[llvm] 23487be - [AMDGPU] Merge the conditions used for deciding CS spills for amdgpu_cs_chain[_preserve] (#109911)

[via llvm-commits]

Author: Christudasan Devadasan
Date: 2024-09-26T10:50:00+05:30
New Revision: 23487be4903630a4c06160562fb939f6389aa99d

URL: https://github.com/llvm/llvm-project/commit/23487be4903630a4c06160562fb939f6389aa99d
DIFF: https://github.com/llvm/llvm-project/commit/23487be4903630a4c06160562fb939f6389aa99d.diff

LOG: [AMDGPU] Merge the conditions used for deciding CS spills for amdgpu_cs_chain[_preserve] (#109911)

Multiple conditions exist to decide whether callee save spills/restores
are required for amdgpu_cs_chain or amdgpu_cs_chain_preserve calling
conventions. This patch consolidates them all and moves to a single
place.

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
    llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp b/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
index 50a6f028f66de6..07505110476b5d 100644
--- a/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
@@ -1342,20 +1342,10 @@ void SIFrameLowering::processFunctionBeforeFrameFinalized(
   SIMachineFunctionInfo *FuncInfo = MF.getInfo<SIMachineFunctionInfo>();
 
   // Allocate spill slots for WWM reserved VGPRs.
-  // For chain functions, we only need to do this if we have calls to
-  // llvm.amdgcn.cs.chain (otherwise there's no one to save them for, since
-  // chain functions do not return) and the function did not contain a call to
-  // llvm.amdgcn.init.whole.wave (since in that case there are no inactive lanes
-  // when entering the function).
-  bool IsChainWithoutRestores =
-      FuncInfo->isChainFunction() &&
-      (!MF.getFrameInfo().hasTailCall() || FuncInfo->hasInitWholeWave());
-  if (!FuncInfo->isEntryFunction() && !IsChainWithoutRestores) {
-    for (Register Reg : FuncInfo->getWWMReservedRegs()) {
-      const TargetRegisterClass *RC = TRI->getPhysRegBaseClass(Reg);
-      FuncInfo->allocateWWMSpill(MF, Reg, TRI->getSpillSize(*RC),
-                                 TRI->getSpillAlign(*RC));
-    }
+  for (Register Reg : FuncInfo->getWWMReservedRegs()) {
+    const TargetRegisterClass *RC = TRI->getPhysRegBaseClass(Reg);
+    FuncInfo->allocateWWMSpill(MF, Reg, TRI->getSpillSize(*RC),
+                               TRI->getSpillAlign(*RC));
   }
 
   const bool SpillVGPRToAGPR = ST.hasMAIInsts() && FuncInfo->hasSpilledVGPRs()

diff  --git a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
index 2237b2e78c4174..f59d29bd81403a 100644
--- a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
@@ -287,8 +287,14 @@ void SIMachineFunctionInfo::allocateWWMSpill(MachineFunction &MF, Register VGPR,
   // amdgpu_cs_chain_preserve calling convention and this is a scratch register.
   // We never need to allocate a spill for these because we don't even need to
   // restore the inactive lanes for them (they're scratchier than the usual
-  // scratch registers).
-  if (isChainFunction() && SIRegisterInfo::isChainScratchRegister(VGPR))
+  // scratch registers). We only need to do this if we have calls to
+  // llvm.amdgcn.cs.chain (otherwise there's no one to save them for, since
+  // chain functions do not return) and the function did not contain a call to
+  // llvm.amdgcn.init.whole.wave (since in that case there are no inactive lanes
+  // when entering the function).
+  if (isChainFunction() &&
+      (SIRegisterInfo::isChainScratchRegister(VGPR) ||
+       !MF.getFrameInfo().hasTailCall() || hasInitWholeWave()))
     return;
 
   WWMSpills.insert(std::make_pair(