2 files changed, 37 insertions, 2 deletions

diff --git a/llvm/lib/CodeGen/DeadMachineInstructionElim.cpp b/llvm/lib/CodeGen/DeadMachineInstructionElim.cpp
index 049ce706330..f1de7b3cc6a 100644
--- a/llvm/lib/CodeGen/DeadMachineInstructionElim.cpp
+++ b/llvm/lib/CodeGen/DeadMachineInstructionElim.cpp
@@ -10,7 +10,9 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/CodeGen/LiveIntervals.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/CodeGen/Passes.h"
@@ -32,6 +34,7 @@ namespace {
     const TargetRegisterInfo *TRI;
     const MachineRegisterInfo *MRI;
     const TargetInstrInfo *TII;
+    LiveIntervals *LIS;
     BitVector LivePhysRegs;
 
   public:
@@ -41,7 +44,7 @@ namespace {
     }
 
     void getAnalysisUsage(AnalysisUsage &AU) const override {
-      AU.setPreservesCFG();
+      AU.setPreservesAll();
       MachineFunctionPass::getAnalysisUsage(AU);
     }
 
@@ -78,9 +81,15 @@ bool DeadMachineInstructionElim::isDead(const MachineInstr *MI) const {
       unsigned Reg = MO.getReg();
       if (TargetRegisterInfo::isPhysicalRegister(Reg)) {
         // Don't delete live physreg defs, or any reserved register defs.
-        if (LivePhysRegs.test(Reg) || MRI->isReserved(Reg))
+        // Do not remove physreg defs if we have LIS as we may be unable
+        // to accurately recompute its liveness.
+        if (LivePhysRegs.test(Reg) || MRI->isReserved(Reg) || LIS)
           return false;
       } else {
+        // An instruction can also use its def in case if it is a tied operand.
+        // TODO: Technically we can also remove it if def dominates the use.
+        //       This can happen when two instructions define different subregs
+        //       of the same register.
         for (const MachineInstr &Use : MRI->use_nodbg_instructions(Reg)) {
           if (&Use != MI)
             // This def has a non-debug use. Don't delete the instruction!
@@ -102,6 +111,8 @@ bool DeadMachineInstructionElim::runOnMachineFunction(MachineFunction &MF) {
   MRI = &MF.getRegInfo();
   TRI = MF.getSubtarget().getRegisterInfo();
   TII = MF.getSubtarget().getInstrInfo();
+  LIS = getAnalysisIfAvailable<LiveIntervals>();
+  DenseSet<unsigned> RecalcRegs;
 
   // Loop over all instructions in all blocks, from bottom to top, so that it's
   // more likely that chains of dependent but ultimately dead instructions will
@@ -127,6 +138,14 @@ bool DeadMachineInstructionElim::runOnMachineFunction(MachineFunction &MF) {
       // If the instruction is dead, delete it!
       if (isDead(MI)) {
         LLVM_DEBUG(dbgs() << "DeadMachineInstructionElim: DELETING: " << *MI);
+        if (LIS) {
+          for (const MachineOperand &MO : MI->operands()) {
+            if (MO.isReg() && TRI->isVirtualRegister(MO.getReg()))
+              RecalcRegs.insert(MO.getReg());
+          }
+          LIS->RemoveMachineInstrFromMaps(*MI);
+        }
+
         // It is possible that some DBG_VALUE instructions refer to this
         // instruction.  They get marked as undef and will be deleted
         // in the live debug variable analysis.
@@ -170,5 +189,12 @@ bool DeadMachineInstructionElim::runOnMachineFunction(MachineFunction &MF) {
   }
 
   LivePhysRegs.clear();
+
+  for (auto Reg : RecalcRegs) {
+    LIS->removeInterval(Reg);
+    if (!MRI->reg_empty(Reg))
+      LIS->createAndComputeVirtRegInterval(Reg);
+  }
+
   return AnyChanges;
 }
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index 84fa5918447..3bfeea197bd 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -163,6 +163,12 @@ static cl::opt<bool> EnableSIModeRegisterPass(
   cl::init(true),
   cl::Hidden);
 
+// Option is used in lit tests to prevent deadcoding of patterns inspected.
+static cl::opt<bool>
+EnableDCEInRA("amdgpu-dce-in-ra",
+    cl::init(true), cl::Hidden,
+    cl::desc("Enable machine DCE inside regalloc"));
+
 extern "C" void LLVMInitializeAMDGPUTarget() {
   // Register the target
   RegisterTargetMachine<R600TargetMachine> X(getTheAMDGPUTarget());
@@ -901,6 +907,9 @@ void GCNPassConfig::addOptimizedRegAlloc() {
   // This must be run just after RegisterCoalescing.
   insertPass(&RegisterCoalescerID, &SIPreAllocateWWMRegsID, false);
 
+  if (EnableDCEInRA)
+    insertPass(&RenameIndependentSubregsID, &DeadMachineInstructionElimID);
+
   TargetPassConfig::addOptimizedRegAlloc();
 }