[LV] Pick correct BB as insert point when fixing PHI for FORs.

Currently we fail to pick the right insertion point when
PreviousLastPart of a first-order-recurrence is a PHI node not in the
LoopVectorBody. This can happen when PreviousLastPart is produce in a
predicated block. In that case, we should pick the insertion point in
the BB the PHI is in.

Fixes PR44020.

Reviewers: hsaito, fhahn, Ayal, dorit

Reviewed By: Ayal

Differential Revision: https://reviews.llvm.org/D71071

Author: fhahn

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -3556,17 +3556,27 @@ void InnerLoopVectorizer::fixFirstOrderRecurrence(PHINode *Phi) {
   // among all unrolled iterations, due to the order of their construction.
   Value *PreviousLastPart = getOrCreateVectorValue(Previous, UF - 1);
 
-  // Set the insertion point after the previous value if it is an instruction.
+  // Find and set the insertion point after the previous value if it is an
+  // instruction.
+  BasicBlock::iterator InsertPt;
   // Note that the previous value may have been constant-folded so it is not
-  // guaranteed to be an instruction in the vector loop. Also, if the previous
-  // value is a phi node, we should insert after all the phi nodes to avoid
-  // breaking basic block verification.
-  if (LI->getLoopFor(LoopVectorBody)->isLoopInvariant(PreviousLastPart) ||
-      isa<PHINode>(PreviousLastPart))
-    Builder.SetInsertPoint(&*LoopVectorBody->getFirstInsertionPt());
-  else
-    Builder.SetInsertPoint(
-        &*++BasicBlock::iterator(cast<Instruction>(PreviousLastPart)));
+  // guaranteed to be an instruction in the vector loop.
+  // FIXME: Loop invariant values do not form recurrences. We should deal with
+  //        them earlier.
+  if (LI->getLoopFor(LoopVectorBody)->isLoopInvariant(PreviousLastPart))
+    InsertPt = LoopVectorBody->getFirstInsertionPt();
+  else {
+    Instruction *PreviousInst = cast<Instruction>(PreviousLastPart);
+    if (isa<PHINode>(PreviousLastPart))
+      // If the previous value is a phi node, we should insert after all the phi
+      // nodes in the block containing the PHI to avoid breaking basic block
+      // verification. Note that the basic block may be different to
+      // LoopVectorBody, in case we predicate the loop.
+      InsertPt = PreviousInst->getParent()->getFirstInsertionPt();
+    else
+      InsertPt = ++PreviousInst->getIterator();
+  }
+  Builder.SetInsertPoint(&*InsertPt);
 
   // We will construct a vector for the recurrence by combining the values for
   // the current and previous iterations. This is the required shuffle mask.

