[PATCH] D110372: [AMDGPU] Limit promote alloca max size in functions

Jay Foad via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Fri Sep 24 02:30:03 PDT 2021


foad added a subscriber: sebastian-ne.
foad added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp:182
+    // Do not promote alloca which will force spilling.
+    if (!AMDGPU::isKernelCC(&F))
+      MaxVGPRs = std::min(MaxVGPRs, 32u);
----------------
rampitec wrote:
> arsenm wrote:
> > Probably should be isEntryFunctionCC
> The difference is the exclusion of AMDGPU_Gfx. What is that anyway?
@sebastian-ne


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D110372/new/

https://reviews.llvm.org/D110372



More information about the llvm-commits mailing list