[PATCH] D90613: [x86] add AVX2 cost model entries for maxnum of 256-bit vectors
Pengfei Wang via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Nov 2 17:09:00 PST 2020
pengfei added inline comments.
================
Comment at: llvm/lib/Target/X86/X86TargetTransformInfo.cpp:2531
{ ISD::USUBSAT, MVT::v8i32, 6 }, // 2 x 128-bit Op + extract/insert
- { ISD::FMAXNUM, MVT::f32, 3 },
+ { ISD::FMAXNUM, MVT::f32, 3 }, // MAXPS + CMPUNORDPS + BLENDVPS
{ ISD::FMAXNUM, MVT::v4f32, 3 },
----------------
Nit: the comments should be MAXSS + CMPUNORDSS.
The same below.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D90613/new/
https://reviews.llvm.org/D90613
More information about the llvm-commits
mailing list