[PATCH] D76664: [ConstantFold][NFC] Compile time optimization for large vectors

[Thomas Raoux via Phabricator via llvm-commits]

ThomasRaoux created this revision.
ThomasRaoux added reviewers: majnemer, spatel.
Herald added subscribers: llvm-commits, hiraditya.
Herald added a project: LLVM.
ThomasRaoux added a subscriber: kariddi.

Optimize the common case of splat vector constant. For large vector going through all the elements is expensive. For splat/broadcast cases we can skip going through all the elements.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D76664

Files:
  llvm/include/llvm/IR/Constants.h
  llvm/lib/Analysis/ValueTracking.cpp
  llvm/lib/IR/ConstantFold.cpp
  llvm/lib/IR/Constants.cpp
  llvm/lib/IR/Instructions.cpp
  llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D76664.252195.patch
Type: text/x-patch
Size: 8364 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200324/9c485420/attachment.bin>