; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp %s -o - | FileCheck %s

%struct.DCT_InstanceTypeDef = type { float*, i32, i32 }

define void @DCT_mve1(%struct.DCT_InstanceTypeDef* nocapture readonly %S, float* nocapture readonly %pIn, float* nocapture %pOut) {
; CHECK-LABEL: DCT_mve1:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, lr}
; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, lr}
; CHECK-NEXT:    ldr r3, [r0, #4]
; CHECK-NEXT:    sub.w r12, r3, #1
; CHECK-NEXT:    cmp.w r12, #2
; CHECK-NEXT:    blo .LBB0_5
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    ldr r5, [r0, #8]
; CHECK-NEXT:    ldr r3, [r0]
; CHECK-NEXT:    add.w r3, r3, r5, lsl #2
; CHECK-NEXT:    movs r0, #1
; CHECK-NEXT:    lsl.w r9, r5, #2
; CHECK-NEXT:  .LBB0_2: @ %for.body
; CHECK-NEXT:    @ =>This Loop Header: Depth=1
; CHECK-NEXT:    @ Child Loop BB0_3 Depth 2
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    mov r6, r1
; CHECK-NEXT:    mov r7, r3
; CHECK-NEXT:    dlstp.32 lr, r5
; CHECK-NEXT:  .LBB0_3: @ %vector.body
; CHECK-NEXT:    @ Parent Loop BB0_2 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vldrw.u32 q1, [r6], #16
; CHECK-NEXT:    vldrw.u32 q2, [r7], #16
; CHECK-NEXT:    vfma.f32 q0, q2, q1
; CHECK-NEXT:    letp lr, .LBB0_3
; CHECK-NEXT:  @ %bb.4: @ %middle.block
; CHECK-NEXT:    @ in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT:    vadd.f32 s2, s2, s3
; CHECK-NEXT:    add.w r7, r2, r0, lsl #2
; CHECK-NEXT:    vadd.f32 s0, s0, s1
; CHECK-NEXT:    adds r0, #1
; CHECK-NEXT:    add r3, r9
; CHECK-NEXT:    cmp r0, r12
; CHECK-NEXT:    vadd.f32 s0, s0, s2
; CHECK-NEXT:    vstr s0, [r7]
; CHECK-NEXT:    bne .LBB0_2
; CHECK-NEXT:  .LBB0_5: @ %for.cond.cleanup
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, pc}
entry:
  %NumInputs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 2
  %0 = load i32, i32* %NumInputs, align 4
  %NumFilters = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 1
  %1 = load i32, i32* %NumFilters, align 4
  %pDCTCoefs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 0
  %2 = load float*, float** %pDCTCoefs, align 4
  %cmp = icmp ugt i32 %0, 1
  tail call void @llvm.assume(i1 %cmp)
  %sub = add i32 %1, -1
  %cmp350 = icmp ugt i32 %sub, 1
  br i1 %cmp350, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %n.rnd.up = add i32 %0, 3
  %n.vec = and i32 %n.rnd.up, -4
  br label %for.body

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  ret void

for.body:                                         ; preds = %for.body.preheader, %middle.block
  %k2.051 = phi i32 [ %add16, %middle.block ], [ 1, %for.body.preheader ]
  %mul4 = mul i32 %k2.051, %0
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %for.body
  %index = phi i32 [ 0, %for.body ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x float> [ zeroinitializer, %for.body ], [ %10, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %0)
  %3 = getelementptr inbounds float, float* %pIn, i32 %index
  %4 = bitcast float* %3 to <4 x float>*
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %4, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %5 = add i32 %index, %mul4
  %6 = getelementptr inbounds float, float* %2, i32 %5
  %7 = bitcast float* %6 to <4 x float>*
  %wide.masked.load53 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %7, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %8 = fmul fast <4 x float> %wide.masked.load53, %wide.masked.load
  %9 = fadd fast <4 x float> %8, %vec.phi
  %10 = select <4 x i1> %active.lane.mask, <4 x float> %9, <4 x float> %vec.phi
  %index.next = add i32 %index, 4
  %11 = icmp eq i32 %index.next, %n.vec
  br i1 %11, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %12 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %10)
  %arrayidx14 = getelementptr inbounds float, float* %pOut, i32 %k2.051
  store float %12, float* %arrayidx14, align 4
  %add16 = add nuw i32 %k2.051, 1
  %exitcond52.not = icmp eq i32 %add16, %sub
  br i1 %exitcond52.not, label %for.cond.cleanup, label %for.body
}

define void @DCT_mve2(%struct.DCT_InstanceTypeDef* nocapture readonly %S, float* nocapture readonly %pIn, float* nocapture %pOut) {
; CHECK-LABEL: DCT_mve2:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    .pad #4
; CHECK-NEXT:    sub sp, #4
; CHECK-NEXT:    str r1, [sp] @ 4-byte Spill
; CHECK-NEXT:    ldr r1, [r0, #4]
; CHECK-NEXT:    subs r1, #2
; CHECK-NEXT:    cmp r1, #2
; CHECK-NEXT:    blo .LBB1_5
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    ldr.w r12, [r0, #8]
; CHECK-NEXT:    movs r4, #1
; CHECK-NEXT:    ldr r3, [r0]
; CHECK-NEXT:    add.w r11, r3, r12, lsl #2
; CHECK-NEXT:    add.w r7, r3, r12, lsl #3
; CHECK-NEXT:    lsl.w r9, r12, #3
; CHECK-NEXT:  .LBB1_2: @ %for.body
; CHECK-NEXT:    @ =>This Loop Header: Depth=1
; CHECK-NEXT:    @ Child Loop BB1_3 Depth 2
; CHECK-NEXT:    ldr r5, [sp] @ 4-byte Reload
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    add.w r10, r4, #1
; CHECK-NEXT:    mov r3, r11
; CHECK-NEXT:    mov r0, r7
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    dlstp.32 lr, r12
; CHECK-NEXT:  .LBB1_3: @ %vector.body
; CHECK-NEXT:    @ Parent Loop BB1_2 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vldrw.u32 q2, [r5], #16
; CHECK-NEXT:    vldrw.u32 q3, [r3], #16
; CHECK-NEXT:    vfma.f32 q1, q3, q2
; CHECK-NEXT:    vldrw.u32 q3, [r0], #16
; CHECK-NEXT:    vfma.f32 q0, q3, q2
; CHECK-NEXT:    letp lr, .LBB1_3
; CHECK-NEXT:  @ %bb.4: @ %middle.block
; CHECK-NEXT:    @ in Loop: Header=BB1_2 Depth=1
; CHECK-NEXT:    vadd.f32 s2, s2, s3
; CHECK-NEXT:    add.w r0, r2, r10, lsl #2
; CHECK-NEXT:    vadd.f32 s0, s0, s1
; CHECK-NEXT:    add r11, r9
; CHECK-NEXT:    vadd.f32 s6, s6, s7
; CHECK-NEXT:    add r7, r9
; CHECK-NEXT:    vadd.f32 s4, s4, s5
; CHECK-NEXT:    vadd.f32 s0, s0, s2
; CHECK-NEXT:    vadd.f32 s2, s4, s6
; CHECK-NEXT:    vstr s0, [r0]
; CHECK-NEXT:    add.w r0, r2, r4, lsl #2
; CHECK-NEXT:    adds r4, #2
; CHECK-NEXT:    cmp r4, r1
; CHECK-NEXT:    vstr s2, [r0]
; CHECK-NEXT:    blo .LBB1_2
; CHECK-NEXT:  .LBB1_5: @ %for.cond.cleanup
; CHECK-NEXT:    add sp, #4
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
entry:
  %NumInputs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 2
  %0 = load i32, i32* %NumInputs, align 4
  %NumFilters = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 1
  %1 = load i32, i32* %NumFilters, align 4
  %pDCTCoefs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 0
  %2 = load float*, float** %pDCTCoefs, align 4
  %cmp = icmp ugt i32 %0, 1
  tail call void @llvm.assume(i1 %cmp)
  %sub = add i32 %1, -2
  %cmp371 = icmp ugt i32 %sub, 1
  br i1 %cmp371, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %n.rnd.up = add i32 %0, 3
  %n.vec = and i32 %n.rnd.up, -4
  br label %for.body

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  ret void

for.body:                                         ; preds = %for.body.preheader, %middle.block
  %k2.072 = phi i32 [ %add25, %middle.block ], [ 1, %for.body.preheader ]
  %mul4 = mul i32 %k2.072, %0
  %add = add nuw i32 %k2.072, 1
  %mul5 = mul i32 %add, %0
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %for.body
  %index = phi i32 [ 0, %for.body ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x float> [ zeroinitializer, %for.body ], [ %15, %vector.body ]
  %vec.phi73 = phi <4 x float> [ zeroinitializer, %for.body ], [ %16, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %0)
  %3 = getelementptr inbounds float, float* %pIn, i32 %index
  %4 = bitcast float* %3 to <4 x float>*
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %4, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %5 = add i32 %index, %mul4
  %6 = getelementptr inbounds float, float* %2, i32 %5
  %7 = bitcast float* %6 to <4 x float>*
  %wide.masked.load74 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %7, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %8 = fmul fast <4 x float> %wide.masked.load74, %wide.masked.load
  %9 = fadd fast <4 x float> %8, %vec.phi73
  %10 = add i32 %index, %mul5
  %11 = getelementptr inbounds float, float* %2, i32 %10
  %12 = bitcast float* %11 to <4 x float>*
  %wide.masked.load75 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %12, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %13 = fmul fast <4 x float> %wide.masked.load75, %wide.masked.load
  %14 = fadd fast <4 x float> %13, %vec.phi
  %15 = select <4 x i1> %active.lane.mask, <4 x float> %14, <4 x float> %vec.phi
  %16 = select <4 x i1> %active.lane.mask, <4 x float> %9, <4 x float> %vec.phi73
  %index.next = add i32 %index, 4
  %17 = icmp eq i32 %index.next, %n.vec
  br i1 %17, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %18 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %16)
  %19 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %15)
  %arrayidx21 = getelementptr inbounds float, float* %pOut, i32 %k2.072
  store float %18, float* %arrayidx21, align 4
  %arrayidx23 = getelementptr inbounds float, float* %pOut, i32 %add
  store float %19, float* %arrayidx23, align 4
  %add25 = add i32 %k2.072, 2
  %cmp3 = icmp ult i32 %add25, %sub
  br i1 %cmp3, label %for.body, label %for.cond.cleanup
}

