[VPlan] Remove dead recipes before sinking.

[fhahn]

Summary

optimizeInductions may leave dead recipes which can prevent sinking.
Sinking on the other hand should not introduce new dead recipes, so
clean up dead recipes before sinking.

Depends on D133760.

[Ayal]

LGTM! Adding a minor nit.

llvm/test/Transforms/LoopVectorize/pointer-induction.ll

39–40

Is this GEP replicated sinking intentional/helpful/harmful?

[fhahn]

Rebase so this can be applied directly on current main. I am planning to land this soon.

[fhahn]

llvm/test/Transforms/LoopVectorize/pointer-induction.ll

39–40

This is intentional and a consequence of VPlan-based sinking. We will keep a uniform GEP in the header and create a new replicate recipe that is sunk to the users in the replicate region. This comes at the cost of not reusing the uniform GEP in the first pred.store.block, but this should be cleaned up by different passes.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

VPlanPtr LoopVectorizationPlanner::buildVPlanWithVPRecipes(
   RSO.flush();
   Plan->setName(PlanName);
 
   // From this point onwards, VPlan-to-VPlan transformations may change the plan
   // in ways that accessing values using original IR values is incorrect.
   Plan->disableValue2VPValue();
 
   VPlanTransforms::optimizeInductions(*Plan, *PSE.getSE());
-  VPlanTransforms::sinkScalarOperands(*Plan);
   VPlanTransforms::removeDeadRecipes(*Plan);
+  VPlanTransforms::sinkScalarOperands(*Plan);
   VPlanTransforms::mergeReplicateRegions(*Plan);
   VPlanTransforms::removeRedundantExpandSCEVRecipes(*Plan);
 
   // Fold Exit block into its predecessor if possible.
   // TODO: Fold block earlier once all VPlan transforms properly maintain a
   // VPBasicBlock as exit.
   VPBlockUtils::tryToMergeBlockIntoPredecessor(TopRegion->getExiting());
 

llvm/test/Transforms/LoopVectorize/pointer-induction.ll

 ; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i8* [[TMP6]] to <4 x i8>*
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i8>, <4 x i8>* [[TMP7]], align 1
 ; CHECK-NEXT:    [[REVERSE:%.*]] = shufflevector <4 x i8> [[WIDE_LOAD]], <4 x i8> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
 ; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq <4 x i8> [[REVERSE]], zeroinitializer
 ; CHECK-NEXT:    [[TMP9:%.*]] = xor <4 x i1> [[TMP8]], <i1 true, i1 true, i1 true, i1 true>
 ; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x i1> [[TMP9]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP10]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
 ; CHECK:       pred.store.if:
-; CHECK-NEXT:    store i8 95, i8* [[TMP4]], align 1
+; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i8, i8* [[NEXT_GEP]], i64 -1
+; CHECK-NEXT:    store i8 95, i8* [[TMP11]], align 1
 ; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE]]
 ; CHECK:       pred.store.continue:
-; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <4 x i1> [[TMP9]], i32 1
-; CHECK-NEXT:    br i1 [[TMP11]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6:%.*]]
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <4 x i1> [[TMP9]], i32 1
+; CHECK-NEXT:    br i1 [[TMP12]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6:%.*]]
 ; CHECK:       pred.store.if5:
-; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[INDEX]], 1
-; CHECK-NEXT:    [[TMP13:%.*]] = mul i64 [[TMP12]], -1
-; CHECK-NEXT:    [[NEXT_GEP2:%.*]] = getelementptr i8, i8* null, i64 [[TMP13]]
-; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i8, i8* [[NEXT_GEP2]], i64 -1
-; CHECK-NEXT:    store i8 95, i8* [[TMP14]], align 1
+; CHECK-NEXT:    [[TMP13:%.*]] = add i64 [[INDEX]], 1
+; CHECK-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], -1
+; CHECK-NEXT:    [[NEXT_GEP2:%.*]] = getelementptr i8, i8* null, i64 [[TMP14]]
+; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i8, i8* [[NEXT_GEP2]], i64 -1
+; CHECK-NEXT:    store i8 95, i8* [[TMP15]], align 1
 ; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE6]]
 ; CHECK:       pred.store.continue6:
-; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <4 x i1> [[TMP9]], i32 2
-; CHECK-NEXT:    br i1 [[TMP15]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8:%.*]]
+; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <4 x i1> [[TMP9]], i32 2
+; CHECK-NEXT:    br i1 [[TMP16]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8:%.*]]
 ; CHECK:       pred.store.if7:
-; CHECK-NEXT:    [[TMP16:%.*]] = add i64 [[INDEX]], 2
-; CHECK-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], -1
-; CHECK-NEXT:    [[NEXT_GEP3:%.*]] = getelementptr i8, i8* null, i64 [[TMP17]]
-; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr inbounds i8, i8* [[NEXT_GEP3]], i64 -1
-; CHECK-NEXT:    store i8 95, i8* [[TMP18]], align 1
+; CHECK-NEXT:    [[TMP17:%.*]] = add i64 [[INDEX]], 2
+; CHECK-NEXT:    [[TMP18:%.*]] = mul i64 [[TMP17]], -1
+; CHECK-NEXT:    [[NEXT_GEP3:%.*]] = getelementptr i8, i8* null, i64 [[TMP18]]
+; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr inbounds i8, i8* [[NEXT_GEP3]], i64 -1
+; CHECK-NEXT:    store i8 95, i8* [[TMP19]], align 1
 ; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE8]]
 ; CHECK:       pred.store.continue8:
-; CHECK-NEXT:    [[TMP19:%.*]] = extractelement <4 x i1> [[TMP9]], i32 3
-; CHECK-NEXT:    br i1 [[TMP19]], label [[PRED_STORE_IF9:%.*]], label [[PRED_STORE_CONTINUE10]]
+; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i1> [[TMP9]], i32 3
+; CHECK-NEXT:    br i1 [[TMP20]], label [[PRED_STORE_IF9:%.*]], label [[PRED_STORE_CONTINUE10]]
 ; CHECK:       pred.store.if9:
-; CHECK-NEXT:    [[TMP20:%.*]] = add i64 [[INDEX]], 3
-; CHECK-NEXT:    [[TMP21:%.*]] = mul i64 [[TMP20]], -1
-; CHECK-NEXT:    [[NEXT_GEP4:%.*]] = getelementptr i8, i8* null, i64 [[TMP21]]
-; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i8, i8* [[NEXT_GEP4]], i64 -1
-; CHECK-NEXT:    store i8 95, i8* [[TMP22]], align 1
+; CHECK-NEXT:    [[TMP21:%.*]] = add i64 [[INDEX]], 3
+; CHECK-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], -1
+; CHECK-NEXT:    [[NEXT_GEP4:%.*]] = getelementptr i8, i8* null, i64 [[TMP22]]
+; CHECK-NEXT:    [[TMP23:%.*]] = getelementptr inbounds i8, i8* [[NEXT_GEP4]], i64 -1
+; CHECK-NEXT:    store i8 95, i8* [[TMP23]], align 1
 ; CHECK-NEXT:    br label [[PRED_STORE_CONTINUE10]]
 ; CHECK:       pred.store.continue10:
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; CHECK-NEXT:    [[TMP23:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP23]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT:    [[TMP24:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP24]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i8* [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ null, [[FOR_BODY_PREHEADER]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.cond.cleanup.loopexit:
 ; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
 ; CHECK:       for.cond.cleanup:
 ; CHECK-NEXT:    ret void
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[C_05:%.*]] = phi i8* [ [[INCDEC_PTR:%.*]], [[IF_END:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
 ; CHECK-NEXT:    [[INCDEC_PTR]] = getelementptr inbounds i8, i8* [[C_05]], i64 -1
-; CHECK-NEXT:    [[TMP24:%.*]] = load i8, i8* [[INCDEC_PTR]], align 1
-; CHECK-NEXT:    [[TOBOOL_NOT:%.*]] = icmp eq i8 [[TMP24]], 0
+; CHECK-NEXT:    [[TMP25:%.*]] = load i8, i8* [[INCDEC_PTR]], align 1
+; CHECK-NEXT:    [[TOBOOL_NOT:%.*]] = icmp eq i8 [[TMP25]], 0
 ; CHECK-NEXT:    br i1 [[TOBOOL_NOT]], label [[IF_END]], label [[IF_THEN:%.*]]
 ; CHECK:       if.then:
 ; CHECK-NEXT:    store i8 95, i8* [[INCDEC_PTR]], align 1
 ; CHECK-NEXT:    br label [[IF_END]]
 ; CHECK:       if.end:
 ; CHECK-NEXT:    [[CMP_NOT:%.*]] = icmp eq i8* [[INCDEC_PTR]], [[B]]
 ; CHECK-NEXT:    br i1 [[CMP_NOT]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
 ;

