This is the mail archive of the
mailing list for the GCC project.
Re: [RFC] GCC port for ARM's Scalable Vector Extension
- From: Richard Sandiford <richard dot sandiford at arm dot com>
- To: gcc at gcc dot gnu dot org
- Cc: alan dot hayward at arm dot com, david dot sherwood at arm dot com
- Date: Wed, 30 Nov 2016 19:29:50 +0000
- Subject: Re: [RFC] GCC port for ARM's Scalable Vector Extension
- Authentication-results: sourceware.org; auth=none
- References: <email@example.com>
Richard Sandiford <firstname.lastname@example.org> writes:
> We have various other changes that aren't yet in the branch. The two
> main ones are:
> (a) Support for gather loads and scatter stores. This includes support
> for using gathers and scatters for strided loads and stores, or for
> grouped loads and stores whose group size is too large for a more
> efficient approach.
> (b) Support for vectorising uncounted loops, i.e. those in which the number
> of iterations isn't known before the loop starts. This has two modes:
> (i) Use alignment to avoid partial faults in speculative loads,
> if alignment is reachable for all loads and if there are no other
> statements with side effects.
> (ii) Use the SVE first-faulting instruction for general speculative
> loads. This is the more general case and works regardless of
> We hope to upload these changes to the branch soon.
FWIW, I've now uploaded those other changes to the branch. The commit
[Branch only patch -- not intended for trunk in its current state]
to mark the patches that we know need tidying up a bit for trunk.
I didn't send them to gcc-patches@ because I thought they would be
The new patches span the range r243045:r243080 inclusive.