xref: /llvm-project/llvm/test/Transforms/LoopVectorize/RISCV/inloop-reduction.ll (revision b759020cc85d023583c948aa93905e38897b2c0a)

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -mtriple riscv64-linux-gnu -mattr=+v,+d -passes=loop-vectorize < %s -S -o - | FileCheck %s -check-prefix=OUTLOOP
; RUN: opt -mtriple riscv64-linux-gnu -mattr=+v,+d -passes=loop-vectorize -prefer-inloop-reductions < %s -S -o - | FileCheck %s -check-prefix=INLOOP
; RUN: opt -passes=loop-vectorize -force-tail-folding-style=data-with-evl -prefer-predicate-over-epilogue=predicate-dont-vectorize -mtriple=riscv64 -mattr=+v -S < %s 2>&1 | FileCheck --check-prefix=IF-EVL-OUTLOOP %s
; RUN: opt -passes=loop-vectorize -prefer-inloop-reductions -force-tail-folding-style=data-with-evl -prefer-predicate-over-epilogue=predicate-dont-vectorize -mtriple=riscv64 -mattr=+v -S < %s 2>&1 | FileCheck --check-prefix=IF-EVL-INLOOP %s


target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n64-S128"
target triple = "riscv64"

define i32 @add_i16_i32(ptr nocapture readonly %x, i32 %n) {
; OUTLOOP-LABEL: @add_i16_i32(
; OUTLOOP-NEXT:  entry:
; OUTLOOP-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; OUTLOOP-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; OUTLOOP:       for.body.preheader:
; OUTLOOP-NEXT:    [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
; OUTLOOP-NEXT:    [[TMP1:%.*]] = mul i32 [[TMP0]], 4
; OUTLOOP-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], [[TMP1]]
; OUTLOOP-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; OUTLOOP:       vector.ph:
; OUTLOOP-NEXT:    [[TMP2:%.*]] = call i32 @llvm.vscale.i32()
; OUTLOOP-NEXT:    [[TMP3:%.*]] = mul i32 [[TMP2]], 4
; OUTLOOP-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N]], [[TMP3]]
; OUTLOOP-NEXT:    [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; OUTLOOP-NEXT:    [[TMP4:%.*]] = call i32 @llvm.vscale.i32()
; OUTLOOP-NEXT:    [[TMP5:%.*]] = mul i32 [[TMP4]], 4
; OUTLOOP-NEXT:    br label [[VECTOR_BODY:%.*]]
; OUTLOOP:       vector.body:
; OUTLOOP-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; OUTLOOP-NEXT:    [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP10:%.*]], [[VECTOR_BODY]] ]
; OUTLOOP-NEXT:    [[TMP6:%.*]] = add i32 [[INDEX]], 0
; OUTLOOP-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i32 [[TMP6]]
; OUTLOOP-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i16, ptr [[TMP7]], i32 0
; OUTLOOP-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i16>, ptr [[TMP8]], align 2
; OUTLOOP-NEXT:    [[TMP9:%.*]] = sext <vscale x 4 x i16> [[WIDE_LOAD]] to <vscale x 4 x i32>
; OUTLOOP-NEXT:    [[TMP10]] = add <vscale x 4 x i32> [[VEC_PHI]], [[TMP9]]
; OUTLOOP-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP5]]
; OUTLOOP-NEXT:    [[TMP11:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; OUTLOOP-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; OUTLOOP:       middle.block:
; OUTLOOP-NEXT:    [[TMP12:%.*]] = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> [[TMP10]])
; OUTLOOP-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; OUTLOOP-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; OUTLOOP:       scalar.ph:
; OUTLOOP-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; OUTLOOP-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP12]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; OUTLOOP-NEXT:    br label [[FOR_BODY:%.*]]
; OUTLOOP:       for.body:
; OUTLOOP-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; OUTLOOP-NEXT:    [[R_07:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; OUTLOOP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, ptr [[X]], i32 [[I_08]]
; OUTLOOP-NEXT:    [[TMP13:%.*]] = load i16, ptr [[ARRAYIDX]], align 2
; OUTLOOP-NEXT:    [[CONV:%.*]] = sext i16 [[TMP13]] to i32
; OUTLOOP-NEXT:    [[ADD]] = add nsw i32 [[R_07]], [[CONV]]
; OUTLOOP-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; OUTLOOP-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; OUTLOOP-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; OUTLOOP:       for.cond.cleanup.loopexit:
; OUTLOOP-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP12]], [[MIDDLE_BLOCK]] ]
; OUTLOOP-NEXT:    br label [[FOR_COND_CLEANUP]]
; OUTLOOP:       for.cond.cleanup:
; OUTLOOP-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[ADD_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ]
