| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --filter-out-after "^for.body:" --filter-out-after "^loop:" |
| ; REQUIRES: asserts |
| ; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-minimum-VF=0 \ |
| ; RUN: -prefer-predicate-over-epilogue=scalar-epilogue -debug-only=loop-vectorize \ |
| ; RUN: -force-target-instruction-cost=1 -S 2>%t | FileCheck %s --check-prefix=CHECK |
| ; RUN: cat %t | FileCheck %s --check-prefix=DEBUG |
| ; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-minimum-VF=0 \ |
| ; RUN: -prefer-predicate-over-epilogue=scalar-epilogue -debug-only=loop-vectorize \ |
| ; RUN: -force-target-instruction-cost=1 -sve-prefer-fixed-over-scalable-if-equal=false \ |
| ; RUN: -S 2>%t | FileCheck %s --check-prefix=CHECK-EPILOG-PREFER-SCALABLE |
| ; RUN: cat %t | FileCheck %s --check-prefix=DEBUG-EPILOG-PREFER-SCALABLE |
| |
| |
| target triple = "aarch64-linux-gnu" |
| |
| ; This file tests the default behavior where we prefer fixed-width epilogue loop over scalable one |
| ; when costs are equal, unless scalable is explicitly preferred. |
| |
| ; DEBUG: LV: Checking a loop in 'main_vf_vscale_x_16' |
| ; 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-EPILOG-PREFER-SCALABLE: LV: Checking a loop in 'main_vf_vscale_x_16' |
| ; DEBUG-EPILOG-PREFER-SCALABLE: Create Skeleton for epilogue vectorized loop (first pass) |
| ; DEBUG-EPILOG-PREFER-SCALABLE: Main Loop VF:vscale x 16, Main Loop UF:2, Epilogue Loop VF:vscale x 8, Epilogue Loop UF:1 |
| |
| define void @main_vf_vscale_x_16(ptr %A, i64 %n) #0 { |
| ; CHECK-LABEL: @main_vf_vscale_x_16( |
| ; CHECK-NEXT: iter.check: |
| ; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[N:%.*]], 8 |
| ; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], 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:%.*]] = shl nuw i64 [[TMP0]], 5 |
| ; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], [[TMP1]] |
| ; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]] |
| ; CHECK: vector.ph: |
| ; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 32 |
| ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]] |
| ; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[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:%.*]] = getelementptr inbounds i8, ptr [[A:%.*]], i64 [[INDEX]] |
| ; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP6:%.*]] = shl nuw i64 [[TMP5]], 4 |
| ; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i64 [[TMP6]] |
| ; CHECK-NEXT: store <vscale x 16 x i8> splat (i8 1), ptr [[TMP4]], align 1 |
| ; CHECK-NEXT: store <vscale x 16 x i8> splat (i8 1), ptr [[TMP7]], align 1 |
| ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]] |
| ; CHECK-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] |
| ; CHECK: middle.block: |
| ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[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 [[N]], [[N_VEC]] |
| ; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8 |
| ; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]], !prof [[PROF3:![0-9]+]] |
| ; 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: [[N_MOD_VF2:%.*]] = urem i64 [[N]], 8 |
| ; CHECK-NEXT: [[N_VEC3:%.*]] = sub i64 [[N]], [[N_MOD_VF2]] |
| ; CHECK-NEXT: br label [[VEC_EPILOG_VECTOR_BODY:%.*]] |
| ; CHECK: vec.epilog.vector.body: |
| ; CHECK-NEXT: [[INDEX1:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[INDEX1]] |
| ; CHECK-NEXT: store <8 x i8> splat (i8 1), ptr [[TMP9]], align 1 |
| ; CHECK-NEXT: [[INDEX_NEXT2]] = add nuw i64 [[INDEX1]], 8 |
| ; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[N_VEC3]] |
| ; CHECK-NEXT: br i1 [[TMP10]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]] |
| ; CHECK: vec.epilog.middle.block: |
| ; CHECK-NEXT: [[CMP_N6:%.*]] = icmp eq i64 [[N]], [[N_VEC3]] |
| ; CHECK-NEXT: br i1 [[CMP_N6]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]] |
| ; CHECK: vec.epilog.scalar.ph: |
| ; 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-EPILOG-PREFER-SCALABLE-LABEL: @main_vf_vscale_x_16( |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: iter.check: |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 3 |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], [[TMP1]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]] |
| ; CHECK-EPILOG-PREFER-SCALABLE: vector.main.loop.iter.check: |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 5 |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[N]], [[TMP3]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: br i1 [[MIN_ITERS_CHECK1]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]] |
| ; CHECK-EPILOG-PREFER-SCALABLE: vector.ph: |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 32 |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP5]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: br label [[VECTOR_BODY:%.*]] |
| ; CHECK-EPILOG-PREFER-SCALABLE: vector.body: |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP6:%.*]] = getelementptr inbounds i8, ptr [[A:%.*]], i64 [[INDEX]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP8:%.*]] = shl nuw i64 [[TMP7]], 4 |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP6]], i64 [[TMP8]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: store <vscale x 16 x i8> splat (i8 1), ptr [[TMP6]], align 1 |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: store <vscale x 16 x i8> splat (i8 1), ptr [[TMP9]], align 1 |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] |
| ; CHECK-EPILOG-PREFER-SCALABLE: middle.block: |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]] |
| ; CHECK-EPILOG-PREFER-SCALABLE: vec.epilog.iter.check: |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[N_VEC_REMAINING:%.*]] = sub i64 [[N]], [[N_VEC]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP11:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP12:%.*]] = shl nuw i64 [[TMP11]], 3 |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP12]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]], !prof [[PROF3:![0-9]+]] |
| ; CHECK-EPILOG-PREFER-SCALABLE: vec.epilog.ph: |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP13:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP14:%.*]] = mul nuw i64 [[TMP13]], 8 |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[N_MOD_VF2:%.*]] = urem i64 [[N]], [[TMP14]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[N_VEC3:%.*]] = sub i64 [[N]], [[N_MOD_VF2]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: br label [[VEC_EPILOG_VECTOR_BODY:%.*]] |
| ; CHECK-EPILOG-PREFER-SCALABLE: vec.epilog.vector.body: |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[INDEX4:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT5:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP15:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[INDEX4]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: store <vscale x 8 x i8> splat (i8 1), ptr [[TMP15]], align 1 |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[INDEX_NEXT5]] = add nuw i64 [[INDEX4]], [[TMP14]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT5]], [[N_VEC3]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: br i1 [[TMP16]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]] |
| ; CHECK-EPILOG-PREFER-SCALABLE: vec.epilog.middle.block: |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[CMP_N6:%.*]] = icmp eq i64 [[N]], [[N_VEC3]] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: br i1 [[CMP_N6]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]] |
| ; CHECK-EPILOG-PREFER-SCALABLE: vec.epilog.scalar.ph: |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC3]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ] |
| ; CHECK-EPILOG-PREFER-SCALABLE-NEXT: br label [[FOR_BODY:%.*]] |
| ; CHECK-EPILOG-PREFER-SCALABLE: for.body: |
| ; |
| entry: |
| br label %for.body |
| |
| for.body: |
| %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] |
| %arrayidx = getelementptr inbounds i8, ptr %A, i64 %iv |
| store i8 1, ptr %arrayidx, align 1 |
| %iv.next = add nuw nsw i64 %iv, 1 |
| %exitcond = icmp ne i64 %iv.next, %n |
| br i1 %exitcond, label %for.body, label %exit |
| |
| exit: |
| ret void |
| } |
| |
| |
| |
| attributes #0 = { "target-features"="+sve" } |
