[PATCH] D100481: [AMDGPU] Disable forceful inline of non-kernel functions which use LDS.
Jon Chesterfield via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Wed Apr 14 08:11:42 PDT 2021
JonChesterfield added a comment.
I agree with the intent. This would be a good change to run through the internal CI before landing.
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp:125
+
+ if (!AMDGPUTargetMachine::EnableLowerModuleLDS) {
+ for (GlobalVariable &GV : M.globals()) {
----------------
What's REGION_ADDRESS? LowerModuleLDS doesn't to do anything with it so this looks like an incidental behaviour change
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp:396
bool AMDGPUTargetMachine::EnableFixedFunctionABI = false;
+bool AMDGPUTargetMachine::EnableLowerModuleLDS = false;
----------------
Why does the cl::opt instance initialize to true, while this initializes to false?
I'm not clear why the storage needs to become external here, but do see that the same thing has been done for the similar variables in this block.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D100481/new/
https://reviews.llvm.org/D100481
More information about the llvm-commits
mailing list