This is the mail archive of the
mailing list for the GCC project.
Re: PPC64 libmvec implementation of sincos
- From: Richard Biener <richard dot guenther at gmail dot com>
- To: gcc at gcc dot gnu dot org,Szabolcs Nagy <Szabolcs dot Nagy at arm dot com>,GT <tnggil at protonmail dot com>,"gcc at gcc dot gnu dot org" <gcc at gcc dot gnu dot org>
- Cc: nd <nd at arm dot com>,Bill Schmidt <wschmidt at linux dot ibm dot com>
- Date: Mon, 30 Sep 2019 20:09:46 +0200
- Subject: Re: PPC64 libmvec implementation of sincos
- References: <GcaLIHZaxSm2PVhunNuxEwEJB-BC3PeXIBlmYb6eMw54vZQ_KF6uBjlTgWmWtPNIMMeXu7UyYg797u1vV1_GS2Qv3ThxrUeORQD0wcddwwofirstname.lastname@example.org> <email@example.com>
On September 30, 2019 3:52:52 PM GMT+02:00, Szabolcs Nagy <Szabolcs.Nagy@arm.com> wrote:
>On 27/09/2019 20:23, GT wrote:
>> I am attempting to create a vector version of sincos for PPC64.
>> The relevant discussion thread is on the GLIBC libc-alpha mailing
>> Navigate it beginning at
>> The intention is to reuse as much as possible from the existing GCC
>implementation of other libmvec functions.
>> My questions are: Which function(s) in GCC;
>> 1. Gather scalar function input arguments, from multiple loop
>iterations, into a single vector input argument for the vector function
>> 2. Distribute scalar function outputs, to appropriate loop iteration
>result, from the single vector function output result?
>> I am referring especially to vectorization of sin and cos.
>i wonder if gcc can auto-vectorize scalar sincos
>calls, the vectorizer seems to want the calls to
>have no side-effect, but attribute pure or const
>is not appropriate for sincos (which has no return
>value but takes writable pointer args)
We have __builtin_cexpi for that but not sure if any of the mechanisms can provide a mapping to a vectorized variant.
>"#pragma omp simd" on a loop seems to work but i
>could not get unannotated sincos loops to vectorize.
>it seems it would be nice if we could add pure/const
>somehow (maybe to the simd variant only? afaik openmp
>requires no sideeffects for simd variants, but that's
>probably only for explicitly marked loops?)