[Loads] Apply loop guards to maximum pointer difference.

Applying loop guards to MaxPtrDiff can improve results in some cases.

Author: fhahn

llvm/lib/Analysis/Loads.cpp

@@ -355,7 +355,10 @@ bool llvm::isDereferenceableAndAlignedInLoop(
   const SCEV *PtrDiff = SE.getMinusSCEV(AccessEnd, AccessStart);
   if (isa<SCEVCouldNotCompute>(PtrDiff))
     return false;
-  APInt MaxPtrDiff = SE.getUnsignedRangeMax(PtrDiff);
+  ScalarEvolution::LoopGuards LoopGuards =
+      ScalarEvolution::LoopGuards::collect(AddRec->getLoop(), SE);
+  APInt MaxPtrDiff =
+      SE.getUnsignedRangeMax(SE.applyLoopGuards(PtrDiff, LoopGuards));
 
   Value *Base = nullptr;
   APInt AccessSize;

llvm/test/Transforms/LoopVectorize/dereferenceable-info-from-assumption-constant-size-needs-loop-guards.ll

@@ -167,31 +167,13 @@ define void @loop_guard_on_trip_count_needed_to_prove_dereferenceable(i32 %x, pt
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_EXT]], [[N_MOD_VF]]
 ; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
 ; CHECK:       [[VECTOR_BODY]]:
-; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[PRED_LOAD_CONTINUE2:.*]] ]
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr i32, ptr [[B]], i64 [[INDEX]]
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i32>, ptr [[TMP0]], align 4
-; CHECK-NEXT:    [[TMP1:%.*]] = icmp ne <2 x i32> [[WIDE_LOAD]], zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x i1> [[TMP1]], i32 0
-; CHECK-NEXT:    br i1 [[TMP2]], label %[[PRED_LOAD_IF:.*]], label %[[PRED_LOAD_CONTINUE:.*]]
-; CHECK:       [[PRED_LOAD_IF]]:
-; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr i32, ptr [[A]], i64 [[TMP3]]
-; CHECK-NEXT:    [[TMP5:%.*]] = load i32, ptr [[TMP4]], align 4
-; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP5]], i32 0
-; CHECK-NEXT:    br label %[[PRED_LOAD_CONTINUE]]
-; CHECK:       [[PRED_LOAD_CONTINUE]]:
-; CHECK-NEXT:    [[TMP7:%.*]] = phi <2 x i32> [ poison, %[[VECTOR_BODY]] ], [ [[TMP6]], %[[PRED_LOAD_IF]] ]
-; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x i1> [[TMP1]], i32 1
-; CHECK-NEXT:    br i1 [[TMP8]], label %[[PRED_LOAD_IF1:.*]], label %[[PRED_LOAD_CONTINUE2]]
-; CHECK:       [[PRED_LOAD_IF1]]:
-; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], 1
-; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i32, ptr [[A]], i64 [[TMP9]]
-; CHECK-NEXT:    [[TMP11:%.*]] = load i32, ptr [[TMP10]], align 4
-; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <2 x i32> [[TMP7]], i32 [[TMP11]], i32 1
-; CHECK-NEXT:    br label %[[PRED_LOAD_CONTINUE2]]
-; CHECK:       [[PRED_LOAD_CONTINUE2]]:
-; CHECK-NEXT:    [[TMP13:%.*]] = phi <2 x i32> [ [[TMP7]], %[[PRED_LOAD_CONTINUE]] ], [ [[TMP12]], %[[PRED_LOAD_IF1]] ]
-; CHECK-NEXT:    [[PREDPHI:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> [[TMP13]], <2 x i32> [[WIDE_LOAD]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp eq <2 x i32> [[WIDE_LOAD]], zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i32, ptr [[A]], i64 [[INDEX]]
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <2 x i32>, ptr [[TMP2]], align 4
+; CHECK-NEXT:    [[PREDPHI:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> [[WIDE_LOAD]], <2 x i32> [[WIDE_LOAD1]]
 ; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[INDEX]]
 ; CHECK-NEXT:    store <2 x i32> [[PREDPHI]], ptr [[TMP14]], align 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2