| ; 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 -prefer-predicate-over-epilogue=scalar-epilogue \ |
| ; RUN: -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 -passes=loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-force-VF=8 \ |
| ; RUN: -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 'main_vf_vscale_x_16' |
| ; DEBUG-NOT: Create Skeleton for epilogue vectorized loop (first pass) |
| ; DEBUG: Executing best plan with VF=vscale x 16, UF=2 |
| |
| ; DEBUG-FORCED: LV: Checking a loop in 'main_vf_vscale_x_16' |
| ; DEBUG-FORCED: LEV: Epilogue vectorization factor is forced. |
| ; DEBUG-FORCED: Create Skeleton for epilogue vectorized loop (first pass) |
| ; DEBUG-FORCED: Main Loop VF:vscale x 16, Main Loop UF:2, Epilogue Loop VF:8, Epilogue Loop UF:1 |
| |
| define void @main_vf_vscale_x_16(ptr %A) #0 { |
| ; CHECK-LABEL: @main_vf_vscale_x_16( |
| ; CHECK-NEXT: entry: |
| ; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 5 |
| ; 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: [[TMP2:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 32 |
| ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]] |
| ; 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:%.*]] = 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 [[VEC_EPILOG_ITER_CHECK:%.*]], 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_PH]] |
| ; CHECK: scalar.ph: |
| ; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]] ] |
| ; CHECK-NEXT: br label [[FOR_BODY:%.*]] |
| ; CHECK: for.body: |
| ; |
| ; CHECK-VF8-LABEL: @main_vf_vscale_x_16( |
| ; 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:%.*]] = shl nuw i64 [[TMP0]], 5 |
| ; 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 nuw 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:%.*]] = getelementptr inbounds i8, ptr [[A:%.*]], i64 [[INDEX]] |
| ; CHECK-VF8-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[TMP6:%.*]] = shl nuw i64 [[TMP5]], 4 |
| ; CHECK-VF8-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i64 [[TMP6]] |
| ; CHECK-VF8-NEXT: store <vscale x 16 x i8> splat (i8 1), ptr [[TMP4]], align 1 |
| ; CHECK-VF8-NEXT: store <vscale x 16 x i8> splat (i8 1), ptr [[TMP7]], align 1 |
| ; CHECK-VF8-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]] |
| ; CHECK-VF8-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-VF8-NEXT: br i1 [[TMP8]], 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: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_MOD_VF]], 8 |
| ; CHECK-VF8-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]], !prof [[PROF3:![0-9]+]] |
| ; 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: [[INDEX1:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-VF8-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[INDEX1]] |
| ; CHECK-VF8-NEXT: store <8 x i8> splat (i8 1), ptr [[TMP9]], align 1 |
| ; CHECK-VF8-NEXT: [[INDEX_NEXT2]] = add nuw i64 [[INDEX1]], 8 |
| ; CHECK-VF8-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT2]], 1024 |
| ; CHECK-VF8-NEXT: br i1 [[TMP10]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]] |
| ; CHECK-VF8: vec.epilog.middle.block: |
| ; CHECK-VF8-NEXT: br i1 true, label [[EXIT]], 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: |
| ; |
| 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, 1024 |
| br i1 %exitcond, label %for.body, label %exit |
| |
| exit: |
| ret void |
| } |
| |
| define void @main_vf_vscale_x_2_no_epi_iteration(ptr %A) #0 vscale_range(8, 8) { |
| ; CHECK-LABEL: @main_vf_vscale_x_2_no_epi_iteration( |
| ; CHECK-NEXT: entry: |
| ; CHECK-NEXT: br label [[VECTOR_PH:%.*]] |
| ; CHECK: vector.ph: |
| ; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 4 |
| ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP1]] |
