[Loads] Also consider getPointerAlignment when checking assumptions. (#120916)

Also use getPointerAlignment when trying to use alignment and
dereferenceable assumptions. This catches cases where dereferencable is
known via the assumption but alignment is known via getPointerAlignment
(e.g. via argument attribute or align of 1)

PR: llvm/llvm-project#120916

Author: fhahn

llvm/lib/Analysis/Loads.cpp

@@ -170,9 +170,10 @@ static bool isDereferenceableAndAlignedPointer(
 
   if (CtxI) {
     /// Look through assumes to see if both dereferencability and alignment can
-    /// be provent by an assume
+    /// be proven by an assume if needed.
     RetainedKnowledge AlignRK;
     RetainedKnowledge DerefRK;
+    bool IsAligned = V->getPointerAlignment(DL) >= Alignment;
     if (getKnowledgeForValue(
             V, {Attribute::Dereferenceable, Attribute::Alignment}, AC,
             [&](RetainedKnowledge RK, Instruction *Assume, auto) {
@@ -182,7 +183,8 @@ static bool isDereferenceableAndAlignedPointer(
                 AlignRK = std::max(AlignRK, RK);
               if (RK.AttrKind == Attribute::Dereferenceable)
                 DerefRK = std::max(DerefRK, RK);
-              if (AlignRK && DerefRK && AlignRK.ArgValue >= Alignment.value() &&
+              IsAligned |= AlignRK && AlignRK.ArgValue >= Alignment.value();
+              if (IsAligned && DerefRK &&
                   DerefRK.ArgValue >= Size.getZExtValue())
                 return true; // We have found what we needed so we stop looking
               return false;  // Other assumes may have better information. so