; OUTLOOP-NEXT:    ret i32 [[R_0_LCSSA]]
;
; INLOOP-LABEL: @add_i16_i32(
; INLOOP-NEXT:  entry:
; INLOOP-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; INLOOP-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; INLOOP:       for.body.preheader:
; INLOOP-NEXT:    [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
; INLOOP-NEXT:    [[TMP1:%.*]] = mul i32 [[TMP0]], 8
; INLOOP-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], [[TMP1]]
; INLOOP-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; INLOOP:       vector.ph:
; INLOOP-NEXT:    [[TMP2:%.*]] = call i32 @llvm.vscale.i32()
; INLOOP-NEXT:    [[TMP3:%.*]] = mul i32 [[TMP2]], 8
; INLOOP-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N]], [[TMP3]]
; INLOOP-NEXT:    [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; INLOOP-NEXT:    [[TMP4:%.*]] = call i32 @llvm.vscale.i32()
; INLOOP-NEXT:    [[TMP5:%.*]] = mul i32 [[TMP4]], 8
; INLOOP-NEXT:    br label [[VECTOR_BODY:%.*]]
; INLOOP:       vector.body:
; INLOOP-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; INLOOP-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP11:%.*]], [[VECTOR_BODY]] ]
; INLOOP-NEXT:    [[TMP6:%.*]] = add i32 [[INDEX]], 0
; INLOOP-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i32 [[TMP6]]
; INLOOP-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i16, ptr [[TMP7]], i32 0
; INLOOP-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 8 x i16>, ptr [[TMP8]], align 2
; INLOOP-NEXT:    [[TMP9:%.*]] = sext <vscale x 8 x i16> [[WIDE_LOAD]] to <vscale x 8 x i32>
; INLOOP-NEXT:    [[TMP10:%.*]] = call i32 @llvm.vector.reduce.add.nxv8i32(<vscale x 8 x i32> [[TMP9]])
; INLOOP-NEXT:    [[TMP11]] = add i32 [[TMP10]], [[VEC_PHI]]
; INLOOP-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP5]]
; INLOOP-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; INLOOP-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; INLOOP:       middle.block:
; INLOOP-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; INLOOP-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; INLOOP:       scalar.ph:
; INLOOP-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; INLOOP-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP11]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; INLOOP-NEXT:    br label [[FOR_BODY:%.*]]
; INLOOP:       for.body:
; INLOOP-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; INLOOP-NEXT:    [[R_07:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; INLOOP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, ptr [[X]], i32 [[I_08]]
; INLOOP-NEXT:    [[TMP13:%.*]] = load i16, ptr [[ARRAYIDX]], align 2
; INLOOP-NEXT:    [[CONV:%.*]] = sext i16 [[TMP13]] to i32
; INLOOP-NEXT:    [[ADD]] = add nsw i32 [[R_07]], [[CONV]]
; INLOOP-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; INLOOP-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; INLOOP-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; INLOOP:       for.cond.cleanup.loopexit:
; INLOOP-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP11]], [[MIDDLE_BLOCK]] ]
; INLOOP-NEXT:    br label [[FOR_COND_CLEANUP]]
; INLOOP:       for.cond.cleanup:
; INLOOP-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[ADD_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ]
; INLOOP-NEXT:    ret i32 [[R_0_LCSSA]]
;
; IF-EVL-OUTLOOP-LABEL: @add_i16_i32(
; IF-EVL-OUTLOOP-NEXT:  entry:
; IF-EVL-OUTLOOP-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; IF-EVL-OUTLOOP-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; IF-EVL-OUTLOOP:       for.body.preheader:
; IF-EVL-OUTLOOP-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; IF-EVL-OUTLOOP:       vector.ph:
; IF-EVL-OUTLOOP-NEXT:    [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
; IF-EVL-OUTLOOP-NEXT:    [[TMP1:%.*]] = mul i32 [[TMP0]], 4
; IF-EVL-OUTLOOP-NEXT:    [[TMP2:%.*]] = sub i32 [[TMP1]], 1
; IF-EVL-OUTLOOP-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], [[TMP2]]
; IF-EVL-OUTLOOP-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], [[TMP1]]
; IF-EVL-OUTLOOP-NEXT:    [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vscale.i32()
; IF-EVL-OUTLOOP-NEXT:    [[TMP4:%.*]] = mul i32 [[TMP3]], 4
; IF-EVL-OUTLOOP-NEXT:    br label [[VECTOR_BODY:%.*]]
; IF-EVL-OUTLOOP:       vector.body:
