Changeset View
Changeset View
Standalone View
Standalone View
llvm/test/Transforms/LoopVectorize/is_fpclass.ll
- This file was added.
| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py | |||||
| ; RUN: opt %s -passes=loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -S | FileCheck %s | |||||
| define void @is_fpclass(ptr %x, ptr %y, i32 %n) { | |||||
| ; CHECK-LABEL: @is_fpclass( | |||||
| ; CHECK-NEXT: entry: | |||||
| ; CHECK-NEXT: [[X2:%.*]] = ptrtoint ptr [[X:%.*]] to i64 | |||||
| ; CHECK-NEXT: [[Y1:%.*]] = ptrtoint ptr [[Y:%.*]] to i64 | |||||
| ; CHECK-NEXT: [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 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 [[N]] to i64 | |||||
| ; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], 4 | |||||
| ; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]] | |||||
| ; CHECK: vector.memcheck: | |||||
| ; CHECK-NEXT: [[TMP0:%.*]] = sub i64 [[Y1]], [[X2]] | |||||
| ; CHECK-NEXT: [[DIFF_CHECK:%.*]] = icmp ult i64 [[TMP0]], 16 | |||||
| ; CHECK-NEXT: br i1 [[DIFF_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]] | |||||
| ; CHECK: vector.ph: | |||||
| ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], 4 | |||||
| ; 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: [[TMP1:%.*]] = add i64 [[INDEX]], 0 | |||||
| ; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, ptr [[X]], i64 [[TMP1]] | |||||
| ; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds float, ptr [[TMP2]], i32 0 | |||||
| ; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP3]], align 4 | |||||
| ; CHECK-NEXT: [[TMP4:%.*]] = call <4 x i1> @llvm.is.fpclass.v4f32(<4 x float> [[WIDE_LOAD]], i32 1) | |||||
| ; CHECK-NEXT: [[TMP5:%.*]] = zext <4 x i1> [[TMP4]] to <4 x i32> | |||||
| ; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, ptr [[Y]], i64 [[TMP1]] | |||||
| ; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[TMP6]], i32 0 | |||||
| ; CHECK-NEXT: store <4 x i32> [[TMP5]], ptr [[TMP7]], align 4 | |||||
| ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4 | |||||
| ; 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 [[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]] ], [ 0, [[VECTOR_MEMCHECK]] ] | |||||
| ; CHECK-NEXT: br label [[FOR_BODY:%.*]] | |||||
| ; CHECK: for.cond.cleanup.loopexit: | |||||
| ; CHECK-NEXT: br label [[FOR_COND_CLEANUP]] | |||||
| ; 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: [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[X]], i64 [[INDVARS_IV]] | |||||
| ; CHECK-NEXT: [[TMP9:%.*]] = load float, ptr [[ARRAYIDX]], align 4 | |||||
| ; CHECK-NEXT: [[TMP10:%.*]] = tail call i1 @llvm.is.fpclass.f32(float [[TMP9]], i32 1) | |||||
| ; CHECK-NEXT: [[TMP11:%.*]] = zext i1 [[TMP10]] to i32 | |||||
| ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, ptr [[Y]], i64 [[INDVARS_IV]] | |||||
| ; CHECK-NEXT: store i32 [[TMP11]], ptr [[ARRAYIDX2]], align 4 | |||||
| ; 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 [[LOOP2:![0-9]+]] | |||||
| ; | |||||
| entry: | |||||
| %cmp6 = icmp sgt i32 %n, 0 | |||||
| br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup | |||||
| for.body.preheader: ; preds = %entry | |||||
| %wide.trip.count = zext i32 %n to i64 | |||||
| br label %for.body | |||||
| for.cond.cleanup: ; preds = %for.body, %entry | |||||
| ret void | |||||
| for.body: ; preds = %for.body.preheader, %for.body | |||||
| %indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ] | |||||
| %arrayidx = getelementptr inbounds float, ptr %x, i64 %indvars.iv | |||||
| %0 = load float, ptr %arrayidx, align 4 | |||||
| %1 = tail call i1 @llvm.is.fpclass.f32(float %0, i32 1) | |||||
| %2 = zext i1 %1 to i32 | |||||
| %arrayidx2 = getelementptr inbounds i32, ptr %y, i64 %indvars.iv | |||||
| store i32 %2, ptr %arrayidx2, align 4 | |||||
| %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, label %for.body | |||||
| } | |||||
| declare i1 @llvm.is.fpclass.f32(float, i32) | |||||