diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -5826,7 +5826,9 @@ // consider interleaving beneficial (eg. MVE). if (TTI.getMaxInterleaveFactor(VF.getKnownMinValue()) <= 1) return false; - if (VF.getFixedValue() >= EpilogueVectorizationMinVF) + // FIXME: We should consider changing the threshold for scalable + // vectors to take VScaleForTuning into account. + if (VF.getKnownMinValue() >= EpilogueVectorizationMinVF) return true; return false; } @@ -5877,29 +5879,21 @@ return Result; } - auto FixedMainLoopVF = ElementCount::getFixed(MainLoopVF.getKnownMinValue()); - if (MainLoopVF.isScalable()) - LLVM_DEBUG( - dbgs() << "LEV: Epilogue vectorization using scalable vectors not " - "yet supported. Converting to fixed-width (VF=" - << FixedMainLoopVF << ") instead\n"); - - if (!isEpilogueVectorizationProfitable(FixedMainLoopVF)) { + if (!isEpilogueVectorizationProfitable(MainLoopVF)) { LLVM_DEBUG(dbgs() << "LEV: Epilogue vectorization is not profitable for " "this loop\n"); return Result; } for (auto &NextVF : ProfitableVFs) - if (ElementCount::isKnownLT(NextVF.Width, FixedMainLoopVF) && - (Result.Width.getFixedValue() == 1 || - isMoreProfitable(NextVF, Result)) && + if (ElementCount::isKnownLT(NextVF.Width, MainLoopVF) && + (Result.Width.isScalar() || isMoreProfitable(NextVF, Result)) && LVP.hasPlanWithVF(NextVF.Width)) Result = NextVF; if (Result != VectorizationFactor::Disabled()) LLVM_DEBUG(dbgs() << "LEV: Vectorizing epilogue loop with VF = " - << Result.Width.getFixedValue() << "\n";); + << Result.Width << "\n";); return Result; } diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll --- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll @@ -1,18 +1,17 @@ ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; REQUIRES: asserts -; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-minimum-VF=0 --debug-only=loop-vectorize -force-target-instruction-cost=1 -S 2>%t | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-minimum-VF=0 --debug-only=loop-vectorize -force-target-instruction-cost=1 -S 2>%t | FileCheck %s --check-prefix=CHECK ; RUN: cat %t | FileCheck %s --check-prefix=DEBUG -; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-minimum-VF=8 --debug-only=loop-vectorize -S 2>%t | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-minimum-VF=8 --debug-only=loop-vectorize -S 2>%t | FileCheck %s --check-prefix=CHECK ; RUN: cat %t | FileCheck %s --check-prefix=DEBUG -; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-force-VF=8 --debug-only=loop-vectorize -S 2>%t | FileCheck %s +; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-force-VF=8 --debug-only=loop-vectorize -S 2>%t | FileCheck %s --check-prefix=CHECK-VF8 ; RUN: cat %t | FileCheck %s --check-prefix=DEBUG-FORCED target triple = "aarch64-linux-gnu" ; DEBUG: LV: Checking a loop in "f1" -; DEBUG: LEV: Epilogue vectorization using scalable vectors not yet supported. Converting to fixed-width (VF=16) instead ; DEBUG: Create Skeleton for epilogue vectorized loop (first pass) -; DEBUG: Main Loop VF:vscale x 16, Main Loop UF:2, Epilogue Loop VF:8, Epilogue Loop UF:1 +; DEBUG: Main Loop VF:vscale x 16, Main Loop UF:2, Epilogue Loop VF:vscale x 8, Epilogue Loop UF:1 ; DEBUG-FORCED: LV: Checking a loop in "f1" ; DEBUG-FORCED: LEV: Epilogue vectorization factor is forced. @@ -22,66 +21,77 @@ define void @f1(i8* %A) #0 { ; CHECK-LABEL: @f1( ; CHECK-NEXT: iter.check: -; CHECK-NEXT: br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]] -; CHECK: vector.main.loop.iter.check: ; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64() -; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 32 +; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 8 ; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]] -; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]] -; CHECK: vector.ph: +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]] +; CHECK: vector.main.loop.iter.check: ; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64() ; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 32 -; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]] +; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 1024, [[TMP3]] +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]] +; CHECK: vector.ph: +; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64() +; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 32 +; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP5]] ; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]] ; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] ; CHECK: vector.body: ; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] -; CHECK-NEXT: [[TMP4:%.*]] = add i64 [[INDEX]], 0 -; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64() -; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 16 -; CHECK-NEXT: [[TMP7:%.*]] = add i64 [[TMP6]], 0 -; CHECK-NEXT: [[TMP8:%.*]] = mul i64 [[TMP7]], 1 -; CHECK-NEXT: [[TMP9:%.*]] = add i64 [[INDEX]], [[TMP8]] -; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[A:%.*]], i64 [[TMP4]] -; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP9]] -; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, i8* [[TMP10]], i32 0 -; CHECK-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to * -; CHECK-NEXT: store shufflevector ( insertelement ( poison, i8 1, i32 0), poison, zeroinitializer), * [[TMP13]], align 1 -; CHECK-NEXT: [[TMP14:%.*]] = call i32 @llvm.vscale.i32() -; CHECK-NEXT: [[TMP15:%.*]] = mul i32 [[TMP14]], 16 -; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, i8* [[TMP10]], i32 [[TMP15]] -; CHECK-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to * -; CHECK-NEXT: store shufflevector ( insertelement ( poison, i8 1, i32 0), poison, zeroinitializer), * [[TMP17]], align 1 -; CHECK-NEXT: [[TMP18:%.*]] = call i64 @llvm.vscale.i64() -; CHECK-NEXT: [[TMP19:%.*]] = mul i64 [[TMP18]], 32 -; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP19]] -; CHECK-NEXT: [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] -; CHECK-NEXT: br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] +; CHECK-NEXT: [[TMP6:%.*]] = add i64 [[INDEX]], 0 +; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64() +; CHECK-NEXT: [[TMP8:%.*]] = mul i64 [[TMP7]], 16 +; CHECK-NEXT: [[TMP9:%.*]] = add i64 [[TMP8]], 0 +; CHECK-NEXT: [[TMP10:%.*]] = mul i64 [[TMP9]], 1 +; CHECK-NEXT: [[TMP11:%.*]] = add i64 [[INDEX]], [[TMP10]] +; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, i8* [[A:%.*]], i64 [[TMP6]] +; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP11]] +; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, i8* [[TMP12]], i32 0 +; CHECK-NEXT: [[TMP15:%.*]] = bitcast i8* [[TMP14]] to * +; CHECK-NEXT: store shufflevector ( insertelement ( poison, i8 1, i32 0), poison, zeroinitializer), * [[TMP15]], align 1 +; CHECK-NEXT: [[TMP16:%.*]] = call i32 @llvm.vscale.i32() +; CHECK-NEXT: [[TMP17:%.*]] = mul i32 [[TMP16]], 16 +; CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds i8, i8* [[TMP12]], i32 [[TMP17]] +; CHECK-NEXT: [[TMP19:%.*]] = bitcast i8* [[TMP18]] to * +; CHECK-NEXT: store shufflevector ( insertelement ( poison, i8 1, i32 0), poison, zeroinitializer), * [[TMP19]], align 1 +; CHECK-NEXT: [[TMP20:%.*]] = call i64 @llvm.vscale.i64() +; CHECK-NEXT: [[TMP21:%.*]] = mul i64 [[TMP20]], 32 +; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP21]] +; CHECK-NEXT: [[TMP22:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] +; CHECK-NEXT: br i1 [[TMP22]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] ; CHECK: middle.block: ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]] ; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]] ; CHECK: vec.epilog.iter.check: ; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i64 1024, [[N_VEC]] -; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8 +; CHECK-NEXT: [[TMP23:%.