define void @DCT_mve3(%struct.DCT_InstanceTypeDef* nocapture readonly %S, float* nocapture readonly %pIn, float* nocapture %pOut) {
; CHECK-LABEL: DCT_mve3:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    .pad #4
; CHECK-NEXT:    sub sp, #4
; CHECK-NEXT:    .vsave {d8, d9}
; CHECK-NEXT:    vpush {d8, d9}
; CHECK-NEXT:    .pad #24
; CHECK-NEXT:    sub sp, #24
; CHECK-NEXT:    str r1, [sp, #16] @ 4-byte Spill
; CHECK-NEXT:    ldr r1, [r0, #4]
; CHECK-NEXT:    str r2, [sp, #8] @ 4-byte Spill
; CHECK-NEXT:    subs r1, #3
; CHECK-NEXT:    str r1, [sp, #12] @ 4-byte Spill
; CHECK-NEXT:    cmp r1, #2
; CHECK-NEXT:    blo .LBB2_5
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    ldr r3, [r0, #8]
; CHECK-NEXT:    movs r5, #1
; CHECK-NEXT:    ldr r1, [r0]
; CHECK-NEXT:    str r3, [sp, #4] @ 4-byte Spill
; CHECK-NEXT:    add.w r0, r3, r3, lsl #1
; CHECK-NEXT:    add.w r9, r1, r3, lsl #2
; CHECK-NEXT:    add.w r12, r1, r3, lsl #3
; CHECK-NEXT:    adds r3, #3
; CHECK-NEXT:    bic r3, r3, #3
; CHECK-NEXT:    ldr r7, [sp, #4] @ 4-byte Reload
; CHECK-NEXT:    add.w r10, r1, r0, lsl #2
; CHECK-NEXT:    subs r3, #4
; CHECK-NEXT:    lsl.w r11, r0, #2
; CHECK-NEXT:    add.w r1, r5, r3, lsr #2
; CHECK-NEXT:    str r1, [sp] @ 4-byte Spill
; CHECK-NEXT:  .LBB2_2: @ %for.body
; CHECK-NEXT:    @ =>This Loop Header: Depth=1
; CHECK-NEXT:    @ Child Loop BB2_3 Depth 2
; CHECK-NEXT:    ldr r6, [sp, #16] @ 4-byte Reload
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    ldr r1, [sp] @ 4-byte Reload
; CHECK-NEXT:    adds r0, r5, #2
; CHECK-NEXT:    adds r2, r5, #1
; CHECK-NEXT:    str r0, [sp, #20] @ 4-byte Spill
; CHECK-NEXT:    mov r3, r9
; CHECK-NEXT:    mov r0, r12
; CHECK-NEXT:    mov r4, r10
; CHECK-NEXT:    vmov q2, q0
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    dlstp.32 lr, r7
; CHECK-NEXT:  .LBB2_3: @ %vector.body
; CHECK-NEXT:    @ Parent Loop BB2_2 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vldrw.u32 q3, [r6], #16
; CHECK-NEXT:    vldrw.u32 q4, [r3], #16
; CHECK-NEXT:    vfma.f32 q1, q4, q3
; CHECK-NEXT:    vldrw.u32 q4, [r0], #16
; CHECK-NEXT:    vfma.f32 q2, q4, q3
; CHECK-NEXT:    vldrw.u32 q4, [r4], #16
; CHECK-NEXT:    vfma.f32 q0, q4, q3
; CHECK-NEXT:    letp lr, .LBB2_3
; CHECK-NEXT:  @ %bb.4: @ %middle.block
; CHECK-NEXT:    @ in Loop: Header=BB2_2 Depth=1
; CHECK-NEXT:    vadd.f32 s10, s10, s11
; CHECK-NEXT:    ldr r1, [sp, #8] @ 4-byte Reload
; CHECK-NEXT:    vadd.f32 s8, s8, s9
; CHECK-NEXT:    add r9, r11
; CHECK-NEXT:    vadd.f32 s6, s6, s7
; CHECK-NEXT:    add.w r0, r1, r2, lsl #2
; CHECK-NEXT:    vadd.f32 s4, s4, s5
; CHECK-NEXT:    add r12, r11
; CHECK-NEXT:    vadd.f32 s2, s2, s3
; CHECK-NEXT:    add r10, r11
; CHECK-NEXT:    vadd.f32 s0, s0, s1
; CHECK-NEXT:    vadd.f32 s8, s8, s10
; CHECK-NEXT:    vadd.f32 s4, s4, s6
; CHECK-NEXT:    vadd.f32 s0, s0, s2
; CHECK-NEXT:    vstr s8, [r0]
; CHECK-NEXT:    add.w r0, r1, r5, lsl #2
; CHECK-NEXT:    adds r5, #3
; CHECK-NEXT:    vstr s4, [r0]
; CHECK-NEXT:    ldr r0, [sp, #20] @ 4-byte Reload
; CHECK-NEXT:    add.w r0, r1, r0, lsl #2
; CHECK-NEXT:    vstr s0, [r0]
; CHECK-NEXT:    ldr r0, [sp, #12] @ 4-byte Reload
; CHECK-NEXT:    cmp r5, r0
; CHECK-NEXT:    blo .LBB2_2
; CHECK-NEXT:  .LBB2_5: @ %for.cond.cleanup
; CHECK-NEXT:    add sp, #24
; CHECK-NEXT:    vpop {d8, d9}
; CHECK-NEXT:    add sp, #4
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
entry:
  %NumInputs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 2
  %0 = load i32, i32* %NumInputs, align 4
  %NumFilters = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 1
  %1 = load i32, i32* %NumFilters, align 4
  %pDCTCoefs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 0
  %2 = load float*, float** %pDCTCoefs, align 4
  %cmp = icmp ugt i32 %0, 1
  tail call void @llvm.assume(i1 %cmp)
  %sub = add i32 %1, -3
  %cmp392 = icmp ugt i32 %sub, 1
  br i1 %cmp392, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %n.rnd.up = add i32 %0, 3
  %n.vec = and i32 %n.rnd.up, -4
  br label %for.body

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  ret void

for.body:                                         ; preds = %for.body.preheader, %middle.block
  %k2.093 = phi i32 [ %add34, %middle.block ], [ 1, %for.body.preheader ]
  %mul4 = mul i32 %k2.093, %0
  %add = add nuw i32 %k2.093, 1
  %mul5 = mul i32 %add, %0
  %add6 = add i32 %k2.093, 2
  %mul7 = mul i32 %add6, %0
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %for.body
  %index = phi i32 [ 0, %for.body ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x float> [ zeroinitializer, %for.body ], [ %20, %vector.body ]
  %vec.phi94 = phi <4 x float> [ zeroinitializer, %for.body ], [ %21, %vector.body ]
  %vec.phi95 = phi <4 x float> [ zeroinitializer, %for.body ], [ %22, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %0)
  %3 = getelementptr inbounds float, float* %pIn, i32 %index
  %4 = bitcast float* %3 to <4 x float>*
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %4, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %5 = add i32 %index, %mul4
  %6 = getelementptr inbounds float, float* %2, i32 %5
  %7 = bitcast float* %6 to <4 x float>*
  %wide.masked.load96 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %7, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %8 = fmul fast <4 x float> %wide.masked.load96, %wide.masked.load
  %9 = fadd fast <4 x float> %8, %vec.phi95
  %10 = add i32 %index, %mul5
  %11 = getelementptr inbounds float, float* %2, i32 %10
  %12 = bitcast float* %11 to <4 x float>*
  %wide.masked.load97 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %12, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %13 = fmul fast <4 x float> %wide.masked.load97, %wide.masked.load
  %14 = fadd fast <4 x float> %13, %vec.phi94
  %15 = add i32 %index, %mul7
  %16 = getelementptr inbounds float, float* %2, i32 %15
  %17 = bitcast float* %16 to <4 x float>*
  %wide.masked.load98 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %17, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %18 = fmul fast <4 x float> %wide.masked.load98, %wide.masked.load
  %19 = fadd fast <4 x float> %18, %vec.phi
  %20 = select <4 x i1> %active.lane.mask, <4 x float> %19, <4 x float> %vec.phi
  %21 = select <4 x i1> %active.lane.mask, <4 x float> %14, <4 x float> %vec.phi94
  %22 = select <4 x i1> %active.lane.mask, <4 x float> %9, <4 x float> %vec.phi95
  %index.next = add i32 %index, 4
  %23 = icmp eq i32 %index.next, %n.vec
  br i1 %23, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %24 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %22)
  %25 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %21)
  %26 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %20)
  %arrayidx28 = getelementptr inbounds float, float* %pOut, i32 %k2.093
  store float %24, float* %arrayidx28, align 4
  %arrayidx30 = getelementptr inbounds float, float* %pOut, i32 %add
  store float %25, float* %arrayidx30, align 4
  %arrayidx32 = getelementptr inbounds float, float* %pOut, i32 %add6
  store float %26, float* %arrayidx32, align 4
  %add34 = add i32 %k2.093, 3
  %cmp3 = icmp ult i32 %add34, %sub
  br i1 %cmp3, label %for.body, label %for.cond.cleanup
}

