[PATCH] D44585: [AMDGPU] Scalarize when scalar code cheaper than vector code.

Farhana Aleen via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Tue Apr 10 15:46:00 PDT 2018

Previous message: [llvm] r328542 - [Pipeliner] Use latency to compute RecMII
Next message: [PATCH] D44668: [demangler] Add a "partial" demangling API for LLDB
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

FarhanaAleen abandoned this revision.
FarhanaAleen added a comment.

Implementing this transformation in the CodeGen seem to be messy since there is no way to classify scalar operations other than hard-code them. I am exploring other viable clean solutions.


https://reviews.llvm.org/D44585

Previous message: [llvm] r328542 - [Pipeliner] Use latency to compute RecMII
Next message: [PATCH] D44668: [demangler] Add a "partial" demangling API for LLDB
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list