*]] = call i64 @llvm.vscale.i64() +; CHECK-NEXT: [[TMP24:%.*]] = mul i64 [[TMP23]], 8 +; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP24]] ; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]] ; CHECK: vec.epilog.ph: ; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[TMP25:%.*]] = call i64 @llvm.vscale.i64() +; CHECK-NEXT: [[TMP26:%.*]] = mul i64 [[TMP25]], 8 +; CHECK-NEXT: [[N_MOD_VF2:%.*]] = urem i64 1024, [[TMP26]] +; CHECK-NEXT: [[N_VEC3:%.*]] = sub i64 1024, [[N_MOD_VF2]] ; CHECK-NEXT: br label [[VEC_EPILOG_VECTOR_BODY:%.*]] ; CHECK: vec.epilog.vector.body: -; CHECK-NEXT: [[INDEX4:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT3:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] -; CHECK-NEXT: [[TMP21:%.*]] = add i64 [[INDEX4]], 0 -; CHECK-NEXT: [[TMP22:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP21]] -; CHECK-NEXT: [[TMP23:%.*]] = getelementptr inbounds i8, i8* [[TMP22]], i32 0 -; CHECK-NEXT: [[TMP24:%.*]] = bitcast i8* [[TMP23]] to <8 x i8>* -; CHECK-NEXT: store <8 x i8> , <8 x i8>* [[TMP24]], align 1 -; CHECK-NEXT: [[INDEX_NEXT3]] = add nuw i64 [[INDEX4]], 8 -; CHECK-NEXT: [[TMP25:%.*]] = icmp eq i64 [[INDEX_NEXT3]], 1024 -; CHECK-NEXT: br i1 [[TMP25]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]] +; CHECK-NEXT: [[INDEX5:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT6:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[TMP27:%.*]] = add i64 [[INDEX5]], 0 +; CHECK-NEXT: [[TMP28:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP27]] +; CHECK-NEXT: [[TMP29:%.*]] = getelementptr inbounds i8, i8* [[TMP28]], i32 0 +; CHECK-NEXT: [[TMP30:%.*]] = bitcast i8* [[TMP29]] to * +; CHECK-NEXT: store shufflevector ( insertelement ( poison, i8 1, i32 0), poison, zeroinitializer), * [[TMP30]], align 1 +; CHECK-NEXT: [[TMP31:%.*]] = call i64 @llvm.vscale.i64() +; CHECK-NEXT: [[TMP32:%.*]] = mul i64 [[TMP31]], 8 +; CHECK-NEXT: [[INDEX_NEXT6]] = add nuw i64 [[INDEX5]], [[TMP32]] +; CHECK-NEXT: [[TMP33:%.*]] = icmp eq i64 [[INDEX_NEXT6]], [[N_VEC3]] +; CHECK-NEXT: br i1 [[TMP33]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]] ; CHECK: vec.epilog.middle.block: -; CHECK-NEXT: [[CMP_N1:%.*]] = icmp eq i64 1024, 1024 -; CHECK-NEXT: br i1 [[CMP_N1]], label [[EXIT_LOOPEXIT:%.*]], label [[VEC_EPILOG_SCALAR_PH]] +; CHECK-NEXT: [[CMP_N4:%.*]] = icmp eq i64 1024, [[N_VEC3]] +; CHECK-NEXT: br i1 [[CMP_N4]], label [[EXIT_LOOPEXIT:%.*]], label [[VEC_EPILOG_SCALAR_PH]] ; CHECK: vec.epilog.scalar.ph: -; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ] +; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC3]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ] ; CHECK-NEXT: br label [[FOR_BODY:%.*]] ; CHECK: for.body: ; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ] @@ -95,7 +105,81 @@ ; CHECK: exit: ; CHECK-NEXT: ret void ; - +; CHECK-VF8-LABEL: @f1( +; CHECK-VF8-NEXT: iter.check: +; CHECK-VF8-NEXT: br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]] +; CHECK-VF8: vector.main.loop.iter.check: +; CHECK-VF8-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64() +; CHECK-VF8-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 32 +; CHECK-VF8-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]] +; CHECK-VF8-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]] +; CHECK-VF8: vector.ph: +; CHECK-VF8-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64() +; CHECK-VF8-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 32 +; CHECK-VF8-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]] +; CHECK-VF8-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]] +; CHECK-VF8-NEXT: br label [[VECTOR_BODY:%.*]] +; CHECK-VF8: vector.body: +; CHECK-VF8-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; CHECK-VF8-NEXT: [[TMP4:%.