define void @DCT_mve4(%struct.DCT_InstanceTypeDef* nocapture readonly %S, float* nocapture readonly %pIn, float* nocapture %pOut) {
; CHECK-LABEL: DCT_mve4:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    .pad #4
; CHECK-NEXT:    sub sp, #4
; CHECK-NEXT:    .vsave {d8, d9, d10, d11}
; CHECK-NEXT:    vpush {d8, d9, d10, d11}
; CHECK-NEXT:    .pad #40
; CHECK-NEXT:    sub sp, #40
; CHECK-NEXT:    str r1, [sp, #24] @ 4-byte Spill
; CHECK-NEXT:    ldr r1, [r0, #4]
; CHECK-NEXT:    str r2, [sp, #16] @ 4-byte Spill
; CHECK-NEXT:    subs r1, #4
; CHECK-NEXT:    str r1, [sp, #20] @ 4-byte Spill
; CHECK-NEXT:    cmp r1, #2
; CHECK-NEXT:    blo.w .LBB3_5
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    ldr r2, [r0, #8]
; CHECK-NEXT:    movs r6, #1
; CHECK-NEXT:    ldr r1, [r0]
; CHECK-NEXT:    add.w r0, r2, r2, lsl #1
; CHECK-NEXT:    add.w r12, r1, r2, lsl #2
; CHECK-NEXT:    add.w r8, r1, r2, lsl #3
; CHECK-NEXT:    add.w r9, r1, r2, lsl #4
; CHECK-NEXT:    add.w r11, r1, r0, lsl #2
; CHECK-NEXT:    adds r0, r2, #3
; CHECK-NEXT:    bic r0, r0, #3
; CHECK-NEXT:    subs r0, #4
; CHECK-NEXT:    add.w r0, r6, r0, lsr #2
; CHECK-NEXT:    strd r0, r2, [sp, #8] @ 8-byte Folded Spill
; CHECK-NEXT:    lsls r0, r2, #4
; CHECK-NEXT:    ldrd r2, r7, [sp, #8] @ 8-byte Folded Reload
; CHECK-NEXT:    str r0, [sp, #4] @ 4-byte Spill
; CHECK-NEXT:  .LBB3_2: @ %for.body
; CHECK-NEXT:    @ =>This Loop Header: Depth=1
; CHECK-NEXT:    @ Child Loop BB3_3 Depth 2
; CHECK-NEXT:    adds r0, r6, #3
; CHECK-NEXT:    str r0, [sp, #36] @ 4-byte Spill
; CHECK-NEXT:    adds r0, r6, #2
; CHECK-NEXT:    ldr r1, [sp, #24] @ 4-byte Reload
; CHECK-NEXT:    vmov.i32 q0, #0x0
; CHECK-NEXT:    str r0, [sp, #32] @ 4-byte Spill
; CHECK-NEXT:    adds r0, r6, #1
; CHECK-NEXT:    str r0, [sp, #28] @ 4-byte Spill
; CHECK-NEXT:    mov r3, r12
; CHECK-NEXT:    mov r0, r8
; CHECK-NEXT:    mov r5, r11
; CHECK-NEXT:    mov r4, r9
; CHECK-NEXT:    vmov q1, q0
; CHECK-NEXT:    vmov q2, q0
; CHECK-NEXT:    vmov q3, q0
; CHECK-NEXT:    dlstp.32 lr, r7
; CHECK-NEXT:  .LBB3_3: @ %vector.body
; CHECK-NEXT:    @ Parent Loop BB3_2 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vldrw.u32 q4, [r1], #16
; CHECK-NEXT:    vldrw.u32 q5, [r0], #16
; CHECK-NEXT:    vfma.f32 q3, q5, q4
; CHECK-NEXT:    vldrw.u32 q5, [r3], #16
; CHECK-NEXT:    vfma.f32 q2, q5, q4
; CHECK-NEXT:    vldrw.u32 q5, [r5], #16
; CHECK-NEXT:    vfma.f32 q1, q5, q4
; CHECK-NEXT:    vldrw.u32 q5, [r4], #16
; CHECK-NEXT:    vfma.f32 q0, q5, q4
; CHECK-NEXT:    letp lr, .LBB3_3
; CHECK-NEXT:  @ %bb.4: @ %middle.block
; CHECK-NEXT:    @ in Loop: Header=BB3_2 Depth=1
; CHECK-NEXT:    vadd.f32 s14, s14, s15
; CHECK-NEXT:    ldr r0, [sp, #28] @ 4-byte Reload
; CHECK-NEXT:    vadd.f32 s12, s12, s13
; CHECK-NEXT:    ldr r1, [sp, #16] @ 4-byte Reload
; CHECK-NEXT:    vadd.f32 s10, s10, s11
; CHECK-NEXT:    vadd.f32 s8, s8, s9
; CHECK-NEXT:    add.w r0, r1, r0, lsl #2
; CHECK-NEXT:    vadd.f32 s6, s6, s7
; CHECK-NEXT:    vadd.f32 s4, s4, s5
; CHECK-NEXT:    vadd.f32 s2, s2, s3
; CHECK-NEXT:    vadd.f32 s0, s0, s1
; CHECK-NEXT:    vadd.f32 s12, s12, s14
; CHECK-NEXT:    vadd.f32 s8, s8, s10
; CHECK-NEXT:    vadd.f32 s4, s4, s6
; CHECK-NEXT:    vadd.f32 s0, s0, s2
; CHECK-NEXT:    vstr s12, [r0]
; CHECK-NEXT:    add.w r0, r1, r6, lsl #2
; CHECK-NEXT:    adds r6, #4
; CHECK-NEXT:    vstr s8, [r0]
; CHECK-NEXT:    ldr r0, [sp, #32] @ 4-byte Reload
; CHECK-NEXT:    add.w r0, r1, r0, lsl #2
; CHECK-NEXT:    vstr s4, [r0]
; CHECK-NEXT:    ldr r0, [sp, #36] @ 4-byte Reload
; CHECK-NEXT:    add.w r0, r1, r0, lsl #2
; CHECK-NEXT:    vstr s0, [r0]
; CHECK-NEXT:    ldr r0, [sp, #4] @ 4-byte Reload
; CHECK-NEXT:    add r12, r0
; CHECK-NEXT:    add r8, r0
; CHECK-NEXT:    add r11, r0
; CHECK-NEXT:    add r9, r0
; CHECK-NEXT:    ldr r0, [sp, #20] @ 4-byte Reload
; CHECK-NEXT:    cmp r6, r0
; CHECK-NEXT:    blo .LBB3_2
; CHECK-NEXT:  .LBB3_5: @ %for.cond.cleanup
; CHECK-NEXT:    add sp, #40
; CHECK-NEXT:    vpop {d8, d9, d10, d11}
; CHECK-NEXT:    add sp, #4
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
entry:
  %NumInputs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 2
  %0 = load i32, i32* %NumInputs, align 4
  %NumFilters = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 1
  %1 = load i32, i32* %NumFilters, align 4
  %pDCTCoefs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 0
  %2 = load float*, float** %pDCTCoefs, align 4
  %cmp = icmp ugt i32 %0, 1
  tail call void @llvm.assume(i1 %cmp)
  %sub = add i32 %1, -4
  %cmp3113 = icmp ugt i32 %sub, 1
  br i1 %cmp3113, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %n.rnd.up = add i32 %0, 3
  %n.vec = and i32 %n.rnd.up, -4
  br label %for.body

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  ret void

for.body:                                         ; preds = %for.body.preheader, %middle.block
  %k2.0114 = phi i32 [ %add43, %middle.block ], [ 1, %for.body.preheader ]
  %mul4 = mul i32 %k2.0114, %0
  %add = add nuw nsw i32 %k2.0114, 1
  %mul5 = mul i32 %add, %0
  %add6 = add nuw nsw i32 %k2.0114, 2
  %mul7 = mul i32 %add6, %0
  %add8 = add i32 %k2.0114, 3
  %mul9 = mul i32 %add8, %0
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %for.body
  %index = phi i32 [ 0, %for.body ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x float> [ zeroinitializer, %for.body ], [ %25, %vector.body ]
  %vec.phi115 = phi <4 x float> [ zeroinitializer, %for.body ], [ %26, %vector.body ]
  %vec.phi116 = phi <4 x float> [ zeroinitializer, %for.body ], [ %27, %vector.body ]
  %vec.phi117 = phi <4 x float> [ zeroinitializer, %for.body ], [ %28, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %0)
  %3 = getelementptr inbounds float, float* %pIn, i32 %index
  %4 = bitcast float* %3 to <4 x float>*
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %4, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %5 = add i32 %index, %mul4
  %6 = getelementptr inbounds float, float* %2, i32 %5
  %7 = bitcast float* %6 to <4 x float>*
  %wide.masked.load118 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %7, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %8 = fmul fast <4 x float> %wide.masked.load118, %wide.masked.load
  %9 = fadd fast <4 x float> %8, %vec.phi116
  %10 = add i32 %index, %mul5
  %11 = getelementptr inbounds float, float* %2, i32 %10
  %12 = bitcast float* %11 to <4 x float>*
  %wide.masked.load119 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %12, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %13 = fmul fast <4 x float> %wide.masked.load119, %wide.masked.load
  %14 = fadd fast <4 x float> %13, %vec.phi117
  %15 = add i32 %index, %mul7
  %16 = getelementptr inbounds float, float* %2, i32 %15
  %17 = bitcast float* %16 to <4 x float>*
  %wide.masked.load120 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %17, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %18 = fmul fast <4 x float> %wide.masked.load120, %wide.masked.load
  %19 = fadd fast <4 x float> %18, %vec.phi115
  %20 = add i32 %index, %mul9
  %21 = getelementptr inbounds float, float* %2, i32 %20
  %22 = bitcast float* %21 to <4 x float>*
  %wide.masked.load121 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %22, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %23 = fmul fast <4 x float> %wide.masked.load121, %wide.masked.load
  %24 = fadd fast <4 x float> %23, %vec.phi
  %25 = select <4 x i1> %active.lane.mask, <4 x float> %24, <4 x float> %vec.phi
  %26 = select <4 x i1> %active.lane.mask, <4 x float> %19, <4 x float> %vec.phi115
  %27 = select <4 x i1> %active.lane.mask, <4 x float> %9, <4 x float> %vec.phi116
  %28 = select <4 x i1> %active.lane.mask, <4 x float> %14, <4 x float> %vec.phi117
  %index.next = add i32 %index, 4
  %29 = icmp eq i32 %index.next, %n.vec
  br i1 %29, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %30 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %28)
  %31 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %27)
  %32 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %26)
  %33 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %25)
  %arrayidx35 = getelementptr inbounds float, float* %pOut, i32 %k2.0114
  store float %31, float* %arrayidx35, align 4
  %arrayidx37 = getelementptr inbounds float, float* %pOut, i32 %add
  store float %30, float* %arrayidx37, align 4
  %arrayidx39 = getelementptr inbounds float, float* %pOut, i32 %add6
  store float %32, float* %arrayidx39, align 4
  %arrayidx41 = getelementptr inbounds float, float* %pOut, i32 %add8
  store float %33, float* %arrayidx41, align 4
  %add43 = add i32 %k2.0114, 4
  %cmp3 = icmp ult i32 %add43, %sub
  br i1 %cmp3, label %for.body, label %for.cond.cleanup
}

