[InstCombine] Fix shift calculation in InstCombineCasts (#84027)

Fixes #84025.

(cherry picked from commit e96c0c1)

Author: dianqk

llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp

@@ -2156,14 +2156,14 @@ static bool collectInsertionElements(Value *V, unsigned Shift,
     Type *ElementIntTy = IntegerType::get(C->getContext(), ElementSize);
 
     for (unsigned i = 0; i != NumElts; ++i) {
-      unsigned ShiftI = Shift + i * ElementSize;
+      unsigned ShiftI = i * ElementSize;
       Constant *Piece = ConstantFoldBinaryInstruction(
           Instruction::LShr, C, ConstantInt::get(C->getType(), ShiftI));
       if (!Piece)
         return false;
 
       Piece = ConstantExpr::getTrunc(Piece, ElementIntTy);
-      if (!collectInsertionElements(Piece, ShiftI, Elements, VecEltTy,
+      if (!collectInsertionElements(Piece, ShiftI + Shift, Elements, VecEltTy,
                                     isBigEndian))
         return false;
     }

llvm/test/Transforms/InstCombine/bitcast.ll

@@ -686,6 +686,21 @@ define ptr @bitcast_from_single_element_pointer_vector_to_pointer(<1 x ptr> %ptr
   ret ptr %ptr
 }
 
+; Sure that we calculate the correct shift.
+define <4 x i32> @bitcast_shl(i32 %arg) {
+; CHECK-LABEL: @bitcast_shl(
+; CHECK-NEXT:    [[I5:%.*]] = insertelement <4 x i32> <i32 0, i32 0, i32 65, i32 poison>, i32 [[ARG:%.*]], i64 3
+; CHECK-NEXT:    ret <4 x i32> [[I5]]
+;
+  %i = zext i32 %arg to i64
+  %i1 = shl i64 %i, 32
+  %i2 = or i64 %i1, 65
+  %i3 = zext i64 %i2 to i128
+  %i4 = shl i128 %i3, 64
+  %i5 = bitcast i128 %i4 to <4 x i32>
+  ret <4 x i32> %i5
+}
+
 declare void @f1()
 declare void @f2()
 define ptr @select_bitcast_unsized_pointer(i1 %c) {