[llvm] [VectorUtils] Check wrap with assume in analyzeInterleaving (PR #161722)

[Florian Hahn via llvm-commits]

================
@@ -351,7 +351,18 @@ define void @gather_interleave_group_with_dead_insert_pos(i64 %N, ptr noalias %s
 ; CHECK-NEXT:    [[TMP0:%.*]] = add nuw i64 [[SMAX]], 1
 ; CHECK-NEXT:    [[TMP1:%.*]] = lshr i64 [[TMP0]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
-; CHECK-NEXT:    br label %[[VECTOR_PH:.*]]
+; CHECK-NEXT:    br label %[[VECTOR_SCEVCHECK:.*]]
+; CHECK:       [[VECTOR_SCEVCHECK]]:
+; CHECK-NEXT:    [[SMAX1:%.*]] = call i64 @llvm.smax.i64(i64 [[N]], i64 0)
+; CHECK-NEXT:    [[TMP3:%.*]] = add nuw i64 [[SMAX1]], 1
+; CHECK-NEXT:    [[TMP4:%.*]] = lshr i64 [[TMP3]], 1
+; CHECK-NEXT:    [[MUL:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 8, i64 [[TMP4]])
+; CHECK-NEXT:    [[MUL_RESULT:%.*]] = extractvalue { i64, i1 } [[MUL]], 0
+; CHECK-NEXT:    [[MUL_OVERFLOW:%.*]] = extractvalue { i64, i1 } [[MUL]], 1
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i8, ptr [[DST]], i64 [[MUL_RESULT]]
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp ult ptr [[TMP5]], [[DST]]
+; CHECK-NEXT:    [[TMP7:%.*]] = or i1 [[TMP6]], [[MUL_OVERFLOW]]
+; CHECK-NEXT:    br i1 [[TMP7]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
----------------
fhahn wrote:

this seems worse now, we created a predicate, but it isn't needed?

https://github.com/llvm/llvm-project/pull/161722