| ; 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: [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]] |
| ; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP4:%.*]] = shl nuw i64 [[TMP3]], 1 |
| ; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[TMP2]], i64 [[TMP4]] |
| ; CHECK-NEXT: store <vscale x 2 x i64> splat (i64 1), ptr [[TMP2]], align 1 |
| ; CHECK-NEXT: store <vscale x 2 x i64> splat (i64 1), ptr [[TMP5]], align 1 |
| ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP1]] |
| ; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]] |
| ; CHECK: middle.block: |
| ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH:%.*]] |
| ; CHECK: scalar.ph: |
| ; CHECK-NEXT: br label [[FOR_BODY:%.*]] |
| ; CHECK: for.body: |
| ; |
| ; CHECK-VF8-LABEL: @main_vf_vscale_x_2_no_epi_iteration( |
| ; 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:%.*]] = shl nuw i64 [[TMP0]], 2 |
| ; 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 nuw i64 [[TMP2]], 4 |
| ; 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:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]] |
| ; CHECK-VF8-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[TMP6:%.*]] = shl nuw i64 [[TMP5]], 1 |
| ; CHECK-VF8-NEXT: [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[TMP4]], i64 [[TMP6]] |
| ; CHECK-VF8-NEXT: store <vscale x 2 x i64> splat (i64 1), ptr [[TMP4]], align 1 |
| ; CHECK-VF8-NEXT: store <vscale x 2 x i64> splat (i64 1), ptr [[TMP7]], align 1 |
| ; CHECK-VF8-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]] |
| ; CHECK-VF8-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-VF8-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![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: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_MOD_VF]], 8 |
| ; CHECK-VF8-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]], !prof [[PROF3]] |
| ; 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: [[INDEX1:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-VF8-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX1]] |
| ; CHECK-VF8-NEXT: store <8 x i64> splat (i64 1), ptr [[TMP9]], align 1 |
| ; CHECK-VF8-NEXT: [[INDEX_NEXT2]] = add nuw i64 [[INDEX1]], 8 |
| ; CHECK-VF8-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT2]], 1024 |
| ; CHECK-VF8-NEXT: br i1 [[TMP10]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]] |
| ; CHECK-VF8: vec.epilog.middle.block: |
| ; CHECK-VF8-NEXT: br i1 true, label [[EXIT]], 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: |
| ; |
| entry: |
| br label %for.body |
| |
| for.body: |
| %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] |
| %arrayidx = getelementptr inbounds i64, ptr %A, i64 %iv |
| store i64 1, ptr %arrayidx, align 1 |
| %iv.next = add nuw nsw i64 %iv, 1 |
| %exitcond = icmp ne i64 %iv.next, 1024 |
| br i1 %exitcond, label %for.body, label %exit |
| |
| exit: |
| ret void |
| } |
| |
| ; DEBUG: LV: Checking a loop in 'main_vf_vscale_x_2' |
| ; DEBUG: Create Skeleton for epilogue vectorized loop (first pass) |
| ; DEBUG: Main Loop VF:vscale x 2, Main Loop UF:2, Epilogue Loop VF:8, Epilogue Loop UF:1 |
| |
| ; DEBUG-FORCED: LV: Checking a loop in 'main_vf_vscale_x_2' |
| ; DEBUG-FORCED: LEV: Epilogue vectorization factor is forced. |
| ; DEBUG-FORCED: Create Skeleton for epilogue vectorized loop (first pass) |
| ; DEBUG-FORCED: Main Loop VF:vscale x 2, Main Loop UF:2, Epilogue Loop VF:8, Epilogue Loop UF:1 |
| |
| ; When the vector.body uses VF=vscale x 1 (or VF=vscale x 2 because |
| ; that's the minimum supported VF by SVE), we could still use a wide |
| ; fixed-width VF=8 for the epilogue if the vectors are known to be |
| ; sufficiently wide. This information can be deduced from vscale_range or |
| ; VScaleForTuning (set by mcpu/mtune). |
| define void @main_vf_vscale_x_2(ptr %A, i64 %n) #0 vscale_range(8, 8) { |