; IF-EVL-OUTLOOP-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT:    [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT:    [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP10:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT:    [[AVL:%.*]] = sub i32 [[N]], [[EVL_BASED_IV]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 4, i1 true)
; IF-EVL-OUTLOOP-NEXT:    [[TMP6:%.*]] = add i32 [[EVL_BASED_IV]], 0
; IF-EVL-OUTLOOP-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i32 [[TMP6]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i16, ptr [[TMP7]], i32 0
; IF-EVL-OUTLOOP-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i16> @llvm.vp.load.nxv4i16.p0(ptr align 2 [[TMP8]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-OUTLOOP-NEXT:    [[TMP9:%.*]] = call <vscale x 4 x i32> @llvm.vp.sext.nxv4i32.nxv4i16(<vscale x 4 x i16> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-OUTLOOP-NEXT:    [[VP_OP:%.*]] = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> [[VEC_PHI]], <vscale x 4 x i32> [[TMP9]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-OUTLOOP-NEXT:    [[TMP10]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[VP_OP]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP5]])
; IF-EVL-OUTLOOP-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP5]], [[EVL_BASED_IV]]
; IF-EVL-OUTLOOP-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP4]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP11:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; IF-EVL-OUTLOOP-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; IF-EVL-OUTLOOP:       middle.block:
; IF-EVL-OUTLOOP-NEXT:    [[TMP12:%.*]] = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> [[TMP10]])
; IF-EVL-OUTLOOP-NEXT:    br i1 true, label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; IF-EVL-OUTLOOP:       scalar.ph:
; IF-EVL-OUTLOOP-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; IF-EVL-OUTLOOP-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP12]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; IF-EVL-OUTLOOP-NEXT:    br label [[FOR_BODY:%.*]]
; IF-EVL-OUTLOOP:       for.body:
; IF-EVL-OUTLOOP-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; IF-EVL-OUTLOOP-NEXT:    [[R_07:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; IF-EVL-OUTLOOP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, ptr [[X]], i32 [[I_08]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP13:%.*]] = load i16, ptr [[ARRAYIDX]], align 2
; IF-EVL-OUTLOOP-NEXT:    [[CONV:%.*]] = sext i16 [[TMP13]] to i32
; IF-EVL-OUTLOOP-NEXT:    [[ADD]] = add nsw i32 [[R_07]], [[CONV]]
; IF-EVL-OUTLOOP-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; IF-EVL-OUTLOOP-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; IF-EVL-OUTLOOP-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; IF-EVL-OUTLOOP:       for.cond.cleanup.loopexit:
; IF-EVL-OUTLOOP-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP12]], [[MIDDLE_BLOCK]] ]
; IF-EVL-OUTLOOP-NEXT:    br label [[FOR_COND_CLEANUP]]
; IF-EVL-OUTLOOP:       for.cond.cleanup:
; IF-EVL-OUTLOOP-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[ADD_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ]
; IF-EVL-OUTLOOP-NEXT:    ret i32 [[R_0_LCSSA]]
;
; IF-EVL-INLOOP-LABEL: @add_i16_i32(
; IF-EVL-INLOOP-NEXT:  entry:
; IF-EVL-INLOOP-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; IF-EVL-INLOOP-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; IF-EVL-INLOOP:       for.body.preheader:
; IF-EVL-INLOOP-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; IF-EVL-INLOOP:       vector.ph:
; IF-EVL-INLOOP-NEXT:    [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
; IF-EVL-INLOOP-NEXT:    [[TMP1:%.*]] = mul i32 [[TMP0]], 8
; IF-EVL-INLOOP-NEXT:    [[TMP2:%.*]] = sub i32 [[TMP1]], 1
; IF-EVL-INLOOP-NEXT:    [[N_RND_UP:%.*]] = add i32 [[N]], [[TMP2]]
; IF-EVL-INLOOP-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], [[TMP1]]
; IF-EVL-INLOOP-NEXT:    [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]]
; IF-EVL-INLOOP-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vscale.i32()
; IF-EVL-INLOOP-NEXT:    [[TMP4:%.*]] = mul i32 [[TMP3]], 8
; IF-EVL-INLOOP-NEXT:    br label [[VECTOR_BODY:%.*]]
; IF-EVL-INLOOP:       vector.body:
; IF-EVL-INLOOP-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT:    [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP11:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT:    [[TMP5:%.*]] = sub i32 [[N]], [[EVL_BASED_IV]]
