From 24e5eb0aab98f14613aab1eded6be20b546cf5f8 Mon Sep 17 00:00:00 2001
From: alex-t <alexander.timofeev@amd.com>
Date: Thu, 18 Mar 2021 22:22:08 +0300
Subject: [PATCH] [AMDGPU] SIOptimizeExecMaskingPreRA should check constant bus
 constraint when folds EXEC copy

Folding EXEC copy into it's single use may lead to constant bus constraint violation as it adds one more SGPR operand.
         This change makes it validate the user instruction with the new SGPR operand and only fold it if it is legal.

Reviewed By: rampitec, arsenm

Differential Revision: https://reviews.llvm.org/D98888
---
 .../AMDGPU/SIOptimizeExecMaskingPreRA.cpp     | 23 +++++++++++--------
 test/CodeGen/AMDGPU/opt_exec_copy_fold.mir    | 23 +++++++++++++++++++
 2 files changed, 37 insertions(+), 9 deletions(-)
 create mode 100644 test/CodeGen/AMDGPU/opt_exec_copy_fold.mir

diff --git a/lib/Target/AMDGPU/SIOptimizeExecMaskingPreRA.cpp b/lib/Target/AMDGPU/SIOptimizeExecMaskingPreRA.cpp
index 162e96655df..5f89f382668 100644
--- a/lib/Target/AMDGPU/SIOptimizeExecMaskingPreRA.cpp
+++ b/lib/Target/AMDGPU/SIOptimizeExecMaskingPreRA.cpp
@@ -416,15 +416,20 @@ bool SIOptimizeExecMaskingPreRA::runOnMachineFunction(MachineFunction &MF) {
         continue;
 
       Register SavedExec = I->getOperand(0).getReg();
-      if (SavedExec.isVirtual() && MRI->hasOneNonDBGUse(SavedExec) &&
-          MRI->use_instr_nodbg_begin(SavedExec)->getParent() ==
-              I->getParent()) {
-        LLVM_DEBUG(dbgs() << "Redundant EXEC COPY: " << *I << '\n');
-        LIS->RemoveMachineInstrFromMaps(*I);
-        I->eraseFromParent();
-        MRI->replaceRegWith(SavedExec, ExecReg);
-        LIS->removeInterval(SavedExec);
-        Changed = true;
+      if (SavedExec.isVirtual() && MRI->hasOneNonDBGUse(SavedExec)) {
+        MachineInstr *SingleExecUser = &*MRI->use_instr_nodbg_begin(SavedExec);
+        int Idx = SingleExecUser->findRegisterUseOperandIdx(SavedExec);
+        assert(Idx != -1);
+        if (SingleExecUser->getParent() == I->getParent() &&
+            !SingleExecUser->getOperand(Idx).isImplicit() &&
+            TII->isOperandLegal(*SingleExecUser, Idx, &I->getOperand(1))) {
+          LLVM_DEBUG(dbgs() << "Redundant EXEC COPY: " << *I << '\n');
+          LIS->RemoveMachineInstrFromMaps(*I);
+          I->eraseFromParent();
+          MRI->replaceRegWith(SavedExec, ExecReg);
+          LIS->removeInterval(SavedExec);
+          Changed = true;
+        }
       }
       break;
     }
diff --git a/test/CodeGen/AMDGPU/opt_exec_copy_fold.mir b/test/CodeGen/AMDGPU/opt_exec_copy_fold.mir
new file mode 100644
index 00000000000..4ebfa2cc964
--- /dev/null
+++ b/test/CodeGen/AMDGPU/opt_exec_copy_fold.mir
@@ -0,0 +1,23 @@
+# RUN: llc -run-pass si-optimize-exec-masking-pre-ra -march=amdgcn -verify-machineinstrs -o - %s | FileCheck --check-prefixes=GCN %s
+---
+# GCN-LABEL: name: opt_exec_copy_fold
+# GCN:             %2:vreg_64 = COPY $exec
+name:            opt_exec_copy_fold
+tracksRegLiveness: true
+liveins:
+  - { reg: '$sgpr0_sgpr1' }
+body:             |
+  bb.0:
+    liveins: $sgpr0_sgpr1
+
+    %0:vgpr_32 = V_CNDMASK_B32_e64 0, 0, 0, 1, $sgpr0_sgpr1, implicit $exec
+    %1:sreg_64 = V_CMP_NE_U32_e64 0, %0, implicit $exec
+    %2:vreg_64 = COPY $exec
+    %3:sreg_64 = V_CMP_EQ_U64_e64 %1, %2, implicit $exec
+    $scc = COPY %3
+    S_CBRANCH_SCC0 %bb.1, implicit $scc
+  
+  bb.1:
+...
+
+