| ; CHECK-LABEL: @main_vf_vscale_x_2( |
| ; CHECK-NEXT: iter.check: |
| ; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], 8 |
| ; 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: [[TMP0:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 2 |
| ; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[N]], [[TMP1]] |
| ; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], 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]], 4 |
| ; 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 i64, ptr [[A:%.*]], i64 [[INDEX]] |
| ; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP6:%.*]] = shl nuw i64 [[TMP5]], 1 |
| ; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[TMP4]], i64 [[TMP6]] |
| ; CHECK-NEXT: store <vscale x 2 x i64> splat (i64 1), ptr [[TMP4]], align 1 |
| ; CHECK-NEXT: store <vscale x 2 x i64> splat (i64 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 [[LOOP6:![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: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_MOD_VF]], 8 |
| ; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]], !prof [[PROF7:![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: [[INDEX4:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT5:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX4]] |
| ; CHECK-NEXT: store <8 x i64> splat (i64 1), ptr [[TMP9]], align 1 |
| ; CHECK-NEXT: [[INDEX_NEXT5]] = add nuw i64 [[INDEX4]], 8 |
| ; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT5]], [[N_VEC3]] |
| ; CHECK-NEXT: br i1 [[TMP10]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP8:![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-VF8-LABEL: @main_vf_vscale_x_2( |
| ; CHECK-VF8-NEXT: iter.check: |
| ; CHECK-VF8-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], 8 |
| ; CHECK-VF8-NEXT: br i1 [[MIN_ITERS_CHECK]], 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:%.*]] = shl nuw i64 [[TMP0]], 2 |
| ; CHECK-VF8-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[N]], [[TMP1]] |
| ; CHECK-VF8-NEXT: br i1 [[MIN_ITERS_CHECK1]], 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 nuw i64 [[TMP2]], 4 |
| ; CHECK-VF8-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]] |
| ; CHECK-VF8-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[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:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]] |
| ; CHECK-VF8-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[TMP6:%.*]] = shl nuw i64 [[TMP5]], 1 |
| ; CHECK-VF8-NEXT: [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[TMP4]], i64 [[TMP6]] |
| ; CHECK-VF8-NEXT: store <vscale x 2 x i64> splat (i64 1), ptr [[TMP4]], align 1 |
| ; CHECK-VF8-NEXT: store <vscale x 2 x i64> splat (i64 1), ptr [[TMP7]], align 1 |
| ; CHECK-VF8-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]] |
| ; CHECK-VF8-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-VF8-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]] |
| ; CHECK-VF8: middle.block: |
| ; CHECK-VF8-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[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: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_MOD_VF]], 8 |
| ; CHECK-VF8-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]], !prof [[PROF3]] |
| ; 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: [[N_MOD_VF2:%.*]] = urem i64 [[N]], 8 |
| ; CHECK-VF8-NEXT: [[N_VEC3:%.*]] = sub i64 [[N]], [[N_MOD_VF2]] |
| ; CHECK-VF8-NEXT: br label [[VEC_EPILOG_VECTOR_BODY:%.*]] |
| ; CHECK-VF8: vec.epilog.vector.body: |
| ; CHECK-VF8-NEXT: [[INDEX4:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT5:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-VF8-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX4]] |
| ; CHECK-VF8-NEXT: store <8 x i64> splat (i64 1), ptr [[TMP9]], align 1 |
