[PATCH] Optimized generic expf and exp2f

[Wilco Dijkstra]

On 05/09/17 17:54, Szabolcs Nagy wrote:
> Based on new expf and exp2f code from
> https://github.com/ARM-software/optimized-routines/
> 
> with https://sourceware.org/ml/libc-alpha/2017-08/msg01126.html
> expf reciprocal-throughput: 3.3x faster
> expf latency: 1.7x faster
>
> forgot to mention that this is on an aarch64 cpu
> on an x86_64 cpu i measure
>
> expf reciprocal-throughput: 1.7x faster than current asm
> expf latency: 1.5x faster than current asm

Also compared to https://sourceware.org/ml/libc-alpha/2017-09/msg00116.html
when running on AArch64:

expf reciprocal-throughput: 1.8x faster
expf latency: 1.1x faster

Wilco