; IF-EVL-INLOOP-NEXT:    [[TMP6:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[TMP5]], i32 8, i1 true)
; IF-EVL-INLOOP-NEXT:    [[TMP7:%.*]] = add i32 [[EVL_BASED_IV]], 0
; IF-EVL-INLOOP-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i32 [[TMP7]]
; IF-EVL-INLOOP-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i16, ptr [[TMP8]], i32 0
; IF-EVL-INLOOP-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 8 x i16> @llvm.vp.load.nxv8i16.p0(ptr align 2 [[TMP9]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP6]])
; IF-EVL-INLOOP-NEXT:    [[TMP14:%.*]] = call <vscale x 8 x i32> @llvm.vp.sext.nxv8i32.nxv8i16(<vscale x 8 x i16> [[VP_OP_LOAD]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP6]])
; IF-EVL-INLOOP-NEXT:    [[TMP10:%.*]] = call i32 @llvm.vp.reduce.add.nxv8i32(i32 0, <vscale x 8 x i32> [[TMP14]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP6]])
; IF-EVL-INLOOP-NEXT:    [[TMP11]] = add i32 [[TMP10]], [[VEC_PHI]]
; IF-EVL-INLOOP-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP6]], [[EVL_BASED_IV]]
; IF-EVL-INLOOP-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP4]]
; IF-EVL-INLOOP-NEXT:    [[TMP12:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; IF-EVL-INLOOP-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; IF-EVL-INLOOP:       middle.block:
; IF-EVL-INLOOP-NEXT:    br i1 true, label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; IF-EVL-INLOOP:       scalar.ph:
; IF-EVL-INLOOP-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; IF-EVL-INLOOP-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP11]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; IF-EVL-INLOOP-NEXT:    br label [[FOR_BODY:%.*]]
; IF-EVL-INLOOP:       for.body:
; IF-EVL-INLOOP-NEXT:    [[I_08:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; IF-EVL-INLOOP-NEXT:    [[R_07:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; IF-EVL-INLOOP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, ptr [[X]], i32 [[I_08]]
; IF-EVL-INLOOP-NEXT:    [[TMP13:%.*]] = load i16, ptr [[ARRAYIDX]], align 2
; IF-EVL-INLOOP-NEXT:    [[CONV:%.*]] = sext i16 [[TMP13]] to i32
; IF-EVL-INLOOP-NEXT:    [[ADD]] = add nsw i32 [[R_07]], [[CONV]]
; IF-EVL-INLOOP-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; IF-EVL-INLOOP-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; IF-EVL-INLOOP-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; IF-EVL-INLOOP:       for.cond.cleanup.loopexit:
; IF-EVL-INLOOP-NEXT:    [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], [[FOR_BODY]] ], [ [[TMP11]], [[MIDDLE_BLOCK]] ]
; IF-EVL-INLOOP-NEXT:    br label [[FOR_COND_CLEANUP]]
; IF-EVL-INLOOP:       for.cond.cleanup:
; IF-EVL-INLOOP-NEXT:    [[R_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[ADD_LCSSA]], [[FOR_COND_CLEANUP_LOOPEXIT]] ]
; IF-EVL-INLOOP-NEXT:    ret i32 [[R_0_LCSSA]]
;
entry:
  %cmp6 = icmp sgt i32 %n, 0
  br i1 %cmp6, label %for.body, label %for.cond.cleanup

for.body:                                         ; preds = %entry, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %r.07 = phi i32 [ %add, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i16, ptr %x, i32 %i.08
  %0 = load i16, ptr %arrayidx, align 2
  %conv = sext i16 %0 to i32
  %add = add nsw i32 %r.07, %conv
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %n
  br i1 %exitcond, label %for.cond.cleanup, label %for.body

for.cond.cleanup:                                 ; preds = %for.body, %entry
  %r.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
  ret i32 %r.0.lcssa
}

define i32 @smin(ptr %a, i64 %n, i32 %start) {
; OUTLOOP-LABEL: @smin(
; OUTLOOP-NEXT:  entry:
; OUTLOOP-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; OUTLOOP-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; OUTLOOP-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], [[TMP1]]
; OUTLOOP-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; OUTLOOP:       vector.ph:
; OUTLOOP-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; OUTLOOP-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; OUTLOOP-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; OUTLOOP-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; OUTLOOP-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; OUTLOOP-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