| ; CHECK-VF8-NEXT: [[INDEX_NEXT5]] = add nuw i64 [[INDEX4]], 8 |
| ; CHECK-VF8-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT5]], [[N_VEC3]] |
| ; CHECK-VF8-NEXT: br i1 [[TMP10]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]] |
| ; CHECK-VF8: vec.epilog.middle.block: |
| ; CHECK-VF8-NEXT: [[CMP_N6:%.*]] = icmp eq i64 [[N]], [[N_VEC3]] |
| ; CHECK-VF8-NEXT: br i1 [[CMP_N6]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]] |
| ; CHECK-VF8: vec.epilog.scalar.ph: |
| ; CHECK-VF8-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC3]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ] |
| ; CHECK-VF8-NEXT: br label [[FOR_BODY:%.*]] |
| ; CHECK-VF8: for.body: |
| ; |
| entry: |
| br label %for.body |
| |
| for.body: |
| %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] |
| %arrayidx = getelementptr inbounds i64, ptr %A, i64 %iv |
| store i64 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 |
| } |
| |
| ; FIXME: The epilogue loop is currently miscompiled: the pointer induction |
| ; uses an incorrect resume value. |
| define void @test_pr57912_pointer_induction(ptr %start) #0 { |
| ; CHECK-LABEL: @test_pr57912_pointer_induction( |
| ; 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:%.*]] = shl nuw i64 [[TMP0]], 5 |
| ; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 10000, [[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 10000, [[TMP3]] |
| ; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 10000, [[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: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START:%.*]], i64 [[INDEX]] |
| ; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP5:%.*]] = shl nuw i64 [[TMP4]], 4 |
| ; CHECK-NEXT: [[TMP6:%.*]] = getelementptr i8, ptr [[NEXT_GEP]], i64 [[TMP5]] |
| ; CHECK-NEXT: store <vscale x 16 x i8> zeroinitializer, ptr [[NEXT_GEP]], align 1 |
| ; CHECK-NEXT: store <vscale x 16 x i8> zeroinitializer, ptr [[TMP6]], align 1 |
| ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]] |
| ; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]] |
| ; CHECK: middle.block: |
| ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 10000, [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]] |
| ; CHECK: vec.epilog.iter.check: |
| ; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC]] |
| ; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_MOD_VF]], 8 |
| ; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]], !prof [[PROF7]] |
| ; 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: [[TMP8:%.*]] = getelementptr i8, ptr [[START]], i64 10000 |
| ; 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_NEXT3:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[NEXT_GEP2:%.*]] = getelementptr i8, ptr [[START]], i64 [[INDEX1]] |
| ; CHECK-NEXT: store <8 x i8> zeroinitializer, ptr [[NEXT_GEP2]], align 1 |
| ; CHECK-NEXT: [[INDEX_NEXT3]] = add nuw i64 [[INDEX1]], 8 |
| ; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT3]], 10000 |
| ; CHECK-NEXT: br i1 [[TMP9]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]] |
| ; CHECK: vec.epilog.middle.block: |
| ; CHECK-NEXT: br i1 true, label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]] |
| ; CHECK: vec.epilog.scalar.ph: |
| ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 10000, [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ] |
| ; CHECK-NEXT: [[BC_RESUME_VAL4:%.*]] = phi ptr [ [[TMP8]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END]], [[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], [[ITER_CHECK]] ] |
| ; CHECK-NEXT: br label [[LOOP:%.*]] |
| ; CHECK: loop: |
| ; |
| ; CHECK-VF8-LABEL: @test_pr57912_pointer_induction( |
| ; 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:%.*]] = shl nuw i64 [[TMP0]], 5 |