define void @DCT_mve5(%struct.DCT_InstanceTypeDef* nocapture readonly %S, float* nocapture readonly %pIn, float* nocapture %pOut) {
; CHECK-LABEL: DCT_mve5:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    .pad #4
; CHECK-NEXT:    sub sp, #4
; CHECK-NEXT:    .vsave {d8, d9, d10, d11, d12, d13}
; CHECK-NEXT:    vpush {d8, d9, d10, d11, d12, d13}
; CHECK-NEXT:    .pad #32
; CHECK-NEXT:    sub sp, #32
; CHECK-NEXT:    str r1, [sp, #20] @ 4-byte Spill
; CHECK-NEXT:    ldr r1, [r0, #4]
; CHECK-NEXT:    subs r1, #5
; CHECK-NEXT:    str r1, [sp, #16] @ 4-byte Spill
; CHECK-NEXT:    cmp r1, #2
; CHECK-NEXT:    blo.w .LBB4_5
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    ldr r3, [r0, #8]
; CHECK-NEXT:    ldr r1, [r0]
; CHECK-NEXT:    adds r0, r3, #3
; CHECK-NEXT:    str r3, [sp, #12] @ 4-byte Spill
; CHECK-NEXT:    bic r0, r0, #3
; CHECK-NEXT:    add.w r8, r1, r3, lsl #2
; CHECK-NEXT:    subs r1, r0, #4
; CHECK-NEXT:    movs r0, #1
; CHECK-NEXT:    lsls r5, r3, #2
; CHECK-NEXT:    add.w r1, r0, r1, lsr #2
; CHECK-NEXT:    str r1, [sp, #8] @ 4-byte Spill
; CHECK-NEXT:    add.w r1, r3, r3, lsl #2
; CHECK-NEXT:    lsls r1, r1, #2
; CHECK-NEXT:    str r1, [sp, #4] @ 4-byte Spill
; CHECK-NEXT:  .LBB4_2: @ %for.body
; CHECK-NEXT:    @ =>This Loop Header: Depth=1
; CHECK-NEXT:    @ Child Loop BB4_3 Depth 2
; CHECK-NEXT:    ldr r7, [sp, #12] @ 4-byte Reload
; CHECK-NEXT:    adds r1, r0, #4
; CHECK-NEXT:    ldr r4, [sp, #20] @ 4-byte Reload
; CHECK-NEXT:    vmov.i32 q1, #0x0
; CHECK-NEXT:    ldr r6, [sp, #8] @ 4-byte Reload
; CHECK-NEXT:    add.w r10, r0, #2
; CHECK-NEXT:    str r1, [sp, #28] @ 4-byte Spill
; CHECK-NEXT:    adds r1, r0, #3
; CHECK-NEXT:    add.w r11, r0, #1
; CHECK-NEXT:    str r1, [sp, #24] @ 4-byte Spill
; CHECK-NEXT:    mov r3, r8
; CHECK-NEXT:    vmov q0, q1
; CHECK-NEXT:    vmov q3, q1
; CHECK-NEXT:    vmov q2, q1
; CHECK-NEXT:    vmov q4, q1
; CHECK-NEXT:    dlstp.32 lr, r7
; CHECK-NEXT:  .LBB4_3: @ %vector.body
; CHECK-NEXT:    @ Parent Loop BB4_2 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    add.w r9, r3, r5
; CHECK-NEXT:    vldrw.u32 q5, [r4], #16
; CHECK-NEXT:    vldrw.u32 q6, [r3], #16
; CHECK-NEXT:    add.w r12, r9, r5
; CHECK-NEXT:    vfma.f32 q3, q6, q5
; CHECK-NEXT:    vldrw.u32 q6, [r9]
; CHECK-NEXT:    add.w r6, r12, r5
; CHECK-NEXT:    vfma.f32 q4, q6, q5
; CHECK-NEXT:    vldrw.u32 q6, [r12]
; CHECK-NEXT:    adds r7, r6, r5
; CHECK-NEXT:    vfma.f32 q2, q6, q5
; CHECK-NEXT:    vldrw.u32 q6, [r6]
; CHECK-NEXT:    vfma.f32 q0, q6, q5
; CHECK-NEXT:    vldrw.u32 q6, [r7]
; CHECK-NEXT:    vfma.f32 q1, q6, q5
; CHECK-NEXT:    letp lr, .LBB4_3
; CHECK-NEXT:  @ %bb.4: @ %middle.block
; CHECK-NEXT:    @ in Loop: Header=BB4_2 Depth=1
; CHECK-NEXT:    vadd.f32 s18, s18, s19
; CHECK-NEXT:    add.w r1, r2, r11, lsl #2
; CHECK-NEXT:    vadd.f32 s16, s16, s17
; CHECK-NEXT:    vadd.f32 s14, s14, s15
; CHECK-NEXT:    vadd.f32 s12, s12, s13
; CHECK-NEXT:    vadd.f32 s6, s6, s7
; CHECK-NEXT:    vadd.f32 s4, s4, s5
; CHECK-NEXT:    vadd.f32 s10, s10, s11
; CHECK-NEXT:    vadd.f32 s8, s8, s9
; CHECK-NEXT:    vadd.f32 s0, s0, s1
; CHECK-NEXT:    vadd.f32 s1, s16, s18
; CHECK-NEXT:    vadd.f32 s2, s2, s3
; CHECK-NEXT:    vadd.f32 s12, s12, s14
; CHECK-NEXT:    vadd.f32 s4, s4, s6
; CHECK-NEXT:    vadd.f32 s6, s8, s10
; CHECK-NEXT:    vstr s1, [r1]
; CHECK-NEXT:    add.w r1, r2, r0, lsl #2
; CHECK-NEXT:    vadd.f32 s0, s0, s2
; CHECK-NEXT:    adds r0, #5
; CHECK-NEXT:    vstr s12, [r1]
; CHECK-NEXT:    add.w r1, r2, r10, lsl #2
; CHECK-NEXT:    vstr s6, [r1]
; CHECK-NEXT:    ldr r1, [sp, #24] @ 4-byte Reload
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s0, [r1]
; CHECK-NEXT:    ldr r1, [sp, #28] @ 4-byte Reload
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s4, [r1]
; CHECK-NEXT:    ldr r1, [sp, #4] @ 4-byte Reload
; CHECK-NEXT:    add r8, r1
; CHECK-NEXT:    ldr r1, [sp, #16] @ 4-byte Reload
; CHECK-NEXT:    cmp r0, r1
; CHECK-NEXT:    blo.w .LBB4_2
; CHECK-NEXT:  .LBB4_5: @ %for.cond.cleanup
; CHECK-NEXT:    add sp, #32
; CHECK-NEXT:    vpop {d8, d9, d10, d11, d12, d13}
; CHECK-NEXT:    add sp, #4
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
entry:
  %NumInputs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 2
  %0 = load i32, i32* %NumInputs, align 4
  %NumFilters = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 1
  %1 = load i32, i32* %NumFilters, align 4
  %pDCTCoefs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 0
  %2 = load float*, float** %pDCTCoefs, align 4
  %cmp = icmp ugt i32 %0, 1
  tail call void @llvm.assume(i1 %cmp)
  %sub = add i32 %1, -5
  %cmp3134 = icmp ugt i32 %sub, 1
  br i1 %cmp3134, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %n.rnd.up = add i32 %0, 3
  %n.vec = and i32 %n.rnd.up, -4
  br label %for.body

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  ret void

for.body:                                         ; preds = %for.body.preheader, %middle.block
  %k2.0135 = phi i32 [ %add52, %middle.block ], [ 1, %for.body.preheader ]
  %mul4 = mul i32 %k2.0135, %0
  %add = add nuw i32 %k2.0135, 1
  %mul5 = mul i32 %add, %0
  %add6 = add i32 %k2.0135, 2
  %mul7 = mul i32 %add6, %0
  %add8 = add i32 %k2.0135, 3
  %mul9 = mul i32 %add8, %0
  %add10 = add i32 %k2.0135, 4
  %mul11 = mul i32 %add10, %0
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %for.body
  %index = phi i32 [ 0, %for.body ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x float> [ zeroinitializer, %for.body ], [ %30, %vector.body ]
  %vec.phi136 = phi <4 x float> [ zeroinitializer, %for.body ], [ %31, %vector.body ]
  %vec.phi137 = phi <4 x float> [ zeroinitializer, %for.body ], [ %32, %vector.body ]
  %vec.phi138 = phi <4 x float> [ zeroinitializer, %for.body ], [ %33, %vector.body ]
  %vec.phi139 = phi <4 x float> [ zeroinitializer, %for.body ], [ %34, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %0)
  %3 = getelementptr inbounds float, float* %pIn, i32 %index
  %4 = bitcast float* %3 to <4 x float>*
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %4, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %5 = add i32 %index, %mul4
  %6 = getelementptr inbounds float, float* %2, i32 %5
  %7 = bitcast float* %6 to <4 x float>*
  %wide.masked.load140 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %7, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %8 = fmul fast <4 x float> %wide.masked.load140, %wide.masked.load
  %9 = fadd fast <4 x float> %8, %vec.phi137
  %10 = add i32 %index, %mul5
  %11 = getelementptr inbounds float, float* %2, i32 %10
  %12 = bitcast float* %11 to <4 x float>*
  %wide.masked.load141 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %12, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %13 = fmul fast <4 x float> %wide.masked.load141, %wide.masked.load
  %14 = fadd fast <4 x float> %13, %vec.phi139
  %15 = add i32 %index, %mul7
  %16 = getelementptr inbounds float, float* %2, i32 %15
  %17 = bitcast float* %16 to <4 x float>*
  %wide.masked.load142 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %17, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %18 = fmul fast <4 x float> %wide.masked.load142, %wide.masked.load
  %19 = fadd fast <4 x float> %18, %vec.phi138
  %20 = add i32 %index, %mul9
  %21 = getelementptr inbounds float, float* %2, i32 %20
  %22 = bitcast float* %21 to <4 x float>*
  %wide.masked.load143 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %22, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %23 = fmul fast <4 x float> %wide.masked.load143, %wide.masked.load
  %24 = fadd fast <4 x float> %23, %vec.phi136
  %25 = add i32 %index, %mul11
  %26 = getelementptr inbounds float, float* %2, i32 %25
  %27 = bitcast float* %26 to <4 x float>*
  %wide.masked.load144 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %27, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %28 = fmul fast <4 x float> %wide.masked.load144, %wide.masked.load
  %29 = fadd fast <4 x float> %28, %vec.phi
  %30 = select <4 x i1> %active.lane.mask, <4 x float> %29, <4 x float> %vec.phi
  %31 = select <4 x i1> %active.lane.mask, <4 x float> %24, <4 x float> %vec.phi136
  %32 = select <4 x i1> %active.lane.mask, <4 x float> %9, <4 x float> %vec.phi137
  %33 = select <4 x i1> %active.lane.mask, <4 x float> %19, <4 x float> %vec.phi138
  %34 = select <4 x i1> %active.lane.mask, <4 x float> %14, <4 x float> %vec.phi139
  %index.next = add i32 %index, 4
  %35 = icmp eq i32 %index.next, %n.vec
  br i1 %35, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %36 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %34)
  %37 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %33)
  %38 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %32)
  %39 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %31)
  %40 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %30)
  %arrayidx42 = getelementptr inbounds float, float* %pOut, i32 %k2.0135
  store float %38, float* %arrayidx42, align 4
  %arrayidx44 = getelementptr inbounds float, float* %pOut, i32 %add
  store float %36, float* %arrayidx44, align 4
  %arrayidx46 = getelementptr inbounds float, float* %pOut, i32 %add6
  store float %37, float* %arrayidx46, align 4
  %arrayidx48 = getelementptr inbounds float, float* %pOut, i32 %add8
  store float %39, float* %arrayidx48, align 4
  %arrayidx50 = getelementptr inbounds float, float* %pOut, i32 %add10
  store float %40, float* %arrayidx50, align 4
  %add52 = add i32 %k2.0135, 5
  %cmp3 = icmp ult i32 %add52, %sub
  br i1 %cmp3, label %for.body, label %for.cond.cleanup
}

