Skip to content

Commit

Permalink
Title: [LV] Handle Fold-Tail of loops with vectorizarion factor equal…
Browse files Browse the repository at this point in the history 
… to 1

Summary:
When handling loops whose VF is 1, fold-tail vectorization sets the
backedge taken count of the original loop with a vector of a single
element. This causes type-mismatch during instruction generartion.

The purpose of this patch is toto address the case of VF==1.

Reviewer: Ayal (Ayal Zaks), bmahjour (Bardia Mahjour), fhahn (Florian Hahn), gilr (Gil Rapaport), rengolin (Renato Golin)

Reviewed By: Ayal (Ayal Zaks), bmahjour (Bardia Mahjour), fhahn (Florian Hahn)

Subscribers: Ayal (Ayal Zaks), rkruppe (Hanna Kruppe), bmahjour (Bardia Mahjour), rogfer01 (Roger Ferrer Ibanez), vkmr (Vineet Kumar), bollu (Siddharth Bhat), hiraditya (Aditya Kumar), llvm-commits (Mailing List llvm-commits)

Tag: LLVM

Differential Revision: https://reviews.llvm.org/D79976
  • Loading branch information
@anhtuyenibm
anhtuyenibm committed May 22, 2020
1 parent 4ed909b commit 13bf603
Show file tree
Hide file tree
Showing 2 changed files with 200 additions and 4 deletions.
15 changes: 11 additions & 4 deletions llvm/lib/Transforms/Vectorize/VPlan.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -441,7 +441,9 @@ void VPlan::execute(VPTransformState *State) {
IRBuilder<> Builder(State->CFG.PrevBB->getTerminator());
auto *TCMO = Builder.CreateSub(TC, ConstantInt::get(TC->getType(), 1),
"trip.count.minus.1");
Value *VTCMO = Builder.CreateVectorSplat(State->VF, TCMO, "broadcast");
auto VF = State->VF;
Value *VTCMO =
VF == 1 ? TCMO : Builder.CreateVectorSplat(VF, TCMO, "broadcast");
for (unsigned Part = 0, UF = State->UF; Part < UF; ++Part)
State->set(BackedgeTakenCount, VTCMO, Part);
}
Expand Down Expand Up @@ -809,12 +811,17 @@ void VPWidenCanonicalIVRecipe::execute(VPTransformState &State) {
Value *CanonicalIV = State.CanonicalIV;
Type *STy = CanonicalIV->getType();
IRBuilder<> Builder(State.CFG.PrevBB->getTerminator());
Value *VStart = Builder.CreateVectorSplat(State.VF, CanonicalIV, "broadcast");
auto VF = State.VF;
Value *VStart = VF == 1
? CanonicalIV
: Builder.CreateVectorSplat(VF, CanonicalIV, "broadcast");
for (unsigned Part = 0, UF = State.UF; Part < UF; ++Part) {
SmallVector<Constant *, 8> Indices;
for (unsigned Lane = 0, VF = State.VF; Lane < VF; ++Lane)
for (unsigned Lane = 0; Lane < VF; ++Lane)
Indices.push_back(ConstantInt::get(STy, Part * VF + Lane));
Constant *VStep = ConstantVector::get(Indices);
// If VF == 1, there is only one iteration in the loop above, thus the
// element pushed back into Indices is ConstantInt::get(STy, Part)
Constant *VStep = VF == 1 ? Indices.back() : ConstantVector::get(Indices);
// Add the consecutive indices to the vector value.
Value *CanonicalVectorIV = Builder.CreateAdd(VStart, VStep, "vec.iv");
State.set(getVPValue(), CanonicalVectorIV, Part);
Expand Down
189 changes: 189 additions & 0 deletions llvm/test/Transforms/LoopVectorize/tail-folding-vectorization-factor-1.ll
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,189 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -loop-vectorize -force-vector-interleave=4 -pass-remarks='loop-vectorize' -disable-output -S 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
; RUN: opt < %s -loop-vectorize -force-vector-interleave=4 -S | FileCheck %s
; RUN: opt < %s -loop-vectorize -force-vector-width=1 -force-vector-interleave=4 -S | FileCheck %s --check-prefix=CHECK-VF1

; These tests are to check that fold-tail procedure produces correct scalar code when
; loop-vectorization is only unrolling but not vectorizing.