; OUTLOOP-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[START:%.*]], i64 0
; OUTLOOP-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; OUTLOOP-NEXT:    br label [[VECTOR_BODY:%.*]]
; OUTLOOP:       vector.body:
; OUTLOOP-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; OUTLOOP-NEXT:    [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ [[BROADCAST_SPLAT]], [[VECTOR_PH]] ], [ [[TMP10:%.*]], [[VECTOR_BODY]] ]
; OUTLOOP-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 0
; OUTLOOP-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP6]]
; OUTLOOP-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, ptr [[TMP7]], i32 0
; OUTLOOP-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
; OUTLOOP-NEXT:    [[TMP9:%.*]] = icmp slt <vscale x 4 x i32> [[WIDE_LOAD]], [[VEC_PHI]]
; OUTLOOP-NEXT:    [[TMP10]] = select <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i32> [[WIDE_LOAD]], <vscale x 4 x i32> [[VEC_PHI]]
; OUTLOOP-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
; OUTLOOP-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; OUTLOOP-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; OUTLOOP:       middle.block:
; OUTLOOP-NEXT:    [[TMP12:%.*]] = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> [[TMP10]])
; OUTLOOP-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
; OUTLOOP-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
; OUTLOOP:       scalar.ph:
; OUTLOOP-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; OUTLOOP-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP12]], [[MIDDLE_BLOCK]] ], [ [[START]], [[ENTRY]] ]
; OUTLOOP-NEXT:    br label [[FOR_BODY:%.*]]
; OUTLOOP:       for.body:
; OUTLOOP-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; OUTLOOP-NEXT:    [[RDX:%.*]] = phi i32 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[SMIN:%.*]], [[FOR_BODY]] ]
; OUTLOOP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IV]]
; OUTLOOP-NEXT:    [[TMP13:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; OUTLOOP-NEXT:    [[CMP_I:%.*]] = icmp slt i32 [[TMP13]], [[RDX]]
; OUTLOOP-NEXT:    [[SMIN]] = select i1 [[CMP_I]], i32 [[TMP13]], i32 [[RDX]]
; OUTLOOP-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; OUTLOOP-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
; OUTLOOP-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; OUTLOOP:       for.end:
; OUTLOOP-NEXT:    [[SMIN_LCSSA:%.*]] = phi i32 [ [[SMIN]], [[FOR_BODY]] ], [ [[TMP12]], [[MIDDLE_BLOCK]] ]
; OUTLOOP-NEXT:    ret i32 [[SMIN_LCSSA]]
;
; INLOOP-LABEL: @smin(
; INLOOP-NEXT:  entry:
; INLOOP-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; INLOOP-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; INLOOP-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], [[TMP1]]
; INLOOP-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; INLOOP:       vector.ph:
; INLOOP-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; INLOOP-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; INLOOP-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; INLOOP-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; INLOOP-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; INLOOP-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
; INLOOP-NEXT:    br label [[VECTOR_BODY:%.*]]
; INLOOP:       vector.body:
; INLOOP-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; INLOOP-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ [[START:%.*]], [[VECTOR_PH]] ], [ [[RDX_MINMAX:%.*]], [[VECTOR_BODY]] ]
; INLOOP-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 0
; INLOOP-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP6]]
; INLOOP-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, ptr [[TMP7]], i32 0
; INLOOP-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
; INLOOP-NEXT:    [[TMP9:%.*]] = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> [[WIDE_LOAD]])
; INLOOP-NEXT:    [[RDX_MINMAX]] = call i32 @llvm.smin.i32(i32 [[TMP9]], i32 [[VEC_PHI]])
; INLOOP-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
; INLOOP-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; INLOOP-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; INLOOP:       middle.block:
; INLOOP-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
; INLOOP-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
; INLOOP:       scalar.ph:
