; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-vectorize -dce -mtriple aarch64-linux-gnu -mattr=+sve \
; RUN: -prefer-predicate-over-epilogue=scalar-epilogue < %s -S | FileCheck %s
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64-unknown-linux-gnu"
; This should be vscale x 8 vectorized, maybe with some interleaving.
define void @fneg(ptr nocapture noundef writeonly %d, ptr nocapture noundef readonly %s, i32 noundef %n) {
; CHECK-LABEL: @fneg(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[S2:%.*]] = ptrtoint ptr [[S:%.*]] to i64
; CHECK-NEXT: [[D1:%.*]] = ptrtoint ptr [[D:%.*]] 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: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 16
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[WIDE_TRIP_COUNT]], [[TMP1]]
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK: vector.memcheck:
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 8
; CHECK-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 4
; CHECK-NEXT: [[TMP5:%.*]] = sub i64 [[D1]], [[S2]]
; CHECK-NEXT: [[DIFF_CHECK:%.*]] = icmp ult i64 [[TMP5]], [[TMP4]]
; CHECK-NEXT: br i1 [[DIFF_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP7:%.*]] = mul i64 [[TMP6]], 16
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[WIDE_TRIP_COUNT]], [[TMP7]]
; 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: [[TMP8:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds half, ptr [[S]], i64 [[TMP8]]
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds half, ptr [[TMP9]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 8 x half>, ptr [[TMP10]], align 2
; CHECK-NEXT: [[TMP11:%.*]] = call i32 @llvm.vscale.i32()
; CHECK-NEXT: [[TMP12:%.*]] = mul i32 [[TMP11]], 8
; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds half, ptr [[TMP9]], i32 [[TMP12]]
; CHECK-NEXT: [[WIDE_LOAD3:%.*]] = load <vscale x 8 x half>, ptr [[TMP13]], align 2
; CHECK-NEXT: [[TMP14:%.*]] = fneg <vscale x 8 x half> [[WIDE_LOAD]]
; CHECK-NEXT: [[TMP15:%.*]] = fneg <vscale x 8 x half> [[WIDE_LOAD3]]
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds half, ptr [[D]], i64 [[TMP8]]
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds half, ptr [[TMP16]], i32 0
; CHECK-NEXT: store <vscale x 8 x half> [[TMP14]], ptr [[TMP17]], align 2
; CHECK-NEXT: [[TMP18:%.*]] = call i32 @llvm.vscale.i32()
; CHECK-NEXT: [[TMP19:%.*]] = mul i32 [[TMP18]], 8
; CHECK-NEXT: [[TMP20:%.*]] = getelementptr inbounds half, ptr [[TMP16]], i32 [[TMP19]]
; CHECK-NEXT: store <vscale x 8 x half> [[TMP15]], ptr [[TMP20]], align 2
; CHECK-NEXT: [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP22:%.*]] = mul i64 [[TMP21]], 16
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP22]]
; CHECK-NEXT: [[TMP23:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP23]], 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 half, ptr [[S]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP24:%.*]] = load half, ptr [[ARRAYIDX]], align 2
; CHECK-NEXT: [[FNEG:%.*]] = fneg half [[TMP24]]
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds half, ptr [[D]], i64 [[INDVARS_IV]]
; CHECK-NEXT: store half [[FNEG]], ptr [[ARRAYIDX2]], align 2
; 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 half, ptr %s, i64 %indvars.iv
%0 = load half, ptr %arrayidx, align 2
%fneg = fneg half %0
%arrayidx2 = getelementptr inbounds half, ptr %d, i64 %indvars.iv
store half %fneg, ptr %arrayidx2, align 2
%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
}