[PATCH] D33983: update add\sub costs of vectors of 64 in X86\SLM arch

Simon Pilgrim via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed Jun 21 05:21:41 PDT 2017


RKSimon accepted this revision.
RKSimon added a comment.
This revision is now accepted and ready to land.

LGTM with one minor about the comment in the lv test



================
Comment at: test/Transforms/LoopVectorize/X86/slm-no-vectorize.ll:5
+; Also addq\subq (quad word) has a high cost on SLM arch.
+; this test has a bad performance (regression of -70%) if vectorized on SLM arch
+; RUN: opt < %s -loop-vectorize -mtriple=x86_64-unknown-linux -S -mcpu=slm -debug 2>&1 | FileCheck -check-prefix=MSG %s
----------------
Very minor but it might be tidier if the comment is put after the RUN target lines.


https://reviews.llvm.org/D33983





More information about the llvm-commits mailing list