llvm/test/CodeGen/Thumb2/mve-float16regloops.ll

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

define arm_aapcs_vfpcc void @test_fadd(half* noalias nocapture readonly %A, half *%BB, half* noalias nocapture %C, i32 %n) {
; CHECK-LABEL: test_fadd:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r3, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r1]
; CHECK-NEXT:    vmov r1, s0
; CHECK-NEXT:    vdup.16 q0, r1
; CHECK-NEXT:  .LBB0_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    subs r3, #8
; CHECK-NEXT:    vadd.f16 q1, q1, q0
; CHECK-NEXT:    vstrb.8 q1, [r2], #16
; CHECK-NEXT:    bne .LBB0_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %B = load half, half* %BB
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp18 = icmp sgt i32 %n, 0
  br i1 %cmp18, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert10 = insertelement <8 x half> undef, half %B, i32 0
  %broadcast.splat11 = shufflevector <8 x half> %broadcast.splatinsert10, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = fadd fast <8 x half> %wide.load, %broadcast.splat11
  %4 = getelementptr inbounds half, half* %C, i32 %index
  %5 = bitcast half* %4 to <8 x half>*
  store <8 x half> %3, <8 x half>* %5, align 4
  %index.next = add i32 %index, 8
  %6 = icmp eq i32 %index.next, %n
  br i1 %6, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_fadd_r(half* noalias nocapture readonly %A, half *%BB, half* noalias nocapture %C, i32 %n) {
; CHECK-LABEL: test_fadd_r:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r3, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r1]
; CHECK-NEXT:    vmov r1, s0
; CHECK-NEXT:    vdup.16 q0, r1
; CHECK-NEXT:  .LBB1_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    subs r3, #8
; CHECK-NEXT:    vadd.f16 q1, q0, q1
; CHECK-NEXT:    vstrb.8 q1, [r2], #16
; CHECK-NEXT:    bne .LBB1_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %B = load half, half* %BB
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp18 = icmp sgt i32 %n, 0
  br i1 %cmp18, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert10 = insertelement <8 x half> undef, half %B, i32 0
  %broadcast.splat11 = shufflevector <8 x half> %broadcast.splatinsert10, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = fadd fast <8 x half> %broadcast.splat11, %wide.load
  %4 = getelementptr inbounds half, half* %C, i32 %index
  %5 = bitcast half* %4 to <8 x half>*
  store <8 x half> %3, <8 x half>* %5, align 4
  %index.next = add i32 %index, 8
  %6 = icmp eq i32 %index.next, %n
  br i1 %6, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_fmul(half* noalias nocapture readonly %A, half *%BB, half* noalias nocapture %C, i32 %n) {
; CHECK-LABEL: test_fmul:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r3, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r1]
; CHECK-NEXT:    vmov r1, s0
; CHECK-NEXT:    vdup.16 q0, r1
; CHECK-NEXT:  .LBB2_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    subs r3, #8
; CHECK-NEXT:    vmul.f16 q1, q1, q0
; CHECK-NEXT:    vstrb.8 q1, [r2], #16
; CHECK-NEXT:    bne .LBB2_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %B = load half, half* %BB
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp18 = icmp sgt i32 %n, 0
  br i1 %cmp18, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert10 = insertelement <8 x half> undef, half %B, i32 0
  %broadcast.splat11 = shufflevector <8 x half> %broadcast.splatinsert10, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = fmul fast <8 x half> %wide.load, %broadcast.splat11
  %4 = getelementptr inbounds half, half* %C, i32 %index
  %5 = bitcast half* %4 to <8 x half>*
  store <8 x half> %3, <8 x half>* %5, align 4
  %index.next = add i32 %index, 8
  %6 = icmp eq i32 %index.next, %n
  br i1 %6, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_fmul_r(half* noalias nocapture readonly %A, half *%BB, half* noalias nocapture %C, i32 %n) {
; CHECK-LABEL: test_fmul_r:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r3, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r1]
; CHECK-NEXT:    vmov r1, s0
; CHECK-NEXT:    vdup.16 q0, r1
; CHECK-NEXT:  .LBB3_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    subs r3, #8
; CHECK-NEXT:    vmul.f16 q1, q0, q1
; CHECK-NEXT:    vstrb.8 q1, [r2], #16
; CHECK-NEXT:    bne .LBB3_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %B = load half, half* %BB
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp18 = icmp sgt i32 %n, 0
  br i1 %cmp18, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert10 = insertelement <8 x half> undef, half %B, i32 0
  %broadcast.splat11 = shufflevector <8 x half> %broadcast.splatinsert10, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = fmul fast <8 x half> %broadcast.splat11, %wide.load
  %4 = getelementptr inbounds half, half* %C, i32 %index
  %5 = bitcast half* %4 to <8 x half>*
  store <8 x half> %3, <8 x half>* %5, align 4
  %index.next = add i32 %index, 8
  %6 = icmp eq i32 %index.next, %n
  br i1 %6, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_fsub(half* noalias nocapture readonly %A, half *%BB, half* noalias nocapture %C, i32 %n) {
; CHECK-LABEL: test_fsub:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r3, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r1]
; CHECK-NEXT:    vmov r1, s0
; CHECK-NEXT:    vdup.16 q0, r1
; CHECK-NEXT:  .LBB4_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    subs r3, #8
; CHECK-NEXT:    vsub.f16 q1, q1, q0
; CHECK-NEXT:    vstrb.8 q1, [r2], #16
; CHECK-NEXT:    bne .LBB4_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %B = load half, half* %BB
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp18 = icmp sgt i32 %n, 0
  br i1 %cmp18, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert10 = insertelement <8 x half> undef, half %B, i32 0
  %broadcast.splat11 = shufflevector <8 x half> %broadcast.splatinsert10, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = fsub fast <8 x half> %wide.load, %broadcast.splat11
  %4 = getelementptr inbounds half, half* %C, i32 %index
  %5 = bitcast half* %4 to <8 x half>*
  store <8 x half> %3, <8 x half>* %5, align 4
  %index.next = add i32 %index, 8
  %6 = icmp eq i32 %index.next, %n
  br i1 %6, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_fsub_r(half* noalias nocapture readonly %A, half *%BB, half* noalias nocapture %C, i32 %n) {
; CHECK-LABEL: test_fsub_r:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r3, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r1]
; CHECK-NEXT:    vmov r1, s0
; CHECK-NEXT:    vdup.16 q0, r1
; CHECK-NEXT:  .LBB5_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    subs r3, #8
; CHECK-NEXT:    vsub.f16 q1, q0, q1
; CHECK-NEXT:    vstrb.8 q1, [r2], #16
; CHECK-NEXT:    bne .LBB5_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %B = load half, half* %BB
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp18 = icmp sgt i32 %n, 0
  br i1 %cmp18, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert10 = insertelement <8 x half> undef, half %B, i32 0
  %broadcast.splat11 = shufflevector <8 x half> %broadcast.splatinsert10, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = fsub fast <8 x half> %broadcast.splat11, %wide.load
  %4 = getelementptr inbounds half, half* %C, i32 %index
  %5 = bitcast half* %4 to <8 x half>*
  store <8 x half> %3, <8 x half>* %5, align 4
  %index.next = add i32 %index, 8
  %6 = icmp eq i32 %index.next, %n
  br i1 %6, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}


