diff options
| author | Adhemerval Zanella <azanella@linux.vnet.ibm.com> | 2013-11-25 06:12:30 -0600 |
|---|---|---|
| committer | Adhemerval Zanella <azanella@linux.vnet.ibm.com> | 2013-11-25 06:34:41 -0600 |
| commit | 41e8926aa4b7f17bc95984737ee82a254ad0911c (patch) | |
| tree | f113bbedd0ec991ae1b9dddf3a36077e22d19815 /sysdeps/powerpc/fpu/fenv_libc.h | |
| parent | 085b5ddfe301eb74bc9f824ff293f054c1c910b7 (diff) | |
| download | glibc-41e8926aa4b7f17bc95984737ee82a254ad0911c.tar.gz glibc-41e8926aa4b7f17bc95984737ee82a254ad0911c.tar.xz glibc-41e8926aa4b7f17bc95984737ee82a254ad0911c.zip | |
PowerPC: Set/restore rounding mode only when needed
This patch helps some math functions performance by adding the libc_fexxx variant of inline functions to handle both FPU round and exception set/restore and by using them on the libc_fexxx_ctx functions. It is based on already coded fexxx family functions for PPC with fpu. Here is the summary of performance improvements due this patch (measured on a POWER7 machine): Before: cos(): ITERS:9.5895e+07: TOTAL:5116.03Mcy, MAX:77.6cy, MIN:49.792cy, 18744 calls/Mcy exp(): ITERS:2.827e+07: TOTAL:5187.15Mcy, MAX:494.018cy, MIN:38.422cy, 5450.01 calls/Mcy pow(): ITERS:6.1705e+07: TOTAL:5144.26Mcy, MAX:171.95cy, MIN:29.935cy, 11994.9 calls/Mcy sin(): ITERS:8.6898e+07: TOTAL:5117.06Mcy, MAX:83.841cy, MIN:46.582cy, 16982 calls/Mcy tan(): ITERS:2.9473e+07: TOTAL:5115.39Mcy, MAX:191.017cy, MIN:172.352cy, 5761.63 calls/Mcy After: cos(): ITERS:2.05265e+08: TOTAL:5111.37Mcy, MAX:78.754cy, MIN:24.196cy, 40158.5 calls/Mcy exp(): ITERS:3.341e+07: TOTAL:5170.84Mcy, MAX:476.317cy, MIN:15.574cy, 6461.23 calls/Mcy pow(): ITERS:7.6153e+07: TOTAL:5129.1Mcy, MAX:147.5cy, MIN:30.916cy, 14847.2 calls/Mcy sin(): ITERS:1.58816e+08: TOTAL:5115.11Mcy, MAX:1490.39cy, MIN:22.341cy, 31048.4 calls/Mcy tan(): ITERS:3.4964e+07: TOTAL:5114.18Mcy, MAX:177.422cy, MIN:146.115cy, 6836.68 calls/Mcy
Diffstat (limited to 'sysdeps/powerpc/fpu/fenv_libc.h')
| -rw-r--r-- | sysdeps/powerpc/fpu/fenv_libc.h | 6 |
1 files changed, 2 insertions, 4 deletions
diff --git a/sysdeps/powerpc/fpu/fenv_libc.h b/sysdeps/powerpc/fpu/fenv_libc.h index cb15c1cecb..ecd6b9192a 100644 --- a/sysdeps/powerpc/fpu/fenv_libc.h +++ b/sysdeps/powerpc/fpu/fenv_libc.h @@ -23,9 +23,9 @@ #include <ldsodefs.h> #include <sysdep.h> -extern const fenv_t *__fe_nomask_env (void); +extern const fenv_t *__fe_nomask_env (void) attribute_hidden; -extern const fenv_t *__fe_mask_env (void); +extern const fenv_t *__fe_mask_env (void) attribute_hidden; /* The sticky bits in the FPSCR indicating exceptions have occurred. */ #define FPSCR_STICKY_BITS ((FE_ALL_EXCEPT | FE_ALL_INVALID) & ~FE_INVALID) @@ -83,7 +83,6 @@ __fegetround (void) "mfcr %0" : "=r"(result) : : "cr7"); return result & 3; } -#define fegetround() __fegetround() static inline int __fesetround (int round) @@ -107,7 +106,6 @@ __fesetround (int round) return 0; } -#define fesetround(mode) __fesetround(mode) /* Definitions of all the FPSCR bit numbers */ enum { |