*]] = add i64 [[INDEX]], 0 +; CHECK-VF8-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64() +; CHECK-VF8-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 16 +; CHECK-VF8-NEXT: [[TMP7:%.*]] = add i64 [[TMP6]], 0 +; CHECK-VF8-NEXT: [[TMP8:%.*]] = mul i64 [[TMP7]], 1 +; CHECK-VF8-NEXT: [[TMP9:%.*]] = add i64 [[INDEX]], [[TMP8]] +; CHECK-VF8-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[A:%.*]], i64 [[TMP4]] +; CHECK-VF8-NEXT: [[TMP11:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP9]] +; CHECK-VF8-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, i8* [[TMP10]], i32 0 +; CHECK-VF8-NEXT: [[TMP13:%.*]] = bitcast i8* [[TMP12]] to * +; CHECK-VF8-NEXT: store shufflevector ( insertelement ( poison, i8 1, i32 0), poison, zeroinitializer), * [[TMP13]], align 1 +; CHECK-VF8-NEXT: [[TMP14:%.*]] = call i32 @llvm.vscale.i32() +; CHECK-VF8-NEXT: [[TMP15:%.*]] = mul i32 [[TMP14]], 16 +; CHECK-VF8-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, i8* [[TMP10]], i32 [[TMP15]] +; CHECK-VF8-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to * +; CHECK-VF8-NEXT: store shufflevector ( insertelement ( poison, i8 1, i32 0), poison, zeroinitializer), * [[TMP17]], align 1 +; CHECK-VF8-NEXT: [[TMP18:%.*]] = call i64 @llvm.vscale.i64() +; CHECK-VF8-NEXT: [[TMP19:%.*]] = mul i64 [[TMP18]], 32 +; CHECK-VF8-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP19]] +; CHECK-VF8-NEXT: [[TMP20:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] +; CHECK-VF8-NEXT: br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] +; CHECK-VF8: middle.block: +; CHECK-VF8-NEXT: [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]] +; CHECK-VF8-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]] +; CHECK-VF8: vec.epilog.iter.check: +; CHECK-VF8-NEXT: [[N_VEC_REMAINING:%.*]] = sub i64 1024, [[N_VEC]] +; CHECK-VF8-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8 +; CHECK-VF8-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]] +; CHECK-VF8: vec.epilog.ph: +; CHECK-VF8-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-VF8-NEXT: br label [[VEC_EPILOG_VECTOR_BODY:%.*]] +; CHECK-VF8: vec.epilog.vector.body: +; CHECK-VF8-NEXT: [[INDEX2:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT3:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-VF8-NEXT: [[TMP21:%.*]] = add i64 [[INDEX2]], 0 +; CHECK-VF8-NEXT: [[TMP22:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[TMP21]] +; CHECK-VF8-NEXT: [[TMP23:%.*]] = getelementptr inbounds i8, i8* [[TMP22]], i32 0 +; CHECK-VF8-NEXT: [[TMP24:%.*]] = bitcast i8* [[TMP23]] to <8 x i8>* +; CHECK-VF8-NEXT: store <8 x i8> , <8 x i8>* [[TMP24]], align 1 +; CHECK-VF8-NEXT: [[INDEX_NEXT3]] = add nuw i64 [[INDEX2]], 8 +; CHECK-VF8-NEXT: [[TMP25:%.*]] = icmp eq i64 [[INDEX_NEXT3]], 1024 +; CHECK-VF8-NEXT: br i1 [[TMP25]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]] +; CHECK-VF8: vec.epilog.middle.block: +; CHECK-VF8-NEXT: [[CMP_N1:%.*]] = icmp eq i64 1024, 1024 +; CHECK-VF8-NEXT: br i1 [[CMP_N1]], label [[EXIT_LOOPEXIT:%.*]], label [[VEC_EPILOG_SCALAR_PH]] +; CHECK-VF8: vec.epilog.scalar.ph: +; CHECK-VF8-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ] +; CHECK-VF8-NEXT: br label [[FOR_BODY:%.*]] +; CHECK-VF8: for.body: +; CHECK-VF8-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ] +; CHECK-VF8-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[A]], i64 [[IV]] +; CHECK-VF8-NEXT: store i8 1, i8* [[ARRAYIDX]], align 1 +; CHECK-VF8-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1 +; CHECK-VF8-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[IV_NEXT]], 1024 +; CHECK-VF8-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[EXIT_LOOPEXIT]], !llvm.loop [[LOOP4:![0-9]+]] +; CHECK-VF8: exit.loopexit: +; CHECK-VF8-NEXT: br label [[EXIT]] +; CHECK-VF8: exit: +; CHECK-VF8-NEXT: ret void +; entry: br label %for.body