[PATCH] D122126: [LoopVectorize] Don't interleave when the number of runtime checks exceeds the threshold

TiehuZhang updated this revision to Diff 427300. TiehuZhang added a comment. Herald added a project: clang. Herald added a subscriber: cfe-commits. Fix the failed case (optimization-remark-options.c), because the remark info should be updated Repository: rG LLVM Github Monorepo CHANGES SINCE

[PATCH] D122126: [LoopVectorize] Don't interleave when the number of runtime checks exceeds the threshold

TiehuZhang updated this revision to Diff 428930. TiehuZhang added a comment. (Updated) Difference with accepted version: Move memory runtime checks to processLoop to control both VF and IC Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION https://reviews.llvm.org/D122126/new/

[PATCH] D122126: [LoopVectorize] Don't interleave when the number of runtime checks exceeds the threshold

TiehuZhang added a comment. The code has been updated since accept. Please review it again. Thank you very much! @fhahn @dmgreen Comment at: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp:10460 IC = CM.selectInterleaveCount(VF.Width, *VF.Cost.getValue()); +if (!UserI

[PATCH] D122126: [LoopVectorize] Don't interleave when the number of runtime checks exceeds the threshold

TiehuZhang updated this revision to Diff 429110. Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION https://reviews.llvm.org/D122126/new/ https://reviews.llvm.org/D122126 Files: llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h llvm/lib/Transforms/Vectorize/LoopVectori

[PATCH] D122126: [LoopVectorize] Don't interleave when the number of runtime checks exceeds the threshold

TiehuZhang added a comment. In D122126#3515070 , @fhahn wrote: > Still LGTM, thanks! The remaining suggestion can be addressed directly before > committing the patch. Thanks, @fhahn! I'll add the precommit test when committing the patch Repository: