| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py |
| ; RUN: opt < %s -passes=loop-vectorize -mtriple=aarch64--linux-gnu -mattr=+neon -force-vector-width=2 -force-vector-interleave=1 \ |
| ; RUN: -prefer-predicate-over-epilogue=scalar-epilogue -S -o - | FileCheck %s |
| ; RUN: opt < %s -passes=loop-vectorize -mtriple=aarch64--linux-gnu -mattr=+sve -force-vector-width=2 -force-vector-interleave=1 \ |
| ; RUN: -prefer-predicate-over-epilogue=scalar-epilogue -scalable-vectorization=on -S -o - | FileCheck --check-prefix=SVE %s |
| |
| define dso_local double @test(ptr nocapture noundef readonly %data, ptr nocapture noundef readonly %offset, i32 noundef %size) local_unnamed_addr { |
| ; CHECK-LABEL: @test( |
| ; CHECK-NEXT: entry: |
| ; CHECK-NEXT: [[CMP6:%.*]] = icmp sgt i32 [[SIZE:%.*]], 0 |
| ; CHECK-NEXT: br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]] |
| ; CHECK: for.body.preheader: |
| ; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[SIZE]] to i64 |
| ; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 2 |
| ; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] |
| ; CHECK: vector.ph: |
| ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 2 |
| ; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[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: [[VEC_PHI:%.*]] = phi <2 x double> [ <double 0.000000e+00, double -0.000000e+00>, [[VECTOR_PH]] ], [ [[TMP14:%.*]], [[VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0 |
| ; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1 |
| ; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[OFFSET:%.*]], i64 [[TMP0]] |
| ; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, ptr [[OFFSET]], i64 [[TMP1]] |
| ; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr [[TMP2]], align 4 |
| ; CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[TMP3]], align 4 |
| ; CHECK-NEXT: [[TMP6:%.*]] = sext i32 [[TMP4]] to i64 |
| ; CHECK-NEXT: [[TMP7:%.*]] = sext i32 [[TMP5]] to i64 |
| ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds double, ptr [[DATA:%.*]], i64 [[TMP6]] |
| ; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds double, ptr [[DATA]], i64 [[TMP7]] |
| ; CHECK-NEXT: [[TMP10:%.*]] = load double, ptr [[TMP8]], align 8 |
| ; CHECK-NEXT: [[TMP11:%.*]] = load double, ptr [[TMP9]], align 8 |
| ; CHECK-NEXT: [[TMP12:%.*]] = insertelement <2 x double> poison, double [[TMP10]], i32 0 |
| ; CHECK-NEXT: [[TMP13:%.*]] = insertelement <2 x double> [[TMP12]], double [[TMP11]], i32 1 |
| ; CHECK-NEXT: [[TMP14]] = fadd <2 x double> [[VEC_PHI]], [[TMP13]] |
| ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2 |
| ; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] |
| ; CHECK: middle.block: |
| ; CHECK-NEXT: [[TMP16:%.*]] = call double @llvm.vector.reduce.fadd.v2f64(double -0.000000e+00, <2 x double> [[TMP14]]) |
| ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[WIDE_TRIP_COUNT]], [[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 i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ] |
| ; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi double [ [[TMP16]], [[MIDDLE_BLOCK]] ], [ 0.000000e+00, [[FOR_BODY_PREHEADER]] ] |
| ; CHECK-NEXT: br label [[FOR_BODY:%.*]] |
| ; CHECK: for.cond.cleanup.loopexit: |
| ; CHECK-NEXT: [[ADD_LCSSA:%.*]] = phi double [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[TMP16]], [[MIDDLE_BLOCK]] ] |
| ; CHECK-NEXT: br label [[FOR_COND_CLEANUP]] |
| ; CHECK: for.cond.cleanup: |
| ; CHECK-NEXT: [[RES_0_LCSSA:%.*]] = phi double [ 0.000000e+00, [[ENTRY:%.*]] ], [ [[ADD_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ] |
| ; CHECK-NEXT: ret double [[RES_0_LCSSA]] |
| ; CHECK: for.body: |
| ; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ] |
| ; CHECK-NEXT: [[RES_07:%.*]] = phi double [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[ADD]], [[FOR_BODY]] ] |
| ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[OFFSET]], i64 [[INDVARS_IV]] |
| ; CHECK-NEXT: [[TMP17:%.*]] = load i32, ptr [[ARRAYIDX]], align 4 |
| ; CHECK-NEXT: [[IDXPROM1:%.*]] = sext i32 [[TMP17]] to i64 |
| ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds double, ptr [[DATA]], i64 [[IDXPROM1]] |
| ; CHECK-NEXT: [[TMP18:%.*]] = load double, ptr [[ARRAYIDX2]], align 8 |
| ; CHECK-NEXT: [[ADD]] = fadd double [[RES_07]], [[TMP18]] |
| ; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1 |
| ; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]] |
| ; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]] |
| ; |
| ; SVE-LABEL: @test( |
| ; SVE-NEXT: entry: |
| ; SVE-NEXT: [[CMP6:%.*]] = icmp sgt i32 [[SIZE:%.*]], 0 |
| ; SVE-NEXT: br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]] |
| ; SVE: for.body.preheader: |
| ; SVE-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[SIZE]] to i64 |
| ; SVE-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64() |
