glibc/benchtests
Siddhesh Poyarekar 48a18de1e1 Prevent optimizing out of benchmark function call
Resolves: #15424

The compiler would optimize the benchmark function call out of the
loop and call it only once, resulting in blazingly fast times for some
benchmarks (notably atan, sin and cos).  Mark the inputs as volatile
so that the code is forced to read again from the input for each
iteration.
2013-05-17 19:10:33 +05:30
..
atan-inputs Allow multiple input domains to be run in the same benchmark program 2013-04-30 14:17:57 +05:30
bench-modf.c Prevent optimizing out of benchmark function call 2013-05-17 19:10:33 +05:30
bench-skeleton.c Use HP_TIMING for benchmarks if available 2013-05-13 13:44:32 +05:30
bench-timing.h Use HP_TIMING for benchmarks if available 2013-05-13 13:44:32 +05:30
cos-inputs Allow multiple input domains to be run in the same benchmark program 2013-04-30 14:17:57 +05:30
exp-inputs Allow multiple input domains to be run in the same benchmark program 2013-04-30 14:17:57 +05:30
Makefile Use HP_TIMING for benchmarks if available 2013-05-13 13:44:32 +05:30
pow-inputs Allow multiple input domains to be run in the same benchmark program 2013-04-30 14:17:57 +05:30
rint-inputs PowerPC: remove branch prediction from rint implementation 2013-04-01 06:36:51 -05:00
sin-inputs Allow multiple input domains to be run in the same benchmark program 2013-04-30 14:17:57 +05:30
tan-inputs Allow multiple input domains to be run in the same benchmark program 2013-04-30 14:17:57 +05:30