[all-commits] [llvm/llvm-project] c428a3: [LoopCacheAnalysis] Enable delinearization of fixe...

[CongzheUalberta via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c428a3d2a09e2d144911290920b1fa59953d7898
      https://github.com/llvm/llvm-project/commit/c428a3d2a09e2d144911290920b1fa59953d7898
  Author: Congzhe Cao <congzhe.cao at huawei.com>
  Date:   2022-04-29 (Fri, 29 Apr 2022)

  Changed paths:
    M llvm/include/llvm/Analysis/LoopCacheAnalysis.h
    M llvm/lib/Analysis/LoopCacheAnalysis.cpp
    A llvm/test/Analysis/LoopCacheAnalysis/PowerPC/LoopnestFixedSize.ll

  Log Message:
  -----------
  [LoopCacheAnalysis] Enable delinearization of fixed sized arrays

Currently loop cache cost (LCC) cannot analyze fix-sized arrays
since it cannot delinearize them. This patch adds the capability
to delinearize fix-sized arrays to LCC. Most of the code is ported
from DependenceAnalysis.cpp and some refactoring will be done in a
next patch.

Reviewed By: #loopoptwg, Meinersbur

Differential Revision: https://reviews.llvm.org/D122857