Revert "Allow MachineCSE to coalesce trivial subregister copies the same way that it coalesces normal copies."

This reverts commit r197414.

It broke the ppc64 bootstrap. I will post a testcase in a sec.

llvm-svn: 197424

llvm/lib/CodeGen/MachineCSE.cpp

@@ -131,18 +131,13 @@ bool MachineCSE::PerformTrivialCoalescing(MachineInstr *MI,
     unsigned SrcReg = DefMI->getOperand(1).getReg();
     if (!TargetRegisterInfo::isVirtualRegister(SrcReg))
       continue;
-    if (DefMI->getOperand(0).getSubReg())
+    if (DefMI->getOperand(0).getSubReg() || DefMI->getOperand(1).getSubReg())
       continue;
-    unsigned SrcSubReg = DefMI->getOperand(1).getSubReg();
-    const TargetRegisterClass *RC = MRI->getRegClass(Reg);
-    if (SrcSubReg)
-      RC = TRI->getMatchingSuperRegClass(MRI->getRegClass(SrcReg), RC,
-                                         SrcSubReg);
-    if (!MRI->constrainRegClass(SrcReg, RC))
+    if (!MRI->constrainRegClass(SrcReg, MRI->getRegClass(Reg)))
       continue;
     DEBUG(dbgs() << "Coalescing: " << *DefMI);
     DEBUG(dbgs() << "***     to: " << *MI);
-    MO.substVirtReg(SrcReg, SrcSubReg, *TRI);
+    MO.setReg(SrcReg);
     MRI->clearKillFlags(SrcReg);
     DefMI->eraseFromParent();
     ++NumCoalesces;

llvm/lib/CodeGen/TwoAddressInstructionPass.cpp

@@ -1349,7 +1349,6 @@ TwoAddressInstructionPass::processTiedPairs(MachineInstr *MI,
   unsigned LastCopiedReg = 0;
   SlotIndex LastCopyIdx;
   unsigned RegB = 0;
-  unsigned SubRegB = 0;
   for (unsigned tpi = 0, tpe = TiedPairs.size(); tpi != tpe; ++tpi) {
     unsigned SrcIdx = TiedPairs[tpi].first;
     unsigned DstIdx = TiedPairs[tpi].second;
@@ -1360,7 +1359,6 @@ TwoAddressInstructionPass::processTiedPairs(MachineInstr *MI,
     // Grab RegB from the instruction because it may have changed if the
     // instruction was commuted.
     RegB = MI->getOperand(SrcIdx).getReg();
-    SubRegB = MI->getOperand(SrcIdx).getSubReg();
 
     if (RegA == RegB) {
       // The register is tied to multiple destinations (or else we would
@@ -1385,25 +1383,8 @@ TwoAddressInstructionPass::processTiedPairs(MachineInstr *MI,
 #endif
 
     // Emit a copy.
-    MachineInstrBuilder MIB = BuildMI(*MI->getParent(), MI, MI->getDebugLoc(),
-                                      TII->get(TargetOpcode::COPY), RegA);
-    // If this operand is folding a truncation, the truncation now moves to the
-    // copy so that the register classes remain valid for the operands.
-    MIB.addReg(RegB, 0, SubRegB);
-    const TargetRegisterClass *RC = MRI->getRegClass(RegB);
-    if (SubRegB) {
-      if (TargetRegisterInfo::isVirtualRegister(RegA)) {
-        assert(TRI->getMatchingSuperRegClass(MRI->getRegClass(RegB),
-                                             MRI->getRegClass(RegA), SubRegB) &&
-               "tied subregister must be a truncation");
-        // The superreg class will not be used to constrain the subreg class.
-        RC = 0;
-      }
-      else {
-        assert(TRI->getMatchingSuperReg(RegA, SubRegB, MRI->getRegClass(RegB))
-               && "tied subregister must be a truncation");
-      }
-    }
+    BuildMI(*MI->getParent(), MI, MI->getDebugLoc(),
+            TII->get(TargetOpcode::COPY), RegA).addReg(RegB);
 
     // Update DistanceMap.
     MachineBasicBlock::iterator PrevMI = MI;
@@ -1423,7 +1404,7 @@ TwoAddressInstructionPass::processTiedPairs(MachineInstr *MI,
       }
     }
 
