[PATCH] D117358: AMDGPU: Correct getMaxNumSGPR treatment of flat_scratch

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added reviewers: AMDGPU, rampitec.
Herald added subscribers: foad, kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl.
arsenm requested review of this revision.
Herald added a subscriber: wdng.
Herald added a project: LLVM.

https://reviews.llvm.org/D117358

Files:
  llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
  llvm/lib/Target/AMDGPU/GCNSubtarget.h


Index: llvm/lib/Target/AMDGPU/GCNSubtarget.h
===================================================================
--- llvm/lib/Target/AMDGPU/GCNSubtarget.h
+++ llvm/lib/Target/AMDGPU/GCNSubtarget.h
@@ -1029,7 +1029,7 @@
   /// \returns Reserved number of SGPRs. This is common
   /// utility function called by MachineFunction and
   /// Function variants of getReservedNumSGPRs.
-  unsigned getBaseReservedNumSGPRs(const bool HasFlatScratchInit) const;
+  unsigned getBaseReservedNumSGPRs(const bool HasFlatScratch) const;
   /// \returns Reserved number of SGPRs for given machine function \p MF.
   unsigned getReservedNumSGPRs(const MachineFunction &MF) const;
 
Index: llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
@@ -772,11 +772,11 @@
 }
 
 unsigned
-GCNSubtarget::getBaseReservedNumSGPRs(const bool HasFlatScratchInit) const {
+GCNSubtarget::getBaseReservedNumSGPRs(const bool HasFlatScratch) const {
   if (getGeneration() >= AMDGPUSubtarget::GFX10)
     return 2; // VCC. FLAT_SCRATCH and XNACK are no longer in SGPRs.
 
-  if (HasFlatScratchInit || HasArchitectedFlatScratch) {
+  if (HasFlatScratch || HasArchitectedFlatScratch) {
     if (getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS)
       return 6; // FLAT_SCRATCH, XNACK, VCC (in that order).
     if (getGeneration() == AMDGPUSubtarget::SEA_ISLANDS)
@@ -794,20 +794,11 @@
 }
 
 unsigned GCNSubtarget::getReservedNumSGPRs(const Function &F) const {
-  // The logic to detect if the function has
-  // flat scratch init is slightly different than how
-  // SIMachineFunctionInfo constructor derives.
-  // We don't use amdgpu-calls, amdgpu-stack-objects
-  // attributes and isAmdHsaOrMesa here as it doesn't really matter.
-  // TODO: Outline this derivation logic and have just
-  // one common function in the backend to avoid duplication.
-  bool isEntry = AMDGPU::isEntryFunctionCC(F.getCallingConv());
-  bool FunctionHasFlatScratchInit = false;
-  if (hasFlatAddressSpace() && isEntry && !flatScratchIsArchitected() &&
-      enableFlatScratch()) {
-    FunctionHasFlatScratchInit = true;
-  }
-  return getBaseReservedNumSGPRs(FunctionHasFlatScratchInit);
+  // In principle we do not need to reserve SGPR pair used for flat_scratch if
+  // we know flat instructions do not access the stack anywhere in the
+  // program. For now assume it's needed if we have flat instructions.
+  const bool KernelUsesFlatScratch = hasFlatAddressSpace();
+  return getBaseReservedNumSGPRs(KernelUsesFlatScratch);
 }
 
 unsigned GCNSubtarget::computeOccupancy(const Function &F, unsigned LDSSize,


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D117358.400135.patch
Type: text/x-patch
Size: 2722 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220114/16ceba5a/attachment-0001.bin>