llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-gather-scatter.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=loop-vectorize \
; RUN: -force-tail-folding-style=data-with-evl \
; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
; RUN: -mtriple=riscv64 -mattr=+v -S < %s | FileCheck %s --check-prefix=IF-EVL

; RUN: opt -passes=loop-vectorize \
; RUN: -force-tail-folding-style=none \
; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
; RUN: -mtriple=riscv64 -mattr=+v -S < %s | FileCheck %s --check-prefix=NO-VP

define void @gather_scatter(ptr noalias %in, ptr noalias %out, ptr noalias %index, i64 %n) {
; IF-EVL-LABEL: @gather_scatter(
; IF-EVL-NEXT:  entry:
; IF-EVL-NEXT:    [[TMP0:%.*]] = sub i64 -1, [[N:%.*]]
; IF-EVL-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP2:%.*]] = mul i64 [[TMP1]], 2
; IF-EVL-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
; IF-EVL-NEXT:    br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; IF-EVL:       vector.ph:
; IF-EVL-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 2
; IF-EVL-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP7:%.*]] = mul i64 [[TMP6]], 2
; IF-EVL-NEXT:    [[TMP8:%.*]] = sub i64 [[TMP7]], 1
; IF-EVL-NEXT:    [[N_RND_UP:%.*]] = add i64 [[N]], [[TMP8]]
; IF-EVL-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
; IF-EVL-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; IF-EVL-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 2
; IF-EVL-NEXT:    [[TMP11:%.*]] = call <vscale x 2 x i64> @llvm.experimental.stepvector.nxv2i64()
; IF-EVL-NEXT:    [[TMP12:%.*]] = add <vscale x 2 x i64> [[TMP11]], zeroinitializer
; IF-EVL-NEXT:    [[TMP13:%.*]] = mul <vscale x 2 x i64> [[TMP12]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
; IF-EVL-NEXT:    [[INDUCTION:%.*]] = add <vscale x 2 x i64> zeroinitializer, [[TMP13]]
; IF-EVL-NEXT:    [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP14]], 2
; IF-EVL-NEXT:    [[TMP16:%.*]] = mul i64 1, [[TMP15]]
; IF-EVL-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP16]], i64 0
; IF-EVL-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; IF-EVL-NEXT:    br label [[VECTOR_BODY:%.*]]
; IF-EVL:       vector.body:
; IF-EVL-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 2 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[TMP17:%.*]] = sub i64 [[N]], [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[TMP18:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[TMP17]], i32 2, i1 true)
; IF-EVL-NEXT:    [[TMP20:%.*]] = getelementptr inbounds i32, ptr [[INDEX:%.*]], <vscale x 2 x i64> [[VEC_IND]]
; IF-EVL-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 2 x i64> @llvm.vp.gather.nxv2i64.nxv2p0(<vscale x 2 x ptr> align 8 [[TMP20]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), i32 [[TMP18]])
; IF-EVL-NEXT:    [[TMP21:%.*]] = getelementptr inbounds float, ptr [[IN:%.*]], <vscale x 2 x i64> [[WIDE_MASKED_GATHER]]
; IF-EVL-NEXT:    [[WIDE_MASKED_GATHER2:%.*]] = call <vscale x 2 x float> @llvm.vp.gather.nxv2f32.nxv2p0(<vscale x 2 x ptr> align 4 [[TMP21]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), i32 [[TMP18]])
; IF-EVL-NEXT:    [[TMP22:%.*]] = getelementptr inbounds float, ptr [[OUT:%.*]], <vscale x 2 x i64> [[WIDE_MASKED_GATHER]]
; IF-EVL-NEXT:    call void @llvm.vp.scatter.nxv2f32.nxv2p0(<vscale x 2 x float> [[WIDE_MASKED_GATHER2]], <vscale x 2 x ptr> align 4 [[TMP22]], <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), i32 [[TMP18]])
; IF-EVL-NEXT:    [[TMP23:%.*]] = zext i32 [[TMP18]] to i64
; IF-EVL-NEXT:    [[INDEX_EVL_NEXT]] = add i64 [[TMP23]], [[EVL_BASED_IV]]
; IF-EVL-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX1]], [[TMP10]]
; IF-EVL-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 2 x i64> [[VEC_IND]], [[BROADCAST_SPLAT]]
; IF-EVL-NEXT:    [[TMP24:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; IF-EVL-NEXT:    br i1 [[TMP24]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; IF-EVL:       middle.block:
; IF-EVL-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; IF-EVL:       scalar.ph:
; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; IF-EVL-NEXT:    br label [[FOR_BODY:%.*]]
; IF-EVL:       for.body:
; IF-EVL-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; IF-EVL-NEXT:    [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, ptr [[INDEX]], i64 [[INDVARS_IV]]
; IF-EVL-NEXT:    [[TMP25:%.*]] = load i64, ptr [[ARRAYIDX3]], align 8
; IF-EVL-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds float, ptr [[IN]], i64 [[TMP25]]
; IF-EVL-NEXT:    [[TMP26:%.*]] = load float, ptr [[ARRAYIDX5]], align 4
; IF-EVL-NEXT:    [[ARRAYIDX7:%.*]] = getelementptr inbounds float, ptr [[OUT]], i64 [[TMP25]]
; IF-EVL-NEXT:    store float [[TMP26]], ptr [[ARRAYIDX7]], align 4
; IF-EVL-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; IF-EVL-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[N]]
; IF-EVL-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; IF-EVL:       for.end:
; IF-EVL-NEXT:    ret void
;
; NO-VP-LABEL: @gather_scatter(
; NO-VP-NEXT:  entry:
; NO-VP-NEXT:    br label [[FOR_BODY:%.*]]
; NO-VP:       for.body:
; NO-VP-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; NO-VP-NEXT:    [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, ptr [[INDEX:%.*]], i64 [[INDVARS_IV]]
; NO-VP-NEXT:    [[TMP0:%.*]] = load i64, ptr [[ARRAYIDX3]], align 8
; NO-VP-NEXT:    [[ARRAYIDX5:%.*]] = getelementptr inbounds float, ptr [[IN:%.*]], i64 [[TMP0]]
; NO-VP-NEXT:    [[TMP1:%.*]] = load float, ptr [[ARRAYIDX5]], align 4
; NO-VP-NEXT:    [[ARRAYIDX7:%.*]] = getelementptr inbounds float, ptr [[OUT:%.*]], i64 [[TMP0]]
; NO-VP-NEXT:    store float [[TMP1]], ptr [[ARRAYIDX7]], align 4
; NO-VP-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; NO-VP-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[N:%.*]]
; NO-VP-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; NO-VP:       for.end:
; NO-VP-NEXT:    ret void
;
entry:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %arrayidx3 = getelementptr inbounds i32, ptr %index, i64 %indvars.iv
  %0 = load i64, ptr %arrayidx3, align 8
  %arrayidx5 = getelementptr inbounds float, ptr %in, i64 %0
  %1 = load float, ptr %arrayidx5, align 4
  %arrayidx7 = getelementptr inbounds float, ptr %out, i64 %0
  store float %1, ptr %arrayidx7, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond.not = icmp eq i64 %indvars.iv.next, %n
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret void
}