; CHECK-REMARKS: remark: {{.*}} interleaved loop (interleaved count: 4)
; CHECK-REMARKS-NEXT: remark: {{.*}} interleaved loop (interleaved count: 4)
; CHECK-REMARKS-NOT: remark: {{.*}} vectorized loop

define void @VF1-VPlanExe() {
; CHECK-LABEL: @VF1-VPlanExe
; 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:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[INDUCTION:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[INDUCTION1:%.*]] = add i64 [[INDEX]], 1
; CHECK-NEXT: [[INDUCTION2:%.*]] = add i64 [[INDEX]], 2
; CHECK-NEXT: [[INDUCTION3:%.*]] = add i64 [[INDEX]], 3
; CHECK-NEXT: [[TMP0:%.*]] = icmp ule i64 [[INDUCTION]], 14
; CHECK-NEXT: [[TMP1:%.*]] = icmp ule i64 [[INDUCTION1]], 14
; CHECK-NEXT: [[TMP2:%.*]] = icmp ule i64 [[INDUCTION2]], 14
; CHECK-NEXT: [[TMP3:%.*]] = icmp ule i64 [[INDUCTION3]], 14
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret void
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 15
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop !2
;
entry:
br label %for.body

for.cond.cleanup:
ret void

for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 15
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}

define void @VF1-VPWidenCanonicalIVRecipeExe(double* %ptr1) {
; CHECK-LABEL: @VF1-VPWidenCanonicalIVRecipeExe
; CHECK-NEXT: entry:
; CHECK-NEXT: [[PTR2:%.*]] = getelementptr inbounds double, double* [[PTR1:%.*]], i64 15
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr double, double* [[PTR1]], i64 16
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1
; CHECK-NEXT: [[NEXT_GEP1:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP1]]
; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2
; CHECK-NEXT: [[NEXT_GEP2:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP2]]
; CHECK-NEXT: [[TMP3:%.*]] = add i64 [[INDEX]], 3
; CHECK-NEXT: [[NEXT_GEP3:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP3]]
; CHECK-NEXT: [[VEC_IV:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[VEC_IV4:%.*]] = add i64 [[INDEX]], 1
; CHECK-NEXT: [[VEC_IV5:%.*]] = add i64 [[INDEX]], 2
; CHECK-NEXT: [[VEC_IV6:%.*]] = add i64 [[INDEX]], 3
; CHECK-NEXT: [[TMP4:%.*]] = icmp ule i64 [[VEC_IV]], 14
; CHECK-NEXT: [[TMP5:%.*]] = icmp ule i64 [[VEC_IV4]], 14
; CHECK-NEXT: [[TMP6:%.*]] = icmp ule i64 [[VEC_IV5]], 14
; CHECK-NEXT: [[TMP7:%.*]] = icmp ule i64 [[VEC_IV6]], 14
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
; CHECK-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !3
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi double* [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[PTR1]], [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret void
; CHECK: for.body:
; CHECK-NEXT: [[ADDR:%.*]] = phi double* [ [[PTR:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[PTR]] = getelementptr inbounds double, double* [[ADDR]], i64 1
; CHECK-NEXT: [[COND:%.*]] = icmp eq double* [[PTR]], [[PTR2]]
; CHECK-NEXT: br i1 [[COND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop !4
;
entry:
%ptr2 = getelementptr inbounds double, double* %ptr1, i64 15
br label %for.body

for.cond.cleanup:
ret void

for.body:
%addr = phi double* [ %ptr, %for.body ], [ %ptr1, %entry ]
%ptr = getelementptr inbounds double, double* %addr, i64 1
%cond = icmp eq double* %ptr, %ptr2
br i1 %cond, label %for.cond.cleanup, label %for.body
}

; The following testcase is extended from the test of https://reviews.llvm.org/D80085
; Similar to two tests above, it is to check that fold-tail procedure produces correct scalar code when
; loop-vectorization is only unrolling but not vectorizing.

