50/+79 |
| | | | | | | | | | This patch enables SSE2 memset for AMD's upcoming Orochi processor. This patch also fixes the following bug: For misaligned blocks larger than > 144 Bytes, memset branches into the integer code path depending on the value of misalignment even if the startup code chooses the SSE2 code path upfront, when multiarch is enabled. | ||||
* | Work around empty line at end file generated by autoconf. | Ulrich Drepper | 2011-02-17 | 2 | -0/+2 |
| | |||||
* | Remove use of ranlib. | Ulrich Drepper | 2011-02-15 | 1 | -12/+91 |
| | |||||
* | Fix some warning nits. | Roland McGrath | 2011-02-04 | 1 | -0/+1 |
| | |||||
* | Clean up some bits/select.h headers. | Ulrich Drepper | 2011-01-09 | 1 | -3/+5 |
| | |||||
* | Make PowerPC64 default to nonexecutable stack | Ryan S. Arnold | 2010-12-19 | 1 | -1/+7 |
| | |||||
* | Support Intel processor model 6 and model 0x2. | H.J. Lu | 2010-11-12 | 1 | -0/+1 |
| | |||||
* | Fix one exit path in x86-64 SSE4.2 str{,n}casecmp. | H.J. Lu | 2010-11-10 | 1 | -0/+6 |
| | |||||
* | Fix warnings in __bswap_16. | Ulrich Drepper | 2010-11-10 | 1 | -14/+15 |
| | |||||
* | Use IFUNC on x86-64 memset | H.J. Lu | 2010-11-08 | 9 | -156/+369 |
| | |||||
* | 32bit memset-sse2.S fails with uneven cache size | Ulrich Drepper | 2010-11-05 | 1 | -2/+18 |
| | | | | | | | | | 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. | ||||
* | Fix x86-64 strchr propagation of search byte into all bytes of SSE register | Richard Li | 2010-10-25 | 1 | -2/+2 |
| | |||||
* | Provide FP_FAST_FMA{,F,L} definitions for x86/x86-64. | Ulrich Drepper | 2010-10-19 | 1 | -1/+15 |
| | |||||
* | Implement accurate fma. | Jakub Jelinek | 2010-10-13 | 1 | -2/+2 |
| | |||||
* | Correct implementation of fmaf. | Jakub Jelinek | 2010-10-11 | 3 | -4/+6 |
| | |||||
* | Fix handling of tail bytes of buffer in SSE2/SSSE3 x86-64 version strn{,case}cmp | Ulrich Drepper | 2010-10-03 | 1 | -16/+16 |
| | |||||
* | Re-enable all strncasecmp versions. | Ulrich Drepper | 2010-09-20 | 1 | -2/+0 |
| | |||||
* | Fix limit detection in x86-64 SSE2 strncasecmp. | Ulrich Drepper | 2010-09-20 | 2 | -1/+3 |
| | |||||
* | Update x86-64 mpn routines from GMP 5.0.1. | Ulrich Drepper | 2010-09-02 | 7 | -182/+467 |
| | |||||
* | Fix typo in last commit. | Ulrich Drepper | 2010-08-26 | 1 | -3/+3 |
| | |||||
* | Move slow Atom code to separate section. | Ulrich Drepper | 2010-08-26 | 1 | -1/+1 |
| | |||||
* | Shorten x86-64 strlen a bit. | Ulrich Drepper | 2010-08-26 | 1 | -7/+3 |
| | |||||
* | Unroll x86-64 strlen | H.J. Lu | 2010-08-26 | 5 | -90/+477 |
| | |||||
* | Missing comma in last commit. | H.J. Lu | 2010-08-26 | 1 | -1/+1 |
| |