define void @DCT_mve6(%struct.DCT_InstanceTypeDef* nocapture readonly %S, float* nocapture readonly %pIn, float* nocapture %pOut) {
; CHECK-LABEL: DCT_mve6:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    .pad #4
; CHECK-NEXT:    sub sp, #4
; CHECK-NEXT:    .vsave {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT:    vpush {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT:    .pad #32
; CHECK-NEXT:    sub sp, #32
; CHECK-NEXT:    str r1, [sp, #16] @ 4-byte Spill
; CHECK-NEXT:    ldr r1, [r0, #4]
; CHECK-NEXT:    subs r1, #6
; CHECK-NEXT:    str r1, [sp, #12] @ 4-byte Spill
; CHECK-NEXT:    cmp r1, #2
; CHECK-NEXT:    blo.w .LBB5_5
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    ldr r3, [r0, #8]
; CHECK-NEXT:    ldr r1, [r0]
; CHECK-NEXT:    adds r0, r3, #3
; CHECK-NEXT:    str r3, [sp, #8] @ 4-byte Spill
; CHECK-NEXT:    bic r0, r0, #3
; CHECK-NEXT:    add.w r8, r1, r3, lsl #2
; CHECK-NEXT:    subs r1, r0, #4
; CHECK-NEXT:    movs r0, #1
; CHECK-NEXT:    lsls r5, r3, #2
; CHECK-NEXT:    add.w r1, r0, r1, lsr #2
; CHECK-NEXT:    str r1, [sp, #4] @ 4-byte Spill
; CHECK-NEXT:    add.w r1, r3, r3, lsl #1
; CHECK-NEXT:    lsls r1, r1, #3
; CHECK-NEXT:    str r1, [sp] @ 4-byte Spill
; CHECK-NEXT:  .LBB5_2: @ %for.body
; CHECK-NEXT:    @ =>This Loop Header: Depth=1
; CHECK-NEXT:    @ Child Loop BB5_3 Depth 2
; CHECK-NEXT:    adds r1, r0, #5
; CHECK-NEXT:    str r1, [sp, #28] @ 4-byte Spill
; CHECK-NEXT:    adds r1, r0, #4
; CHECK-NEXT:    str r1, [sp, #24] @ 4-byte Spill
; CHECK-NEXT:    adds r1, r0, #3
; CHECK-NEXT:    ldr r7, [sp, #8] @ 4-byte Reload
; CHECK-NEXT:    str r1, [sp, #20] @ 4-byte Spill
; CHECK-NEXT:    vmov.i32 q1, #0x0
; CHECK-NEXT:    ldr r1, [sp, #16] @ 4-byte Reload
; CHECK-NEXT:    add.w r11, r0, #2
; CHECK-NEXT:    ldr r6, [sp, #4] @ 4-byte Reload
; CHECK-NEXT:    adds r4, r0, #1
; CHECK-NEXT:    mov r3, r8
; CHECK-NEXT:    vmov q3, q1
; CHECK-NEXT:    vmov q4, q1
; CHECK-NEXT:    vmov q0, q1
; CHECK-NEXT:    vmov q5, q1
; CHECK-NEXT:    vmov q2, q1
; CHECK-NEXT:    dlstp.32 lr, r7
; CHECK-NEXT:  .LBB5_3: @ %vector.body
; CHECK-NEXT:    @ Parent Loop BB5_2 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    add.w r12, r3, r5
; CHECK-NEXT:    vldrw.u32 q6, [r1], #16
; CHECK-NEXT:    vldrw.u32 q7, [r3], #16
; CHECK-NEXT:    add.w r10, r12, r5
; CHECK-NEXT:    vfma.f32 q4, q7, q6
; CHECK-NEXT:    vldrw.u32 q7, [r12]
; CHECK-NEXT:    add.w r6, r10, r5
; CHECK-NEXT:    vfma.f32 q5, q7, q6
; CHECK-NEXT:    vldrw.u32 q7, [r10]
; CHECK-NEXT:    adds r7, r6, r5
; CHECK-NEXT:    vfma.f32 q2, q7, q6
; CHECK-NEXT:    vldrw.u32 q7, [r6]
; CHECK-NEXT:    adds r6, r7, r5
; CHECK-NEXT:    vfma.f32 q0, q7, q6
; CHECK-NEXT:    vldrw.u32 q7, [r7]
; CHECK-NEXT:    vfma.f32 q3, q7, q6
; CHECK-NEXT:    vldrw.u32 q7, [r6]
; CHECK-NEXT:    vfma.f32 q1, q7, q6
; CHECK-NEXT:    letp lr, .LBB5_3
; CHECK-NEXT:  @ %bb.4: @ %middle.block
; CHECK-NEXT:    @ in Loop: Header=BB5_2 Depth=1
; CHECK-NEXT:    vadd.f32 s22, s22, s23
; CHECK-NEXT:    add.w r1, r2, r4, lsl #2
; CHECK-NEXT:    vadd.f32 s20, s20, s21
; CHECK-NEXT:    vadd.f32 s18, s18, s19
; CHECK-NEXT:    vadd.f32 s16, s16, s17
; CHECK-NEXT:    vadd.f32 s10, s10, s11
; CHECK-NEXT:    vadd.f32 s8, s8, s9
; CHECK-NEXT:    vadd.f32 s0, s0, s1
; CHECK-NEXT:    vadd.f32 s2, s2, s3
; CHECK-NEXT:    vadd.f32 s1, s20, s22
; CHECK-NEXT:    vadd.f32 s6, s6, s7
; CHECK-NEXT:    vadd.f32 s3, s16, s18
; CHECK-NEXT:    vadd.f32 s4, s4, s5
; CHECK-NEXT:    vadd.f32 s8, s8, s10
; CHECK-NEXT:    vadd.f32 s14, s14, s15
; CHECK-NEXT:    vadd.f32 s12, s12, s13
; CHECK-NEXT:    vstr s1, [r1]
; CHECK-NEXT:    add.w r1, r2, r0, lsl #2
; CHECK-NEXT:    vadd.f32 s0, s0, s2
; CHECK-NEXT:    adds r0, #6
; CHECK-NEXT:    vstr s3, [r1]
; CHECK-NEXT:    add.w r1, r2, r11, lsl #2
; CHECK-NEXT:    vadd.f32 s4, s4, s6
; CHECK-NEXT:    vstr s8, [r1]
; CHECK-NEXT:    ldr r1, [sp, #20] @ 4-byte Reload
; CHECK-NEXT:    vadd.f32 s6, s12, s14
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s0, [r1]
; CHECK-NEXT:    ldr r1, [sp, #24] @ 4-byte Reload
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s6, [r1]
; CHECK-NEXT:    ldr r1, [sp, #28] @ 4-byte Reload
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s4, [r1]
; CHECK-NEXT:    ldr r1, [sp] @ 4-byte Reload
; CHECK-NEXT:    add r8, r1
; CHECK-NEXT:    ldr r1, [sp, #12] @ 4-byte Reload
; CHECK-NEXT:    cmp r0, r1
; CHECK-NEXT:    blo.w .LBB5_2
; CHECK-NEXT:  .LBB5_5: @ %for.cond.cleanup
; CHECK-NEXT:    add sp, #32
; CHECK-NEXT:    vpop {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT:    add sp, #4
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
entry:
  %NumInputs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 2
  %0 = load i32, i32* %NumInputs, align 4
  %NumFilters = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 1
  %1 = load i32, i32* %NumFilters, align 4
  %pDCTCoefs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 0
  %2 = load float*, float** %pDCTCoefs, align 4
  %cmp = icmp ugt i32 %0, 1
  tail call void @llvm.assume(i1 %cmp)
  %sub = add i32 %1, -6
  %cmp3155 = icmp ugt i32 %sub, 1
  br i1 %cmp3155, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %n.rnd.up = add i32 %0, 3
  %n.vec = and i32 %n.rnd.up, -4
  br label %for.body

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  ret void

for.body:                                         ; preds = %for.body.preheader, %middle.block
  %k2.0156 = phi i32 [ %add61, %middle.block ], [ 1, %for.body.preheader ]
  %mul4 = mul i32 %k2.0156, %0
  %add = add nuw i32 %k2.0156, 1
  %mul5 = mul i32 %add, %0
  %add6 = add i32 %k2.0156, 2
  %mul7 = mul i32 %add6, %0
  %add8 = add i32 %k2.0156, 3
  %mul9 = mul i32 %add8, %0
  %add10 = add i32 %k2.0156, 4
  %mul11 = mul i32 %add10, %0
  %add12 = add i32 %k2.0156, 5
  %mul13 = mul i32 %add12, %0
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %for.body
  %index = phi i32 [ 0, %for.body ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x float> [ zeroinitializer, %for.body ], [ %35, %vector.body ]
  %vec.phi157 = phi <4 x float> [ zeroinitializer, %for.body ], [ %36, %vector.body ]
  %vec.phi158 = phi <4 x float> [ zeroinitializer, %for.body ], [ %37, %vector.body ]
  %vec.phi159 = phi <4 x float> [ zeroinitializer, %for.body ], [ %38, %vector.body ]
  %vec.phi160 = phi <4 x float> [ zeroinitializer, %for.body ], [ %39, %vector.body ]
  %vec.phi161 = phi <4 x float> [ zeroinitializer, %for.body ], [ %40, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %0)
  %3 = getelementptr inbounds float, float* %pIn, i32 %index
  %4 = bitcast float* %3 to <4 x float>*
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %4, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %5 = add i32 %index, %mul4
  %6 = getelementptr inbounds float, float* %2, i32 %5
  %7 = bitcast float* %6 to <4 x float>*
  %wide.masked.load162 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %7, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %8 = fmul fast <4 x float> %wide.masked.load162, %wide.masked.load
  %9 = fadd fast <4 x float> %8, %vec.phi158
  %10 = add i32 %index, %mul5
  %11 = getelementptr inbounds float, float* %2, i32 %10
  %12 = bitcast float* %11 to <4 x float>*
  %wide.masked.load163 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %12, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %13 = fmul fast <4 x float> %wide.masked.load163, %wide.masked.load
  %14 = fadd fast <4 x float> %13, %vec.phi160
  %15 = add i32 %index, %mul7
  %16 = getelementptr inbounds float, float* %2, i32 %15
  %17 = bitcast float* %16 to <4 x float>*
  %wide.masked.load164 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %17, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %18 = fmul fast <4 x float> %wide.masked.load164, %wide.masked.load
  %19 = fadd fast <4 x float> %18, %vec.phi161
  %20 = add i32 %index, %mul9
  %21 = getelementptr inbounds float, float* %2, i32 %20
  %22 = bitcast float* %21 to <4 x float>*
  %wide.masked.load165 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %22, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %23 = fmul fast <4 x float> %wide.masked.load165, %wide.masked.load
  %24 = fadd fast <4 x float> %23, %vec.phi159
  %25 = add i32 %index, %mul11
  %26 = getelementptr inbounds float, float* %2, i32 %25
  %27 = bitcast float* %26 to <4 x float>*
  %wide.masked.load166 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %27, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %28 = fmul fast <4 x float> %wide.masked.load166, %wide.masked.load
  %29 = fadd fast <4 x float> %28, %vec.phi157
  %30 = add i32 %index, %mul13
  %31 = getelementptr inbounds float, float* %2, i32 %30
  %32 = bitcast float* %31 to <4 x float>*
  %wide.masked.load167 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %32, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %33 = fmul fast <4 x float> %wide.masked.load167, %wide.masked.load
  %34 = fadd fast <4 x float> %33, %vec.phi
  %35 = select <4 x i1> %active.lane.mask, <4 x float> %34, <4 x float> %vec.phi
  %36 = select <4 x i1> %active.lane.mask, <4 x float> %29, <4 x float> %vec.phi157
  %37 = select <4 x i1> %active.lane.mask, <4 x float> %9, <4 x float> %vec.phi158
  %38 = select <4 x i1> %active.lane.mask, <4 x float> %24, <4 x float> %vec.phi159
  %39 = select <4 x i1> %active.lane.mask, <4 x float> %14, <4 x float> %vec.phi160
  %40 = select <4 x i1> %active.lane.mask, <4 x float> %19, <4 x float> %vec.phi161
  %index.next = add i32 %index, 4
  %41 = icmp eq i32 %index.next, %n.vec
  br i1 %41, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %42 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %40)
  %43 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %39)
  %44 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %38)
  %45 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %37)
  %46 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %36)
  %47 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %35)
  %arrayidx49 = getelementptr inbounds float, float* %pOut, i32 %k2.0156
  store float %45, float* %arrayidx49, align 4
  %arrayidx51 = getelementptr inbounds float, float* %pOut, i32 %add
  store float %43, float* %arrayidx51, align 4
  %arrayidx53 = getelementptr inbounds float, float* %pOut, i32 %add6
  store float %42, float* %arrayidx53, align 4
  %arrayidx55 = getelementptr inbounds float, float* %pOut, i32 %add8
  store float %44, float* %arrayidx55, align 4
  %arrayidx57 = getelementptr inbounds float, float* %pOut, i32 %add10
  store float %46, float* %arrayidx57, align 4
  %arrayidx59 = getelementptr inbounds float, float* %pOut, i32 %add12
  store float %47, float* %arrayidx59, align 4
  %add61 = add i32 %k2.0156, 6
  %cmp3 = icmp ult i32 %add61, %sub
  br i1 %cmp3, label %for.body, label %for.cond.cleanup
}

