ARM-software / optimized-routines

Optimized implementations of various library functions for ARM architecture processors
Other
601 stars 96 forks source link

sinf.c vs v_sinf.c #49

Closed godmiaozi closed 1 year ago

godmiaozi commented 1 year ago

Hi

Wilco1 commented 1 year ago

v_sinf is the vector version that computes 4 results at a time, so it's suitable for vectorized code. Generally vector versions have worse accuracy and higher latency but significantly more throughput.