; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=loop-vectorize,instcombine,simplifycfg -simplifycfg-require-and-preserve-domtree=1 -tail-predication=enabled -force-vector-interleave=2 < %s -S -o - | FileCheck %s

target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv8.1m.main-arm-none-eabi"

; 4x to use VADDLV
define i64 @add_i32_i64(ptr nocapture readonly %x, i32 %n) #0 {
; CHECK-LABEL: @add_i32_i64(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N:%.*]], 8
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N]], -8
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[TMP3:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[TMP7:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds nuw i8, ptr [[TMP0]], i32 16
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[WIDE_LOAD2:%.*]] = load <4 x i32>, ptr [[TMP8]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = sext <4 x i32> [[WIDE_LOAD]] to <4 x i64>
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> [[TMP1]])
; CHECK-NEXT:    [[TMP3]] = add i64 [[VEC_PHI]], [[TMP2]]
; CHECK-NEXT:    [[TMP9:%.*]] = sext <4 x i32> [[WIDE_LOAD2]] to <4 x i64>
; CHECK-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> [[TMP9]])
; CHECK-NEXT:    [[TMP7]] = add i64 [[VEC_PHI1]], [[TMP6]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[BIN_RDX:%.*]] = add i64 [[TMP7]], [[TMP3]]
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER:%.*]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i64 [ [[BIN_RDX]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[I_08:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[R_07:%.*]] = phi i64 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[ADD:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[X]], i32 [[I_08]]
; CHECK-NEXT:    [[TMP5:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[CONV:%.*]] = sext i32 [[TMP5]] to i64
; CHECK-NEXT:    [[ADD]] = add nsw i64 [[R_07]], [[CONV]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_08]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ [[ADD]], [[FOR_BODY]] ], [ [[BIN_RDX]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i64 [[R_0_LCSSA]]
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
  %red = phi i64 [ 0, %entry ], [ %red.next, %loop ]
  %gep.x = getelementptr inbounds i32, ptr %x, i32 %iv
  %0 = load i32, ptr %gep.x, align 4
  %conv = sext i32 %0 to i64
  %red.next = add nsw i64 %red, %conv
  %iv.next = add nuw nsw i32 %iv, 1
  %ec = icmp eq i32 %iv.next, %n
  br i1 %ec, label %exit, label %loop

exit:
  %red.lcssa = phi i64 [ %red.next, %loop ]
  ret i64 %red.lcssa
}

; 4x to use VMLAL.u32
define i64 @mla_i32_i64(ptr nocapture readonly %x, ptr nocapture readonly %y, i32 %n) #0 {
; CHECK-LABEL: @mla_i32_i64(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N:%.*]], 8
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_VEC:%.*]] = and i32 [[N]], -8
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[TMP5:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[TMP11:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[X:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds nuw i8, ptr [[TMP0]], i32 16
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[WIDE_LOAD2:%.*]] = load <4 x i32>, ptr [[TMP12]], align 4
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, ptr [[Y:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds nuw i8, ptr [[TMP1]], i32 16
; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x i32>, ptr [[TMP1]], align 4
; CHECK-NEXT:    [[WIDE_LOAD4:%.*]] = load <4 x i32>, ptr [[TMP13]], align 4
; CHECK-NEXT:    [[TMP2:%.*]] = mul nsw <4 x i32> [[WIDE_LOAD1]], [[WIDE_LOAD]]
; CHECK-NEXT:    [[TMP14:%.*]] = mul nsw <4 x i32> [[WIDE_LOAD4]], [[WIDE_LOAD2]]
; CHECK-NEXT:    [[TMP3:%.*]] = sext <4 x i32> [[TMP2]] to <4 x i64>
; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> [[TMP3]])
; CHECK-NEXT:    [[TMP5]] = add i64 [[VEC_PHI]], [[TMP4]]
; CHECK-NEXT:    [[TMP9:%.*]] = sext <4 x i32> [[TMP14]] to <4 x i64>
; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> [[TMP9]])
; CHECK-NEXT:    [[TMP11]] = add i64 [[VEC_PHI1]], [[TMP10]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 8
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[BIN_RDX:%.*]] = add i64 [[TMP11]], [[TMP5]]
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER:%.*]] ]
; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i64 [ [[BIN_RDX]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[I_010:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[R_09:%.*]] = phi i64 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[ADD:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[X]], i32 [[I_010]]
; CHECK-NEXT:    [[TMP7:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[Y]], i32 [[I_010]]
; CHECK-NEXT:    [[TMP8:%.*]] = load i32, ptr [[ARRAYIDX1]], align 4
; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP8]], [[TMP7]]
; CHECK-NEXT:    [[CONV:%.*]] = sext i32 [[MUL]] to i64
; CHECK-NEXT:    [[ADD]] = add nsw i64 [[R_09]], [[CONV]]
; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_010]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], [[N]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    [[R_0_LCSSA:%.*]] = phi i64 [ [[ADD]], [[FOR_BODY]] ], [ [[BIN_RDX]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i64 [[R_0_LCSSA]]
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
  %red = phi i64 [ 0, %entry ], [ %red.next, %loop ]
  %gep.x = getelementptr inbounds i32, ptr %x, i32 %iv
  %0 = load i32, ptr %gep.x, align 4
  %gep.y = getelementptr inbounds i32, ptr %y, i32 %iv
  %1 = load i32, ptr %gep.y, align 4
  %mul = mul nsw i32 %1, %0
  %conv = sext i32 %mul to i64
  %red.next = add nsw i64 %red, %conv
  %iv.next = add nuw nsw i32 %iv, 1
  %ec = icmp eq i32 %iv.next, %n
  br i1 %ec, label %exit, label %loop

exit:
  %red.lcssa = phi i64 [ %red.next, %loop ]
  ret i64 %red.lcssa
}

attributes #0 = { "target-features"="+mve" }