llvm/test/Transforms/LoopVectorize/SystemZ at ccd4f446eb6f2890dce79a1a104f6ae4e4bc0a7d - llvm

RPCS3/llvm

mirror of https://github.com/RPCS3/llvm.git synced 2026-07-20 19:04:10 -04:00

Files

T

Jonas Paulsson ccd4f446eb [LoopVectorizer] Fix for cost values of memory accesses.

This commit is a combination of two patches:

* "Fix in getScalarizationOverhead()"

   If target returns false in TTI.prefersVectorizedAddressing(), it means the
   address registers will not need to be extracted. Therefore, there should
   be no operands scalarization overhead for a load instruction.

* "Don't pass the instruction pointer from getMemInstScalarizationCost."

   Since VF is always > 1, this is a cost query for an instruction in the
   vectorized loop and it should not be evaluated within the scalar
   context of the instruction.

Review: Ulrich Weigand, Hal Finkel
https://reviews.llvm.org/D52351
https://reviews.llvm.org/D52417

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@345603 91177308-0d34-0410-b5e6-96231b3b80d8

2018-10-30 14:34:15 +00:00

addressing.ll

[LoopVectorizer] Let target prefer scalar addressing computations.

2017-05-24 13:42:56 +00:00

branch-for-predicated-block.ll

[LoopVectorizer] Improve handling of branches during cost estimation.

2017-04-12 13:13:15 +00:00

lit.local.cfg

[SystemZ] Fix more target specific tests

2017-04-12 18:03:09 +00:00

load-scalarization-cost-0.ll

[LoopVectorizer] Fix for cost values of memory accesses.