aboutsummaryrefslogtreecommitdiff
path: root/sysdeps
AgeCommit message (Collapse)Author
2011-11-12Prepare dwarf2.h for multiple inclusionUlrich Drepper
2011-11-12Fix incomplete edit in last patchUlrich Drepper
2011-11-12Avoid redefinition of DWARF constantsUlrich Drepper
2011-11-12Avoid warning from shiftingUlrich Drepper
2011-11-12Fix warnings in fallback C code of x86-32 wide memory functionsUlrich Drepper
2011-11-11PowerPC: Arithmetic function optimizations for POWERAdhemerval Zanella
2011-11-11Remove unused variablesMarek Polacek
2011-11-08Remove unnecessary code from x86-32 SSSE3 strncmpUlrich Drepper
2011-11-01Fix test of non-ASCII locales in x86-64 strcasecmp et.al.Ulrich Drepper
2011-11-01unsigned long it better for the size argumentsUlrich Drepper
The new syscalls should use unsigned long not size_t. The parameters are not a direct measure of memory size.
2011-11-01New Linux syscalls process_vm_readv and process_vm_writevUlrich Drepper
2011-10-31Cache network interface informationUlrich Drepper
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.
2011-10-30Fix potential double close in __check_fd if OOMUlrich Drepper
2011-10-29Fix accuracy problem in generic sinUlrich Drepper
2011-10-28More cleanups of x86-64 strstrUlrich Drepper
2011-10-28Clean up x86-64 strcasestrUlrich Drepper
Actually describe in the C code what is going on.
2011-10-28Remove code without too much effectsUlrich Drepper
Some of the AVX-specific code is not giving enough speed-up to justify the extra code.
2011-10-28Fix some warning nitsAndreas Schwab
2011-10-28Move wide char related routines to wcsmbs subdirAndreas Schwab
2011-10-26Fix uses of math_force_evalAndreas Schwab
2011-10-26Make math_force_eval accept non-addressable argumentsAndreas Schwab
2011-10-25Add AVX optimized versions for some x86-64 math functionsUlrich Drepper
2011-10-25Optimize x86-64 SSE4.2+ strcmp a bit moreUlrich Drepper
2011-10-25Use math_force_eval in more placesUlrich Drepper
2011-10-25Use VEX encoding in inline math functions on x86-64 when possibleUlrich Drepper
2011-10-25Cleanup FMA4 patchUlrich Drepper
Move the FMA4 code into its own section. Avoid some of the duplication of data resulting from the double use of source files.
2011-10-24Better DLA_FMSUlrich Drepper
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.
2011-10-24Use inline asm for DLA_FMS because of broken old compilersUlrich Drepper
2011-10-24Optimize accurate 64-bit routines for FMA4 on x86-64Ulrich Drepper
2011-10-24Finish renamed DLA_FMA -> DLA_FMSUlrich Drepper
2011-10-23Optimized remquo for 64-bit platformsUlrich Drepper
2011-10-23Optimize f_modUlrich Drepper
Branch prediction for the 32-bit implementation and a new optimized 64-bit implementation.
2011-10-23Fix strnlen changeUlrich Drepper
2011-10-23Add optimized wcslen and strnlen for x86-32Liubov Dmitrieva
2011-10-23Fix WSUlrich Drepper
2011-10-23Optimized strnlen and wcscmp for x86-64Liubov Dmitrieva
2011-10-23Improve x86-32 SSSE3 memcpyMichael Zolotukhin
2011-10-23Fix WSUlrich Drepper
2011-10-23Fix signedness in wcscmp comparisonLiubov Dmitrieva
2011-10-23Clean up FMA useUlrich Drepper
The macro's name should reflect that subtraction is being done. And use __builtin_fma, it seems to work after all.
2011-10-23Clean up last dla.h changeUlrich Drepper
2011-10-23Add missing _finite aliasesAndreas Schwab
2011-10-22Fix typo in last changeUlrich Drepper
2011-10-22Update ULPs for x86-64Ulrich Drepper
2011-10-22Improve DLA_FMA for FMA4Ulrich Drepper
2011-10-22Start using fma in the libm implementationUlrich Drepper
2011-10-22Fix compilation due to __nan definesAndreas Schwab
2011-10-22Optimization to some complex math functionsUlrich Drepper
Also, change last reference to __sqrt into __sqrt to easily.
2011-10-21Fix compilation problems in x86-64 init-archUlrich Drepper
2011-10-21Add some __builtin_expect to generic __ieee754_logUlrich Drepper