| ; CHECK-VF8-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 10000, [[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 nuw i64 [[TMP2]], 32 |
| ; CHECK-VF8-NEXT: [[N_MOD_VF:%.*]] = urem i64 10000, [[TMP3]] |
| ; CHECK-VF8-NEXT: [[N_VEC:%.*]] = sub i64 10000, [[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: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START:%.*]], i64 [[INDEX]] |
| ; CHECK-VF8-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[TMP5:%.*]] = shl nuw i64 [[TMP4]], 4 |
| ; CHECK-VF8-NEXT: [[TMP6:%.*]] = getelementptr i8, ptr [[NEXT_GEP]], i64 [[TMP5]] |
| ; CHECK-VF8-NEXT: store <vscale x 16 x i8> zeroinitializer, ptr [[NEXT_GEP]], align 1 |
| ; CHECK-VF8-NEXT: store <vscale x 16 x i8> zeroinitializer, ptr [[TMP6]], align 1 |
| ; CHECK-VF8-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]] |
| ; CHECK-VF8-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-VF8-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]] |
| ; CHECK-VF8: middle.block: |
| ; CHECK-VF8-NEXT: [[CMP_N:%.*]] = icmp eq i64 10000, [[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: [[IND_END:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC]] |
| ; CHECK-VF8-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_MOD_VF]], 8 |
| ; CHECK-VF8-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]], !prof [[PROF3]] |
| ; 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: [[TMP8:%.*]] = getelementptr i8, ptr [[START]], i64 10000 |
| ; CHECK-VF8-NEXT: br label [[VEC_EPILOG_VECTOR_BODY:%.*]] |
| ; CHECK-VF8: vec.epilog.vector.body: |
| ; CHECK-VF8-NEXT: [[INDEX1:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT3:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-VF8-NEXT: [[NEXT_GEP2:%.*]] = getelementptr i8, ptr [[START]], i64 [[INDEX1]] |
| ; CHECK-VF8-NEXT: store <8 x i8> zeroinitializer, ptr [[NEXT_GEP2]], align 1 |
| ; CHECK-VF8-NEXT: [[INDEX_NEXT3]] = add nuw i64 [[INDEX1]], 8 |
| ; CHECK-VF8-NEXT: [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT3]], 10000 |
| ; CHECK-VF8-NEXT: br i1 [[TMP9]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]] |
| ; CHECK-VF8: vec.epilog.middle.block: |
| ; CHECK-VF8-NEXT: br i1 true, label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]] |
| ; CHECK-VF8: vec.epilog.scalar.ph: |
| ; CHECK-VF8-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 10000, [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ] |
| ; CHECK-VF8-NEXT: [[BC_RESUME_VAL4:%.*]] = phi ptr [ [[TMP8]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END]], [[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], [[ITER_CHECK]] ] |
| ; CHECK-VF8-NEXT: br label [[LOOP:%.*]] |
| ; CHECK-VF8: loop: |
| ; |
| entry: |
| br label %loop |
| |
| loop: |
| %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ] |
| %ptr.iv = phi ptr [ %start, %entry ], [ %ptr.iv.next, %loop ] |
| store i8 0, ptr %ptr.iv, align 1 |
| %ptr.iv.next = getelementptr inbounds i8, ptr %ptr.iv, i64 1 |
| %iv.next = add nuw nsw i64 %iv, 1 |
| %cmp = icmp eq i64 %iv.next, 10000 |
| br i1 %cmp, label %exit, label %loop |
| |
| exit: |
| ret void |
| } |
| |
| ; Loop with vscale-based trip count vscale x 1033. |
| define void @trip_count_vscale(ptr noalias %a, ptr noalias %b) vscale_range(1, 16) #0 { |
| ; CHECK-LABEL: @trip_count_vscale( |
| ; CHECK-NEXT: iter.check: |
| ; CHECK-NEXT: [[V:%.*]] = tail call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[N:%.*]] = mul nuw nsw i64 [[V]], 1033 |
| ; 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:%.*]] = shl nuw i64 [[TMP0]], 3 |
| ; 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]], 8 |
| ; 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 nuw float, ptr [[A:%.*]], i64 [[INDEX]] |
| ; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP6:%.*]] = shl nuw i64 [[TMP5]], 2 |
| ; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds nuw float, ptr [[TMP4]], i64 [[TMP6]] |
| ; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x float>, ptr [[TMP4]], align 4 |
| ; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <vscale x 4 x float>, ptr [[TMP7]], align 4 |
| ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds nuw float, ptr [[B:%.*]], i64 [[INDEX]] |
| ; CHECK-NEXT: [[TMP9:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP10:%.*]] = shl nuw i64 [[TMP9]], 2 |
| ; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds nuw float, ptr [[TMP8]], i64 [[TMP10]] |
| ; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <vscale x 4 x float>, ptr [[TMP8]], align 4 |
| ; CHECK-NEXT: [[WIDE_LOAD3:%.*]] = load <vscale x 4 x float>, ptr [[TMP11]], align 4 |
| ; CHECK-NEXT: [[TMP12:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD]], [[WIDE_LOAD2]] |
| ; CHECK-NEXT: [[TMP13:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD1]], [[WIDE_LOAD3]] |
| ; CHECK-NEXT: store <vscale x 4 x float> [[TMP12]], ptr [[TMP8]], align 4 |
| ; CHECK-NEXT: store <vscale x 4 x float> [[TMP13]], ptr [[TMP11]], align 4 |
| ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]] |
| ; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP13:![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: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_MOD_VF]], 2 |
| ; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]], !prof [[PROF14:![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_VF4:%.*]] = urem i64 [[N]], 2 |
| ; CHECK-NEXT: [[N_VEC5:%.*]] = sub i64 [[N]], [[N_MOD_VF4]] |
| ; CHECK-NEXT: br label [[VEC_EPILOG_VECTOR_BODY:%.*]] |
| ; CHECK: vec.epilog.vector.body: |
| ; CHECK-NEXT: [[INDEX6:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT9:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds nuw float, ptr [[A]], i64 [[INDEX6]] |
| ; CHECK-NEXT: [[WIDE_LOAD7:%.*]] = load <2 x float>, ptr [[TMP15]], align 4 |
| ; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds nuw float, ptr [[B]], i64 [[INDEX6]] |
| ; CHECK-NEXT: [[WIDE_LOAD8:%.*]] = load <2 x float>, ptr [[TMP16]], align 4 |
| ; CHECK-NEXT: [[TMP17:%.*]] = fmul <2 x float> [[WIDE_LOAD7]], [[WIDE_LOAD8]] |
| ; CHECK-NEXT: store <2 x float> [[TMP17]], ptr [[TMP16]], align 4 |
| ; CHECK-NEXT: [[INDEX_NEXT9]] = add nuw i64 [[INDEX6]], 2 |
| ; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT9]], [[N_VEC5]] |
| ; CHECK-NEXT: br i1 [[TMP18]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]] |
| ; CHECK: vec.epilog.middle.block: |
| ; CHECK-NEXT: [[CMP_N10:%.*]] = icmp eq i64 [[N]], [[N_VEC5]] |
| ; CHECK-NEXT: br i1 [[CMP_N10]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]] |
| ; CHECK: vec.epilog.scalar.ph: |
| ; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC5]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ] |
| ; CHECK-NEXT: br label [[FOR_BODY:%.*]] |
| ; CHECK: for.body: |
| ; |
| ; CHECK-VF8-LABEL: @trip_count_vscale( |
| ; CHECK-VF8-NEXT: entry: |
| ; CHECK-VF8-NEXT: [[V:%.*]] = tail call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[N:%.*]] = mul nuw nsw i64 [[V]], 1033 |
| ; CHECK-VF8-NEXT: br label [[VECTOR_PH:%.*]] |
| ; CHECK-VF8: vector.ph: |
| ; CHECK-VF8-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 8 |
| ; CHECK-VF8-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP1]] |
| ; CHECK-VF8-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[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: [[TMP2:%.*]] = getelementptr inbounds nuw float, ptr [[A:%.*]], i64 [[INDEX]] |
| ; CHECK-VF8-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[TMP4:%.*]] = shl nuw i64 [[TMP3]], 2 |
| ; CHECK-VF8-NEXT: [[TMP5:%.*]] = getelementptr inbounds nuw float, ptr [[TMP2]], i64 [[TMP4]] |