define arm_aapcs_vfpcc void @test_fmas(half* noalias nocapture readonly %A, half* noalias nocapture readonly %B, half *%CC, half* noalias nocapture %D, i32 %n) {
; CHECK-LABEL: test_fmas:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    ldr.w r12, [sp]
; CHECK-NEXT:    cmp.w r12, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r2]
; CHECK-NEXT:    vmov r2, s0
; CHECK-NEXT:    vdup.16 q0, r2
; CHECK-NEXT:  .LBB6_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    vldrw.u32 q2, [r1], #16
; CHECK-NEXT:    vmov q3, q0
; CHECK-NEXT:    subs.w r12, r12, #8
; CHECK-NEXT:    vfma.f16 q3, q2, q1
; CHECK-NEXT:    vstrb.8 q3, [r3], #16
; CHECK-NEXT:    bne .LBB6_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %C = load half, half* %CC
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp110 = icmp sgt i32 %n, 0
  br i1 %cmp110, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert13 = insertelement <8 x half> undef, half %C, i32 0
  %broadcast.splat14 = shufflevector <8 x half> %broadcast.splatinsert13, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = getelementptr inbounds half, half* %B, i32 %index
  %4 = bitcast half* %3 to <8 x half>*
  %wide.load12 = load <8 x half>, <8 x half>* %4, align 4
  %5 = fmul fast <8 x half> %wide.load12, %wide.load
  %6 = fadd fast <8 x half> %5, %broadcast.splat14
  %7 = getelementptr inbounds half, half* %D, i32 %index
  %8 = bitcast half* %7 to <8 x half>*
  store <8 x half> %6, <8 x half>* %8, align 4
  %index.next = add i32 %index, 8
  %9 = icmp eq i32 %index.next, %n
  br i1 %9, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_fmas_r(half* noalias nocapture readonly %A, half* noalias nocapture readonly %B, half *%CC, half* noalias nocapture %D, i32 %n) {
; CHECK-LABEL: test_fmas_r:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    ldr.w r12, [sp]
; CHECK-NEXT:    cmp.w r12, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r2]
; CHECK-NEXT:    vmov r2, s0
; CHECK-NEXT:    vdup.16 q0, r2
; CHECK-NEXT:  .LBB7_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    vldrw.u32 q2, [r1], #16
; CHECK-NEXT:    vmov q3, q0
; CHECK-NEXT:    subs.w r12, r12, #8
; CHECK-NEXT:    vfma.f16 q3, q2, q1
; CHECK-NEXT:    vstrb.8 q3, [r3], #16
; CHECK-NEXT:    bne .LBB7_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %C = load half, half* %CC
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp110 = icmp sgt i32 %n, 0
  br i1 %cmp110, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert13 = insertelement <8 x half> undef, half %C, i32 0
  %broadcast.splat14 = shufflevector <8 x half> %broadcast.splatinsert13, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = getelementptr inbounds half, half* %B, i32 %index
  %4 = bitcast half* %3 to <8 x half>*
  %wide.load12 = load <8 x half>, <8 x half>* %4, align 4
  %5 = fmul fast <8 x half> %wide.load12, %wide.load
  %6 = fadd fast <8 x half> %broadcast.splat14, %5
  %7 = getelementptr inbounds half, half* %D, i32 %index
  %8 = bitcast half* %7 to <8 x half>*
  store <8 x half> %6, <8 x half>* %8, align 4
  %index.next = add i32 %index, 8
  %9 = icmp eq i32 %index.next, %n
  br i1 %9, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_fma(half* noalias nocapture readonly %A, half* noalias nocapture readonly %B, half *%CC, half* noalias nocapture %D, i32 %n) {
; CHECK-LABEL: test_fma:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    ldr.w r12, [sp]
; CHECK-NEXT:    cmp.w r12, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r2]
; CHECK-NEXT:    vmov r2, s0
; CHECK-NEXT:    vdup.16 q0, r2
; CHECK-NEXT:  .LBB8_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    vldrw.u32 q2, [r1], #16
; CHECK-NEXT:    subs.w r12, r12, #8
; CHECK-NEXT:    vfma.f16 q2, q1, q0
; CHECK-NEXT:    vstrb.8 q2, [r3], #16
; CHECK-NEXT:    bne .LBB8_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %C = load half, half* %CC
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp110 = icmp sgt i32 %n, 0
  br i1 %cmp110, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert12 = insertelement <8 x half> undef, half %C, i32 0
  %broadcast.splat13 = shufflevector <8 x half> %broadcast.splatinsert12, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = fmul fast <8 x half> %wide.load, %broadcast.splat13
  %4 = getelementptr inbounds half, half* %B, i32 %index
  %5 = bitcast half* %4 to <8 x half>*
  %wide.load14 = load <8 x half>, <8 x half>* %5, align 4
  %6 = fadd fast <8 x half> %3, %wide.load14
  %7 = getelementptr inbounds half, half* %D, i32 %index
  %8 = bitcast half* %7 to <8 x half>*
  store <8 x half> %6, <8 x half>* %8, align 4
  %index.next = add i32 %index, 8
  %9 = icmp eq i32 %index.next, %n
  br i1 %9, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_fma_r(half* noalias nocapture readonly %A, half* noalias nocapture readonly %B, half *%CC, half* noalias nocapture %D, i32 %n) {
; CHECK-LABEL: test_fma_r:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    ldr.w r12, [sp]
; CHECK-NEXT:    cmp.w r12, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r2]
; CHECK-NEXT:    vmov r2, s0
; CHECK-NEXT:    vdup.16 q0, r2
; CHECK-NEXT:  .LBB9_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    vldrw.u32 q2, [r1], #16
; CHECK-NEXT:    subs.w r12, r12, #8
; CHECK-NEXT:    vfma.f16 q2, q0, q1
; CHECK-NEXT:    vstrb.8 q2, [r3], #16
; CHECK-NEXT:    bne .LBB9_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %C = load half, half* %CC
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp110 = icmp sgt i32 %n, 0
  br i1 %cmp110, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert12 = insertelement <8 x half> undef, half %C, i32 0
  %broadcast.splat13 = shufflevector <8 x half> %broadcast.splatinsert12, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = fmul fast <8 x half> %broadcast.splat13, %wide.load
  %4 = getelementptr inbounds half, half* %B, i32 %index
  %5 = bitcast half* %4 to <8 x half>*
  %wide.load14 = load <8 x half>, <8 x half>* %5, align 4
  %6 = fadd fast <8 x half> %3, %wide.load14
  %7 = getelementptr inbounds half, half* %D, i32 %index
  %8 = bitcast half* %7 to <8 x half>*
  store <8 x half> %6, <8 x half>* %8, align 4
  %index.next = add i32 %index, 8
  %9 = icmp eq i32 %index.next, %n
  br i1 %9, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}


define arm_aapcs_vfpcc void @test_fmss(half* noalias nocapture readonly %A, half* noalias nocapture readonly %B, half *%CC, half* noalias nocapture %D, i32 %n) {
; CHECK-LABEL: test_fmss:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    ldr.w r12, [sp]
; CHECK-NEXT:    cmp.w r12, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r2]
; CHECK-NEXT:    vmov r2, s0
; CHECK-NEXT:    vdup.16 q0, r2
; CHECK-NEXT:    vneg.f16 q0, q0
; CHECK-NEXT:  .LBB10_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    vldrw.u32 q2, [r1], #16
; CHECK-NEXT:    vmov q3, q0
; CHECK-NEXT:    subs.w r12, r12, #8
; CHECK-NEXT:    vfma.f16 q3, q2, q1
; CHECK-NEXT:    vstrb.8 q3, [r3], #16
; CHECK-NEXT:    bne .LBB10_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %C = load half, half* %CC
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp110 = icmp sgt i32 %n, 0
  br i1 %cmp110, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert13 = insertelement <8 x half> undef, half %C, i32 0
  %broadcast.splat14 = shufflevector <8 x half> %broadcast.splatinsert13, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = getelementptr inbounds half, half* %B, i32 %index
  %4 = bitcast half* %3 to <8 x half>*
  %wide.load12 = load <8 x half>, <8 x half>* %4, align 4
  %5 = fmul fast <8 x half> %wide.load12, %wide.load
  %6 = fsub fast <8 x half> %5, %broadcast.splat14
  %7 = getelementptr inbounds half, half* %D, i32 %index
  %8 = bitcast half* %7 to <8 x half>*
  store <8 x half> %6, <8 x half>* %8, align 4
  %index.next = add i32 %index, 8
  %9 = icmp eq i32 %index.next, %n
  br i1 %9, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_fmss_r(half* noalias nocapture readonly %A, half* noalias nocapture readonly %B, half *%CC, half* noalias nocapture %D, i32 %n) {
; CHECK-LABEL: test_fmss_r:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    ldr.w r12, [sp]
; CHECK-NEXT:    cmp.w r12, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r2]
; CHECK-NEXT:    vmov r2, s0
; CHECK-NEXT:    vdup.16 q0, r2
; CHECK-NEXT:  .LBB11_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    vldrw.u32 q2, [r1], #16
; CHECK-NEXT:    vmov q3, q0
; CHECK-NEXT:    subs.w r12, r12, #8
; CHECK-NEXT:    vfms.f16 q3, q2, q1
; CHECK-NEXT:    vstrb.8 q3, [r3], #16
; CHECK-NEXT:    bne .LBB11_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %C = load half, half* %CC
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp110 = icmp sgt i32 %n, 0
  br i1 %cmp110, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert13 = insertelement <8 x half> undef, half %C, i32 0
  %broadcast.splat14 = shufflevector <8 x half> %broadcast.splatinsert13, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = getelementptr inbounds half, half* %B, i32 %index
  %4 = bitcast half* %3 to <8 x half>*
  %wide.load12 = load <8 x half>, <8 x half>* %4, align 4
  %5 = fmul fast <8 x half> %wide.load12, %wide.load
  %6 = fsub fast <8 x half> %broadcast.splat14, %5
  %7 = getelementptr inbounds half, half* %D, i32 %index
  %8 = bitcast half* %7 to <8 x half>*
  store <8 x half> %6, <8 x half>* %8, align 4
  %index.next = add i32 %index, 8
  %9 = icmp eq i32 %index.next, %n
  br i1 %9, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_fms(half* noalias nocapture readonly %A, half* noalias nocapture readonly %B, half *%CC, half* noalias nocapture %D, i32 %n) {
; CHECK-LABEL: test_fms:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    ldr.w r12, [sp]
; CHECK-NEXT:    cmp.w r12, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r2]
; CHECK-NEXT:    vmov r2, s0
; CHECK-NEXT:    vdup.16 q0, r2
; CHECK-NEXT:  .LBB12_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r1], #16
; CHECK-NEXT:    vldrw.u32 q2, [r0], #16
; CHECK-NEXT:    subs.w r12, r12, #8
; CHECK-NEXT:    vneg.f16 q1, q1
; CHECK-NEXT:    vfma.f16 q1, q2, q0
; CHECK-NEXT:    vstrb.8 q1, [r3], #16
; CHECK-NEXT:    bne .LBB12_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %C = load half, half* %CC
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp110 = icmp sgt i32 %n, 0
  br i1 %cmp110, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert12 = insertelement <8 x half> undef, half %C, i32 0
  %broadcast.splat13 = shufflevector <8 x half> %broadcast.splatinsert12, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = fmul fast <8 x half> %wide.load, %broadcast.splat13
  %4 = getelementptr inbounds half, half* %B, i32 %index
  %5 = bitcast half* %4 to <8 x half>*
  %wide.load14 = load <8 x half>, <8 x half>* %5, align 4
  %6 = fsub fast <8 x half> %3, %wide.load14
  %7 = getelementptr inbounds half, half* %D, i32 %index
  %8 = bitcast half* %7 to <8 x half>*
  store <8 x half> %6, <8 x half>* %8, align 4
  %index.next = add i32 %index, 8
  %9 = icmp eq i32 %index.next, %n
  br i1 %9, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}