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

@@ -104,8 +104,8 @@ exit:
   ret void
 }
 
-define void @deref_assumption_in_header_constant_trip_count_loop_invariant_ptr(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
-; CHECK-LABEL: define void @deref_assumption_in_header_constant_trip_count_loop_invariant_ptr(
+define void @align_deref_assumption_in_header_constant_trip_count_loop_invariant_ptr(ptr noalias %a, ptr noalias %b, ptr noalias %c) {
+; CHECK-LABEL: define void @align_deref_assumption_in_header_constant_trip_count_loop_invariant_ptr(
 ; CHECK-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], ptr noalias [[C:%.*]]) {
 ; CHECK-NEXT:  [[ENTRY:.*]]:
 ; CHECK-NEXT:    call void @llvm.assume(i1 true) [ "align"(ptr [[A]], i64 4), "dereferenceable"(ptr [[A]], i64 4) ]
@@ -899,32 +899,15 @@ define void @deref_assumption_in_preheader_constant_trip_count_align_1(ptr noali
 ; CHECK:       [[VECTOR_PH]]:
 ; 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:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i32 0
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i32>, ptr [[TMP2]], align 4
 ; CHECK-NEXT:    [[TMP3:%.*]] = icmp sge <2 x i32> [[WIDE_LOAD]], zeroinitializer
-; CHECK-NEXT:    [[TMP4:%.*]] = xor <2 x i1> [[TMP3]], splat (i1 true)
-; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x i1> [[TMP4]], i32 0
-; CHECK-NEXT:    br i1 [[TMP5]], label %[[PRED_LOAD_IF:.*]], label %[[PRED_LOAD_CONTINUE:.*]]
-; CHECK:       [[PRED_LOAD_IF]]:
 ; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr i32, ptr [[A]], i64 [[TMP0]]
-; CHECK-NEXT:    [[TMP7:%.*]] = load i32, ptr [[TMP6]], align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x i32> poison, i32 [[TMP7]], i32 0
-; CHECK-NEXT:    br label %[[PRED_LOAD_CONTINUE]]
-; CHECK:       [[PRED_LOAD_CONTINUE]]:
-; CHECK-NEXT:    [[TMP9:%.*]] = phi <2 x i32> [ poison, %[[VECTOR_BODY]] ], [ [[TMP8]], %[[PRED_LOAD_IF]] ]
-; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x i1> [[TMP4]], i32 1
-; CHECK-NEXT:    br i1 [[TMP10]], label %[[PRED_LOAD_IF1:.*]], label %[[PRED_LOAD_CONTINUE2]]
-; CHECK:       [[PRED_LOAD_IF1]]:
-; CHECK-NEXT:    [[TMP11:%.*]] = add i64 [[INDEX]], 1
-; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[A]], i64 [[TMP11]]
-; CHECK-NEXT:    [[TMP13:%.*]] = load i32, ptr [[TMP12]], align 1
-; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <2 x i32> [[TMP9]], i32 [[TMP13]], i32 1
-; CHECK-NEXT:    br label %[[PRED_LOAD_CONTINUE2]]
-; CHECK:       [[PRED_LOAD_CONTINUE2]]:
-; CHECK-NEXT:    [[TMP15:%.*]] = phi <2 x i32> [ [[TMP9]], %[[PRED_LOAD_CONTINUE]] ], [ [[TMP14]], %[[PRED_LOAD_IF1]] ]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i32, ptr [[TMP6]], i32 0
+; CHECK-NEXT:    [[TMP15:%.*]] = load <2 x i32>, ptr [[TMP5]], align 1
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <2 x i1> [[TMP3]], <2 x i32> [[WIDE_LOAD]], <2 x i32> [[TMP15]]
 ; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
@@ -1168,32 +1151,15 @@ define void @deref_assumption_in_preheader_constant_trip_count_align_4_known_via
 ; CHECK:       [[VECTOR_PH]]:
 ; 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:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, ptr [[B]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i32 0
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i32>, ptr [[TMP2]], align 4
 ; CHECK-NEXT:    [[TMP3:%.*]] = icmp sge <2 x i32> [[WIDE_LOAD]], zeroinitializer
-; CHECK-NEXT:    [[TMP4:%.*]] = xor <2 x i1> [[TMP3]], splat (i1 true)
-; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x i1> [[TMP4]], i32 0
-; CHECK-NEXT:    br i1 [[TMP5]], label %[[PRED_LOAD_IF:.*]], label %[[PRED_LOAD_CONTINUE:.*]]
-; CHECK:       [[PRED_LOAD_IF]]:
 ; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr i32, ptr [[A]], i64 [[TMP0]]
-; CHECK-NEXT:    [[TMP7:%.*]] = load i32, ptr [[TMP6]], align 4
-; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x i32> poison, i32 [[TMP7]], i32 0
-; CHECK-NEXT:    br label %[[PRED_LOAD_CONTINUE]]
-; CHECK:       [[PRED_LOAD_CONTINUE]]:
-; CHECK-NEXT:    [[TMP9:%.*]] = phi <2 x i32> [ poison, %[[VECTOR_BODY]] ], [ [[TMP8]], %[[PRED_LOAD_IF]] ]
-; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x i1> [[TMP4]], i32 1
-; CHECK-NEXT:    br i1 [[TMP10]], label %[[PRED_LOAD_IF1:.*]], label %[[PRED_LOAD_CONTINUE2]]
-; CHECK:       [[PRED_LOAD_IF1]]:
-; CHECK-NEXT:    [[TMP11:%.*]] = add i64 [[INDEX]], 1
-; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[A]], i64 [[TMP11]]
-; CHECK-NEXT:    [[TMP13:%.*]] = load i32, ptr [[TMP12]], align 4
-; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <2 x i32> [[TMP9]], i32 [[TMP13]], i32 1
-; CHECK-NEXT:    br label %[[PRED_LOAD_CONTINUE2]]
-; CHECK:       [[PRED_LOAD_CONTINUE2]]:
-; CHECK-NEXT:    [[TMP15:%.*]] = phi <2 x i32> [ [[TMP9]], %[[PRED_LOAD_CONTINUE]] ], [ [[TMP14]], %[[PRED_LOAD_IF1]] ]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i32, ptr [[TMP6]], i32 0
+; CHECK-NEXT:    [[TMP15:%.*]] = load <2 x i32>, ptr [[TMP5]], align 4
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <2 x i1> [[TMP3]], <2 x i32> [[WIDE_LOAD]], <2 x i32> [[TMP15]]
 ; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[C]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0