Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | PowerPC: strspn optimization for PPC64/POWER7 | Vidya Ranganathan | 2014-03-11 | 6 | -1/+279 |
| | | | | | | | | The optimization is achieved by following techniques: > hashing of needle. > hashing avoids scanning of duplicate entries in needle across the string. > initializing the hash table with Vector instructions (VSX) by quadword access. > unrolling when scanning for character in string across hash table. | ||||
* | PowerPC: strncat optimization for PPC64 | Adhemerval Zanella | 2014-03-10 | 6 | -1/+333 |
| | | | | | | | | The optimization is achieved by following techniques: 1. Doubleword aligned memory access and compares using cmpb instruction. 2. Loop unrolling for byte load/store. 3. CPU pre-fetch to avoid cache miss. | ||||
* | PowerPC: strrchr optimization for POWER7/PPC64 | Rajalakshmi Srinivasaraghavan | 2014-03-03 | 6 | -1/+372 |
| | | | | | | This patch optimizes strrchr() for ppc64. It uses aligned memory access along with cmpb instruction and CPU prefetch to avoid cache misses for speed improvement. | ||||
* | PowerPC: llround/llroundf POWER8 optimization | Adhemerval Zanella | 2014-02-27 | 4 | -5/+86 |
| | | | | | | This patch add a optimized llround/llroundf implementation for POWER8 using the new Move From VSR Doubleword instruction to gains some cycles from FP to GRP register move. | ||||
* | PowerPC: llrint/llrintf POWER8 optimization | Adhemerval Zanella | 2014-02-27 | 4 | -3/+83 |
| | | | | | | This patch add a optimized llrint/llrintf implementation for POWER8 using the new Move From VSR Doubleword instruction to gains some cycles from FP to GRP register move. | ||||
* | PowerPC: Optimized finite/finitef for POWER8 | Adhemerval Zanella | 2014-02-27 | 6 | -6/+102 |
| | | | | | | This patch add a optimized finite/finitef implementation for POWER8 using the new Move From VSR Doubleword instruction to gains some cycles from FP to GRP register move. | ||||
* | PowerPC: Optimized isinf/isinff for POWER8 | Adhemerval Zanella | 2014-02-27 | 6 | -6/+108 |
| | | | | | | This patch add a optimized isinf/isinff implementation for POWER8 using the new Move From VSR Doubleword instruction to gains some cycles from FP to GRP register move. | ||||
* | PowerPC: Optimized isnan/isnanf for POWER8 | Adhemerval Zanella | 2014-02-27 | 6 | -17/+111 |
| | | | | | | This patch add a optimized isnan/isnanf implementation for POWER8 using the new Move From VSR Doubleword instruction to gains some cycles from FP to GRP register move. | ||||
* | Use glibc_likely instead __builtin_expect. | Ondřej Bílka | 2014-02-10 | 2 | -5/+5 |
| | |||||
* | PowerPC: remove wrong truncl implementation for PowerPC64 | Adhemerval Zanella | 2014-01-08 | 1 | -120/+0 |
| | | | | | | | | | | | | | | | The truncl assembly implementation (sysdeps/powerpc/powerpc64/fpu/s_truncl.S) returns wrong results for some inputs where first double is a exact integer and the precision is determined by second long double. Checking on implementation comments and history, I am very confident the assembly implementation was based on a version before commit 5c68d401698a58cf7da150d9cce769fa6679ba5f that fixes BZ#2423 (Errors in long double (ldbl-128ibm) rounding functions in glibc-2.4). By just removing the implementation and make the build select sysdeps/ieee754/ldbl-128ibm/s_truncl.c instead it fixes tgammal issues regarding wrong result sign. | ||||
* | PowerPC: Fix compiler warnings | Adhemerval Zanella | 2014-01-03 | 4 | -4/+4 |
| | | | | | This patch fixes some compile warnings related to extra tokens at end of #undef directive from multilib patchset. | ||||
* | Update copyright notices with scripts/update-copyrights | Allan McRae | 2014-01-01 | 259 | -259/+259 |
| | |||||
* | Fix uses of CALL_MCOUNT in ppc64 assembler sources | Andreas Schwab | 2013-12-19 | 3 | -2/+6 |
| | |||||
* | PowerPC: multiarch hypot/hypotf for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 7 | -1/+158 |
| | |||||
* | PowerPC: multiarch modf/modff for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 7 | -2/+173 |
| | |||||
* | PowerPC: multiarch logb/logbl/logbf for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 10 | -1/+244 |
| | |||||
* | PowerPC: multiarch isinf/isinff for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 6 | -2/+178 |
| | |||||
* | PowerPC: multiarch finite/finitef for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 6 | -2/+186 |