define arm_aapcs_vfpcc void @test_fms_r(half* noalias nocapture readonly %A, half* noalias nocapture readonly %B, half *%CC, half* noalias nocapture %D, i32 %n) {
; CHECK-LABEL: test_fms_r:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    ldr.w r12, [sp]
; CHECK-NEXT:    cmp.w r12, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:    vldr.16 s0, [r2]
; CHECK-NEXT:    vmov r2, s0
; CHECK-NEXT:    vdup.16 q0, r2
; CHECK-NEXT:  .LBB13_1: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q1, [r1], #16
; CHECK-NEXT:    vldrw.u32 q2, [r0], #16
; CHECK-NEXT:    subs.w r12, r12, #8
; CHECK-NEXT:    vneg.f16 q1, q1
; CHECK-NEXT:    vfma.f16 q1, q0, q2
; CHECK-NEXT:    vstrb.8 q1, [r3], #16
; CHECK-NEXT:    bne .LBB13_1
; CHECK-NEXT:  @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT:    bx lr
entry:
  %C = load half, half* %CC
  %0 = and i32 %n, 7
  %cmp = icmp eq i32 %0, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp110 = icmp sgt i32 %n, 0
  br i1 %cmp110, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %broadcast.splatinsert12 = insertelement <8 x half> undef, half %C, i32 0
  %broadcast.splat13 = shufflevector <8 x half> %broadcast.splatinsert12, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
  %1 = getelementptr inbounds half, half* %A, i32 %index
  %2 = bitcast half* %1 to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %2, align 4
  %3 = fmul fast <8 x half> %broadcast.splat13, %wide.load
  %4 = getelementptr inbounds half, half* %B, i32 %index
  %5 = bitcast half* %4 to <8 x half>*
  %wide.load14 = load <8 x half>, <8 x half>* %5, align 4
  %6 = fsub fast <8 x half> %3, %wide.load14
  %7 = getelementptr inbounds half, half* %D, i32 %index
  %8 = bitcast half* %7 to <8 x half>*
  store <8 x half> %6, <8 x half>* %8, align 4
  %index.next = add i32 %index, 8
  %9 = icmp eq i32 %index.next, %n
  br i1 %9, label %for.cond.cleanup, label %vector.body

for.cond.cleanup:                                 ; preds = %vector.body, %entry
  ret void
}


define dso_local void @test_nested(half* noalias nocapture %pInT1, half* noalias nocapture readonly %pOutT1, half* noalias nocapture readonly %pPRT_in, half* noalias nocapture readnone %pPRT_pDst, i32 %numRows, i32 %numCols, i32 %l, half *%ina) local_unnamed_addr #0 {
; CHECK-LABEL: test_nested:
; CHECK:       @ %bb.0: @ %for.body.us.preheader
; CHECK-NEXT:    .save {r4, r5, r6, r7, lr}
; CHECK-NEXT:    push {r4, r5, r6, r7, lr}
; CHECK-NEXT:    ldrd lr, r12, [sp, #20]
; CHECK-NEXT:    lsl.w r3, r12, #1
; CHECK-NEXT:    dls lr, lr
; CHECK-NEXT:  .LBB14_1: @ %for.body.us
; CHECK-NEXT:    @ =>This Loop Header: Depth=1
; CHECK-NEXT:    @ Child Loop BB14_2 Depth 2
; CHECK-NEXT:    vldr.16 s0, [r1]
; CHECK-NEXT:    mov r5, r12
; CHECK-NEXT:    vmov r4, s0
; CHECK-NEXT:    vdup.16 q0, r4
; CHECK-NEXT:    movs r4, #0
; CHECK-NEXT:  .LBB14_2: @ %vector.body
; CHECK-NEXT:    @ Parent Loop BB14_1 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    adds r6, r0, r4
; CHECK-NEXT:    adds r7, r2, r4
; CHECK-NEXT:    vldrw.u32 q1, [r7]
; CHECK-NEXT:    vldrw.u32 q2, [r6]
; CHECK-NEXT:    adds r4, #16
; CHECK-NEXT:    subs r5, #8
; CHECK-NEXT:    vfms.f16 q2, q1, q0
; CHECK-NEXT:    vstrw.32 q2, [r6]
; CHECK-NEXT:    bne .LBB14_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond6.for.end_crit_edge.us
; CHECK-NEXT:    @ in Loop: Header=BB14_1 Depth=1
; CHECK-NEXT:    add r0, r3
; CHECK-NEXT:    add r2, r3
; CHECK-NEXT:    adds r1, #2
; CHECK-NEXT:    le lr, .LBB14_1
; CHECK-NEXT:  @ %bb.4: @ %for.end14
; CHECK-NEXT:    pop {r4, r5, r6, r7, pc}
for.body.us.preheader:
  %in = load half, half* %ina
  %cmp = icmp sgt i32 %numRows, 0
  tail call void @llvm.assume(i1 %cmp)
  %cmp1 = icmp sgt i32 %numCols, 0
  tail call void @llvm.assume(i1 %cmp1)
  %rem = and i32 %numCols, 7
  %cmp2 = icmp eq i32 %rem, 0
  tail call void @llvm.assume(i1 %cmp2)
  %cmp3 = icmp slt i32 %l, %numCols
  tail call void @llvm.assume(i1 %cmp3)
  br label %for.body.us

for.body.us:                                      ; preds = %for.cond6.for.end_crit_edge.us, %for.body.us.preheader
  %pInT1.addr.038.us = phi half* [ %scevgep40, %for.cond6.for.end_crit_edge.us ], [ %pInT1, %for.body.us.preheader ]
  %i.037.us = phi i32 [ %inc13.us, %for.cond6.for.end_crit_edge.us ], [ 0, %for.body.us.preheader ]
  %pOutT1.addr.036.us = phi half* [ %incdec.ptr.us, %for.cond6.for.end_crit_edge.us ], [ %pOutT1, %for.body.us.preheader ]
  %pPRT_in.addr.035.us = phi half* [ %scevgep, %for.cond6.for.end_crit_edge.us ], [ %pPRT_in, %for.body.us.preheader ]
  %scevgep = getelementptr half, half* %pPRT_in.addr.035.us, i32 %numCols
  %0 = load half, half* %pOutT1.addr.036.us, align 4
  %broadcast.splatinsert47 = insertelement <8 x half> undef, half %0, i32 0
  %broadcast.splat48 = shufflevector <8 x half> %broadcast.splatinsert47, <8 x half> undef, <8 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %for.body.us
  %index = phi i32 [ 0, %for.body.us ], [ %index.next, %vector.body ]
  %next.gep = getelementptr half, half* %pInT1.addr.038.us, i32 %index
  %next.gep45 = getelementptr half, half* %pPRT_in.addr.035.us, i32 %index
  %1 = bitcast half* %next.gep to <8 x half>*
  %wide.load = load <8 x half>, <8 x half>* %1, align 4
  %2 = bitcast half* %next.gep45 to <8 x half>*
  %wide.load46 = load <8 x half>, <8 x half>* %2, align 4
  %3 = fmul fast <8 x half> %wide.load46, %broadcast.splat48
  %4 = fsub fast <8 x half> %wide.load, %3
  store <8 x half> %4, <8 x half>* %1, align 4
  %index.next = add i32 %index, 8
  %5 = icmp eq i32 %index.next, %numCols
  br i1 %5, label %for.cond6.for.end_crit_edge.us, label %vector.body

for.cond6.for.end_crit_edge.us:                   ; preds = %vector.body
  %incdec.ptr.us = getelementptr inbounds half, half* %pOutT1.addr.036.us, i32 1
  %scevgep40 = getelementptr half, half* %pInT1.addr.038.us, i32 %numCols
  %inc13.us = add nuw nsw i32 %i.037.us, 1
  %exitcond41 = icmp eq i32 %inc13.us, %numRows
  br i1 %exitcond41, label %for.end14, label %for.body.us

for.end14:                                        ; preds = %for.cond6.for.end_crit_edge.us
  ret void
}

