[PATCH] D75920: [LoopCacheAnalysis}: Improve cost heuristic.

[Ettore Tiotto via Phabricator via llvm-commits]

etiotto created this revision.
etiotto added reviewers: Whitney, bmahjour, Meinersbur, kbarton.
Herald added subscribers: llvm-commits, hiraditya, nemanjai.
Herald added a project: LLVM.

Improve the cache cost estimation for indexed references that are not consecutive. For example, given the indexed reference 'A[i][j][k]', and assuming the j-loop is in the innermost position in the loop nest containing the array reference, the cost would be equal to the RefCost cost times the iterations of the j-loop (rather than just the RefCost).


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D75920

Files:
  llvm/include/llvm/Analysis/LoopCacheAnalysis.h
  llvm/lib/Analysis/LoopCacheAnalysis.cpp
  llvm/test/Analysis/LoopCacheAnalysis/PowerPC/matvecmul.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D75920.249359.patch
Type: text/x-patch
Size: 6864 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200310/3c733a94/attachment.bin>