define void @DCT_mve7(%struct.DCT_InstanceTypeDef* nocapture readonly %S, float* nocapture readonly %pIn, float* nocapture %pOut) {
; CHECK-LABEL: DCT_mve7:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    .pad #4
; CHECK-NEXT:    sub sp, #4
; CHECK-NEXT:    .vsave {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT:    vpush {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT:    .pad #72
; CHECK-NEXT:    sub sp, #72
; CHECK-NEXT:    str r1, [sp, #20] @ 4-byte Spill
; CHECK-NEXT:    ldr r1, [r0, #4]
; CHECK-NEXT:    subs r1, #7
; CHECK-NEXT:    str r1, [sp, #16] @ 4-byte Spill
; CHECK-NEXT:    cmp r1, #2
; CHECK-NEXT:    blo.w .LBB6_5
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    ldr r3, [r0, #8]
; CHECK-NEXT:    ldr r1, [r0]
; CHECK-NEXT:    adds r0, r3, #3
; CHECK-NEXT:    str r3, [sp, #12] @ 4-byte Spill
; CHECK-NEXT:    bic r0, r0, #3
; CHECK-NEXT:    add.w r9, r1, r3, lsl #2
; CHECK-NEXT:    subs r1, r0, #4
; CHECK-NEXT:    movs r0, #1
; CHECK-NEXT:    lsls r5, r3, #2
; CHECK-NEXT:    add.w r1, r0, r1, lsr #2
; CHECK-NEXT:    str r1, [sp, #8] @ 4-byte Spill
; CHECK-NEXT:    rsb r1, r3, r3, lsl #3
; CHECK-NEXT:    lsls r1, r1, #2
; CHECK-NEXT:    str r1, [sp, #4] @ 4-byte Spill
; CHECK-NEXT:  .LBB6_2: @ %for.body
; CHECK-NEXT:    @ =>This Loop Header: Depth=1
; CHECK-NEXT:    @ Child Loop BB6_3 Depth 2
; CHECK-NEXT:    adds r1, r0, #6
; CHECK-NEXT:    str r1, [sp, #36] @ 4-byte Spill
; CHECK-NEXT:    adds r1, r0, #5
; CHECK-NEXT:    str r1, [sp, #32] @ 4-byte Spill
; CHECK-NEXT:    adds r1, r0, #4
; CHECK-NEXT:    str r1, [sp, #28] @ 4-byte Spill
; CHECK-NEXT:    adds r1, r0, #3
; CHECK-NEXT:    ldr r7, [sp, #12] @ 4-byte Reload
; CHECK-NEXT:    str r1, [sp, #24] @ 4-byte Spill
; CHECK-NEXT:    vmov.i32 q2, #0x0
; CHECK-NEXT:    ldr r1, [sp, #20] @ 4-byte Reload
; CHECK-NEXT:    adds r4, r0, #2
; CHECK-NEXT:    ldr r6, [sp, #8] @ 4-byte Reload
; CHECK-NEXT:    add.w r8, r0, #1
; CHECK-NEXT:    mov r3, r9
; CHECK-NEXT:    vmov q4, q2
; CHECK-NEXT:    vmov q5, q2
; CHECK-NEXT:    vmov q3, q2
; CHECK-NEXT:    vmov q6, q2
; CHECK-NEXT:    vmov q1, q2
; CHECK-NEXT:    mov r12, r7
; CHECK-NEXT:    vstrw.32 q2, [sp, #56] @ 16-byte Spill
; CHECK-NEXT:    dls lr, r6
; CHECK-NEXT:  .LBB6_3: @ %vector.body
; CHECK-NEXT:    @ Parent Loop BB6_2 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vctp.32 r12
; CHECK-NEXT:    add.w r10, r3, r5
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vldrwt.u32 q7, [r1], #16
; CHECK-NEXT:    vldrwt.u32 q0, [r3], #16
; CHECK-NEXT:    add.w r11, r10, r5
; CHECK-NEXT:    sub.w r12, r12, #4
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vfmat.f32 q5, q0, q7
; CHECK-NEXT:    vldrwt.u32 q0, [r10]
; CHECK-NEXT:    add.w r6, r11, r5
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vfmat.f32 q6, q0, q7
; CHECK-NEXT:    vldrwt.u32 q0, [r11]
; CHECK-NEXT:    vstrw.32 q6, [sp, #40] @ 16-byte Spill
; CHECK-NEXT:    vmov q6, q5
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vfmat.f32 q1, q0, q7
; CHECK-NEXT:    vmov q5, q4
; CHECK-NEXT:    vmov q4, q3
; CHECK-NEXT:    vmov q3, q1
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vldrwt.u32 q0, [r6]
; CHECK-NEXT:    vldrw.u32 q1, [sp, #56] @ 16-byte Reload
; CHECK-NEXT:    adds r7, r6, r5
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vfmat.f32 q1, q0, q7
; CHECK-NEXT:    vldrwt.u32 q0, [r7]
; CHECK-NEXT:    adds r6, r7, r5
; CHECK-NEXT:    vstrw.32 q1, [sp, #56] @ 16-byte Spill
; CHECK-NEXT:    vmov q1, q3
; CHECK-NEXT:    vmov q3, q4
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vfmat.f32 q3, q0, q7
; CHECK-NEXT:    vldrwt.u32 q0, [r6]
; CHECK-NEXT:    vmov q4, q5
; CHECK-NEXT:    adds r7, r6, r5
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vfmat.f32 q4, q0, q7
; CHECK-NEXT:    vldrwt.u32 q0, [r7]
; CHECK-NEXT:    vmov q5, q6
; CHECK-NEXT:    vldrw.u32 q6, [sp, #40] @ 16-byte Reload
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vfmat.f32 q2, q0, q7
; CHECK-NEXT:    le lr, .LBB6_3
; CHECK-NEXT:  @ %bb.4: @ %middle.block
; CHECK-NEXT:    @ in Loop: Header=BB6_2 Depth=1
; CHECK-NEXT:    vadd.f32 s0, s26, s27
; CHECK-NEXT:    add.w r1, r2, r8, lsl #2
; CHECK-NEXT:    vadd.f32 s2, s24, s25
; CHECK-NEXT:    vadd.f32 s1, s22, s23
; CHECK-NEXT:    vadd.f32 s3, s20, s21
; CHECK-NEXT:    vadd.f32 s6, s6, s7
; CHECK-NEXT:    vadd.f32 s4, s4, s5
; CHECK-NEXT:    vadd.f32 s10, s10, s11
; CHECK-NEXT:    vadd.f32 s8, s8, s9
; CHECK-NEXT:    vadd.f32 s0, s2, s0
; CHECK-NEXT:    vadd.f32 s9, s18, s19
; CHECK-NEXT:    vadd.f32 s11, s16, s17
; CHECK-NEXT:    vldrw.u32 q4, [sp, #56] @ 16-byte Reload
; CHECK-NEXT:    vadd.f32 s2, s3, s1
; CHECK-NEXT:    vadd.f32 s5, s18, s19
; CHECK-NEXT:    vadd.f32 s7, s16, s17
; CHECK-NEXT:    vadd.f32 s4, s4, s6
; CHECK-NEXT:    vstr s0, [r1]
; CHECK-NEXT:    add.w r1, r2, r0, lsl #2
; CHECK-NEXT:    vadd.f32 s14, s14, s15
; CHECK-NEXT:    adds r0, #7
; CHECK-NEXT:    vadd.f32 s12, s12, s13
; CHECK-NEXT:    vstr s2, [r1]
; CHECK-NEXT:    add.w r1, r2, r4, lsl #2
; CHECK-NEXT:    vadd.f32 s8, s8, s10
; CHECK-NEXT:    vadd.f32 s6, s7, s5
; CHECK-NEXT:    vstr s4, [r1]
; CHECK-NEXT:    vadd.f32 s10, s11, s9
; CHECK-NEXT:    ldr r1, [sp, #24] @ 4-byte Reload
; CHECK-NEXT:    vadd.f32 s12, s12, s14
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s6, [r1]
; CHECK-NEXT:    ldr r1, [sp, #28] @ 4-byte Reload
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s12, [r1]
; CHECK-NEXT:    ldr r1, [sp, #32] @ 4-byte Reload
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s10, [r1]
; CHECK-NEXT:    ldr r1, [sp, #36] @ 4-byte Reload
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s8, [r1]
; CHECK-NEXT:    ldr r1, [sp, #4] @ 4-byte Reload
; CHECK-NEXT:    add r9, r1
; CHECK-NEXT:    ldr r1, [sp, #16] @ 4-byte Reload
; CHECK-NEXT:    cmp r0, r1
; CHECK-NEXT:    blo.w .LBB6_2
; CHECK-NEXT:  .LBB6_5: @ %for.cond.cleanup
; CHECK-NEXT:    add sp, #72
; CHECK-NEXT:    vpop {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT:    add sp, #4
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
entry:
  %NumInputs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 2
  %0 = load i32, i32* %NumInputs, align 4
  %NumFilters = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 1
  %1 = load i32, i32* %NumFilters, align 4
  %pDCTCoefs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 0
  %2 = load float*, float** %pDCTCoefs, align 4
  %cmp = icmp ugt i32 %0, 1
  tail call void @llvm.assume(i1 %cmp)
  %sub = add i32 %1, -7
  %cmp3176 = icmp ugt i32 %sub, 1
  br i1 %cmp3176, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %n.rnd.up = add i32 %0, 3
  %n.vec = and i32 %n.rnd.up, -4
  br label %for.body