| ; CHECK-VF8-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x float>, ptr [[TMP2]], align 4 |
| ; CHECK-VF8-NEXT: [[WIDE_LOAD1:%.*]] = load <vscale x 4 x float>, ptr [[TMP5]], align 4 |
| ; CHECK-VF8-NEXT: [[TMP6:%.*]] = getelementptr inbounds nuw float, ptr [[B:%.*]], i64 [[INDEX]] |
| ; CHECK-VF8-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[TMP8:%.*]] = shl nuw i64 [[TMP7]], 2 |
| ; CHECK-VF8-NEXT: [[TMP9:%.*]] = getelementptr inbounds nuw float, ptr [[TMP6]], i64 [[TMP8]] |
| ; CHECK-VF8-NEXT: [[WIDE_LOAD2:%.*]] = load <vscale x 4 x float>, ptr [[TMP6]], align 4 |
| ; CHECK-VF8-NEXT: [[WIDE_LOAD3:%.*]] = load <vscale x 4 x float>, ptr [[TMP9]], align 4 |
| ; CHECK-VF8-NEXT: [[TMP10:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD]], [[WIDE_LOAD2]] |
| ; CHECK-VF8-NEXT: [[TMP11:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD1]], [[WIDE_LOAD3]] |
| ; CHECK-VF8-NEXT: store <vscale x 4 x float> [[TMP10]], ptr [[TMP6]], align 4 |
| ; CHECK-VF8-NEXT: store <vscale x 4 x float> [[TMP11]], ptr [[TMP9]], align 4 |
| ; CHECK-VF8-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP1]] |
| ; CHECK-VF8-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-VF8-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]] |
| ; CHECK-VF8: middle.block: |
| ; CHECK-VF8-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]] |
| ; CHECK-VF8-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH:%.*]] |
| ; CHECK-VF8: scalar.ph: |
| ; CHECK-VF8-NEXT: br label [[FOR_BODY:%.*]] |
| ; CHECK-VF8: for.body: |
| ; |
| entry: |
| %v = tail call i64 @llvm.vscale.i64() |
| %n = mul nuw nsw i64 %v, 1033 |
| br label %for.body |
| |
| for.body: |
| %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] |
| %arrayidx = getelementptr inbounds nuw float, ptr %a, i64 %iv |
| %l.a = load float, ptr %arrayidx, align 4 |
| %arrayidx3 = getelementptr inbounds nuw float, ptr %b, i64 %iv |
| %l.b = load float, ptr %arrayidx3, align 4 |
| %mul4 = fmul float %l.a, %l.b |
| store float %mul4, ptr %arrayidx3, align 4 |
| %iv.next = add nuw nsw i64 %iv, 1 |
| %ec = icmp eq i64 %iv.next, %n |
| br i1 %ec, label %exit, label %for.body |
| |
| exit: |
| ret void |
| } |
| |
| ; Loop with vscale-based trip count vscale x 1024. |
| define void @trip_count_vscale_no_epilogue_iterations(ptr noalias %a, ptr noalias %b) vscale_range(1, 16) #0 { |
| ; CHECK-LABEL: @trip_count_vscale_no_epilogue_iterations( |
| ; CHECK-NEXT: entry: |
| ; CHECK-NEXT: [[V:%.*]] = tail call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[N:%.*]] = mul nuw nsw i64 [[V]], 1024 |
| ; CHECK-NEXT: br label [[VECTOR_PH:%.*]] |
| ; CHECK: vector.ph: |
| ; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 8 |
| ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP1]] |
| ; 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: [[TMP2:%.*]] = getelementptr inbounds nuw float, ptr [[A:%.*]], i64 [[INDEX]] |
| ; CHECK-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP4:%.*]] = shl nuw i64 [[TMP3]], 2 |
| ; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds nuw float, ptr [[TMP2]], i64 [[TMP4]] |
| ; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x float>, ptr [[TMP2]], align 4 |
| ; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <vscale x 4 x float>, ptr [[TMP5]], align 4 |
| ; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds nuw float, ptr [[B:%.*]], i64 [[INDEX]] |
| ; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-NEXT: [[TMP8:%.*]] = shl nuw i64 [[TMP7]], 2 |
| ; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds nuw float, ptr [[TMP6]], i64 [[TMP8]] |
| ; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <vscale x 4 x float>, ptr [[TMP6]], align 4 |
| ; CHECK-NEXT: [[WIDE_LOAD3:%.*]] = load <vscale x 4 x float>, ptr [[TMP9]], align 4 |
