Automerge: [SCEV] Check if predicate is known false for predicated AddRecs. (#151134)

Similarly to llvm/llvm-project#131538, we can
also try and check if a predicate is known to wrap given the backedge
taken count.

For now, this just checks directly when we try to create predicated
AddRecs. This both helps to avoid spending compile-time on optimizations
where we know the predicate is false, and can also help to allow
additional vectorization (e.g. by deciding to scalarize memory accesses
when otherwise we would try to create a predicated AddRec with a
predicate that's always false).

The initial version is quite restricted, but can be extended in
follow-ups to cover more cases.

PR: llvm/llvm-project#151134

Author: fhahn

llvm/lib/Analysis/ScalarEvolution.cpp

@@ -14952,6 +14952,29 @@ const SCEVAddRecExpr *ScalarEvolution::convertSCEVToAddRecWithPredicates(
   if (!AddRec)
     return nullptr;
 
+  // Check if any of the transformed predicates is known to be false. In that
+  // case, it doesn't make sense to convert to a predicated AddRec, as the
+  // versioned loop will never execute.
+  for (const SCEVPredicate *Pred : TransformPreds) {
+    auto *WrapPred = dyn_cast<SCEVWrapPredicate>(Pred);
+    if (!WrapPred || WrapPred->getFlags() != SCEVWrapPredicate::IncrementNSSW)
+      continue;
+
+    const SCEVAddRecExpr *AddRecToCheck = WrapPred->getExpr();
+    const SCEV *ExitCount = getBackedgeTakenCount(AddRecToCheck->getLoop());
+    if (isa<SCEVCouldNotCompute>(ExitCount))
+      continue;
+
+    const SCEV *Step = AddRecToCheck->getStepRecurrence(*this);
+    if (!Step->isOne())
+      continue;
+
+    ExitCount = getTruncateOrSignExtend(ExitCount, Step->getType());
+    const SCEV *Add = getAddExpr(AddRecToCheck->getStart(), ExitCount);
+    if (isKnownPredicate(CmpInst::ICMP_SLT, Add, AddRecToCheck->getStart()))
+      return nullptr;
+  }
+
   // Since the transformation was successful, we can now transfer the SCEV
   // predicates.
   Preds.append(TransformPreds.begin(), TransformPreds.end());