%struct.arm_fir_instance_f32 = type { i16, half*, half* }
define void @arm_fir_f32_1_4_mve(%struct.arm_fir_instance_f32* nocapture readonly %S, half* nocapture readonly %pSrc, half* %pDst, i32 %blockSize) {
; CHECK-LABEL: arm_fir_f32_1_4_mve:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, r5, r6, r7, r8, r9, r10, lr}
; CHECK-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, lr}
; CHECK-NEXT:    .vsave {d8, d9, d10, d11}
; CHECK-NEXT:    vpush {d8, d9, d10, d11}
; CHECK-NEXT:    ldrh.w r9, [r0]
; CHECK-NEXT:    ldr.w r12, [r0, #4]
; CHECK-NEXT:    sub.w r7, r9, #1
; CHECK-NEXT:    cmp r7, #3
; CHECK-NEXT:    bhi .LBB15_6
; CHECK-NEXT:  @ %bb.1: @ %if.then
; CHECK-NEXT:    ldr r6, [r0, #8]
; CHECK-NEXT:    vldr.16 s0, [r6]
; CHECK-NEXT:    vmov lr, s0
; CHECK-NEXT:    vldr.16 s0, [r6, #2]
; CHECK-NEXT:    vdup.16 q3, lr
; CHECK-NEXT:    lsr.w lr, r3, #2
; CHECK-NEXT:    vmov r5, s0
; CHECK-NEXT:    vldr.16 s0, [r6, #4]
; CHECK-NEXT:    vdup.16 q2, r5
; CHECK-NEXT:    vmov r4, s0
; CHECK-NEXT:    vldr.16 s0, [r6, #6]
; CHECK-NEXT:    vdup.16 q1, r4
; CHECK-NEXT:    add.w r4, r12, r7, lsl #1
; CHECK-NEXT:    vmov r6, s0
; CHECK-NEXT:    vdup.16 q0, r6
; CHECK-NEXT:    wls lr, lr, .LBB15_5
; CHECK-NEXT:  @ %bb.2: @ %while.body.lr.ph
; CHECK-NEXT:    bic r10, r3, #3
; CHECK-NEXT:    movs r6, #0
; CHECK-NEXT:    add.w r8, r2, r10, lsl #1
; CHECK-NEXT:  .LBB15_3: @ %while.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    adds r5, r1, r6
; CHECK-NEXT:    vldrw.u32 q4, [r5]
; CHECK-NEXT:    adds r5, r4, r6
; CHECK-NEXT:    vstrw.32 q4, [r5]
; CHECK-NEXT:    add.w r5, r12, r6
; CHECK-NEXT:    vldrw.u32 q4, [r5]
; CHECK-NEXT:    adds r7, r5, #2
; CHECK-NEXT:    vldrw.u32 q5, [r7]
; CHECK-NEXT:    vmul.f16 q4, q4, q3
; CHECK-NEXT:    vfma.f16 q4, q5, q2
; CHECK-NEXT:    vldrw.u32 q5, [r5, #4]
; CHECK-NEXT:    adds r5, #6
; CHECK-NEXT:    vfma.f16 q4, q5, q1
; CHECK-NEXT:    vldrw.u32 q5, [r5]
; CHECK-NEXT:    adds r5, r2, r6
; CHECK-NEXT:    adds r6, #8
; CHECK-NEXT:    vfma.f16 q4, q5, q0
; CHECK-NEXT:    vstrw.32 q4, [r5]
; CHECK-NEXT:    le lr, .LBB15_3
; CHECK-NEXT:  @ %bb.4: @ %while.end.loopexit
; CHECK-NEXT:    add r4, r6
; CHECK-NEXT:    add.w r12, r12, r10, lsl #1
; CHECK-NEXT:    add.w r1, r1, r10, lsl #1
; CHECK-NEXT:    mov r2, r8
; CHECK-NEXT:  .LBB15_5: @ %while.end
; CHECK-NEXT:    and r7, r3, #3
; CHECK-NEXT:    vldrw.u32 q4, [r1]
; CHECK-NEXT:    vctp.16 r7
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vstrht.16 q4, [r4]
; CHECK-NEXT:    vldrw.u32 q4, [r12]
; CHECK-NEXT:    add.w r1, r12, #2
; CHECK-NEXT:    vmul.f16 q3, q4, q3
; CHECK-NEXT:    vldrw.u32 q4, [r1]
; CHECK-NEXT:    add.w r1, r12, #6
; CHECK-NEXT:    vfma.f16 q3, q4, q2
; CHECK-NEXT:    vldrw.u32 q2, [r12, #4]
; CHECK-NEXT:    vfma.f16 q3, q2, q1
; CHECK-NEXT:    vldrw.u32 q1, [r1]
; CHECK-NEXT:    vfma.f16 q3, q1, q0
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vstrht.16 q3, [r2]
; CHECK-NEXT:    ldr.w r12, [r0, #4]
; CHECK-NEXT:  .LBB15_6: @ %if.end
; CHECK-NEXT:    add.w r0, r12, r3, lsl #1
; CHECK-NEXT:    lsr.w lr, r9, #2
; CHECK-NEXT:    wls lr, lr, .LBB15_10
; CHECK-NEXT:  @ %bb.7: @ %while.body51.preheader
; CHECK-NEXT:    bic r2, r9, #3
; CHECK-NEXT:    adds r1, r2, r3
; CHECK-NEXT:    mov r3, r12
; CHECK-NEXT:    add.w r1, r12, r1, lsl #1
; CHECK-NEXT:  .LBB15_8: @ %while.body51
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r0], #8
; CHECK-NEXT:    vstrb.8 q0, [r3], #8
; CHECK-NEXT:    le lr, .LBB15_8
; CHECK-NEXT:  @ %bb.9: @ %while.end55.loopexit
; CHECK-NEXT:    add.w r12, r12, r2, lsl #1
; CHECK-NEXT:    mov r0, r1
; CHECK-NEXT:  .LBB15_10: @ %while.end55
; CHECK-NEXT:    ands r1, r9, #3
; CHECK-NEXT:    beq .LBB15_12
; CHECK-NEXT:  @ %bb.11: @ %if.then59
; CHECK-NEXT:    vldrw.u32 q0, [r0]
; CHECK-NEXT:    vctp.16 r1
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vstrht.16 q0, [r12]
; CHECK-NEXT:  .LBB15_12: @ %if.end61
; CHECK-NEXT:    vpop {d8, d9, d10, d11}
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, pc}
entry:
  %pState1 = getelementptr inbounds %struct.arm_fir_instance_f32, %struct.arm_fir_instance_f32* %S, i32 0, i32 1
  %0 = load half*, half** %pState1, align 4
  %pCoeffs2 = getelementptr inbounds %struct.arm_fir_instance_f32, %struct.arm_fir_instance_f32* %S, i32 0, i32 2
  %1 = load half*, half** %pCoeffs2, align 4
  %numTaps3 = getelementptr inbounds %struct.arm_fir_instance_f32, %struct.arm_fir_instance_f32* %S, i32 0, i32 0
  %2 = load i16, i16* %numTaps3, align 4
  %conv = zext i16 %2 to i32
  %sub = add nsw i32 %conv, -1
  %cmp = icmp ult i32 %sub, 4
  br i1 %cmp, label %if.then, label %if.end

if.then:                                          ; preds = %entry
  %arrayidx = getelementptr inbounds half, half* %0, i32 %sub
  %incdec.ptr = getelementptr inbounds half, half* %1, i32 1
  %3 = load half, half* %1, align 4
  %incdec.ptr6 = getelementptr inbounds half, half* %1, i32 2
  %4 = load half, half* %incdec.ptr, align 4
  %incdec.ptr7 = getelementptr inbounds half, half* %1, i32 3
  %5 = load half, half* %incdec.ptr6, align 4
  %6 = load half, half* %incdec.ptr7, align 4
  %shr = lshr i32 %blockSize, 2
  %cmp9146 = icmp eq i32 %shr, 0
  %.pre161 = insertelement <8 x half> undef, half %3, i32 0
  %.pre162 = shufflevector <8 x half> %.pre161, <8 x half> undef, <8 x i32> zeroinitializer
  %.pre163 = insertelement <8 x half> undef, half %4, i32 0
  %.pre164 = shufflevector <8 x half> %.pre163, <8 x half> undef, <8 x i32> zeroinitializer
  %.pre165 = insertelement <8 x half> undef, half %5, i32 0
  %.pre166 = shufflevector <8 x half> %.pre165, <8 x half> undef, <8 x i32> zeroinitializer
  %.pre167 = insertelement <8 x half> undef, half %6, i32 0
  %.pre168 = shufflevector <8 x half> %.pre167, <8 x half> undef, <8 x i32> zeroinitializer
  br i1 %cmp9146, label %while.end, label %while.body.lr.ph

while.body.lr.ph:                                 ; preds = %if.then
  %7 = and i32 %blockSize, -4
  %scevgep158 = getelementptr half, half* %pDst, i32 %7
  br label %while.body