define void @pr45679(i32* %A) optsize {
; CHECK-VF1-LABEL: @pr45679
; CHECK-VF1-NEXT: entry:
; CHECK-VF1-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK-VF1: vector.ph:
; CHECK-VF1-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK-VF1: vector.body:
; CHECK-VF1-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE9:%.*]] ]
; CHECK-VF1-NEXT: [[INDUCTION:%.*]] = add i32 [[INDEX]], 0
; CHECK-VF1-NEXT: [[INDUCTION1:%.*]] = add i32 [[INDEX]], 1
; CHECK-VF1-NEXT: [[INDUCTION2:%.*]] = add i32 [[INDEX]], 2
; CHECK-VF1-NEXT: [[INDUCTION3:%.*]] = add i32 [[INDEX]], 3
; CHECK-VF1-NEXT: [[TMP0:%.*]] = icmp ule i32 [[INDUCTION]], 13
; CHECK-VF1-NEXT: [[TMP1:%.*]] = icmp ule i32 [[INDUCTION1]], 13
; CHECK-VF1-NEXT: [[TMP2:%.*]] = icmp ule i32 [[INDUCTION2]], 13
; CHECK-VF1-NEXT: [[TMP3:%.*]] = icmp ule i32 [[INDUCTION3]], 13
; CHECK-VF1-NEXT: br i1 [[TMP0]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
; CHECK-VF1: pred.store.if:
; CHECK-VF1-NEXT: [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[INDUCTION]]
; CHECK-VF1-NEXT: store i32 13, i32* [[TMP4]], align 1
; CHECK-VF1-NEXT: br label [[PRED_STORE_CONTINUE]]
; CHECK-VF1: pred.store.continue:
; CHECK-VF1-NEXT: br i1 [[TMP1]], label [[PRED_STORE_IF4:%.*]], label [[PRED_STORE_CONTINUE5:%.*]]
; CHECK-VF1: pred.store.if4:
; CHECK-VF1-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[INDUCTION1]]
; CHECK-VF1-NEXT: store i32 13, i32* [[TMP5]], align 1
; CHECK-VF1-NEXT: br label [[PRED_STORE_CONTINUE5]]
; CHECK-VF1: pred.store.continue5:
; CHECK-VF1-NEXT: br i1 [[TMP2]], label [[PRED_STORE_IF6:%.*]], label [[PRED_STORE_CONTINUE7:%.*]]
; CHECK-VF1: pred.store.if6:
; CHECK-VF1-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[INDUCTION2]]
; CHECK-VF1-NEXT: store i32 13, i32* [[TMP6]], align 1
; CHECK-VF1-NEXT: br label [[PRED_STORE_CONTINUE7]]
; CHECK-VF1: pred.store.continue7:
; CHECK-VF1-NEXT: br i1 [[TMP3]], label [[PRED_STORE_IF8:%.*]], label [[PRED_STORE_CONTINUE9]]
; CHECK-VF1: pred.store.if8:
; CHECK-VF1-NEXT: [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[INDUCTION3]]
; CHECK-VF1-NEXT: store i32 13, i32* [[TMP7]], align 1
; CHECK-VF1-NEXT: br label [[PRED_STORE_CONTINUE9]]
; CHECK-VF1: pred.store.continue9:
; CHECK-VF1-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-VF1-NEXT: [[TMP8:%.*]] = icmp eq i32 [[INDEX_NEXT]], 16
; CHECK-VF1-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]]
; CHECK-VF1: middle.block:
; CHECK-VF1-NEXT: br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK-VF1: scalar.ph:
; CHECK-VF1-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-VF1-NEXT: br label [[LOOP:%.*]]
; CHECK-VF1: loop:
; CHECK-VF1-NEXT: [[RIV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[RIVPLUS1:%.*]], [[LOOP]] ]
; CHECK-VF1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[RIV]]
; CHECK-VF1-NEXT: store i32 13, i32* [[ARRAYIDX]], align 1
; CHECK-VF1-NEXT: [[RIVPLUS1]] = add nuw nsw i32 [[RIV]], 1
; CHECK-VF1-NEXT: [[COND:%.*]] = icmp eq i32 [[RIVPLUS1]], 14
; CHECK-VF1-NEXT: br i1 [[COND]], label [[EXIT]], label [[LOOP]]
; CHECK-VF1: exit:
; CHECK-VF1-NEXT: ret void
;
entry:
br label %loop

loop:
%riv = phi i32 [ 0, %entry ], [ %rivPlus1, %loop ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %riv
store i32 13, i32* %arrayidx, align 1
%rivPlus1 = add nuw nsw i32 %riv, 1
%cond = icmp eq i32 %rivPlus1, 14
br i1 %cond, label %exit, label %loop

exit:
ret void
}

0 comments on commit 13bf603

Please sign in to comment.