llvm/test/Transforms/LoopVectorize/first-order-recurrence-dead-instructions.ll

@@ -6,16 +6,61 @@ define i8 @recurrence_phi_with_same_incoming_values_after_simplifications(i8 %fo
 ; CHECK-LABEL: define i8 @recurrence_phi_with_same_incoming_values_after_simplifications(
 ; CHECK-SAME: i8 [[FOR_START:%.*]], ptr [[DST:%.*]]) {
 ; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i8> poison, i8 [[FOR_START]], i64 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT]], <4 x i8> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLAT]], <4 x i8> [[BROADCAST_SPLAT]], <4 x i32> <i32 3, i32 4, i32 5, i32 6>
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i32 1, [[INDEX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[OFFSET_IDX]], 0
+; CHECK-NEXT:    [[TMP2:%.*]] = add i32 [[OFFSET_IDX]], 1
+; CHECK-NEXT:    [[TMP3:%.*]] = add i32 [[OFFSET_IDX]], 2
+; CHECK-NEXT:    [[TMP4:%.*]] = add i32 [[OFFSET_IDX]], 3
+; CHECK-NEXT:    [[TMP5:%.*]] = add i32 [[OFFSET_IDX]], 4
+; CHECK-NEXT:    [[TMP6:%.*]] = add i32 [[OFFSET_IDX]], 5
+; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[OFFSET_IDX]], 6
+; CHECK-NEXT:    [[TMP8:%.*]] = add i32 [[OFFSET_IDX]], 7
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[DST]], i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i8, ptr [[DST]], i32 [[TMP2]]
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i8, ptr [[DST]], i32 [[TMP3]]
+; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i8, ptr [[DST]], i32 [[TMP4]]
+; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i8, ptr [[DST]], i32 [[TMP5]]
+; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[DST]], i32 [[TMP6]]
+; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i8, ptr [[DST]], i32 [[TMP7]]
+; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[DST]], i32 [[TMP8]]
+; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <4 x i8> [[TMP0]], i32 0
+; CHECK-NEXT:    store i8 [[TMP17]], ptr [[TMP9]], align 1
+; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <4 x i8> [[TMP0]], i32 1
+; CHECK-NEXT:    store i8 [[TMP18]], ptr [[TMP10]], align 1
+; CHECK-NEXT:    [[TMP19:%.*]] = extractelement <4 x i8> [[TMP0]], i32 2
+; CHECK-NEXT:    store i8 [[TMP19]], ptr [[TMP11]], align 1
+; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i8> [[TMP0]], i32 3
+; CHECK-NEXT:    store i8 [[TMP20]], ptr [[TMP12]], align 1
+; CHECK-NEXT:    store i8 [[TMP17]], ptr [[TMP13]], align 1
+; CHECK-NEXT:    store i8 [[TMP18]], ptr [[TMP14]], align 1
+; CHECK-NEXT:    store i8 [[TMP19]], ptr [[TMP15]], align 1
+; CHECK-NEXT:    store i8 [[TMP20]], ptr [[TMP16]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 8
+; CHECK-NEXT:    [[TMP21:%.*]] = icmp eq i32 [[INDEX_NEXT]], -8
+; CHECK-NEXT:    br i1 [[TMP21]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    br label %[[SCALAR_PH]]
+; CHECK:       [[SCALAR_PH]]:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ -7, %[[MIDDLE_BLOCK]] ], [ 1, %[[ENTRY]] ]
+; CHECK-NEXT:    [[SCALAR_RECUR_INIT:%.*]] = phi i8 [ [[FOR_START]], %[[MIDDLE_BLOCK]] ], [ [[FOR_START]], %[[ENTRY]] ]
 ; CHECK-NEXT:    br label %[[LOOP:.*]]
 ; CHECK:       [[LOOP]]:
-; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 1, %[[ENTRY]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
-; CHECK-NEXT:    [[FOR:%.*]] = phi i8 [ [[FOR_START]], %[[ENTRY]] ], [ [[FOR_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[FOR:%.*]] = phi i8 [ [[SCALAR_RECUR_INIT]], %[[SCALAR_PH]] ], [ [[FOR_NEXT:%.*]], %[[LOOP]] ]
 ; CHECK-NEXT:    [[FOR_NEXT]] = and i8 [[FOR_START]], -1
 ; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1
 ; CHECK-NEXT:    [[GEP_DST:%.*]] = getelementptr inbounds i8, ptr [[DST]], i32 [[IV]]
 ; CHECK-NEXT:    store i8 [[FOR]], ptr [[GEP_DST]], align 1
 ; CHECK-NEXT:    [[EC:%.*]] = icmp eq i32 [[IV_NEXT]], 0
-; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT:.*]], label %[[LOOP]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT:.*]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
 ; CHECK:       [[EXIT]]:
 ; CHECK-NEXT:    [[FOR_NEXT_LCSSA:%.*]] = phi i8 [ [[FOR_NEXT]], %[[LOOP]] ]
 ; CHECK-NEXT:    ret i8 [[FOR_NEXT_LCSSA]]
@@ -61,7 +106,7 @@ define i32 @sink_after_dead_inst(ptr %A.ptr) {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 8
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i16> [[STEP_ADD]], splat (i16 4)
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], 16
-; CHECK-NEXT:    br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
 ; CHECK:       [[MIDDLE_BLOCK]]:
 ; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <4 x i32> [[TMP2]], i32 2
 ; CHECK-NEXT:    br label %[[FOR_END:.*]]
@@ -82,7 +127,7 @@ define i32 @sink_after_dead_inst(ptr %A.ptr) {
 ; CHECK-NEXT:    [[EXT:%.*]] = zext i1 [[B3]] to i32
 ; CHECK-NEXT:    [[A_GEP:%.*]] = getelementptr i32, ptr [[A_PTR]], i16 [[IV]]
 ; CHECK-NEXT:    store i32 0, ptr [[A_GEP]], align 4
-; CHECK-NEXT:    br i1 [[VEC_DEAD]], label %[[FOR_END]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK-NEXT:    br i1 [[VEC_DEAD]], label %[[FOR_END]], label %[[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
 ; CHECK:       [[FOR_END]]:
 ; CHECK-NEXT:    [[FOR_LCSSA:%.*]] = phi i32 [ [[FOR]], %[[LOOP]] ], [ [[VECTOR_RECUR_EXTRACT_FOR_PHI]], %[[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    ret i32 [[FOR_LCSSA]]
@@ -142,7 +187,7 @@ define void @sink_dead_inst(ptr %a) {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 8
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i16> [[STEP_ADD]], splat (i16 4)
 ; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[INDEX_NEXT]], 40
-; CHECK-NEXT:    br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
 ; CHECK:       [[MIDDLE_BLOCK]]:
 ; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i16> [[TMP4]], i32 3
 ; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT1:%.*]] = extractelement <4 x i32> [[TMP2]], i32 3
@@ -163,7 +208,7 @@ define void @sink_dead_inst(ptr %a) {
 ; CHECK-NEXT:    [[REC_1_PREV]] = add i16 [[IV_NEXT]], 5
 ; CHECK-NEXT:    [[GEP:%.*]] = getelementptr i16, ptr [[A]], i16 [[IV]]
 ; CHECK-NEXT:    store i16 [[USE_REC_1]], ptr [[GEP]], align 2
-; CHECK-NEXT:    br i1 [[CMP]], label %[[FOR_END:.*]], label %[[FOR_COND]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-NEXT:    br i1 [[CMP]], label %[[FOR_END:.*]], label %[[FOR_COND]], !llvm.loop [[LOOP7:![0-9]+]]
 ; CHECK:       [[FOR_END]]:
 ; CHECK-NEXT:    ret void
 ;
@@ -205,7 +250,7 @@ define void @unused_recurrence(ptr %a) {
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 8
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i16> [[STEP_ADD]], splat (i16 4)
 ; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1024
-; CHECK-NEXT:    br i1 [[TMP2]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK-NEXT:    br i1 [[TMP2]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
 ; CHECK:       [[MIDDLE_BLOCK]]:
 ; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i16> [[TMP1]], i32 3
 ; CHECK-NEXT:    br label %[[SCALAR_PH]]
@@ -220,7 +265,7 @@ define void @unused_recurrence(ptr %a) {
 ; CHECK-NEXT:    [[IV_NEXT]] = add i16 [[IV]], 1
 ; CHECK-NEXT:    [[REC_1_PREV]] = add i16 [[IV_NEXT]], 5
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i16 [[IV]], 1000
-; CHECK-NEXT:    br i1 [[CMP]], label %[[FOR_END:.*]], label %[[FOR_COND]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK-NEXT:    br i1 [[CMP]], label %[[FOR_END:.*]], label %[[FOR_COND]], !llvm.loop [[LOOP9:![0-9]+]]
 ; CHECK:       [[FOR_END]]:
 ; CHECK-NEXT:    ret void
 ;