AMDGPU: Change API for checking for exec modification

[arsenm]

Summary

Invert the name and return value to better reflect the imprecise
nature.

Force passing in the DefMI, since it's known in the 2 users and could
ossibly fail for an arbitrary vreg.

Allow specifying a specific user instruction. Scan through use
instructions, instead of use operands. Add scan thresholds instead of
searching infinitely.

Stop using a set to track seen uses. I didn't understand this usage,
or why it would not check the last use. I don't think the order of the
use list has any particular order.

[nhaehnle]

LGTM

[arsenm]

r363675

lib/Target/AMDGPU/GCNDPPCombine.cpp

 
 bool GCNDPPCombine::combineDPPMov(MachineInstr &MovMI) const {
   assert(MovMI.getOpcode() == AMDGPU::V_MOV_B32_dpp);
   LLVM_DEBUG(dbgs() << "\nDPP combine: " << MovMI);
 
   auto *DstOpnd = TII->getNamedOperand(MovMI, AMDGPU::OpName::vdst);
   assert(DstOpnd && DstOpnd->isReg());
   auto DPPMovReg = DstOpnd->getReg();
-  if (!isEXECMaskConstantBetweenDefAndUses(DPPMovReg, *MRI)) {
+  if (execMayBeModifiedBeforeUse(*MRI, DPPMovReg, MovMI)) {
     LLVM_DEBUG(dbgs() << "  failed: EXEC mask should remain the same"
                          " for all uses\n");
     return false;
   }
 
   auto *RowMaskOpnd = TII->getNamedOperand(MovMI, AMDGPU::OpName::row_mask);
   assert(RowMaskOpnd && RowMaskOpnd->isImm());
   auto *BankMaskOpnd = TII->getNamedOperand(MovMI, AMDGPU::OpName::bank_mask);

lib/Target/AMDGPU/SIFoldOperands.cpp

if (UseOpc == AMDGPU::V_READFIRSTLANE_B32 ||
         (UseOpc == AMDGPU::V_READLANE_B32 &&
          (int)UseOpIdx ==
          AMDGPU::getNamedOperandIdx(UseOpc, AMDGPU::OpName::src0))) {
       // %vgpr = V_MOV_B32 imm
       // %sgpr = V_READFIRSTLANE_B32 %vgpr
       // =>
       // %sgpr = S_MOV_B32 imm
       if (FoldingImm) {
-        if (!isEXECMaskConstantBetweenDefAndUses(
-              UseMI->getOperand(UseOpIdx).getReg(), *MRI))
+        if (execMayBeModifiedBeforeUse(*MRI,
+                                       UseMI->getOperand(UseOpIdx).getReg(),
+                                       *OpToFold.getParent(),
+                                       UseMI))
           return;
 
         UseMI->setDesc(TII->get(AMDGPU::S_MOV_B32));
         UseMI->getOperand(1).ChangeToImmediate(OpToFold.getImm());
         UseMI->RemoveOperand(2); // Remove exec read (or src1 for readlane)
         return;
       }
 
       if (OpToFold.isReg() && TRI->isSGPRReg(*MRI, OpToFold.getReg())) {
-        if (!isEXECMaskConstantBetweenDefAndUses(
-              UseMI->getOperand(UseOpIdx).getReg(), *MRI))
+        if (execMayBeModifiedBeforeUse(*MRI,
+                                       UseMI->getOperand(UseOpIdx).getReg(),
+                                       *OpToFold.getParent(),
+                                       UseMI))
           return;
 
         // %vgpr = COPY %sgpr0
         // %sgpr1 = V_READFIRSTLANE_B32 %vgpr
         // =>
         // %sgpr1 = COPY %sgpr0
         UseMI->setDesc(TII->get(AMDGPU::COPY));
         UseMI->RemoveOperand(2); // Remove exec read (or src1 for readlane)

lib/Target/AMDGPU/SIInstrInfo.h

TargetInstrInfo::RegSubRegPair getRegSequenceSubReg(MachineInstr &MI,
                                                     unsigned SubReg);
 
