[PATCH] D68881: [AMDGPU] Improve code size cost model

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUInline.cpp:54
 static cl::opt<size_t>
-MaxBB("amdgpu-inline-max-bb", cl::Hidden, cl::init(300),
+MaxBB("amdgpu-inline-max-bb", cl::Hidden, cl::init(1100),
       cl::desc("Maximum BB number allowed in a function after inlining"
----------------
This is a separate change


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp:698
+                                 ArrayRef<const Value *> Operands) {
+  // Estimate extractelement elimination
+  if (const ExtractElementInst *EE = dyn_cast<ExtractElementInst>(U)) {
----------------
We already report vector insert/extract as free. Why does this need to look at these specifically? What is the purpose of Operands which seems to be ignored?

What uses this version? I thought the set of cost model function with specific value contexts were only used by the vectorizers


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h:207
 
-  unsigned getInliningThresholdMultiplier() { return 7; }
+  unsigned getInliningThresholdMultiplier() { return 9; }
 
----------------
This is a separate change


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D68881/new/

https://reviews.llvm.org/D68881