| ; SVE-NEXT: [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 1 |
| ; SVE-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], [[TMP1]] |
| ; SVE-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] |
| ; SVE: vector.ph: |
| ; SVE-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64() |
| ; SVE-NEXT: [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 1 |
| ; SVE-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], [[TMP3]] |
| ; SVE-NEXT: [[N_VEC:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[N_MOD_VF]] |
| ; SVE-NEXT: br label [[VECTOR_BODY:%.*]] |
| ; SVE: vector.body: |
| ; SVE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] |
| ; SVE-NEXT: [[VEC_PHI:%.*]] = phi <vscale x 2 x double> [ insertelement (<vscale x 2 x double> splat (double -0.000000e+00), double 0.000000e+00, i32 0), [[VECTOR_PH]] ], [ [[TMP9:%.*]], [[VECTOR_BODY]] ] |
| ; SVE-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, ptr [[OFFSET:%.*]], i64 [[INDEX]] |
| ; SVE-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 2 x i32>, ptr [[TMP5]], align 4 |
| ; SVE-NEXT: [[TMP7:%.*]] = sext <vscale x 2 x i32> [[WIDE_LOAD]] to <vscale x 2 x i64> |
| ; SVE-NEXT: [[TMP8:%.*]] = getelementptr inbounds double, ptr [[DATA:%.*]], <vscale x 2 x i64> [[TMP7]] |
| ; SVE-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64.nxv2p0(<vscale x 2 x ptr> align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), <vscale x 2 x double> poison) |
| ; SVE-NEXT: [[TMP9]] = fadd <vscale x 2 x double> [[VEC_PHI]], [[WIDE_MASKED_GATHER]] |
| ; SVE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]] |
| ; SVE-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; SVE-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] |
| ; SVE: middle.block: |
| ; SVE-NEXT: [[TMP15:%.*]] = call double @llvm.vector.reduce.fadd.nxv2f64(double -0.000000e+00, <vscale x 2 x double> [[TMP9]]) |
| ; SVE-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[WIDE_TRIP_COUNT]], [[N_VEC]] |
| ; SVE-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]] |
| ; SVE: scalar.ph: |
| ; SVE-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ] |
| ; SVE-NEXT: [[BC_MERGE_RDX:%.*]] = phi double [ [[TMP15]], [[MIDDLE_BLOCK]] ], [ 0.000000e+00, [[FOR_BODY_PREHEADER]] ] |
| ; SVE-NEXT: br label [[FOR_BODY:%.*]] |
| ; SVE: for.cond.cleanup.loopexit: |
| ; SVE-NEXT: [[ADD_LCSSA:%.*]] = phi double [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[TMP15]], [[MIDDLE_BLOCK]] ] |
| ; SVE-NEXT: br label [[FOR_COND_CLEANUP]] |
| ; SVE: for.cond.cleanup: |
| ; SVE-NEXT: [[RES_0_LCSSA:%.*]] = phi double [ 0.000000e+00, [[ENTRY:%.*]] ], [ [[ADD_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ] |
| ; SVE-NEXT: ret double [[RES_0_LCSSA]] |
| ; SVE: for.body: |
| ; SVE-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ] |
| ; SVE-NEXT: [[RES_07:%.*]] = phi double [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[ADD]], [[FOR_BODY]] ] |
| ; SVE-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[OFFSET]], i64 [[INDVARS_IV]] |
| ; SVE-NEXT: [[TMP13:%.*]] = load i32, ptr [[ARRAYIDX]], align 4 |
| ; SVE-NEXT: [[IDXPROM1:%.*]] = sext i32 [[TMP13]] to i64 |
| ; SVE-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds double, ptr [[DATA]], i64 [[IDXPROM1]] |
| ; SVE-NEXT: [[TMP14:%.*]] = load double, ptr [[ARRAYIDX2]], align 8 |
| ; SVE-NEXT: [[ADD]] = fadd double [[RES_07]], [[TMP14]] |
| ; SVE-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1 |
| ; SVE-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]] |
| ; SVE-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]] |
| ; |
| entry: |
| %cmp6 = icmp sgt i32 %size, 0 |
| br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup |
| |
| for.body.preheader: ; preds = %entry |
| %wide.trip.count = zext i32 %size to i64 |
| br label %for.body |
| |
| for.cond.cleanup.loopexit: ; preds = %for.body |
| %add.lcssa = phi double [ %add, %for.body ] |
| br label %for.cond.cleanup |
| |
| for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry |
| %res.0.lcssa = phi double [ 0.000000e+00, %entry ], [ %add.lcssa, %for.cond.cleanup.loopexit ] |
| ret double %res.0.lcssa |
| |
| for.body: ; preds = %for.body.preheader, %for.body |
| %indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ] |
| %res.07 = phi double [ 0.000000e+00, %for.body.preheader ], [ %add, %for.body ] |
| %arrayidx = getelementptr inbounds i32, ptr %offset, i64 %indvars.iv |
| %0 = load i32, ptr %arrayidx, align 4 |
| %idxprom1 = sext i32 %0 to i64 |
| %arrayidx2 = getelementptr inbounds double, ptr %data, i64 %idxprom1 |
| %1 = load double, ptr %arrayidx2, align 8 |
| %add = fadd double %res.07, %1 |
| %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 |
| %exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count |
| br i1 %exitcond.not, label %for.cond.cleanup.loopexit, label %for.body |
| } |
