VectorCombine: fix logical error after m_Trunc match (#91201)

The matcher m_Trunc() matches an Operator with a given Opcode, which
could either be an Instruction or ConstExpr.
VectorCombine::foldTruncFromReductions() incorrectly assumes that the
pattern matched is always an Instruction, and attempts a cast. Fix this.

Fixes #88796.

Author: artagnon

llvm/lib/Transforms/Vectorize/VectorCombine.cpp

@@ -1961,17 +1961,17 @@ bool VectorCombine::foldTruncFromReductions(Instruction &I) {
   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 OldCost = TTI.getArithmeticReductionCost(
+      ReductionOpc, ReductionSrcTy, std::nullopt, CostKind);
+  if (auto *Trunc = dyn_cast<CastInst>(ReductionSrc))
+    OldCost +=
+        TTI.getCastInstrCost(Instruction::Trunc, ReductionSrcTy, TruncSrcTy,
+                             TTI::CastContextHint::None, CostKind, Trunc);
   InstructionCost NewCost =
       TTI.getArithmeticReductionCost(ReductionOpc, TruncSrcTy, std::nullopt,
                                      CostKind) +

llvm/test/Transforms/VectorCombine/pr88796.ll

@@ -1,7 +1,12 @@
-; REQUIRES: asserts
-; RUN: not --crash opt -passes=vector-combine -disable-output %s
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt -passes=vector-combine -S %s | FileCheck %s
 
 define i32 @test() {
+; CHECK-LABEL: define i32 @test() {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = tail call i16 @llvm.vector.reduce.and.nxv8i16(<vscale x 8 x i16> trunc (<vscale x 8 x i32> shufflevector (<vscale x 8 x i32> insertelement (<vscale x 8 x i32> poison, i32 268435456, i64 0), <vscale x 8 x i32> poison, <vscale x 8 x i32> zeroinitializer) to <vscale x 8 x i16>))
+; CHECK-NEXT:    ret i32 0
+;
 entry:
   %0 = tail call i16 @llvm.vector.reduce.and.nxv8i16(<vscale x 8 x i16> trunc (<vscale x 8 x i32> shufflevector (<vscale x 8 x i32> insertelement (<vscale x 8 x i32> poison, i32 268435456, i64 0), <vscale x 8 x i32> poison, <vscale x 8 x i32> zeroinitializer) to <vscale x 8 x i16>))
   ret i32 0