[PATCH] D105432: [Analysis] Add simple cost model for strict (in-order) reductions
Simon Pilgrim via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Jul 19 06:42:12 PDT 2021
RKSimon added inline comments.
================
Comment at: llvm/test/Analysis/CostModel/X86/reduce-fadd.ll:73
+ %V8 = call fast double @llvm.vector.reduce.fadd.v8f64(double %arg, <8 x double> undef)
+ %V16 = call fast double @llvm.vector.reduce.fadd.v16f64(double %arg, <16 x double> undef)
ret void
----------------
please can you remove this change now that we have this test coverage below
================
Comment at: llvm/test/Analysis/CostModel/X86/reduce-fadd.ll:146
+ %V16 = call fast float @llvm.vector.reduce.fadd.v16f32(float %arg, <16 x float> undef)
+ %V32 = call fast float @llvm.vector.reduce.fadd.v32f32(float %arg, <32 x float> undef)
ret void
----------------
please can you remove this change now that we have this test coverage below
================
Comment at: llvm/test/Analysis/CostModel/X86/reduce-fmul.ll:73
+ %V8 = call fast double @llvm.vector.reduce.fmul.v8f64(double %arg, <8 x double> undef)
+ %V16 = call fast double @llvm.vector.reduce.fmul.v16f64(double %arg, <16 x double> undef)
ret void
----------------
please can you remove this change now that we have this test coverage below
================
Comment at: llvm/test/Analysis/CostModel/X86/reduce-fmul.ll:146
+ %V16 = call fast float @llvm.vector.reduce.fmul.v16f32(float %arg, <16 x float> undef)
+ %V32 = call fast float @llvm.vector.reduce.fmul.v32f32(float %arg, <32 x float> undef)
ret void
----------------
please can you remove this change now that we have this test coverage below
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D105432/new/
https://reviews.llvm.org/D105432
More information about the llvm-commits
mailing list