[AMDGPU] Run SIShrinkInstructions before post-RA scheduling

Run post-RA SIShrinkInstructions just before post-RA scheduling, instead
of afterwards. After the fixes in D112305 and D112317 this seems to make
no difference, but it paves the way for scheduler tweaks that are
sensitive to the e32 vs e64 encoding of VALU instructions.

Differential Revision: https://reviews.llvm.org/D112341

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index 1687304..3e41ae2 100644 (file)
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -1327,6 +1327,8 @@ void GCNPassConfig::addPostRegAlloc() {
 }
 
 void GCNPassConfig::addPreSched2() {
+  if (TM->getOptLevel() > CodeGenOpt::None)
+    addPass(createSIShrinkInstructionsPass());
   addPass(&SIPostRABundlerID);
 }
 
@@ -1334,9 +1336,6 @@ void GCNPassConfig::addPreEmitPass() {
   addPass(createSIMemoryLegalizerPass());
   addPass(createSIInsertWaitcntsPass());
 
-  if (TM->getOptLevel() > CodeGenOpt::None)
-    addPass(createSIShrinkInstructionsPass());
-
   addPass(createSIModeRegisterPass());
 
   if (getOptLevel() > CodeGenOpt::None)

diff --git a/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll b/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
index d137f8a..a0ad604 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
+++ b/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
@@ -367,6 +367,7 @@
 ; GCN-O1-NEXT:        Tail Duplication
 ; GCN-O1-NEXT:        Machine Copy Propagation Pass
 ; GCN-O1-NEXT:        Post-RA pseudo instruction expansion pass
+; GCN-O1-NEXT:        SI Shrink Instructions
 ; GCN-O1-NEXT:        SI post-RA bundler
 ; GCN-O1-NEXT:        MachineDominator Tree Construction
 ; GCN-O1-NEXT:        Machine Natural Loop Construction
@@ -379,7 +380,6 @@
 ; GCN-O1-NEXT:        SI Memory Legalizer
 ; GCN-O1-NEXT:        MachinePostDominator Tree Construction
 ; GCN-O1-NEXT:        SI insert wait instructions
-; GCN-O1-NEXT:        SI Shrink Instructions
 ; GCN-O1-NEXT:        Insert required mode register values
 ; GCN-O1-NEXT:        SI Insert Hard Clauses
 ; GCN-O1-NEXT:        MachineDominator Tree Construction
@@ -651,6 +651,7 @@
 ; GCN-O1-OPTS-NEXT:        Tail Duplication
 ; GCN-O1-OPTS-NEXT:        Machine Copy Propagation Pass
 ; GCN-O1-OPTS-NEXT:        Post-RA pseudo instruction expansion pass
+; GCN-O1-OPTS-NEXT:        SI Shrink Instructions
 ; GCN-O1-OPTS-NEXT:        SI post-RA bundler
 ; GCN-O1-OPTS-NEXT:        MachineDominator Tree Construction
 ; GCN-O1-OPTS-NEXT:        Machine Natural Loop Construction
@@ -663,7 +664,6 @@
 ; GCN-O1-OPTS-NEXT:        SI Memory Legalizer
 ; GCN-O1-OPTS-NEXT:        MachinePostDominator Tree Construction
 ; GCN-O1-OPTS-NEXT:        SI insert wait instructions
-; GCN-O1-OPTS-NEXT:        SI Shrink Instructions
 ; GCN-O1-OPTS-NEXT:        Insert required mode register values
 ; GCN-O1-OPTS-NEXT:        SI Insert Hard Clauses
 ; GCN-O1-OPTS-NEXT:        MachineDominator Tree Construction
@@ -937,6 +937,7 @@
 ; GCN-O2-NEXT:        Tail Duplication
 ; GCN-O2-NEXT:        Machine Copy Propagation Pass
 ; GCN-O2-NEXT:        Post-RA pseudo instruction expansion pass
+; GCN-O2-NEXT:        SI Shrink Instructions
 ; GCN-O2-NEXT:        SI post-RA bundler
 ; GCN-O2-NEXT:        MachineDominator Tree Construction
 ; GCN-O2-NEXT:        Machine Natural Loop Construction
@@ -949,7 +950,6 @@
 ; GCN-O2-NEXT:        SI Memory Legalizer
 ; GCN-O2-NEXT:        MachinePostDominator Tree Construction
 ; GCN-O2-NEXT:        SI insert wait instructions
-; GCN-O2-NEXT:        SI Shrink Instructions
 ; GCN-O2-NEXT:        Insert required mode register values
 ; GCN-O2-NEXT:        SI Insert Hard Clauses
 ; GCN-O2-NEXT:        MachineDominator Tree Construction
@@ -1236,6 +1236,7 @@
 ; GCN-O3-NEXT:        Tail Duplication
 ; GCN-O3-NEXT:        Machine Copy Propagation Pass
 ; GCN-O3-NEXT:        Post-RA pseudo instruction expansion pass
+; GCN-O3-NEXT:        SI Shrink Instructions
 ; GCN-O3-NEXT:        SI post-RA bundler
 ; GCN-O3-NEXT:        MachineDominator Tree Construction
 ; GCN-O3-NEXT:        Machine Natural Loop Construction
@@ -1248,7 +1249,6 @@
 ; GCN-O3-NEXT:        SI Memory Legalizer
 ; GCN-O3-NEXT:        MachinePostDominator Tree Construction
 ; GCN-O3-NEXT:        SI insert wait instructions
-; GCN-O3-NEXT:        SI Shrink Instructions
 ; GCN-O3-NEXT:        Insert required mode register values
 ; GCN-O3-NEXT:        SI Insert Hard Clauses
 ; GCN-O3-NEXT:        MachineDominator Tree Construction