about summary refs log tree commit diff
path: root/sysdeps/x86_64
Commit message (Collapse)AuthorAgeFilesLines
* Clean up some bits/select.h headers.Ulrich Drepper2011-01-091-3/+5
|
* Make PowerPC64 default to nonexecutable stackRyan S. Arnold2010-12-191-1/+7
|
* Support Intel processor model 6 and model 0x2.H.J. Lu2010-11-121-0/+1
|
* Fix one exit path in x86-64 SSE4.2 str{,n}casecmp.H.J. Lu2010-11-101-0/+6
|
* Fix warnings in __bswap_16.Ulrich Drepper2010-11-101-14/+15
|
* Use IFUNC on x86-64 memsetH.J. Lu2010-11-089-156/+369
|
* 32bit memset-sse2.S fails with uneven cache sizeUlrich Drepper2010-11-051-2/+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 registerRichard Li2010-10-251-2/+2
|
* Provide FP_FAST_FMA{,F,L} definitions for x86/x86-64.Ulrich Drepper2010-10-191-1/+15
|
* Implement accurate fma.Jakub Jelinek2010-10-131-2/+2
|
* Correct implementation of fmaf.Jakub Jelinek2010-10-113-4/+6
|
* Fix handling of tail bytes of buffer in SSE2/SSSE3 x86-64 version strn{,case}cmpUlrich Drepper2010-10-031-16/+16
|
* Re-enable all strncasecmp versions.Ulrich Drepper2010-09-201-2/+0
|
* Fix limit detection in x86-64 SSE2 strncasecmp.Ulrich Drepper2010-09-202-1/+3
|
* Update x86-64 mpn routines from GMP 5.0.1.Ulrich Drepper2010-09-027-182/+467
|
* Fix typo in last commit.Ulrich Drepper2010-08-261-3/+3
|
* Move slow Atom code to separate section.Ulrich Drepper2010-08-261-1/+1
|
* Shorten x86-64 strlen a bit.Ulrich Drepper2010-08-261-7/+3
|
* Unroll x86-64 strlenH.J. Lu2010-08-265-90/+477
|
* Missing comma in last commit.H.J. Lu2010-08-261-1/+1
|
* Clean up warnings in new x86_64/multiarch code.Roland McGrath2010-08-255-21/+63
|
* Unroll 32bit SSE strlen and handle slow bsfH.J. Lu2010-08-252-0/+12
|
* Add missing copyright year updated and pretty printing.Ulrich Drepper2010-08-243-3/+3
|
* Clean up SSE variable shiftsRichard Henderson2010-08-246-354/+73
|
* Fix two typos in x86-64 SSE4.2 strncasecmp implementation.Ulrich Drepper2010-08-191-2/+2
|
* Fix fourth parameter of SSE4.2 strcmp for x86-64.Ulrich Drepper2010-08-151-3/+3
|
* Use correct register for fourth parameter of x86-64 strncasecmp_l.Ulrich Drepper2010-08-151-3/+3
|
* Undo inccorect change.Ulrich Drepper2010-08-151-1/+1
|
* Add optimized strncasecmp versions for x86-64.Ulrich Drepper2010-08-1410-283/+435
|
* Fix x86-64 build without multiarch.Ulrich Drepper2010-08-142-1/+1
|
* x86: Add support for frame pointer less mcountAndi Kleen2010-08-071-0/+38
|
* Add support for SSSE3 and SSE4.2 versions of strcasecmp on x86-64.Ulrich Drepper2010-07-315-22/+384
|
* Pretty printing x86-64 SSE4.3 strcmp.Ulrich Drepper2010-07-301-29/+29
|
* Implement optimized strcaecmp for x86-64.Ulrich Drepper2010-07-306-2/+160
|
* Fix tolower operation in strcasestr.Ulrich Drepper2010-07-301-1/+1
|
* Avoid compiling unneeded file in ld.so.Ulrich Drepper2010-07-271-3/+5
|
* Add optimized x86-64 implementation of strnlen.Ulrich Drepper2010-07-261-0/+64
| | | | | While at it, beef up the test suite for strnlen and add performance tests for it, too.
* Speed up x86-64 strcasestr a bit moew.Ulrich Drepper2010-07-241-5/+11
| | | | | Using the new SSE4.2 instructions is cool but not really the fastest. Some older SSE instructions can do the trick faster.
* Add strcasestr-nonascii to i386 buildAndreas Schwab2010-07-212-7/+10
|
* Fix non-ASCII case of SSE4.2 strcasstr.Ulrich Drepper2010-07-161-0/+2
|
* Speed up SSE4.2 strcasestr by avoiding indirect function call.Ulrich Drepper2010-07-164-49/+76
|
* Improve 64bit memcpy/memmove for Atom, Core 2 and Core i7H.J. Lu2010-06-3018-8/+6640
| | | | | | | This patch includes optimized 64bit memcpy/memmove for Atom, Core 2 and Core i7. It improves memcpy by up to 3X on Atom, up to 4X on Core 2 and up to 1X on Core i7. It also improves memmove by up to 3X on Atom, up to 4X on Core 2 and up to 2X on Core i7.
* Incorrect x86 CPU family and model check.H.J. Lu2010-05-271-3/+3
|
* Whitespace fix.Ulrich Drepper2010-04-141-1/+0
|
* Add x86-32 FMA supportH.J. Lu2010-04-142-36/+0
|
* Check DATA_CACHE_SIZE_HALFH.J. Lu2010-04-141-2/+2
|
* Optimie x86-64 SSE4 memcmp for unaligned data.H.J. Lu2010-04-141-6/+371
|
* x86-64 SSE4 optimized memcmpH.J. Lu2010-04-144-1/+1331
| | | | | This is 64bit SSE4 optimized memcmp. It improves memcmp by upto 3X on Intel Core i7.
* Update x86-64 cpu multiarch selection header.Ulrich Drepper2010-04-131-17/+21
|
* Fix concurrent handling of __cpu_features.Ulrich Drepper2010-04-042-14/+23
|