while.body:                                       ; preds = %while.body.lr.ph, %while.body
  %pStateCur.0151 = phi half* [ %arrayidx, %while.body.lr.ph ], [ %add.ptr, %while.body ]
  %pSamples.0150 = phi half* [ %0, %while.body.lr.ph ], [ %add.ptr24, %while.body ]
  %pOutput.0149 = phi half* [ %pDst, %while.body.lr.ph ], [ %add.ptr23, %while.body ]
  %pTempSrc.0148 = phi half* [ %pSrc, %while.body.lr.ph ], [ %add.ptr11, %while.body ]
  %blkCnt.0147 = phi i32 [ %shr, %while.body.lr.ph ], [ %dec, %while.body ]
  %8 = bitcast half* %pTempSrc.0148 to <8 x half>*
  %9 = load <8 x half>, <8 x half>* %8, align 4
  %10 = bitcast half* %pStateCur.0151 to <8 x half>*
  store <8 x half> %9, <8 x half>* %10, align 4
  %add.ptr = getelementptr inbounds half, half* %pStateCur.0151, i32 4
  %add.ptr11 = getelementptr inbounds half, half* %pTempSrc.0148, i32 4
  %11 = bitcast half* %pSamples.0150 to <8 x half>*
  %12 = load <8 x half>, <8 x half>* %11, align 4
  %13 = fmul fast <8 x half> %12, %.pre162
  %arrayidx12 = getelementptr inbounds half, half* %pSamples.0150, i32 1
  %14 = bitcast half* %arrayidx12 to <8 x half>*
  %15 = load <8 x half>, <8 x half>* %14, align 4
  %mul = fmul fast <8 x half> %15, %.pre164
  %add = fadd fast <8 x half> %mul, %13
  %arrayidx13 = getelementptr inbounds half, half* %pSamples.0150, i32 2
  %16 = bitcast half* %arrayidx13 to <8 x half>*
  %17 = load <8 x half>, <8 x half>* %16, align 4
  %mul16 = fmul fast <8 x half> %17, %.pre166
  %add17 = fadd fast <8 x half> %add, %mul16
  %arrayidx18 = getelementptr inbounds half, half* %pSamples.0150, i32 3
  %18 = bitcast half* %arrayidx18 to <8 x half>*
  %19 = load <8 x half>, <8 x half>* %18, align 4
  %mul21 = fmul fast <8 x half> %19, %.pre168
  %add22 = fadd fast <8 x half> %add17, %mul21
  %20 = bitcast half* %pOutput.0149 to <8 x half>*
  store <8 x half> %add22, <8 x half>* %20, align 4
  %add.ptr23 = getelementptr inbounds half, half* %pOutput.0149, i32 4
  %add.ptr24 = getelementptr inbounds half, half* %pSamples.0150, i32 4
  %dec = add nsw i32 %blkCnt.0147, -1
  %cmp9 = icmp eq i32 %dec, 0
  br i1 %cmp9, label %while.end.loopexit, label %while.body

while.end.loopexit:                               ; preds = %while.body
  %scevgep157 = getelementptr half, half* %pSrc, i32 %7
  %scevgep159 = getelementptr half, half* %0, i32 %7
  br label %while.end

while.end:                                        ; preds = %if.then, %while.end.loopexit
  %pTempSrc.0.lcssa = phi half* [ %scevgep157, %while.end.loopexit ], [ %pSrc, %if.then ]
  %pOutput.0.lcssa = phi half* [ %scevgep158, %while.end.loopexit ], [ %pDst, %if.then ]
  %pSamples.0.lcssa = phi half* [ %scevgep159, %while.end.loopexit ], [ %0, %if.then ]
  %pStateCur.0.lcssa = phi half* [ %add.ptr, %while.end.loopexit ], [ %arrayidx, %if.then ]
  %and = and i32 %blockSize, 3
  %21 = tail call <8 x i1> @llvm.arm.mve.vctp16(i32 %and)
  %22 = bitcast half* %pTempSrc.0.lcssa to <8 x half>*
  %23 = load <8 x half>, <8 x half>* %22, align 4
  %24 = bitcast half* %pStateCur.0.lcssa to <8 x half>*
  tail call void @llvm.masked.store.v8f16.p0v8f16(<8 x half> %23, <8 x half>* %24, i32 4, <8 x i1> %21)
  %25 = bitcast half* %pSamples.0.lcssa to <8 x half>*
  %26 = load <8 x half>, <8 x half>* %25, align 4
  %27 = fmul fast <8 x half> %26, %.pre162
  %arrayidx29 = getelementptr inbounds half, half* %pSamples.0.lcssa, i32 1
  %28 = bitcast half* %arrayidx29 to <8 x half>*
  %29 = load <8 x half>, <8 x half>* %28, align 4
  %mul32 = fmul fast <8 x half> %29, %.pre164
  %add33 = fadd fast <8 x half> %mul32, %27
  %arrayidx34 = getelementptr inbounds half, half* %pSamples.0.lcssa, i32 2
  %30 = bitcast half* %arrayidx34 to <8 x half>*
  %31 = load <8 x half>, <8 x half>* %30, align 4
  %mul37 = fmul fast <8 x half> %31, %.pre166
  %add38 = fadd fast <8 x half> %add33, %mul37
  %arrayidx39 = getelementptr inbounds half, half* %pSamples.0.lcssa, i32 3
  %32 = bitcast half* %arrayidx39 to <8 x half>*
  %33 = load <8 x half>, <8 x half>* %32, align 4
  %mul42 = fmul fast <8 x half> %33, %.pre168
  %add43 = fadd fast <8 x half> %add38, %mul42
  %34 = bitcast half* %pOutput.0.lcssa to <8 x half>*
  tail call void @llvm.masked.store.v8f16.p0v8f16(<8 x half> %add43, <8 x half>* %34, i32 4, <8 x i1> %21)
  %.pre = load half*, half** %pState1, align 4
  br label %if.end

if.end:                                           ; preds = %while.end, %entry
  %35 = phi half* [ %.pre, %while.end ], [ %0, %entry ]
  %arrayidx45 = getelementptr inbounds half, half* %35, i32 %blockSize
  %shr47 = lshr i32 %conv, 2
  %cmp49141 = icmp eq i32 %shr47, 0
  br i1 %cmp49141, label %while.end55, label %while.body51.preheader

while.body51.preheader:                           ; preds = %if.end
  %36 = and i32 %conv, 65532
  %37 = add i32 %36, %blockSize
  %scevgep = getelementptr half, half* %35, i32 %37
  br label %while.body51

while.body51:                                     ; preds = %while.body51.preheader, %while.body51
  %pTempSrc.1144 = phi half* [ %add.ptr52, %while.body51 ], [ %arrayidx45, %while.body51.preheader ]
  %pTempDest.0143 = phi half* [ %add.ptr53, %while.body51 ], [ %35, %while.body51.preheader ]
  %blkCnt.1142 = phi i32 [ %dec54, %while.body51 ], [ %shr47, %while.body51.preheader ]
  %38 = bitcast half* %pTempSrc.1144 to <8 x half>*
  %39 = load <8 x half>, <8 x half>* %38, align 4
  %40 = bitcast half* %pTempDest.0143 to <8 x half>*
  store <8 x half> %39, <8 x half>* %40, align 4
  %add.ptr52 = getelementptr inbounds half, half* %pTempSrc.1144, i32 4
  %add.ptr53 = getelementptr inbounds half, half* %pTempDest.0143, i32 4
  %dec54 = add nsw i32 %blkCnt.1142, -1
  %cmp49 = icmp eq i32 %dec54, 0
  br i1 %cmp49, label %while.end55.loopexit, label %while.body51

while.end55.loopexit:                             ; preds = %while.body51
  %scevgep156 = getelementptr half, half* %35, i32 %36
  br label %while.end55

while.end55:                                      ; preds = %while.end55.loopexit, %if.end
  %pTempDest.0.lcssa = phi half* [ %35, %if.end ], [ %scevgep156, %while.end55.loopexit ]
  %pTempSrc.1.lcssa = phi half* [ %arrayidx45, %if.end ], [ %scevgep, %while.end55.loopexit ]
  %and56 = and i32 %conv, 3
  %cmp57 = icmp eq i32 %and56, 0
  br i1 %cmp57, label %if.end61, label %if.then59

if.then59:                                        ; preds = %while.end55
  %41 = tail call <8 x i1> @llvm.arm.mve.vctp16(i32 %and56)
  %42 = bitcast half* %pTempSrc.1.lcssa to <8 x half>*
  %43 = load <8 x half>, <8 x half>* %42, align 4
  %44 = bitcast half* %pTempDest.0.lcssa to <8 x half>*
  tail call void @llvm.masked.store.v8f16.p0v8f16(<8 x half> %43, <8 x half>* %44, i32 4, <8 x i1> %41)
  br label %if.end61

if.end61:                                         ; preds = %while.end55, %if.then59
  ret void
}