 /// \brief Return the defining instruction for a given reg:subreg pair
 /// skipping copy like instructions and subreg-manipulation pseudos.
 /// Following another subreg of a reg:subreg isn't supported.
 MachineInstr *getVRegSubRegDef(const TargetInstrInfo::RegSubRegPair &P,
                                MachineRegisterInfo &MRI);
 
-/// \brief Return true if EXEC mask isnt' changed between the def and
-/// all uses of VReg. Currently if def and uses are in different BBs -
-/// simply return false. Should be run on SSA.
-bool isEXECMaskConstantBetweenDefAndUses(unsigned VReg,
-                                         const MachineRegisterInfo &MRI);
+/// \brief Return false if EXEC is not changed between the def of \p VReg at \p
+/// DefMI and uses. If \p UseMI is not specified, this checks all uses of \p
+/// VReg. Should be run on SSA. Currently does not attempt to track between
+/// blocks.
+bool execMayBeModifiedBeforeUse(const MachineRegisterInfo &MRI,
+                                unsigned VReg,
+                                const MachineInstr &DefMI,
+                                const MachineInstr *UseMI = nullptr);
 
 namespace AMDGPU {
 
   LLVM_READONLY
   int getVOPe64(uint16_t Opcode);
 
   LLVM_READONLY
   int getVOPe32(uint16_t Opcode);

lib/Target/AMDGPU/SIInstrInfo.cpp

default:
       }
     }
     if (!DefInst)
       return MI;
   }
   return nullptr;
 }
 
-bool llvm::isEXECMaskConstantBetweenDefAndUses(unsigned VReg,
-                                               const MachineRegisterInfo &MRI) {
+bool llvm::execMayBeModifiedBeforeUse(const MachineRegisterInfo &MRI,
+                                      unsigned VReg,
+                                      const MachineInstr &DefMI,
+                                      const MachineInstr *UseMI) {
   assert(MRI.isSSA() && "Must be run on SSA");
+  assert(DefMI.definesRegister(VReg) && "wrong def instruction");
+
   auto *TRI = MRI.getTargetRegisterInfo();
+  auto *DefBB = DefMI.getParent();
 
-  auto *DefI = MRI.getVRegDef(VReg);
-  auto *BB = DefI->getParent();
+  if (UseMI) {
+    // Don't bother searching between blocks, although it is possible this block
+    // doesn't modify exec.
+    if (UseMI->getParent() != DefBB)
+      return true;
+  } else {
+    unsigned NumUse = 0;
+    const unsigned MaxUseScan = 10;
 
-  DenseSet<MachineInstr*> Uses;
-  for (auto &Use : MRI.use_nodbg_operands(VReg)) {
-    auto *I = Use.getParent();
-    if (I->getParent() != BB)
-      return false;
-    Uses.insert(I);
+    for (auto &UseInst : MRI.use_nodbg_instructions(VReg)) {
+      if (UseInst.getParent() != DefBB)
+        return true;
+
+      if (NumUse++ > MaxUseScan)
+        return true;
+    }
   }
 
-  auto E = BB->end();
-  for (auto I = std::next(DefI->getIterator()); I != E; ++I) {
-    Uses.erase(&*I);
-    // don't check the last use
-    if (Uses.empty() || I->modifiesRegister(AMDGPU::EXEC, TRI))
-      break;
+  const unsigned MaxInstScan = 20;
+  unsigned NumScan = 0;
+
+  auto E = DefBB->end();
+  for (auto I = std::next(DefMI.getIterator()); I != E; ++I) {
+    if (I->isDebugInstr())
+      continue;
+
+    if (NumScan++ > MaxInstScan)
+      return true;
+
+    if (I->modifiesRegister(AMDGPU::EXEC, TRI))
+      return true;
   }
-  return Uses.empty();
+
+  return false;
 }