; INLOOP-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; INLOOP-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[RDX_MINMAX]], [[MIDDLE_BLOCK]] ], [ [[START]], [[ENTRY]] ]
; INLOOP-NEXT:    br label [[FOR_BODY:%.*]]
; INLOOP:       for.body:
; INLOOP-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; INLOOP-NEXT:    [[RDX:%.*]] = phi i32 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[SMIN:%.*]], [[FOR_BODY]] ]
; INLOOP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IV]]
; INLOOP-NEXT:    [[TMP11:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; INLOOP-NEXT:    [[CMP_I:%.*]] = icmp slt i32 [[TMP11]], [[RDX]]
; INLOOP-NEXT:    [[SMIN]] = select i1 [[CMP_I]], i32 [[TMP11]], i32 [[RDX]]
; INLOOP-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; INLOOP-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
; INLOOP-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; INLOOP:       for.end:
; INLOOP-NEXT:    [[SMIN_LCSSA:%.*]] = phi i32 [ [[SMIN]], [[FOR_BODY]] ], [ [[RDX_MINMAX]], [[MIDDLE_BLOCK]] ]
; INLOOP-NEXT:    ret i32 [[SMIN_LCSSA]]
;
; IF-EVL-OUTLOOP-LABEL: @smin(
; IF-EVL-OUTLOOP-NEXT:  entry:
; IF-EVL-OUTLOOP-NEXT:    [[TMP0:%.*]] = sub i64 -1, [[N:%.*]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-OUTLOOP-NEXT:    [[TMP2:%.*]] = mul i64 [[TMP1]], 4
; IF-EVL-OUTLOOP-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
; IF-EVL-OUTLOOP-NEXT:    br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; IF-EVL-OUTLOOP:       vector.ph:
; IF-EVL-OUTLOOP-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-OUTLOOP-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
; IF-EVL-OUTLOOP-NEXT:    [[TMP6:%.*]] = sub i64 [[TMP5]], 1
; IF-EVL-OUTLOOP-NEXT:    [[N_RND_UP:%.*]] = add i64 [[N]], [[TMP6]]
; IF-EVL-OUTLOOP-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
; IF-EVL-OUTLOOP-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-OUTLOOP-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 4
; IF-EVL-OUTLOOP-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[START:%.*]], i64 0
; IF-EVL-OUTLOOP-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; IF-EVL-OUTLOOP-NEXT:    br label [[VECTOR_BODY:%.*]]
; IF-EVL-OUTLOOP:       vector.body:
; IF-EVL-OUTLOOP-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT:    [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ [[BROADCAST_SPLAT]], [[VECTOR_PH]] ], [ [[TMP15:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT:    [[AVL:%.*]] = sub i64 [[N]], [[EVL_BASED_IV]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP9:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 4, i1 true)
; IF-EVL-OUTLOOP-NEXT:    [[TMP10:%.*]] = add i64 [[EVL_BASED_IV]], 0
; IF-EVL-OUTLOOP-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP10]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[TMP11]], i32 0
; IF-EVL-OUTLOOP-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP12]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
; IF-EVL-OUTLOOP-NEXT:    [[TMP13:%.*]] = icmp slt <vscale x 4 x i32> [[VP_OP_LOAD]], [[VEC_PHI]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP14:%.*]] = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> [[TMP13]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP9]])
; IF-EVL-OUTLOOP-NEXT:    [[TMP15]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[TMP14]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP9]])
; IF-EVL-OUTLOOP-NEXT:    [[TMP16:%.*]] = zext i32 [[TMP9]] to i64
; IF-EVL-OUTLOOP-NEXT:    [[INDEX_EVL_NEXT]] = add i64 [[TMP16]], [[EVL_BASED_IV]]
; IF-EVL-OUTLOOP-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP8]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; IF-EVL-OUTLOOP-NEXT:    br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; IF-EVL-OUTLOOP:       middle.block:
; IF-EVL-OUTLOOP-NEXT:    [[TMP18:%.*]] = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> [[TMP15]])
; IF-EVL-OUTLOOP-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; IF-EVL-OUTLOOP:       scalar.ph:
; IF-EVL-OUTLOOP-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; IF-EVL-OUTLOOP-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP18]], [[MIDDLE_BLOCK]] ], [ [[START]], [[ENTRY]] ]
; IF-EVL-OUTLOOP-NEXT:    br label [[FOR_BODY:%.*]]
; IF-EVL-OUTLOOP:       for.body:
