[PATCH] D114893: [CostModel][AMDGPU] Fix instructions costs estimation for vector types.
Daniil Fukalov via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Wed Dec 1 11:06:04 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 vector instructions costs estimations incosistency - removed different logic for "not simple types" since it biases costs for these types.
2. Fixed legalization penalty for vectors too big for the target: changed from overwrite default legalization cost value estimation to added penalty.
3. Fixed few typos in tests.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D114893
Files:
llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
llvm/test/Analysis/CostModel/AMDGPU/add-sub.ll
llvm/test/Analysis/CostModel/AMDGPU/fabs.ll
llvm/test/Analysis/CostModel/AMDGPU/fadd.ll
llvm/test/Analysis/CostModel/AMDGPU/fdiv.ll
llvm/test/Analysis/CostModel/AMDGPU/fmul.ll
llvm/test/Analysis/CostModel/AMDGPU/fneg.ll
llvm/test/Analysis/CostModel/AMDGPU/fsub.ll
llvm/test/Analysis/CostModel/AMDGPU/mul.ll
llvm/test/Analysis/CostModel/AMDGPU/shifts.ll
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D114893.391085.patch
Type: text/x-patch
Size: 126745 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211201/f857ff73/attachment-0001.bin>
More information about the llvm-commits
mailing list