diff options
| author | Mingming Liu <mingmingl@google.com> | 2022-08-03 14:20:30 -0700 |
|---|---|---|
| committer | Mingming Liu <mingmingl@google.com> | 2022-08-04 12:58:25 -0700 |
| commit | bc8f2f36496a3fda32943f261eebb9b053e44016 (patch) | |
| tree | 3f6c8454f247858e698ac1771063f84becba18d2 /llvm/lib/CodeGen/CodeGenPrepare.cpp | |
| parent | 6e193b5cbb6d7591280e4d03a658bb11f9fcd4d9 (diff) | |
| download | llvm-bc8f2f36496a3fda32943f261eebb9b053e44016.zip llvm-bc8f2f36496a3fda32943f261eebb9b053e44016.tar.gz llvm-bc8f2f36496a3fda32943f261eebb9b053e44016.tar.bz2 | |
[AArch64][TTI][NFC] Overload method 'getVectorInstrCost' to provide vector instruction itself, as a context information for cost estimation.
1) Overloaded (instruction-based) method is a wrapper around the current (opcode-based) method.
2) This patch also changes a few callsites (VectorCombine.cpp,
SLPVectorizer.cpp, CodeGenPrepare.cpp) to call the overloaded method.
3) This is a split of D128302.
Differential Revision: https://reviews.llvm.org/D131114
Diffstat (limited to 'llvm/lib/CodeGen/CodeGenPrepare.cpp')
| -rw-r--r-- | llvm/lib/CodeGen/CodeGenPrepare.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp index b100fbe..57423ff 100644 --- a/llvm/lib/CodeGen/CodeGenPrepare.cpp +++ b/llvm/lib/CodeGen/CodeGenPrepare.cpp @@ -7261,7 +7261,7 @@ class VectorPromoteHelper { // scalar to vector. // The vector chain has to account for the combining cost. InstructionCost ScalarCost = - TTI.getVectorInstrCost(Transition->getOpcode(), PromotedType, Index); + TTI.getVectorInstrCost(Transition, PromotedType, Index); InstructionCost VectorCost = StoreExtractCombineCost; enum TargetTransformInfo::TargetCostKind CostKind = TargetTransformInfo::TCK_RecipThroughput; |