forked from OSchip/llvm-project
2ff187fbc9
Implement cosf function that is correctly rounded to all rounding modes. Performance benchmark using perf tool from CORE-MATH project (https://gitlab.inria.fr/core-math/core-math/-/tree/master) on Ryzen 1700: Before this patch (not correctly rounded): ``` $ CORE_MATH_PERF_MODE="rdtsc" ./perf.sh cosf CORE-MATH reciprocal throughput : 19.043 System LIBC reciprocal throughput : 26.328 LIBC reciprocal throughput : 30.955 $ CORE_MATH_PERF_MODE="rdtsc" ./perf.sh cosf --latency GNU libc version: 2.31 GNU libc release: stable CORE-MATH latency : 49.995 System LIBC latency : 59.286 LIBC latency : 60.174 ``` After this patch (correctly rounded): ``` $ CORE_MATH_PERF_MODE="rdtsc" ./perf.sh cosf GNU libc version: 2.31 GNU libc release: stable CORE-MATH reciprocal throughput : 19.072 System LIBC reciprocal throughput : 26.286 LIBC reciprocal throughput : 13.631 $ CORE_MATH_PERF_MODE="rdtsc" ./perf.sh cosf --latency GNU libc version: 2.31 GNU libc release: stable CORE-MATH latency : 49.872 System LIBC latency : 59.468 LIBC latency : 56.119 ``` Reviewed By: orex, zimmermann6 Differential Revision: https://reviews.llvm.org/D130644 |
||
---|---|---|
.. | ||
arcanist | ||
bazel |