define void @fir(%struct.arm_fir_instance_f32* nocapture readonly %S, half* nocapture readonly %pSrc, half* nocapture %pDst, i32 %blockSize) {
; CHECK-LABEL: fir:
; 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 #16
; CHECK-NEXT:    sub sp, #16
; CHECK-NEXT:    cmp r3, #8
; CHECK-NEXT:    blo.w .LBB16_12
; CHECK-NEXT:  @ %bb.1: @ %if.then
; CHECK-NEXT:    movs r7, #0
; CHECK-NEXT:    cmp.w r7, r3, lsr #2
; CHECK-NEXT:    beq.w .LBB16_12
; CHECK-NEXT:  @ %bb.2: @ %while.body.lr.ph
; CHECK-NEXT:    ldrh.w r11, [r0]
; CHECK-NEXT:    mov.w r8, #1
; CHECK-NEXT:    ldrd r5, r12, [r0, #4]
; CHECK-NEXT:    lsrs r3, r3, #2
; CHECK-NEXT:    sub.w r0, r11, #8
; CHECK-NEXT:    and r10, r0, #7
; CHECK-NEXT:    add.w r7, r0, r0, lsr #29
; CHECK-NEXT:    add.w r0, r10, #1
; CHECK-NEXT:    asrs r6, r7, #3
; CHECK-NEXT:    cmp r6, #1
; CHECK-NEXT:    it gt
; CHECK-NEXT:    asrgt.w r8, r7, #3
; CHECK-NEXT:    add.w r7, r5, r11, lsl #1
; CHECK-NEXT:    subs r4, r7, #2
; CHECK-NEXT:    rsb.w r7, r11, #0
; CHECK-NEXT:    str r7, [sp, #12] @ 4-byte Spill
; CHECK-NEXT:    add.w r7, r12, #16
; CHECK-NEXT:    str r7, [sp, #8] @ 4-byte Spill
; CHECK-NEXT:    str r0, [sp, #4] @ 4-byte Spill
; CHECK-NEXT:    b .LBB16_4
; CHECK-NEXT:  .LBB16_3: @ %while.end
; CHECK-NEXT:    @ in Loop: Header=BB16_4 Depth=1
; CHECK-NEXT:    ldr r0, [sp, #12] @ 4-byte Reload
; CHECK-NEXT:    subs r3, #1
; CHECK-NEXT:    vstrb.8 q0, [r2], #8
; CHECK-NEXT:    add.w r0, r9, r0, lsl #1
; CHECK-NEXT:    add.w r5, r0, #8
; CHECK-NEXT:    beq.w .LBB16_12
; CHECK-NEXT:  .LBB16_4: @ %while.body
; CHECK-NEXT:    @ =>This Loop Header: Depth=1
; CHECK-NEXT:    @ Child Loop BB16_6 Depth 2
; CHECK-NEXT:    @ Child Loop BB16_10 Depth 2
; CHECK-NEXT:    vldrw.u32 q0, [r1], #8
; CHECK-NEXT:    vldr.16 s7, [r12]
; CHECK-NEXT:    vldr.16 s4, [r12, #14]
; CHECK-NEXT:    vldr.16 s6, [r12, #12]
; CHECK-NEXT:    vldr.16 s8, [r12, #10]
; CHECK-NEXT:    vldr.16 s10, [r12, #8]
; CHECK-NEXT:    vldr.16 s12, [r12, #6]
; CHECK-NEXT:    vldr.16 s14, [r12, #4]
; CHECK-NEXT:    vldr.16 s5, [r12, #2]
; CHECK-NEXT:    vstrb.8 q0, [r4], #8
; CHECK-NEXT:    vldrw.u32 q0, [r5]
; CHECK-NEXT:    vmov r0, s7
; CHECK-NEXT:    adds r6, r5, #2
; CHECK-NEXT:    add.w r9, r5, #16
; CHECK-NEXT:    vmul.f16 q0, q0, r0
; CHECK-NEXT:    vldrw.u32 q4, [r6]
; CHECK-NEXT:    vmov r0, s5
; CHECK-NEXT:    adds r6, r5, #6
; CHECK-NEXT:    vfma.f16 q0, q4, r0
; CHECK-NEXT:    vldrw.u32 q4, [r5, #4]
; CHECK-NEXT:    vmov r0, s14
; CHECK-NEXT:    cmp.w r11, #16
; CHECK-NEXT:    vfma.f16 q0, q4, r0
; CHECK-NEXT:    vmov r0, s12
; CHECK-NEXT:    vldrw.u32 q3, [r6]
; CHECK-NEXT:    add.w r6, r5, #10
; CHECK-NEXT:    vfma.f16 q0, q3, r0
; CHECK-NEXT:    vldrw.u32 q3, [r5, #8]
; CHECK-NEXT:    vmov r0, s10
; CHECK-NEXT:    vfma.f16 q0, q3, r0
; CHECK-NEXT:    vmov r0, s8
; CHECK-NEXT:    vldrw.u32 q2, [r6]
; CHECK-NEXT:    add.w r6, r5, #14
; CHECK-NEXT:    vfma.f16 q0, q2, r0
; CHECK-NEXT:    vldrw.u32 q2, [r5, #12]
; CHECK-NEXT:    vmov r0, s6
; CHECK-NEXT:    vfma.f16 q0, q2, r0
; CHECK-NEXT:    vmov r0, s4
; CHECK-NEXT:    vldrw.u32 q1, [r6]
; CHECK-NEXT:    vfma.f16 q0, q1, r0
; CHECK-NEXT:    blo .LBB16_8
; CHECK-NEXT:  @ %bb.5: @ %for.body.preheader
; CHECK-NEXT:    @ in Loop: Header=BB16_4 Depth=1
; CHECK-NEXT:    dls lr, r8
; CHECK-NEXT:    ldr r6, [sp, #8] @ 4-byte Reload
; CHECK-NEXT:  .LBB16_6: @ %for.body
; CHECK-NEXT:    @ Parent Loop BB16_4 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vldr.16 s4, [r6]
; CHECK-NEXT:    add.w r5, r9, #2
; CHECK-NEXT:    vmov r0, s4
; CHECK-NEXT:    vldrw.u32 q1, [r9]
; CHECK-NEXT:    vfma.f16 q0, q1, r0
; CHECK-NEXT:    vldr.16 s4, [r6, #2]
; CHECK-NEXT:    vmov r0, s4
; CHECK-NEXT:    vldrw.u32 q1, [r5]
; CHECK-NEXT:    add.w r5, r9, #6
; CHECK-NEXT:    vfma.f16 q0, q1, r0
; CHECK-NEXT:    vldr.16 s4, [r6, #4]
; CHECK-NEXT:    vmov r0, s4
; CHECK-NEXT:    vldrw.u32 q1, [r9, #4]
; CHECK-NEXT:    vfma.f16 q0, q1, r0
; CHECK-NEXT:    vldr.16 s4, [r6, #6]
; CHECK-NEXT:    vmov r0, s4
; CHECK-NEXT:    vldrw.u32 q1, [r5]
; CHECK-NEXT:    add.w r5, r9, #10
; CHECK-NEXT:    vfma.f16 q0, q1, r0
; CHECK-NEXT:    vldr.16 s4, [r6, #8]
; CHECK-NEXT:    vmov r0, s4
; CHECK-NEXT:    vldrw.u32 q1, [r9, #8]
; CHECK-NEXT:    vfma.f16 q0, q1, r0
; CHECK-NEXT:    vldr.16 s4, [r6, #10]
; CHECK-NEXT:    vmov r0, s4
; CHECK-NEXT:    vldrw.u32 q1, [r5]
; CHECK-NEXT:    add.w r5, r9, #14
; CHECK-NEXT:    vfma.f16 q0, q1, r0
; CHECK-NEXT:    vldr.16 s4, [r6, #12]
; CHECK-NEXT:    vmov r0, s4
; CHECK-NEXT:    vldrw.u32 q1, [r9, #12]
; CHECK-NEXT:    add.w r9, r9, #16
; CHECK-NEXT:    vfma.f16 q0, q1, r0
; CHECK-NEXT:    vldr.16 s4, [r6, #14]
; CHECK-NEXT:    adds r6, #16
; CHECK-NEXT:    vmov r0, s4
; CHECK-NEXT:    vldrw.u32 q1, [r5]
; CHECK-NEXT:    vfma.f16 q0, q1, r0
; CHECK-NEXT:    le lr, .LBB16_6
; CHECK-NEXT:  @ %bb.7: @ %for.end
; CHECK-NEXT:    @ in Loop: Header=BB16_4 Depth=1
; CHECK-NEXT:    cmp.w r10, #0
; CHECK-NEXT:    bne .LBB16_9
; CHECK-NEXT:    b .LBB16_3
; CHECK-NEXT:  .LBB16_8: @ in Loop: Header=BB16_4 Depth=1
; CHECK-NEXT:    ldr r6, [sp, #8] @ 4-byte Reload
; CHECK-NEXT:    cmp.w r10, #0
; CHECK-NEXT:    beq.w .LBB16_3
; CHECK-NEXT:  .LBB16_9: @ %while.body76.preheader
; CHECK-NEXT:    @ in Loop: Header=BB16_4 Depth=1
; CHECK-NEXT:    ldr r0, [sp, #4] @ 4-byte Reload
; CHECK-NEXT:    mov r5, r9
; CHECK-NEXT:  .LBB16_10: @ %while.body76
; CHECK-NEXT:    @ Parent Loop BB16_4 Depth=1
; CHECK-NEXT:    @ => This Inner Loop Header: Depth=2
; CHECK-NEXT:    vldr.16 s4, [r6]
; CHECK-NEXT:    subs r0, #1
; CHECK-NEXT:    adds r6, #2
; CHECK-NEXT:    cmp r0, #1
; CHECK-NEXT:    vmov r7, s4
; CHECK-NEXT:    vldrh.u16 q1, [r5], #2
; CHECK-NEXT:    vfma.f16 q0, q1, r7
; CHECK-NEXT:    bgt .LBB16_10
; CHECK-NEXT:  @ %bb.11: @ %while.end.loopexit
; CHECK-NEXT:    @ in Loop: Header=BB16_4 Depth=1
; CHECK-NEXT:    add.w r9, r9, r10, lsl #1
; CHECK-NEXT:    b .LBB16_3
; CHECK-NEXT:  .LBB16_12: @ %if.end
; CHECK-NEXT:    add sp, #16
; CHECK-NEXT:    vpop {d8, d9}
; CHECK-NEXT:    add sp, #4
; CHECK-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11, pc}
entry:
  %pState1 = getelementptr inbounds %struct.arm_fir_instance_f32, %struct.arm_fir_instance_f32* %S, i32 0, i32 1
  %0 = load half*, half** %pState1, align 4
  %pCoeffs2 = getelementptr inbounds %struct.arm_fir_instance_f32, %struct.arm_fir_instance_f32* %S, i32 0, i32 2
  %1 = load half*, half** %pCoeffs2, align 4
  %numTaps3 = getelementptr inbounds %struct.arm_fir_instance_f32, %struct.arm_fir_instance_f32* %S, i32 0, i32 0
  %2 = load i16, i16* %numTaps3, align 4
  %conv = zext i16 %2 to i32
  %cmp = icmp ugt i32 %blockSize, 7
  br i1 %cmp, label %if.then, label %if.end

