This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH] Optimized generic expf and exp2f
- From: Wilco Dijkstra <Wilco dot Dijkstra at arm dot com>
- To: "libc-alpha at sourceware dot org" <libc-alpha at sourceware dot org>
- Cc: nd <nd at arm dot com>
- Date: Tue, 5 Sep 2017 18:08:53 +0000
- Subject: Re: [PATCH] Optimized generic expf and exp2f
- Authentication-results: sourceware.org; auth=none
- Authentication-results: spf=none (sender IP is ) smtp.mailfrom=Wilco dot Dijkstra at arm dot com;
- Nodisclaimer: True
- Spamdiagnosticmetadata: NSPM
- Spamdiagnosticoutput: 1:99
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