[LV] Preserve GEP nusw when widening memory

Author: artagnon

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -7487,12 +7487,11 @@ VPRecipeBuilder::tryToWidenMemory(Instruction *I, ArrayRef<VPValue *> Operands,
     VPSingleDefRecipe *VectorPtr;
     if (Reverse) {
       // When folding the tail, we may compute an address that we don't in the
-      // original scalar loop and it may not be inbounds. Drop Inbounds in that
-      // case.
+      // original scalar loop: use none in this case.
       GEPNoWrapFlags Flags =
-          (CM.foldTailByMasking() || !GEP || !GEP->isInBounds())
+          CM.foldTailByMasking() || !GEP
               ? GEPNoWrapFlags::none()
-              : GEPNoWrapFlags::inBounds();
+              : GEP->getNoWrapFlags().withoutNoUnsignedWrap();
       VectorPtr =
           new VPVectorEndPointerRecipe(Ptr, &Plan.getVF(), getLoadStoreType(I),
                                        /*Stride*/ -1, Flags, I->getDebugLoc());

llvm/test/Transforms/LoopVectorize/reverse-induction-gep-nowrap-flags.ll

@@ -74,8 +74,8 @@ define i32 @preserve_nusw(i64 %start, ptr %ptr) {
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = sub i64 [[START]], [[INDEX]]
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], -1
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr nusw i32, ptr [[PTR]], i64 [[TMP0]]
-; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i32, ptr [[TMP1]], i32 0
-; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr i32, ptr [[TMP2]], i32 -3
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr nusw i32, ptr [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr nusw i32, ptr [[TMP2]], i32 -3
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP3]], align 4
 ; CHECK-NEXT:    [[REVERSE:%.*]] = shufflevector <4 x i32> [[WIDE_LOAD]], <4 x i32> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
 ; CHECK-NEXT:    [[TMP4]] = add <4 x i32> [[REVERSE]], [[VEC_PHI]]