if.then:                                          ; preds = %entry
  %shr = lshr i32 %blockSize, 2
  %cmp5217 = icmp eq i32 %shr, 0
  br i1 %cmp5217, label %if.end, label %while.body.lr.ph

while.body.lr.ph:                                 ; preds = %if.then
  %sub = add nsw i32 %conv, -1
  %arrayidx = getelementptr inbounds half, half* %0, i32 %sub
  %incdec.ptr = getelementptr inbounds half, half* %1, i32 1
  %incdec.ptr7 = getelementptr inbounds half, half* %1, i32 2
  %incdec.ptr8 = getelementptr inbounds half, half* %1, i32 3
  %incdec.ptr9 = getelementptr inbounds half, half* %1, i32 4
  %incdec.ptr10 = getelementptr inbounds half, half* %1, i32 5
  %incdec.ptr11 = getelementptr inbounds half, half* %1, i32 6
  %incdec.ptr12 = getelementptr inbounds half, half* %1, i32 7
  %sub37 = add nsw i32 %conv, -8
  %div = sdiv i32 %sub37, 8
  %pCoeffsCur.0199 = getelementptr inbounds half, half* %1, i32 8
  %cmp38201 = icmp ugt i16 %2, 15
  %and = and i32 %sub37, 7
  %cmp74210 = icmp eq i32 %and, 0
  %idx.neg = sub nsw i32 0, %conv
  %3 = icmp sgt i32 %div, 1
  %smax = select i1 %3, i32 %div, i32 1
  br label %while.body

while.body:                                       ; preds = %while.body.lr.ph, %while.end
  %blkCnt.0222 = phi i32 [ %shr, %while.body.lr.ph ], [ %dec84, %while.end ]
  %pStateCur.0221 = phi half* [ %arrayidx, %while.body.lr.ph ], [ %add.ptr, %while.end ]
  %pSamples.0220 = phi half* [ %0, %while.body.lr.ph ], [ %add.ptr83, %while.end ]
  %pTempSrc.0219 = phi half* [ %pSrc, %while.body.lr.ph ], [ %add.ptr14, %while.end ]
  %pOutput.0218 = phi half* [ %pDst, %while.body.lr.ph ], [ %add.ptr81, %while.end ]
  %4 = load half, half* %1, align 4
  %5 = load half, half* %incdec.ptr, align 4
  %6 = load half, half* %incdec.ptr7, align 4
  %7 = load half, half* %incdec.ptr8, align 4
  %8 = load half, half* %incdec.ptr9, align 4
  %9 = load half, half* %incdec.ptr10, align 4
  %10 = load half, half* %incdec.ptr11, align 4
  %11 = load half, half* %incdec.ptr12, align 4
  %12 = bitcast half* %pTempSrc.0219 to <8 x half>*
  %13 = load <8 x half>, <8 x half>* %12, align 4
  %14 = bitcast half* %pStateCur.0221 to <8 x half>*
  store <8 x half> %13, <8 x half>* %14, align 4
  %add.ptr = getelementptr inbounds half, half* %pStateCur.0221, i32 4
  %add.ptr14 = getelementptr inbounds half, half* %pTempSrc.0219, i32 4
  %15 = bitcast half* %pSamples.0220 to <8 x half>*
  %16 = load <8 x half>, <8 x half>* %15, align 4
  %.splatinsert = insertelement <8 x half> undef, half %4, i32 0
  %.splat = shufflevector <8 x half> %.splatinsert, <8 x half> undef, <8 x i32> zeroinitializer
  %17 = fmul fast <8 x half> %16, %.splat
  %arrayidx15 = getelementptr inbounds half, half* %pSamples.0220, i32 1
  %18 = bitcast half* %arrayidx15 to <8 x half>*
  %19 = load <8 x half>, <8 x half>* %18, align 4
  %.splatinsert16 = insertelement <8 x half> undef, half %5, i32 0
  %.splat17 = shufflevector <8 x half> %.splatinsert16, <8 x half> undef, <8 x i32> zeroinitializer
  %20 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %19, <8 x half> %.splat17, <8 x half> %17)
  %arrayidx18 = getelementptr inbounds half, half* %pSamples.0220, i32 2
  %21 = bitcast half* %arrayidx18 to <8 x half>*
  %22 = load <8 x half>, <8 x half>* %21, align 4
  %.splatinsert19 = insertelement <8 x half> undef, half %6, i32 0
  %.splat20 = shufflevector <8 x half> %.splatinsert19, <8 x half> undef, <8 x i32> zeroinitializer
  %23 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %22, <8 x half> %.splat20, <8 x half> %20)
  %arrayidx21 = getelementptr inbounds half, half* %pSamples.0220, i32 3
  %24 = bitcast half* %arrayidx21 to <8 x half>*
  %25 = load <8 x half>, <8 x half>* %24, align 4
  %.splatinsert22 = insertelement <8 x half> undef, half %7, i32 0
  %.splat23 = shufflevector <8 x half> %.splatinsert22, <8 x half> undef, <8 x i32> zeroinitializer
  %26 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %25, <8 x half> %.splat23, <8 x half> %23)
  %arrayidx24 = getelementptr inbounds half, half* %pSamples.0220, i32 4
  %27 = bitcast half* %arrayidx24 to <8 x half>*
  %28 = load <8 x half>, <8 x half>* %27, align 4
  %.splatinsert25 = insertelement <8 x half> undef, half %8, i32 0
  %.splat26 = shufflevector <8 x half> %.splatinsert25, <8 x half> undef, <8 x i32> zeroinitializer
  %29 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %28, <8 x half> %.splat26, <8 x half> %26)
  %arrayidx27 = getelementptr inbounds half, half* %pSamples.0220, i32 5
  %30 = bitcast half* %arrayidx27 to <8 x half>*
  %31 = load <8 x half>, <8 x half>* %30, align 4
  %.splatinsert28 = insertelement <8 x half> undef, half %9, i32 0
  %.splat29 = shufflevector <8 x half> %.splatinsert28, <8 x half> undef, <8 x i32> zeroinitializer
  %32 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %31, <8 x half> %.splat29, <8 x half> %29)
  %arrayidx30 = getelementptr inbounds half, half* %pSamples.0220, i32 6
  %33 = bitcast half* %arrayidx30 to <8 x half>*
  %34 = load <8 x half>, <8 x half>* %33, align 4
  %.splatinsert31 = insertelement <8 x half> undef, half %10, i32 0
  %.splat32 = shufflevector <8 x half> %.splatinsert31, <8 x half> undef, <8 x i32> zeroinitializer
  %35 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %34, <8 x half> %.splat32, <8 x half> %32)
  %arrayidx33 = getelementptr inbounds half, half* %pSamples.0220, i32 7
  %36 = bitcast half* %arrayidx33 to <8 x half>*
  %37 = load <8 x half>, <8 x half>* %36, align 4
  %.splatinsert34 = insertelement <8 x half> undef, half %11, i32 0
  %.splat35 = shufflevector <8 x half> %.splatinsert34, <8 x half> undef, <8 x i32> zeroinitializer
  %38 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %37, <8 x half> %.splat35, <8 x half> %35)
  %pSamples.1200 = getelementptr inbounds half, half* %pSamples.0220, i32 8
  br i1 %cmp38201, label %for.body, label %for.end