| | |||||
* | PowerPC: multiarch llrint/lrint for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -1/+122 |
| | |||||
* | PowerPC: multiarch copysign/copysignf for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -2/+155 |
| | |||||
* | PowerPC: multiarch trunc/truncf for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 7 | -1/+188 |
| | |||||
* | PowerPC: multiarch round/roundf for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 7 | -1/+188 |
| | |||||
* | PowerPC: multiarch floor/floorf for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 7 | -1/+190 |
| | |||||
* | PowerPC: multiarch ceil/ceilf for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 7 | -1/+188 |
| | |||||
* | PowerPC: multiarch llround/lround for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 6 | -1/+155 |
| | |||||
* | PowerPC: multiarch isnan/isnanf for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 8 | -0/+264 |
| | |||||
* | PowerPC: Adjust multiarch Implies for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -0/+5 |
| | | | | | | This patch adds Implies files on multiarch folder for POWER chips so multirach is enabled when building with --with-cpu and powerN option. | ||||
* | PowerPC: Cleaning up uneeded sqrt routines | Adhemerval Zanella | 2013-12-13 | 2 | -108/+0 |
| | | | | | | | | For PPC64, all the wrappers at sysdeps are superfluous: they are basically the same implementation from math/w_sqrt.c with the '#ifdef _IEEE_LIBM'. And the power4 version just force the 'fsqrt' instruction utilization with an inline assembly, which is already handled by math_private.h __ieee754_sqrt implementation. | ||||
* | PowerPC: multiarch stpcpy for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -1/+130 |
| | |||||
* | PowerPC: multiarch strcpy for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -1/+123 |
| | |||||
* | PowerPC: multiarch wordcopy for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -1/+146 |
| | |||||
* | PowerPC: multiarch wcscpy for PowerPC64. | Adhemerval Zanella | 2013-12-13 | 6 | -1/+106 |
| | |||||
* | PowerPC: multiarch wcsrchr for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 6 | -1/+107 |
| | |||||
* | PowerPC: multiarch wcschr for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 6 | -1/+109 |
| | |||||
* | PowerPC: multiarch strchrnul for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -1/+105 |
| | |||||
* | PowerPC: multiarch strchr for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 6 | -1/+143 |
| | |||||
* | PowerPC: multiarch strncmp for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 6 | -1/+169 |
| | |||||
* | PowerPC: multiarch strncasecmp for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 6 | -1/+152 |
| | |||||
* | PowerPC: multiarch strcasecmp for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 6 | -1/+182 |
| | |||||
* | PowerPC: multiarch strnlen for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -1/+104 |
| | |||||
* | PowerPC: multiarch strlen for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -1/+120 |
| | |||||
* | PowerPC: multiarch rawmemchr for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -1/+102 |
| | |||||
* | PowerPC: multiarch memrchr for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -1/+107 |
| | |||||
* | PowerPC: multiarch memchr for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -1/+107 |
| | |||||
* | PowerPC: multiarch mempcpy for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 5 | -1/+109 |
| | |||||
* | PowerPC: multiarch memset/bzero for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 16 | -1/+385 |
| | |||||
* | PowerPC: multirach memcmp for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 6 | -1/+166 |
| | |||||
* | PowerPC: multiarch memcpy for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 10 | -0/+379 |
| | |||||
* | PowerPC: Adjust multiarch Implies for PowerPC64 | Adhemerval Zanella | 2013-12-13 | 15 | -2/+14 |
| | | | | | | This patch adds Implies files on multiarch folder for POWER chips so multirach is enabled when building with --with-cpu and powerN option. | ||||
* | PowerPC: Optimized mpn functions for PowerPC64/POWER7 | Adhemerval Zanella | 2013-12-06 | 2 | -0/+121 |
| | | | | | This patch add optimized __mpn_add_n/__mpn_sub_n for PowerPC64/POWER7. They are originally from GMP with adjustments for GLIBC. |