[PATCH] D115385: [CostModel][AMDGPU] Fix intrinsics costs estimations.
Daniil Fukalov via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Wed Dec 8 12:58:00 PST 2021
dfukalov created this revision.
dfukalov added a reviewer: rampitec.
Herald added subscribers: foad, kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl, arsenm.
dfukalov requested review of this revision.
Herald added a subscriber: wdng.
Herald added a project: LLVM.
1. Fixed costs inconsistency for llvm.fma.vXf16 instinsiscs.
2. Added tests for llvm.sadd.sat, llvm.ssub.sat, llvm.uadd.sat, llvm.usub.sat intrisics since they have special processing in cost model.
3. Minor intrisics' costs tests updat and refinement.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D115385
Files:
llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
llvm/test/Analysis/CostModel/AMDGPU/arith-ssat.ll
llvm/test/Analysis/CostModel/AMDGPU/arith-usat.ll
llvm/test/Analysis/CostModel/AMDGPU/fma.ll
llvm/test/Analysis/CostModel/AMDGPU/reduce-and.ll
llvm/test/Analysis/CostModel/AMDGPU/reduce-or.ll
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D115385.392897.patch
Type: text/x-patch
Size: 123543 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211208/e4c26895/attachment-0001.bin>
More information about the llvm-commits
mailing list