[PATCH] D42981: [COST] Fix cost model of load instructions on X86

[Alexey Bataev via Phabricator via llvm-commits]

ABataev updated this revision to Diff 133273.
ABataev added a comment.

Fixed cost model for floating point math instructions.


Repository:
  rL LLVM

https://reviews.llvm.org/D42981

Files:
  lib/Target/X86/X86TargetTransformInfo.cpp
  lib/Transforms/Vectorize/SLPVectorizer.cpp
  test/Analysis/CostModel/X86/interleaved-load-i8.ll
  test/Analysis/CostModel/X86/vectorized-loop.ll
  test/Transforms/SLPVectorizer/X86/PR36280.ll
  test/Transforms/SLPVectorizer/X86/arith-add.ll
  test/Transforms/SLPVectorizer/X86/arith-mul.ll
  test/Transforms/SLPVectorizer/X86/arith-sub.ll
  test/Transforms/SLPVectorizer/X86/extract_in_tree_user.ll
  test/Transforms/SLPVectorizer/X86/horizontal.ll
  test/Transforms/SLPVectorizer/X86/reduction_unrolled.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D42981.133273.patch
Type: text/x-patch
Size: 37235 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180207/0da7de7a/attachment.bin>