; IF-EVL-OUTLOOP-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT:    [[RDX:%.*]] = phi i32 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[SMIN:%.*]], [[FOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IV]]
; IF-EVL-OUTLOOP-NEXT:    [[TMP19:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; IF-EVL-OUTLOOP-NEXT:    [[CMP_I:%.*]] = icmp slt i32 [[TMP19]], [[RDX]]
; IF-EVL-OUTLOOP-NEXT:    [[SMIN]] = select i1 [[CMP_I]], i32 [[TMP19]], i32 [[RDX]]
; IF-EVL-OUTLOOP-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-OUTLOOP-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
; IF-EVL-OUTLOOP-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; IF-EVL-OUTLOOP:       for.end:
; IF-EVL-OUTLOOP-NEXT:    [[SMIN_LCSSA:%.*]] = phi i32 [ [[SMIN]], [[FOR_BODY]] ], [ [[TMP18]], [[MIDDLE_BLOCK]] ]
; IF-EVL-OUTLOOP-NEXT:    ret i32 [[SMIN_LCSSA]]
;
; IF-EVL-INLOOP-LABEL: @smin(
; IF-EVL-INLOOP-NEXT:  entry:
; IF-EVL-INLOOP-NEXT:    [[TMP0:%.*]] = sub i64 -1, [[N:%.*]]
; IF-EVL-INLOOP-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-INLOOP-NEXT:    [[TMP2:%.*]] = mul i64 [[TMP1]], 4
; IF-EVL-INLOOP-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
; IF-EVL-INLOOP-NEXT:    br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; IF-EVL-INLOOP:       vector.ph:
; IF-EVL-INLOOP-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-INLOOP-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
; IF-EVL-INLOOP-NEXT:    [[TMP6:%.*]] = sub i64 [[TMP5]], 1
; IF-EVL-INLOOP-NEXT:    [[N_RND_UP:%.*]] = add i64 [[N]], [[TMP6]]
; IF-EVL-INLOOP-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
; IF-EVL-INLOOP-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; IF-EVL-INLOOP-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-INLOOP-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 4
; IF-EVL-INLOOP-NEXT:    br label [[VECTOR_BODY:%.*]]
; IF-EVL-INLOOP:       vector.body:
; IF-EVL-INLOOP-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT:    [[VEC_PHI:%.*]] = phi i32 [ [[START:%.*]], [[VECTOR_PH]] ], [ [[RDX_MINMAX:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT:    [[AVL:%.*]] = sub i64 [[N]], [[EVL_BASED_IV]]
; IF-EVL-INLOOP-NEXT:    [[TMP9:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 4, i1 true)
; IF-EVL-INLOOP-NEXT:    [[TMP10:%.*]] = add i64 [[EVL_BASED_IV]], 0
; IF-EVL-INLOOP-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP10]]
; IF-EVL-INLOOP-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[TMP11]], i32 0
; IF-EVL-INLOOP-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP12]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
; IF-EVL-INLOOP-NEXT:    [[TMP13:%.*]] = call i32 @llvm.vp.reduce.smin.nxv4i32(i32 2147483647, <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
; IF-EVL-INLOOP-NEXT:    [[RDX_MINMAX]] = call i32 @llvm.smin.i32(i32 [[TMP13]], i32 [[VEC_PHI]])
; IF-EVL-INLOOP-NEXT:    [[TMP14:%.*]] = zext i32 [[TMP9]] to i64
; IF-EVL-INLOOP-NEXT:    [[INDEX_EVL_NEXT]] = add i64 [[TMP14]], [[EVL_BASED_IV]]
; IF-EVL-INLOOP-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP8]]
; IF-EVL-INLOOP-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; IF-EVL-INLOOP-NEXT:    br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; IF-EVL-INLOOP:       middle.block:
; IF-EVL-INLOOP-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; IF-EVL-INLOOP:       scalar.ph:
; IF-EVL-INLOOP-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; IF-EVL-INLOOP-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[RDX_MINMAX]], [[MIDDLE_BLOCK]] ], [ [[START]], [[ENTRY]] ]
; IF-EVL-INLOOP-NEXT:    br label [[FOR_BODY:%.*]]
; IF-EVL-INLOOP:       for.body:
; IF-EVL-INLOOP-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; IF-EVL-INLOOP-NEXT:    [[RDX:%.*]] = phi i32 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[SMIN:%.*]], [[FOR_BODY]] ]
; IF-EVL-INLOOP-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IV]]
; IF-EVL-INLOOP-NEXT:    [[TMP16:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; IF-EVL-INLOOP-NEXT:    [[CMP_I:%.*]] = icmp slt i32 [[TMP16]], [[RDX]]
; IF-EVL-INLOOP-NEXT:    [[SMIN]] = select i1 [[CMP_I]], i32 [[TMP16]], i32 [[RDX]]
; IF-EVL-INLOOP-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-INLOOP-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
; IF-EVL-INLOOP-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; IF-EVL-INLOOP:       for.end:
