Hi Andrew!
On 2024-11-06T15:27:19+, Andrew Stubbs wrote:
> If requested, return the vectorization factor appropriate for the offload
> device, if any.
> --- a/gcc/omp-general.cc
> +++ b/gcc/omp-general.cc
> @@ -987,10 +987,11 @@ find_combined_omp_for (tree *tp, int *walk_subtrees,
> void *d
On 06/11/2024 17:59, Jakub Jelinek wrote:
On Wed, Nov 06, 2024 at 05:53:53PM +, Andrew Stubbs wrote:
I'm not sure why I didn't see this.
Was it bootstrap tested or just built without bootstrap + tested?
Otherwise it is just a warning.
Apparently I forgot to rerun the bootstrap after maki
On Wed, Nov 06, 2024 at 05:53:53PM +, Andrew Stubbs wrote:
> I'm not sure why I didn't see this.
Was it bootstrap tested or just built without bootstrap + tested?
Otherwise it is just a warning.
> I'm testing the attached patch.
If it makes it to stage3, this is ok for trunk.
Just 64U would
On 06/11/2024 17:38, Andrew Pinski wrote:
+ if (ENABLE_OFFLOADING && offload)
+{
+ for (const char *c = getenv ("OFFLOAD_TARGET_NAMES"); c;)
+ {
+ if (startswith (c, "amdgcn"))
+ return ordered_max (64, omp_max_vf (false));
This causes a bootstrap failure for m
On Wed, Nov 06, 2024 at 09:38:21AM -0800, Andrew Pinski wrote:
> > + for (const char *c = getenv ("OFFLOAD_TARGET_NAMES"); c;)
> > + {
> > + if (startswith (c, "amdgcn"))
> > + return ordered_max (64, omp_max_vf (false));
>
> This causes a bootstrap failure for me (and
On Wed, Nov 6, 2024 at 7:28 AM Andrew Stubbs wrote:
>
> If requested, return the vectorization factor appropriate for the offload
> device, if any.
>
> This change gives a significant speedup in the BabelStream "dot" benchmark on
> amdgcn.
>
> The omp_adjust_chunk_size usecase is set "false", for
If requested, return the vectorization factor appropriate for the offload
device, if any.
This change gives a significant speedup in the BabelStream "dot" benchmark on
amdgcn.
The omp_adjust_chunk_size usecase is set "false", for now, but I intend to
change that in a follow-up patch.
Note that N
On Wed, Nov 06, 2024 at 03:27:19PM +, Andrew Stubbs wrote:
> If requested, return the vectorization factor appropriate for the offload
> device, if any.
>
> This change gives a significant speedup in the BabelStream "dot" benchmark on
> amdgcn.
>
> The omp_adjust_chunk_size usecase is set "fa