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  ret void

for.body:                                         ; preds = %for.body.preheader, %middle.block
  %k2.0177 = phi i32 [ %add70, %middle.block ], [ 1, %for.body.preheader ]
  %mul4 = mul i32 %k2.0177, %0
  %add = add nuw i32 %k2.0177, 1
  %mul5 = mul i32 %add, %0
  %add6 = add i32 %k2.0177, 2
  %mul7 = mul i32 %add6, %0
  %add8 = add i32 %k2.0177, 3
  %mul9 = mul i32 %add8, %0
  %add10 = add i32 %k2.0177, 4
  %mul11 = mul i32 %add10, %0
  %add12 = add i32 %k2.0177, 5
  %mul13 = mul i32 %add12, %0
  %add14 = add i32 %k2.0177, 6
  %mul15 = mul i32 %add14, %0
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %for.body
  %index = phi i32 [ 0, %for.body ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x float> [ zeroinitializer, %for.body ], [ %40, %vector.body ]
  %vec.phi178 = phi <4 x float> [ zeroinitializer, %for.body ], [ %41, %vector.body ]
  %vec.phi179 = phi <4 x float> [ zeroinitializer, %for.body ], [ %42, %vector.body ]
  %vec.phi180 = phi <4 x float> [ zeroinitializer, %for.body ], [ %43, %vector.body ]
  %vec.phi181 = phi <4 x float> [ zeroinitializer, %for.body ], [ %44, %vector.body ]
  %vec.phi182 = phi <4 x float> [ zeroinitializer, %for.body ], [ %45, %vector.body ]
  %vec.phi183 = phi <4 x float> [ zeroinitializer, %for.body ], [ %46, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %0)
  %3 = getelementptr inbounds float, float* %pIn, i32 %index
  %4 = bitcast float* %3 to <4 x float>*
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %4, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %5 = add i32 %index, %mul4
  %6 = getelementptr inbounds float, float* %2, i32 %5
  %7 = bitcast float* %6 to <4 x float>*
  %wide.masked.load184 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %7, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %8 = fmul fast <4 x float> %wide.masked.load184, %wide.masked.load
  %9 = fadd fast <4 x float> %8, %vec.phi179
  %10 = add i32 %index, %mul5
  %11 = getelementptr inbounds float, float* %2, i32 %10
  %12 = bitcast float* %11 to <4 x float>*
  %wide.masked.load185 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %12, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %13 = fmul fast <4 x float> %wide.masked.load185, %wide.masked.load
  %14 = fadd fast <4 x float> %13, %vec.phi181
  %15 = add i32 %index, %mul7
  %16 = getelementptr inbounds float, float* %2, i32 %15
  %17 = bitcast float* %16 to <4 x float>*
  %wide.masked.load186 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %17, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %18 = fmul fast <4 x float> %wide.masked.load186, %wide.masked.load
  %19 = fadd fast <4 x float> %18, %vec.phi183
  %20 = add i32 %index, %mul9
  %21 = getelementptr inbounds float, float* %2, i32 %20
  %22 = bitcast float* %21 to <4 x float>*
  %wide.masked.load187 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %22, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %23 = fmul fast <4 x float> %wide.masked.load187, %wide.masked.load
  %24 = fadd fast <4 x float> %23, %vec.phi182
  %25 = add i32 %index, %mul11
  %26 = getelementptr inbounds float, float* %2, i32 %25
  %27 = bitcast float* %26 to <4 x float>*
  %wide.masked.load188 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %27, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %28 = fmul fast <4 x float> %wide.masked.load188, %wide.masked.load
  %29 = fadd fast <4 x float> %28, %vec.phi180
  %30 = add i32 %index, %mul13
  %31 = getelementptr inbounds float, float* %2, i32 %30
  %32 = bitcast float* %31 to <4 x float>*
  %wide.masked.load189 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %32, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %33 = fmul fast <4 x float> %wide.masked.load189, %wide.masked.load
  %34 = fadd fast <4 x float> %33, %vec.phi178
  %35 = add i32 %index, %mul15
  %36 = getelementptr inbounds float, float* %2, i32 %35
  %37 = bitcast float* %36 to <4 x float>*
  %wide.masked.load190 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %37, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %38 = fmul fast <4 x float> %wide.masked.load190, %wide.masked.load
  %39 = fadd fast <4 x float> %38, %vec.phi
  %40 = select <4 x i1> %active.lane.mask, <4 x float> %39, <4 x float> %vec.phi
  %41 = select <4 x i1> %active.lane.mask, <4 x float> %34, <4 x float> %vec.phi178
  %42 = select <4 x i1> %active.lane.mask, <4 x float> %9, <4 x float> %vec.phi179
  %43 = select <4 x i1> %active.lane.mask, <4 x float> %29, <4 x float> %vec.phi180
  %44 = select <4 x i1> %active.lane.mask, <4 x float> %14, <4 x float> %vec.phi181
  %45 = select <4 x i1> %active.lane.mask, <4 x float> %24, <4 x float> %vec.phi182
  %46 = select <4 x i1> %active.lane.mask, <4 x float> %19, <4 x float> %vec.phi183
  %index.next = add i32 %index, 4
  %47 = icmp eq i32 %index.next, %n.vec
  br i1 %47, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %48 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %46)
  %49 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %45)
  %50 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %44)
  %51 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %43)
  %52 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %42)
  %53 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %41)
  %54 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %40)
  %arrayidx56 = getelementptr inbounds float, float* %pOut, i32 %k2.0177
  store float %52, float* %arrayidx56, align 4
  %arrayidx58 = getelementptr inbounds float, float* %pOut, i32 %add
  store float %50, float* %arrayidx58, align 4
  %arrayidx60 = getelementptr inbounds float, float* %pOut, i32 %add6
  store float %48, float* %arrayidx60, align 4
  %arrayidx62 = getelementptr inbounds float, float* %pOut, i32 %add8
  store float %49, float* %arrayidx62, align 4
  %arrayidx64 = getelementptr inbounds float, float* %pOut, i32 %add10
  store float %51, float* %arrayidx64, align 4
  %arrayidx66 = getelementptr inbounds float, float* %pOut, i32 %add12
  store float %53, float* %arrayidx66, align 4
  %arrayidx68 = getelementptr inbounds float, float* %pOut, i32 %add14
  store float %54, float* %arrayidx68, align 4
  %add70 = add i32 %k2.0177, 7
  %cmp3 = icmp ult i32 %add70, %sub
  br i1 %cmp3, label %for.body, label %for.cond.cleanup
}

define void @DCT_mve8(%struct.DCT_InstanceTypeDef* nocapture readonly %S, float* nocapture readonly %pIn, float* nocapture %pOut) {
; CHECK-LABEL: DCT_mve8:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11, lr}
; CHECK-NEXT:    .pad #4
; CHECK-NEXT:    sub sp, #4
; CHECK-NEXT:    .vsave {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT:    vpush {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT:    .pad #88
; CHECK-NEXT:    sub sp, #88
; CHECK-NEXT:    str r1, [sp, #20] @ 4-byte Spill
; CHECK-NEXT:    ldr r1, [r0, #4]
; CHECK-NEXT:    subs r1, #8
; CHECK-NEXT:    str r1, [sp, #16] @ 4-byte Spill
; CHECK-NEXT:    cmp r1, #2
; CHECK-NEXT:    blo.w .LBB7_5
; CHECK-NEXT:  @ %bb.1: @ %for.body.preheader
; CHECK-NEXT:    ldr r3, [r0, #8]
; CHECK-NEXT:    ldr r1, [r0]
; CHECK-NEXT:    adds r0, r3, #3
; CHECK-NEXT:    str r3, [sp, #12] @ 4-byte Spill
; CHECK-NEXT:    bic r0, r0, #3
; CHECK-NEXT:    add.w r12, r1, r3, lsl #2
; CHECK-NEXT:    subs r1, r0, #4
; CHECK-NEXT:    movs r0, #1
; CHECK-NEXT:    lsls r5, r3, #2
; CHECK-NEXT:    add.w r1, r0, r1, lsr #2
; CHECK-NEXT:    str r1, [sp, #8] @ 4-byte Spill
; CHECK-NEXT:    lsls r1, r3, #5
; CHECK-NEXT:    str r1, [sp, #4] @ 4-byte Spill
; CHECK-NEXT:  .LBB7_2: @ %for.body
; CHECK-NEXT:    @ =>This Loop Header: Depth=1
; CHECK-NEXT:    @ Child Loop BB7_3 Depth 2
; CHECK-NEXT:    adds r1, r0, #7
; CHECK-NEXT:    str r1, [sp, #36] @ 4-byte Spill
; CHECK-NEXT:    adds r1, r0, #6
; CHECK-NEXT:    str r1, [sp, #32] @ 4-byte Spill
; CHECK-NEXT:    adds r1, r0, #5
; CHECK-NEXT:    ldr r7, [sp, #12] @ 4-byte Reload
; CHECK-NEXT:    str r1, [sp, #28] @ 4-byte Spill
; CHECK-NEXT:    adds r1, r0, #4
; CHECK-NEXT:    ldr.w r9, [sp, #20] @ 4-byte Reload
; CHECK-NEXT:    vmov.i32 q3, #0x0
; CHECK-NEXT:    ldr r6, [sp, #8] @ 4-byte Reload
; CHECK-NEXT:    adds r4, r0, #3
; CHECK-NEXT:    str r1, [sp, #24] @ 4-byte Spill
; CHECK-NEXT:    add.w r8, r0, #2
; CHECK-NEXT:    adds r1, r0, #1
; CHECK-NEXT:    mov r3, r12
; CHECK-NEXT:    vmov q5, q3
; CHECK-NEXT:    vmov q6, q3
; CHECK-NEXT:    vmov q4, q3
; CHECK-NEXT:    vmov q7, q3
; CHECK-NEXT:    vmov q2, q3
; CHECK-NEXT:    mov r10, r7
; CHECK-NEXT:    vstrw.32 q3, [sp, #56] @ 16-byte Spill
; CHECK-NEXT:    vstrw.32 q3, [sp, #72] @ 16-byte Spill
; CHECK-NEXT:    dls lr, r6
; CHECK-NEXT:  .LBB7_3: @ %vector.body
; CHECK-NEXT:    @ Parent Loop BB7_2 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vctp.32 r10
; CHECK-NEXT:    add.w r11, r3, r5
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vldrwt.u32 q0, [r9], #16
; CHECK-NEXT:    vldrwt.u32 q1, [r3], #16
; CHECK-NEXT:    add.w r6, r11, r5
; CHECK-NEXT:    sub.w r10, r10, #4
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vfmat.f32 q6, q1, q0
; CHECK-NEXT:    vldrwt.u32 q1, [r11]
; CHECK-NEXT:    vstrw.32 q6, [sp, #40] @ 16-byte Spill
; CHECK-NEXT:    vmov q6, q5
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vfmat.f32 q7, q1, q0
; CHECK-NEXT:    vmov q5, q3
; CHECK-NEXT:    vmov q3, q4
; CHECK-NEXT:    vmov q4, q2
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vldrwt.u32 q1, [r6]
; CHECK-NEXT:    vldrw.u32 q2, [sp, #56] @ 16-byte Reload
; CHECK-NEXT:    adds r7, r6, r5
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vfmat.f32 q2, q1, q0
; CHECK-NEXT:    vldrwt.u32 q1, [r7]
; CHECK-NEXT:    vstrw.32 q2, [sp, #56] @ 16-byte Spill
; CHECK-NEXT:    vldrw.u32 q2, [sp, #72] @ 16-byte Reload
; CHECK-NEXT:    adds r6, r7, r5
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vfmat.f32 q2, q1, q0
; CHECK-NEXT:    vldrwt.u32 q1, [r6]
; CHECK-NEXT:    adds r7, r6, r5
; CHECK-NEXT:    vstrw.32 q2, [sp, #72] @ 16-byte Spill
; CHECK-NEXT:    vmov q2, q4
; CHECK-NEXT:    vmov q4, q3
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vfmat.f32 q2, q1, q0
; CHECK-NEXT:    vldrwt.u32 q1, [r7]
; CHECK-NEXT:    adds r6, r7, r5
; CHECK-NEXT:    vmov q3, q5
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vfmat.f32 q4, q1, q0
; CHECK-NEXT:    vldrwt.u32 q1, [r6]
; CHECK-NEXT:    vmov q5, q6
; CHECK-NEXT:    add r6, r5
; CHECK-NEXT:    vpstt
; CHECK-NEXT:    vfmat.f32 q5, q1, q0
; CHECK-NEXT:    vldrwt.u32 q1, [r6]
; CHECK-NEXT:    vldrw.u32 q6, [sp, #40] @ 16-byte Reload
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vfmat.f32 q3, q1, q0
; CHECK-NEXT:    le lr, .LBB7_3
; CHECK-NEXT:  @ %bb.4: @ %middle.block
; CHECK-NEXT:    @ in Loop: Header=BB7_2 Depth=1
; CHECK-NEXT:    vadd.f32 s0, s30, s31
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vadd.f32 s2, s28, s29
; CHECK-NEXT:    vadd.f32 s4, s26, s27
; CHECK-NEXT:    vadd.f32 s6, s24, s25
; CHECK-NEXT:    vadd.f32 s5, s18, s19
; CHECK-NEXT:    vadd.f32 s7, s16, s17
; CHECK-NEXT:    vldrw.u32 q4, [sp, #56] @ 16-byte Reload
; CHECK-NEXT:    vadd.f32 s10, s10, s11
; CHECK-NEXT:    vadd.f32 s8, s8, s9
; CHECK-NEXT:    vadd.f32 s9, s18, s19
; CHECK-NEXT:    vadd.f32 s11, s16, s17
; CHECK-NEXT:    vldrw.u32 q4, [sp, #72] @ 16-byte Reload
; CHECK-NEXT:    vadd.f32 s14, s14, s15
; CHECK-NEXT:    vadd.f32 s12, s12, s13
; CHECK-NEXT:    vadd.f32 s13, s18, s19
; CHECK-NEXT:    vadd.f32 s15, s16, s17
; CHECK-NEXT:    vadd.f32 s0, s2, s0
; CHECK-NEXT:    vadd.f32 s2, s6, s4
; CHECK-NEXT:    vadd.f32 s8, s8, s10
; CHECK-NEXT:    vadd.f32 s10, s11, s9
; CHECK-NEXT:    vadd.f32 s6, s12, s14
; CHECK-NEXT:    vadd.f32 s1, s22, s23
; CHECK-NEXT:    vadd.f32 s14, s15, s13
; CHECK-NEXT:    vstr s0, [r1]
; CHECK-NEXT:    add.w r1, r2, r0, lsl #2
; CHECK-NEXT:    vadd.f32 s3, s20, s21
; CHECK-NEXT:    adds r0, #8
; CHECK-NEXT:    vstr s2, [r1]
; CHECK-NEXT:    add.w r1, r2, r8, lsl #2
; CHECK-NEXT:    vadd.f32 s12, s7, s5
; CHECK-NEXT:    vstr s10, [r1]
; CHECK-NEXT:    add.w r1, r2, r4, lsl #2
; CHECK-NEXT:    vstr s14, [r1]
; CHECK-NEXT:    ldr r1, [sp, #24] @ 4-byte Reload
; CHECK-NEXT:    vadd.f32 s4, s3, s1
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s8, [r1]
; CHECK-NEXT:    ldr r1, [sp, #28] @ 4-byte Reload
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s12, [r1]
; CHECK-NEXT:    ldr r1, [sp, #32] @ 4-byte Reload
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s4, [r1]
; CHECK-NEXT:    ldr r1, [sp, #36] @ 4-byte Reload
; CHECK-NEXT:    add.w r1, r2, r1, lsl #2
; CHECK-NEXT:    vstr s6, [r1]
; CHECK-NEXT:    ldr r1, [sp, #4] @ 4-byte Reload
; CHECK-NEXT:    add r12, r1
; CHECK-NEXT:    ldr r1, [sp, #16] @ 4-byte Reload
; CHECK-NEXT:    cmp r0, r1
; CHECK-NEXT:    blo.w .LBB7_2
; CHECK-NEXT:  .LBB7_5: @ %for.cond.cleanup
; CHECK-NEXT:    add sp, #88
; CHECK-NEXT:    vpop {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT:    add sp, #4
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
entry:
  %NumInputs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 2
  %0 = load i32, i32* %NumInputs, align 4
  %NumFilters = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 1
  %1 = load i32, i32* %NumFilters, align 4
  %pDCTCoefs = getelementptr inbounds %struct.DCT_InstanceTypeDef, %struct.DCT_InstanceTypeDef* %S, i32 0, i32 0
  %2 = load float*, float** %pDCTCoefs, align 4
  %cmp = icmp ugt i32 %0, 1
  tail call void @llvm.assume(i1 %cmp)
  %sub = add i32 %1, -8
  %cmp3197 = icmp ugt i32 %sub, 1
  br i1 %cmp3197, label %for.body.preheader, label %for.cond.cleanup