; IF-EVL-INLOOP-NEXT:    [[SMIN_LCSSA:%.*]] = phi i32 [ [[SMIN]], [[FOR_BODY]] ], [ [[RDX_MINMAX]], [[MIDDLE_BLOCK]] ]
; IF-EVL-INLOOP-NEXT:    ret i32 [[SMIN_LCSSA]]
;
; IF-EVL-LABEL: @smin(
; 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]], 4
; 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]], 4
; IF-EVL-NEXT:    [[TMP6:%.*]] = sub i64 [[TMP5]], 1
; IF-EVL-NEXT:    [[N_RND_UP:%.*]] = add i64 [[N]], [[TMP6]]
; 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:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[N]], 1
; IF-EVL-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; IF-EVL-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 4
; IF-EVL-NEXT:    [[MINMAX_IDENT_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[START:%.*]], i64 0
; IF-EVL-NEXT:    [[MINMAX_IDENT_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[MINMAX_IDENT_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; IF-EVL-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
; IF-EVL-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT1]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; IF-EVL-NEXT:    br label [[VECTOR_BODY:%.*]]
; IF-EVL:       vector.body:
; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ [[MINMAX_IDENT_SPLAT]], [[VECTOR_PH]] ], [ [[TMP16:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], 0
; IF-EVL-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[INDEX]], i64 0
; IF-EVL-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; IF-EVL-NEXT:    [[TMP10:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
; IF-EVL-NEXT:    [[TMP11:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP10]]
; IF-EVL-NEXT:    [[VEC_IV:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT]], [[TMP11]]
; IF-EVL-NEXT:    [[TMP12:%.*]] = icmp ule <vscale x 4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT2]]
; IF-EVL-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP9]]
; IF-EVL-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[TMP13]], i32 0
; IF-EVL-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr [[TMP14]], i32 4, <vscale x 4 x i1> [[TMP12]], <vscale x 4 x i32> poison)
; IF-EVL-NEXT:    [[TMP15:%.*]] = icmp slt <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], [[VEC_PHI]]
; IF-EVL-NEXT:    [[TMP16]] = select <vscale x 4 x i1> [[TMP15]], <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], <vscale x 4 x i32> [[VEC_PHI]]
; IF-EVL-NEXT:    [[TMP17:%.*]] = select <vscale x 4 x i1> [[TMP12]], <vscale x 4 x i32> [[TMP16]], <vscale x 4 x i32> [[VEC_PHI]]
; IF-EVL-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP8]]
; IF-EVL-NEXT:    [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; IF-EVL-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; IF-EVL:       middle.block:
; IF-EVL-NEXT:    [[TMP19:%.*]] = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> [[TMP17]])
; 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:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP19]], [[MIDDLE_BLOCK]] ], [ [[START]], [[ENTRY]] ]
; IF-EVL-NEXT:    br label [[FOR_BODY:%.*]]
; IF-EVL:       for.body:
; IF-EVL-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; IF-EVL-NEXT:    [[RDX:%.*]] = phi i32 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[SMIN:%.*]], [[FOR_BODY]] ]
; IF-EVL-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[IV]]
; IF-EVL-NEXT:    [[TMP20:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; IF-EVL-NEXT:    [[CMP_I:%.*]] = icmp slt i32 [[TMP20]], [[RDX]]
; IF-EVL-NEXT:    [[SMIN]] = select i1 [[CMP_I]], i32 [[TMP20]], i32 [[RDX]]
; IF-EVL-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; IF-EVL-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
; IF-EVL-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; IF-EVL:       for.end:
; IF-EVL-NEXT:    [[SMIN_LCSSA:%.*]] = phi i32 [ [[SMIN]], [[FOR_BODY]] ], [ [[TMP19]], [[MIDDLE_BLOCK]] ]
; IF-EVL-NEXT:    ret i32 [[SMIN_LCSSA]]
entry:
  br label %for.body

for.body:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %rdx = phi i32 [ %start, %entry ], [ %smin, %for.body ]
  %arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
  %0 = load i32, ptr %arrayidx, align 4
  %cmp.i = icmp slt i32 %0, %rdx
  %smin = select i1 %cmp.i, i32 %0, i32 %rdx
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, %n
  br i1 %exitcond.not, label %for.end, label %for.body

for.end:
  ret i32 %smin
}