about summary refs log tree commit diff
path: root/sysdeps
Commit message (Collapse)AuthorAgeFilesLines
* Remove unnecessary code from x86-32 SSSE3 strncmpUlrich Drepper2011-11-081-3/+1
|
* Fix test of non-ASCII locales in x86-64 strcasecmp et.al.Ulrich Drepper2011-11-012-5/+5
|
* unsigned long it better for the size argumentsUlrich Drepper2011-11-011-4/+6
| | | | | The new syscalls should use unsigned long not size_t. The parameters are not a direct measure of memory size.
* New Linux syscalls process_vm_readv and process_vm_writevUlrich Drepper2011-11-013-1/+30
|
* Cache network interface informationUlrich Drepper2011-10-313-38/+149
| | | | | | | | | | | | Whenever getaddrinfo needed network interface information it used the netlink interface to read the information every single time. The problem is that this information can change at any time. The patch implements monitoring of the network interfaces through nscd. If no change is detected the previously read information can be reused (which is the norm). This timestamp information is also made available to other processes using the shared memory segment between nscd and those processes.
* Fix potential double close in __check_fd if OOMUlrich Drepper2011-10-301-15/+18
|
* Fix accuracy problem in generic sinUlrich Drepper2011-10-291-1/+1
|
* More cleanups of x86-64 strstrUlrich Drepper2011-10-281-13/+12
|
* Clean up x86-64 strcasestrUlrich Drepper2011-10-281-13/+12
| | | | Actually describe in the C code what is going on.
* Remove code without too much effectsUlrich Drepper2011-10-2815-113/+5
| | | | | Some of the AVX-specific code is not giving enough speed-up to justify the extra code.
* Fix some warning nitsAndreas Schwab2011-10-282-7/+5
|
* Move wide char related routines to wcsmbs subdirAndreas Schwab2011-10-281-3/+7
|
* Fix uses of math_force_evalAndreas Schwab2011-10-263-6/+6
|
* Make math_force_eval accept non-addressable argumentsAndreas Schwab2011-10-261-3/+4
|
* Add AVX optimized versions for some x86-64 math functionsUlrich Drepper2011-10-2529-92/+335
|
* Optimize x86-64 SSE4.2+ strcmp a bit moreUlrich Drepper2011-10-251-175/+130
|
* Use math_force_eval in more placesUlrich Drepper2011-10-2520-310/+235
|
* Use VEX encoding in inline math functions on x86-64 when possibleUlrich Drepper2011-10-251-48/+138
|
* Cleanup FMA4 patchUlrich Drepper2011-10-2546-198/+444
| | | | | Move the FMA4 code into its own section. Avoid some of the duplication of data resulting from the double use of source files.
* Better DLA_FMSUlrich Drepper2011-10-241-1/+8
| | | | | It's better to use __builtin_fma if it works. Use it for gcc 4.6 and higher. Move the x86-64 dla.h to the correct place.
* Use inline asm for DLA_FMS because of broken old compilersUlrich Drepper2011-10-241-2/+6
|
* Optimize accurate 64-bit routines for FMA4 on x86-64Ulrich Drepper2011-10-2443-176/+533
|
* Finish renamed DLA_FMA -> DLA_FMSUlrich Drepper2011-10-248-9/+9
|
* Optimized remquo for 64-bit platformsUlrich Drepper2011-10-231-0/+112
|
* Optimize f_modUlrich Drepper2011-10-232-6/+109
| | | | | Branch prediction for the 32-bit implementation and a new optimized 64-bit implementation.
* Fix strnlen changeUlrich Drepper2011-10-231-0/+1
|
* Add optimized wcslen and strnlen for x86-32Liubov Dmitrieva2011-10-238-40/+723
|
* Fix WSUlrich Drepper2011-10-231-1/+1
|
* Optimized strnlen and wcscmp for x86-64Liubov Dmitrieva2011-10-238-317/+987
|
* Improve x86-32 SSSE3 memcpyMichael Zolotukhin2011-10-231-219/+708
|
* Fix WSUlrich Drepper2011-10-232-10/+10
|
* Fix signedness in wcscmp comparisonLiubov Dmitrieva2011-10-232-116/+151
|
* Clean up FMA useUlrich Drepper2011-10-232-9/+6
| | | | | The macro's name should reflect that subtraction is being done. And use __builtin_fma, it seems to work after all.
* Clean up last dla.h changeUlrich Drepper2011-10-2311-21/+18
|
* Add missing _finite aliasesAndreas Schwab2011-10-231-0/+2
|
* Fix typo in last changeUlrich Drepper2011-10-221-1/+1
|
* Update ULPs for x86-64Ulrich Drepper2011-10-221-4/+12
|
* Improve DLA_FMA for FMA4Ulrich Drepper2011-10-221-2/+2
|
* Start using fma in the libm implementationUlrich Drepper2011-10-229-150/+192
|
* Fix compilation due to __nan definesAndreas Schwab2011-10-221-0/+1
|
* Optimization to some complex math functionsUlrich Drepper2011-10-223-3/+3
| | | | Also, change last reference to __sqrt into __sqrt to easily.
* Fix compilation problems in x86-64 init-archUlrich Drepper2011-10-211-1/+2
|
* Add some __builtin_expect to generic __ieee754_logUlrich Drepper2011-10-211-3/+3
|
* Don't use NULL in last s_fma{,f} changeUlrich Drepper2011-10-212-2/+2
|
* Check for FMA4 support and generate appropriate fma functionsUlrich Drepper2011-10-206-27/+103
|
* Move fma routines to right placeUlrich Drepper2011-10-202-0/+0
|
* Optimize x86-64 rawmemchr and add testUlrich Drepper2011-10-191-4/+3
|
* Add optimized str{,n}casecmp for AVX on x86-64Ulrich Drepper2011-10-193-1798/+1870
|
* Fix PLT use for feraiseexcept on x86_64Andreas Schwab2011-10-191-1/+1
|
* Use new internal libc_fe* interfaces in more functionsUlrich Drepper2011-10-186-56/+63
|