[llvm] [AMDGPU][AMDGPU-CodeGenPrepare] Narrow 64 bit math to 32 bit if profitable (PR #130577)

[Simon Pilgrim via llvm-commits]

================
@@ -1560,6 +1560,86 @@ void AMDGPUCodeGenPrepareImpl::expandDivRem64(BinaryOperator &I) const {
   llvm_unreachable("not a division");
 }
 
+Type *findSmallestLegalBits(Instruction *I, int OrigBit, int MaxBitsNeeded,
+                            const TargetLowering *TLI, const DataLayout &DL) {
+  if (MaxBitsNeeded >= OrigBit) {
+    return nullptr;
+  }
+  Type *NewType = I->getType()->getWithNewBitWidth(MaxBitsNeeded);
+  while (OrigBit > MaxBitsNeeded) {
+    if (TLI->isOperationLegalOrCustom(
+            TLI->InstructionOpcodeToISD(I->getOpcode()),
+            TLI->getValueType(DL, NewType, true))) {
+      return NewType;
+    }
+    MaxBitsNeeded *= 2;
+    NewType = I->getType()->getWithNewBitWidth(MaxBitsNeeded);
+  }
+  return nullptr;
+}
+
+static bool tryNarrowMathIfNoOverflow(Instruction *I, const TargetLowering *TLI,
+                                      const TargetTransformInfo &TTI,
+                                      const DataLayout &DL) {
+  unsigned Opc = I->getOpcode();
+  Type *OldType = I->getType();
+
+  if (Opc != Instruction::Add && Opc != Instruction::Mul)
+    return false;
+
+  unsigned OrigBit = OldType->getScalarSizeInBits();
+  unsigned MaxBitsNeeded = OrigBit;
+  switch (Opc) {
+  case Instruction::Add:
+    MaxBitsNeeded = KnownBits::add(computeKnownBits(I->getOperand(0), DL),
+                                   computeKnownBits(I->getOperand(1), DL))
+                        .countMaxActiveBits();
+    break;
+  case Instruction::Mul:
+    MaxBitsNeeded = KnownBits::mul(computeKnownBits(I->getOperand(0), DL),
+                                   computeKnownBits(I->getOperand(1), DL))
+                        .countMaxActiveBits();
+    break;
+  default:
+    break;
----------------
RKSimon wrote:

Use llvm_unreachable() here?

https://github.com/llvm/llvm-project/pull/130577