for.body.preheader:                               ; preds = %entry
  %n.rnd.up = add i32 %0, 3
  %n.vec = and i32 %n.rnd.up, -4
  br label %for.body

for.cond.cleanup:                                 ; preds = %middle.block, %entry
  ret void

for.body:                                         ; preds = %for.body.preheader, %middle.block
  %k2.0198 = phi i32 [ %add79, %middle.block ], [ 1, %for.body.preheader ]
  %mul4 = mul i32 %k2.0198, %0
  %add = add nuw nsw i32 %k2.0198, 1
  %mul5 = mul i32 %add, %0
  %add6 = add nuw nsw i32 %k2.0198, 2
  %mul7 = mul i32 %add6, %0
  %add8 = add nuw nsw i32 %k2.0198, 3
  %mul9 = mul i32 %add8, %0
  %add10 = add nuw nsw i32 %k2.0198, 4
  %mul11 = mul i32 %add10, %0
  %add12 = add nuw nsw i32 %k2.0198, 5
  %mul13 = mul i32 %add12, %0
  %add14 = add nuw nsw i32 %k2.0198, 6
  %mul15 = mul i32 %add14, %0
  %add16 = add i32 %k2.0198, 7
  %mul17 = mul i32 %add16, %0
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %for.body
  %index = phi i32 [ 0, %for.body ], [ %index.next, %vector.body ]
  %vec.phi = phi <4 x float> [ zeroinitializer, %for.body ], [ %45, %vector.body ]
  %vec.phi199 = phi <4 x float> [ zeroinitializer, %for.body ], [ %46, %vector.body ]
  %vec.phi200 = phi <4 x float> [ zeroinitializer, %for.body ], [ %47, %vector.body ]
  %vec.phi201 = phi <4 x float> [ zeroinitializer, %for.body ], [ %48, %vector.body ]
  %vec.phi202 = phi <4 x float> [ zeroinitializer, %for.body ], [ %49, %vector.body ]
  %vec.phi203 = phi <4 x float> [ zeroinitializer, %for.body ], [ %50, %vector.body ]
  %vec.phi204 = phi <4 x float> [ zeroinitializer, %for.body ], [ %51, %vector.body ]
  %vec.phi205 = phi <4 x float> [ zeroinitializer, %for.body ], [ %52, %vector.body ]
  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %0)
  %3 = getelementptr inbounds float, float* %pIn, i32 %index
  %4 = bitcast float* %3 to <4 x float>*
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %4, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %5 = add i32 %index, %mul4
  %6 = getelementptr inbounds float, float* %2, i32 %5
  %7 = bitcast float* %6 to <4 x float>*
  %wide.masked.load206 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %7, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %8 = fmul fast <4 x float> %wide.masked.load206, %wide.masked.load
  %9 = fadd fast <4 x float> %8, %vec.phi200
  %10 = add i32 %index, %mul5
  %11 = getelementptr inbounds float, float* %2, i32 %10
  %12 = bitcast float* %11 to <4 x float>*
  %wide.masked.load207 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %12, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %13 = fmul fast <4 x float> %wide.masked.load207, %wide.masked.load
  %14 = fadd fast <4 x float> %13, %vec.phi202
  %15 = add i32 %index, %mul7
  %16 = getelementptr inbounds float, float* %2, i32 %15
  %17 = bitcast float* %16 to <4 x float>*
  %wide.masked.load208 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %17, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %18 = fmul fast <4 x float> %wide.masked.load208, %wide.masked.load
  %19 = fadd fast <4 x float> %18, %vec.phi204
  %20 = add i32 %index, %mul9
  %21 = getelementptr inbounds float, float* %2, i32 %20
  %22 = bitcast float* %21 to <4 x float>*
  %wide.masked.load209 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %22, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %23 = fmul fast <4 x float> %wide.masked.load209, %wide.masked.load
  %24 = fadd fast <4 x float> %23, %vec.phi205
  %25 = add i32 %index, %mul11
  %26 = getelementptr inbounds float, float* %2, i32 %25
  %27 = bitcast float* %26 to <4 x float>*
  %wide.masked.load210 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %27, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %28 = fmul fast <4 x float> %wide.masked.load210, %wide.masked.load
  %29 = fadd fast <4 x float> %28, %vec.phi203
  %30 = add i32 %index, %mul13
  %31 = getelementptr inbounds float, float* %2, i32 %30
  %32 = bitcast float* %31 to <4 x float>*
  %wide.masked.load211 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %32, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %33 = fmul fast <4 x float> %wide.masked.load211, %wide.masked.load
  %34 = fadd fast <4 x float> %33, %vec.phi201
  %35 = add i32 %index, %mul15
  %36 = getelementptr inbounds float, float* %2, i32 %35
  %37 = bitcast float* %36 to <4 x float>*
  %wide.masked.load212 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %37, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %38 = fmul fast <4 x float> %wide.masked.load212, %wide.masked.load
  %39 = fadd fast <4 x float> %38, %vec.phi199
  %40 = add i32 %index, %mul17
  %41 = getelementptr inbounds float, float* %2, i32 %40
  %42 = bitcast float* %41 to <4 x float>*
  %wide.masked.load213 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %42, i32 4, <4 x i1> %active.lane.mask, <4 x float> undef)
  %43 = fmul fast <4 x float> %wide.masked.load213, %wide.masked.load
  %44 = fadd fast <4 x float> %43, %vec.phi
  %45 = select <4 x i1> %active.lane.mask, <4 x float> %44, <4 x float> %vec.phi
  %46 = select <4 x i1> %active.lane.mask, <4 x float> %39, <4 x float> %vec.phi199
  %47 = select <4 x i1> %active.lane.mask, <4 x float> %9, <4 x float> %vec.phi200
  %48 = select <4 x i1> %active.lane.mask, <4 x float> %34, <4 x float> %vec.phi201
  %49 = select <4 x i1> %active.lane.mask, <4 x float> %14, <4 x float> %vec.phi202
  %50 = select <4 x i1> %active.lane.mask, <4 x float> %29, <4 x float> %vec.phi203
  %51 = select <4 x i1> %active.lane.mask, <4 x float> %19, <4 x float> %vec.phi204
  %52 = select <4 x i1> %active.lane.mask, <4 x float> %24, <4 x float> %vec.phi205
  %index.next = add i32 %index, 4
  %53 = icmp eq i32 %index.next, %n.vec
  br i1 %53, label %middle.block, label %vector.body

middle.block:                                     ; preds = %vector.body
  %54 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %52)
  %55 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %51)
  %56 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %50)
  %57 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %49)
  %58 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %48)
  %59 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %47)
  %60 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %46)
  %61 = call fast float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> %45)
  %arrayidx63 = getelementptr inbounds float, float* %pOut, i32 %k2.0198
  store float %59, float* %arrayidx63, align 4
  %arrayidx65 = getelementptr inbounds float, float* %pOut, i32 %add
  store float %57, float* %arrayidx65, align 4
  %arrayidx67 = getelementptr inbounds float, float* %pOut, i32 %add6
  store float %55, float* %arrayidx67, align 4
  %arrayidx69 = getelementptr inbounds float, float* %pOut, i32 %add8
  store float %54, float* %arrayidx69, align 4
  %arrayidx71 = getelementptr inbounds float, float* %pOut, i32 %add10
  store float %56, float* %arrayidx71, align 4
  %arrayidx73 = getelementptr inbounds float, float* %pOut, i32 %add12
  store float %58, float* %arrayidx73, align 4
  %arrayidx75 = getelementptr inbounds float, float* %pOut, i32 %add14
  store float %60, float* %arrayidx75, align 4
  %arrayidx77 = getelementptr inbounds float, float* %pOut, i32 %add16
  store float %61, float* %arrayidx77, align 4
  %add79 = add i32 %k2.0198, 8
  %cmp3 = icmp ult i32 %add79, %sub
  br i1 %cmp3, label %for.body, label %for.cond.cleanup
}

declare void @llvm.assume(i1 noundef)
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32 immarg, <4 x i1>, <4 x float>)
declare float @llvm.vector.reduce.fadd.v4f32(float, <4 x float>)