llvm/test/Transforms/LoopVectorize/SystemZ/predicated-first-order-recurrence.ll

@@ -0,0 +1,103 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -loop-vectorize -mtriple=s390x-ibm-linux -mcpu=z13 -force-vector-width=2 -S %s | FileCheck %s
+
+; Test case from PR44020.
+
+; In func_21, %rec forms a first order recurrence and we predicate to avoid
+; scalar iteration overhead for a low trip count loop. Make sure we pick
+; the correct insertion point when fixing first order recurrences.
+
+@A = external dso_local global [5 x i32], align 4
+@B = external dso_local global [5 x i32], align 4
+
+define void @func_21() {
+; CHECK-LABEL: @func_21(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE4:%.*]] ]
+; CHECK-NEXT:    [[VECTOR_RECUR:%.*]] = phi <2 x i32> [ <i32 undef, i32 0>, [[VECTOR_PH]] ], [ [[TMP12:%.*]], [[PRED_STORE_CONTINUE4]] ]
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i64> undef, i64 [[INDEX]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i64> [[BROADCAST_SPLATINSERT]], <2 x i64> undef, <2 x i32> zeroinitializer
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add <2 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1>
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 1
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp ule <2 x i64> [[INDUCTION]], <i64 4, i64 4>
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x i1> [[TMP2]], i32 0
+; CHECK-NEXT:    br i1 [[TMP3]], label [[PRED_LOAD_IF:%.*]], label [[PRED_LOAD_CONTINUE:%.*]]
+; CHECK:       pred.load.if:
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @A, i64 0, i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP5:%.*]] = load i32, i32* [[TMP4]], align 4
+; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <2 x i32> undef, i32 [[TMP5]], i32 0
+; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE]]
+; CHECK:       pred.load.continue:
+; CHECK-NEXT:    [[TMP7:%.*]] = phi <2 x i32> [ undef, [[VECTOR_BODY]] ], [ [[TMP6]], [[PRED_LOAD_IF]] ]
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x i1> [[TMP2]], i32 1
+; CHECK-NEXT:    br i1 [[TMP8]], label [[PRED_LOAD_IF1:%.*]], label [[PRED_LOAD_CONTINUE2:%.*]]
+; CHECK:       pred.load.if1:
+; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @A, i64 0, i64 [[TMP1]]
+; CHECK-NEXT:    [[TMP10:%.*]] = load i32, i32* [[TMP9]], align 4
+; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <2 x i32> [[TMP7]], i32 [[TMP10]], i32 1
+; CHECK-NEXT:    br label [[PRED_LOAD_CONTINUE2]]
+; CHECK:       pred.load.continue2:
+; CHECK-NEXT:    [[TMP12]] = phi <2 x i32> [ [[TMP7]], [[PRED_LOAD_CONTINUE]] ], [ [[TMP11]], [[PRED_LOAD_IF1]] ]
+; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <2 x i32> [[VECTOR_RECUR]], <2 x i32> [[TMP12]], <2 x i32> <i32 1, i32 2>
+; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <2 x i1> [[TMP2]], i32 0
+; CHECK-NEXT:    br i1 [[TMP14]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
+; CHECK:       pred.store.if:
+; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @B, i64 0, i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <2 x i32> [[TMP13]], i32 0
+; CHECK-NEXT:    store i32 [[TMP16]], i32* [[TMP15]], align 4
+; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE]]
+; CHECK:       pred.store.continue:
+; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <2 x i1> [[TMP2]], i32 1
+; CHECK-NEXT:    br i1 [[TMP17]], label [[PRED_STORE_IF3:%.*]], label [[PRED_STORE_CONTINUE4]]
+; CHECK:       pred.store.if3:
+; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @B, i64 0, i64 [[TMP1]]
+; CHECK-NEXT:    [[TMP19:%.*]] = extractelement <2 x i32> [[TMP13]], i32 1
+; CHECK-NEXT:    store i32 [[TMP19]], i32* [[TMP18]], align 4
+; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE4]]
+; CHECK:       pred.store.continue4:
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 2
+; CHECK-NEXT:    [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], 6
+; CHECK-NEXT:    br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <2 x i32> [[TMP12]], i32 1
+; CHECK-NEXT:    [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <2 x i32> [[TMP12]], i32 0
+; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[SCALAR_RECUR_INIT:%.*]] = phi i32 [ [[VECTOR_RECUR_EXTRACT]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 6, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ]
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[SCALAR_RECUR:%.*]] = phi i32 [ [[SCALAR_RECUR_INIT]], [[SCALAR_PH]] ], [ [[LV:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[LOOP]] ]
+; CHECK-NEXT:    [[A_PTR:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @A, i64 0, i64 [[INDVARS_IV]]
+; CHECK-NEXT:    [[LV]] = load i32, i32* [[A_PTR]], align 4
+; CHECK-NEXT:    [[B_PTR:%.*]] = getelementptr inbounds [5 x i32], [5 x i32]* @B, i64 0, i64 [[INDVARS_IV]]
+; CHECK-NEXT:    store i32 [[SCALAR_RECUR]], i32* [[B_PTR]], align 4
+; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 5
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[EXIT]], label [[LOOP]], !llvm.loop !2
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+
+loop:                                    ; preds = %loop, %entry
+  %rec = phi i32 [ 0, %entry], [ %lv, %loop ]
+  %indvars.iv = phi i64 [ 0, %entry], [ %indvars.iv.next, %loop ]
+  %A.ptr= getelementptr inbounds [5 x i32], [5 x i32]* @A, i64 0, i64 %indvars.iv
+  %lv = load i32, i32* %A.ptr, align 4
+  %B.ptr = getelementptr inbounds [5 x i32], [5 x i32]* @B, i64 0, i64 %indvars.iv
+  store i32 %rec, i32* %B.ptr, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 5
+  br i1 %exitcond, label %exit, label %loop
+
+exit:                                             ; preds = %loop
+  ret void
+}