-    DEBUG(dbgs() << "\t\tprepend:\t" << *MIB);
+    DEBUG(dbgs() << "\t\tprepend:\t" << *PrevMI);
 
     MachineOperand &MO = MI->getOperand(SrcIdx);
     assert(MO.isReg() && MO.getReg() == RegB && MO.isUse() &&
@@ -1436,9 +1417,9 @@ TwoAddressInstructionPass::processTiedPairs(MachineInstr *MI,
     // Make sure regA is a legal regclass for the SrcIdx operand.
     if (TargetRegisterInfo::isVirtualRegister(RegA) &&
         TargetRegisterInfo::isVirtualRegister(RegB))
-      MRI->constrainRegClass(RegA, RC);
+      MRI->constrainRegClass(RegA, MRI->getRegClass(RegB));
+
     MO.setReg(RegA);
-    MO.setSubReg(0);
 
     // Propagate SrcRegMap.
     SrcRegMap[RegA] = RegB;
@@ -1450,14 +1431,12 @@ TwoAddressInstructionPass::processTiedPairs(MachineInstr *MI,
       // Replace other (un-tied) uses of regB with LastCopiedReg.
       for (unsigned i = 0, e = MI->getNumOperands(); i != e; ++i) {
         MachineOperand &MO = MI->getOperand(i);
-        if (MO.isReg() && MO.getReg() == RegB && MO.getSubReg() == SubRegB &&
-            MO.isUse()) {
+        if (MO.isReg() && MO.getReg() == RegB && MO.isUse()) {
           if (MO.isKill()) {
             MO.setIsKill(false);
             RemovedKillFlag = true;
           }
           MO.setReg(LastCopiedReg);
-          MO.setSubReg(0);
         }
       }
     }

llvm/test/CodeGen/X86/cmov.ll

@@ -41,8 +41,8 @@ declare void @bar(i64) nounwind
 
 define void @test3(i64 %a, i64 %b, i1 %p) nounwind {
 ; CHECK-LABEL: test3:
-; CHECK:      cmov{{n?}}el %[[R1:e..]], %[[R2:e..]]
-; CHECK-NEXT: movl    %[[R2]], %[[R2]]
+; CHECK:      cmovnel %edi, %esi
+; CHECK-NEXT: movl    %esi, %edi
 
   %c = trunc i64 %a to i32
   %d = trunc i64 %b to i32

llvm/test/CodeGen/X86/cse-add-with-overflow.ll

@@ -1,42 +0,0 @@
-; RUN: llc < %s -mtriple=x86_64-darwin -mcpu=generic | FileCheck %s
-; rdar:15661073 simple example of redundant adds
-;
-; MachineCSE should coalesce trivial subregister copies.
-;
-; The extra movl+addl should be removed during MachineCSE.
-; CHECK-LABEL: redundantadd
-; CHECK: cmpq
-; CHECK: movq
-; CHECK-NOT: movl
-; CHECK: addl
-; CHECK-NOT: addl
-; CHECK: ret
-
-define i64 @redundantadd(i64* %a0, i64* %a1) {
-entry:
-  %tmp8 = load i64* %a0, align 8
-  %tmp12 = load i64* %a1, align 8
-  %tmp13 = icmp ult i64 %tmp12, -281474976710656
-  br i1 %tmp13, label %exit1, label %body
-
-exit1:
-  unreachable
-
-body:
-  %tmp14 = trunc i64 %tmp8 to i32
-  %tmp15 = trunc i64 %tmp12 to i32
-  %tmp16 = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 %tmp14, i32 %tmp15)
-  %tmp17 = extractvalue { i32, i1 } %tmp16, 1
-  br i1 %tmp17, label %exit2, label %return
-
-exit2:
-  unreachable
-
-return:
-  %tmp18 = add i64 %tmp12, %tmp8
-  %tmp19 = and i64 %tmp18, 4294967295
-  %tmp20 = or i64 %tmp19, -281474976710656
-  ret i64 %tmp20
-}
-
-declare { i32, i1 } @llvm.sadd.with.overflow.i32(i32, i32)