[llvm] [VectorCombine] Fold reduce(trunc(x)) -> trunc(reduce(x)) iff cost effective (PR #81852)

[Simon Pilgrim via llvm-commits]

================
@@ -1526,6 +1528,60 @@ bool VectorCombine::foldShuffleFromReductions(Instruction &I) {
   return foldSelectShuffle(*Shuffle, true);
 }
 
+/// Determine if its more efficient to fold:
+///   reduce(trunc(x)) -> trunc(reduce(x)).
+bool VectorCombine::foldTruncFromReductions(Instruction &I) {
+  auto *II = dyn_cast<IntrinsicInst>(&I);
+  if (!II)
+    return false;
+
+  Intrinsic::ID IID = II->getIntrinsicID();
+  switch (IID) {
+  case Intrinsic::vector_reduce_add:
+  case Intrinsic::vector_reduce_mul:
+  case Intrinsic::vector_reduce_and:
+  case Intrinsic::vector_reduce_or:
+  case Intrinsic::vector_reduce_xor:
+    break;
+  default:
+    return false;
+  }
+
+  unsigned ReductionOpc = getArithmeticReductionInstruction(IID);
+  Value *ReductionSrc = I.getOperand(0);
+
+  Value *TruncSrc;
+  if (!match(ReductionSrc, m_OneUse(m_Trunc(m_Value(TruncSrc)))))
+    return false;
+
+  auto *Trunc = cast<CastInst>(ReductionSrc);
+  auto *TruncSrcTy = cast<VectorType>(TruncSrc->getType());
+  auto *ReductionSrcTy = cast<VectorType>(ReductionSrc->getType());
+  Type *ResultTy = I.getType();
+
+  TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
+  InstructionCost OldCost =
+      TTI.getCastInstrCost(Instruction::Trunc, ReductionSrcTy, TruncSrcTy,
+                           TTI::CastContextHint::None, CostKind, Trunc) +
+      TTI.getArithmeticReductionCost(ReductionOpc, ReductionSrcTy, std::nullopt,
+                                     CostKind);
+  InstructionCost NewCost =
+      TTI.getArithmeticReductionCost(ReductionOpc, TruncSrcTy, std::nullopt,
+                                     CostKind) +
+      TTI.getCastInstrCost(Instruction::Trunc, ResultTy,
+                           ReductionSrcTy->getScalarType(),
+                           TTI::CastContextHint::None, CostKind);
+
+  if (OldCost < NewCost || !NewCost.isValid())
----------------
RKSimon wrote:

Nice catch - fixed.

https://github.com/llvm/llvm-project/pull/81852