for.body:                                         ; preds = %while.body, %for.body
  %pSamples.1207 = phi half* [ %pSamples.1, %for.body ], [ %pSamples.1200, %while.body ]
  %pCoeffsCur.0206 = phi half* [ %pCoeffsCur.0, %for.body ], [ %pCoeffsCur.0199, %while.body ]
  %.pn205 = phi half* [ %pCoeffsCur.0206, %for.body ], [ %1, %while.body ]
  %i.0204 = phi i32 [ %inc, %for.body ], [ 0, %while.body ]
  %vecAcc0.0203 = phi <8 x half> [ %70, %for.body ], [ %38, %while.body ]
  %pSamples.0.pn202 = phi half* [ %pSamples.1207, %for.body ], [ %pSamples.0220, %while.body ]
  %incdec.ptr40 = getelementptr inbounds half, half* %.pn205, i32 9
  %39 = load half, half* %pCoeffsCur.0206, align 4
  %incdec.ptr41 = getelementptr inbounds half, half* %.pn205, i32 10
  %40 = load half, half* %incdec.ptr40, align 4
  %incdec.ptr42 = getelementptr inbounds half, half* %.pn205, i32 11
  %41 = load half, half* %incdec.ptr41, align 4
  %incdec.ptr43 = getelementptr inbounds half, half* %.pn205, i32 12
  %42 = load half, half* %incdec.ptr42, align 4
  %incdec.ptr44 = getelementptr inbounds half, half* %.pn205, i32 13
  %43 = load half, half* %incdec.ptr43, align 4
  %incdec.ptr45 = getelementptr inbounds half, half* %.pn205, i32 14
  %44 = load half, half* %incdec.ptr44, align 4
  %incdec.ptr46 = getelementptr inbounds half, half* %.pn205, i32 15
  %45 = load half, half* %incdec.ptr45, align 4
  %46 = load half, half* %incdec.ptr46, align 4
  %47 = bitcast half* %pSamples.1207 to <8 x half>*
  %48 = load <8 x half>, <8 x half>* %47, align 4
  %.splatinsert48 = insertelement <8 x half> undef, half %39, i32 0
  %.splat49 = shufflevector <8 x half> %.splatinsert48, <8 x half> undef, <8 x i32> zeroinitializer
  %49 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %48, <8 x half> %.splat49, <8 x half> %vecAcc0.0203)
  %arrayidx50 = getelementptr inbounds half, half* %pSamples.0.pn202, i32 9
  %50 = bitcast half* %arrayidx50 to <8 x half>*
  %51 = load <8 x half>, <8 x half>* %50, align 4
  %.splatinsert51 = insertelement <8 x half> undef, half %40, i32 0
  %.splat52 = shufflevector <8 x half> %.splatinsert51, <8 x half> undef, <8 x i32> zeroinitializer
  %52 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %51, <8 x half> %.splat52, <8 x half> %49)
  %arrayidx53 = getelementptr inbounds half, half* %pSamples.0.pn202, i32 10
  %53 = bitcast half* %arrayidx53 to <8 x half>*
  %54 = load <8 x half>, <8 x half>* %53, align 4
  %.splatinsert54 = insertelement <8 x half> undef, half %41, i32 0
  %.splat55 = shufflevector <8 x half> %.splatinsert54, <8 x half> undef, <8 x i32> zeroinitializer
  %55 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %54, <8 x half> %.splat55, <8 x half> %52)
  %arrayidx56 = getelementptr inbounds half, half* %pSamples.0.pn202, i32 11
  %56 = bitcast half* %arrayidx56 to <8 x half>*
  %57 = load <8 x half>, <8 x half>* %56, align 4
  %.splatinsert57 = insertelement <8 x half> undef, half %42, i32 0
  %.splat58 = shufflevector <8 x half> %.splatinsert57, <8 x half> undef, <8 x i32> zeroinitializer
  %58 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %57, <8 x half> %.splat58, <8 x half> %55)
  %arrayidx59 = getelementptr inbounds half, half* %pSamples.0.pn202, i32 12
  %59 = bitcast half* %arrayidx59 to <8 x half>*
  %60 = load <8 x half>, <8 x half>* %59, align 4
  %.splatinsert60 = insertelement <8 x half> undef, half %43, i32 0
  %.splat61 = shufflevector <8 x half> %.splatinsert60, <8 x half> undef, <8 x i32> zeroinitializer
  %61 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %60, <8 x half> %.splat61, <8 x half> %58)
  %arrayidx62 = getelementptr inbounds half, half* %pSamples.0.pn202, i32 13
  %62 = bitcast half* %arrayidx62 to <8 x half>*
  %63 = load <8 x half>, <8 x half>* %62, align 4
  %.splatinsert63 = insertelement <8 x half> undef, half %44, i32 0
  %.splat64 = shufflevector <8 x half> %.splatinsert63, <8 x half> undef, <8 x i32> zeroinitializer
  %64 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %63, <8 x half> %.splat64, <8 x half> %61)
  %arrayidx65 = getelementptr inbounds half, half* %pSamples.0.pn202, i32 14
  %65 = bitcast half* %arrayidx65 to <8 x half>*
  %66 = load <8 x half>, <8 x half>* %65, align 4
  %.splatinsert66 = insertelement <8 x half> undef, half %45, i32 0
  %.splat67 = shufflevector <8 x half> %.splatinsert66, <8 x half> undef, <8 x i32> zeroinitializer
  %67 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %66, <8 x half> %.splat67, <8 x half> %64)
  %arrayidx68 = getelementptr inbounds half, half* %pSamples.0.pn202, i32 15
  %68 = bitcast half* %arrayidx68 to <8 x half>*
  %69 = load <8 x half>, <8 x half>* %68, align 4
  %.splatinsert69 = insertelement <8 x half> undef, half %46, i32 0
  %.splat70 = shufflevector <8 x half> %.splatinsert69, <8 x half> undef, <8 x i32> zeroinitializer
  %70 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %69, <8 x half> %.splat70, <8 x half> %67)
  %inc = add nuw nsw i32 %i.0204, 1
  %pCoeffsCur.0 = getelementptr inbounds half, half* %pCoeffsCur.0206, i32 8
  %pSamples.1 = getelementptr inbounds half, half* %pSamples.1207, i32 8
  %exitcond = icmp eq i32 %inc, %smax
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %while.body
  %vecAcc0.0.lcssa = phi <8 x half> [ %38, %while.body ], [ %70, %for.body ]
  %pCoeffsCur.0.lcssa = phi half* [ %pCoeffsCur.0199, %while.body ], [ %pCoeffsCur.0, %for.body ]
  %pSamples.1.lcssa = phi half* [ %pSamples.1200, %while.body ], [ %pSamples.1, %for.body ]
  br i1 %cmp74210, label %while.end, label %while.body76

while.body76:                                     ; preds = %for.end, %while.body76
  %pCoeffsCur.1214 = phi half* [ %incdec.ptr77, %while.body76 ], [ %pCoeffsCur.0.lcssa, %for.end ]
  %vecAcc0.1213 = phi <8 x half> [ %74, %while.body76 ], [ %vecAcc0.0.lcssa, %for.end ]
  %numCnt.0212 = phi i32 [ %dec, %while.body76 ], [ %and, %for.end ]
  %pSamples.2211 = phi half* [ %incdec.ptr80, %while.body76 ], [ %pSamples.1.lcssa, %for.end ]
  %incdec.ptr77 = getelementptr inbounds half, half* %pCoeffsCur.1214, i32 1
  %71 = load half, half* %pCoeffsCur.1214, align 4
  %72 = bitcast half* %pSamples.2211 to <8 x half>*
  %73 = load <8 x half>, <8 x half>* %72, align 4
  %.splatinsert78 = insertelement <8 x half> undef, half %71, i32 0
  %.splat79 = shufflevector <8 x half> %.splatinsert78, <8 x half> undef, <8 x i32> zeroinitializer
  %74 = tail call fast <8 x half> @llvm.fma.v8f16(<8 x half> %73, <8 x half> %.splat79, <8 x half> %vecAcc0.1213)
  %incdec.ptr80 = getelementptr inbounds half, half* %pSamples.2211, i32 1
  %dec = add nsw i32 %numCnt.0212, -1
  %cmp74 = icmp sgt i32 %numCnt.0212, 1
  br i1 %cmp74, label %while.body76, label %while.end.loopexit

while.end.loopexit:                               ; preds = %while.body76
  %scevgep = getelementptr half, half* %pSamples.1.lcssa, i32 %and
  br label %while.end

while.end:                                        ; preds = %while.end.loopexit, %for.end
  %pSamples.2.lcssa = phi half* [ %pSamples.1.lcssa, %for.end ], [ %scevgep, %while.end.loopexit ]
  %vecAcc0.1.lcssa = phi <8 x half> [ %vecAcc0.0.lcssa, %for.end ], [ %74, %while.end.loopexit ]
  %75 = bitcast half* %pOutput.0218 to <8 x half>*
  store <8 x half> %vecAcc0.1.lcssa, <8 x half>* %75, align 4
  %add.ptr81 = getelementptr inbounds half, half* %pOutput.0218, i32 4
  %add.ptr82 = getelementptr inbounds half, half* %pSamples.2.lcssa, i32 4
  %add.ptr83 = getelementptr inbounds half, half* %add.ptr82, i32 %idx.neg
  %dec84 = add nsw i32 %blkCnt.0222, -1
  %cmp5 = icmp eq i32 %dec84, 0
  br i1 %cmp5, label %if.end, label %while.body

if.end:                                           ; preds = %while.end, %if.then, %entry
  ret void
}

declare void @llvm.assume(i1)
declare <8 x i1> @llvm.arm.mve.vctp16(i32)
declare <8 x half> @llvm.fma.v8f16(<8 x half>, <8 x half>, <8 x half>)
declare void @llvm.masked.store.v8f16.p0v8f16(<8 x half>, <8 x half>*, i32 immarg, <8 x i1>)