[PATCH] D92985: [SystemZTTIImpl::getMinPrefetchStride] Allow some non-prefetched mem accesses.

Jonas Paulsson via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Thu Dec 10 11:30:52 PST 2020


jonpa added a comment.

In D92985#2445068 <https://reviews.llvm.org/D92985#2445068>, @uweigand wrote:

>> It doesn't seem right to bail just for one non-prefetched access, so it seems reasonable to allow a relatively very small amount of non-prefetched instructions, to make the heuristic more stable. This patch suggests allowing 1 non-prefetched memory access per 32 prefetched ones. This handles LBM, and also gives two prefetches to imagick which however do not seem to play a role.
>
> This sounds reasonable to me, but this is the kind of question that in the end only measurement can decide ...   What is the overall effect of this patch on benchmarks?  Anything else beyond lbm and imagick?

No other benchmarks were affected

In D92985#2445068 <https://reviews.llvm.org/D92985#2445068>, @uweigand wrote:

>> It doesn't seem right to bail just for one non-prefetched access, so it seems reasonable to allow a relatively very small amount of non-prefetched instructions, to make the heuristic more stable. This patch suggests allowing 1 non-prefetched memory access per 32 prefetched ones. This handles LBM, and also gives two prefetches to imagick which however do not seem to play a role.
>
> This sounds reasonable to me, but this is the kind of question that in the end only measurement can decide ...   What is the overall effect of this patch on benchmarks?  Anything else beyond lbm and imagick?

Only two files changed in total, one each for lbm/imagick.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D92985/new/

https://reviews.llvm.org/D92985



More information about the llvm-commits mailing list