| ; CHECK-NEXT: [[TMP10:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD]], [[WIDE_LOAD2]] |
| ; CHECK-NEXT: [[TMP11:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD1]], [[WIDE_LOAD3]] |
| ; CHECK-NEXT: store <vscale x 4 x float> [[TMP10]], ptr [[TMP6]], align 4 |
| ; CHECK-NEXT: store <vscale x 4 x float> [[TMP11]], ptr [[TMP9]], align 4 |
| ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP1]] |
| ; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP17:![0-9]+]] |
| ; CHECK: middle.block: |
| ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH:%.*]] |
| ; CHECK: scalar.ph: |
| ; CHECK-NEXT: br label [[FOR_BODY:%.*]] |
| ; CHECK: for.body: |
| ; |
| ; CHECK-VF8-LABEL: @trip_count_vscale_no_epilogue_iterations( |
| ; CHECK-VF8-NEXT: entry: |
| ; CHECK-VF8-NEXT: [[V:%.*]] = tail call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[N:%.*]] = mul nuw nsw i64 [[V]], 1024 |
| ; CHECK-VF8-NEXT: br label [[VECTOR_PH:%.*]] |
| ; CHECK-VF8: vector.ph: |
| ; CHECK-VF8-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 8 |
| ; CHECK-VF8-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP1]] |
| ; CHECK-VF8-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[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: [[TMP2:%.*]] = getelementptr inbounds nuw float, ptr [[A:%.*]], i64 [[INDEX]] |
| ; CHECK-VF8-NEXT: [[TMP3:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[TMP4:%.*]] = shl nuw i64 [[TMP3]], 2 |
| ; CHECK-VF8-NEXT: [[TMP5:%.*]] = getelementptr inbounds nuw float, ptr [[TMP2]], i64 [[TMP4]] |
| ; CHECK-VF8-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x float>, ptr [[TMP2]], align 4 |
| ; CHECK-VF8-NEXT: [[WIDE_LOAD1:%.*]] = load <vscale x 4 x float>, ptr [[TMP5]], align 4 |
| ; CHECK-VF8-NEXT: [[TMP6:%.*]] = getelementptr inbounds nuw float, ptr [[B:%.*]], i64 [[INDEX]] |
| ; CHECK-VF8-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64() |
| ; CHECK-VF8-NEXT: [[TMP8:%.*]] = shl nuw i64 [[TMP7]], 2 |
| ; CHECK-VF8-NEXT: [[TMP9:%.*]] = getelementptr inbounds nuw float, ptr [[TMP6]], i64 [[TMP8]] |
| ; CHECK-VF8-NEXT: [[WIDE_LOAD2:%.*]] = load <vscale x 4 x float>, ptr [[TMP6]], align 4 |
| ; CHECK-VF8-NEXT: [[WIDE_LOAD3:%.*]] = load <vscale x 4 x float>, ptr [[TMP9]], align 4 |
| ; CHECK-VF8-NEXT: [[TMP10:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD]], [[WIDE_LOAD2]] |
| ; CHECK-VF8-NEXT: [[TMP11:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD1]], [[WIDE_LOAD3]] |
| ; CHECK-VF8-NEXT: store <vscale x 4 x float> [[TMP10]], ptr [[TMP6]], align 4 |
| ; CHECK-VF8-NEXT: store <vscale x 4 x float> [[TMP11]], ptr [[TMP9]], align 4 |
| ; CHECK-VF8-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP1]] |
| ; CHECK-VF8-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-VF8-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP17:![0-9]+]] |
| ; CHECK-VF8: middle.block: |
| ; CHECK-VF8-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]] |
| ; CHECK-VF8-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH:%.*]] |
| ; CHECK-VF8: scalar.ph: |
| ; CHECK-VF8-NEXT: br label [[FOR_BODY:%.*]] |
| ; CHECK-VF8: for.body: |
| ; |
| entry: |
| %v = tail call i64 @llvm.vscale.i64() |
| %n = mul nuw nsw i64 %v, 1024 |
| br label %for.body |
| |
| for.body: |
| %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] |
| %arrayidx = getelementptr inbounds nuw float, ptr %a, i64 %iv |
| %l.a = load float, ptr %arrayidx, align 4 |
| %arrayidx3 = getelementptr inbounds nuw float, ptr %b, i64 %iv |
| %l.b = load float, ptr %arrayidx3, align 4 |
| %mul4 = fmul float %l.a, %l.b |
| store float %mul4, ptr %arrayidx3, align 4 |
| %iv.next = add nuw nsw i64 %iv, 1 |
| %ec = icmp eq i64 %iv.next, %n |
| br i1 %ec, label %exit, label %for.body |
| |
| exit: |
| ret void |
| } |
| |
| attributes #0 = { "target-features"="+sve" } |