llvm/test/Transforms/LoopVectorize/vplan-sink-scalars-and-merge.ll

 ; CHECK-EMPTY:
 ; CHECK-NEXT: vector.ph:
 ; CHECK-NEXT: Successor(s): vector loop
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <x1> vector loop: {
 ; CHECK-NEXT:   vector.body:
 ; CHECK-NEXT:     EMIT vp<[[CAN_IV:%.+]]> = CANONICAL-INDUCTION
 ; CHECK-NEXT:     EMIT ir<%ptr.iv> = WIDEN-POINTER-INDUCTION ir<%start>, -1
-; CHECK-NEXT:     REPLICATE ir<%ptr.iv.next> = getelementptr ir<%ptr.iv>, ir<-1>
+; CHECK-NEXT:     CLONE ir<%ptr.iv.next> = getelementptr ir<%ptr.iv>, ir<-1>
 ; CHECK-NEXT:     WIDEN ir<%l> = load ir<%ptr.iv.next>
 ; CHECK-NEXT:     WIDEN ir<%c.1> = icmp ir<%l>, ir<0>
 ; CHECK-NEXT:   Successor(s): if.then
 ; CHECK-EMPTY:
 ; CHECK-NEXT:   if.then:
 ; CHECK-NEXT:     EMIT vp<[[NEG:%.+]]> = not ir<%c.1>
 ; CHECK-NEXT:   Successor(s): pred.store
 ; CHECK-EMPTY:
 ; CHECK-NEXT:   <xVFxUF> pred.store: {
 ; CHECK-NEXT:     pred.store.entry:
 ; CHECK-NEXT:       BRANCH-ON-MASK vp<[[NEG]]>
 ; CHECK-NEXT:     Successor(s): pred.store.if, pred.store.continue
 ; CHECK-EMPTY:
 ; CHECK-NEXT:     pred.store.if:
+; CHECK-NEXT:       REPLICATE ir<%ptr.iv.next> = getelementptr ir<%ptr.iv>, ir<-1>
 ; CHECK-NEXT:       REPLICATE store ir<95>, ir<%ptr.iv.next>
 ; CHECK-NEXT:     Successor(s): pred.store.continue
 ; CHECK-EMPTY:
 ; CHECK-NEXT:     pred.store.continue:
 ; CHECK-NEXT:     No successors
 ; CHECK-NEXT:   }
 ; CHECK-NEXT:   Successor(s): if.then.0
 ; CHECK-EMPTY: