llvm/test/CodeGen/Thumb2/mve-tailpred-nonzerostart.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp %s -o - | FileCheck %s

define arm_aapcs_vfpcc void @start12(ptr nocapture readonly %x, ptr nocapture readonly %y, ptr noalias nocapture %z, float %a, i32 %n) {
; CHECK-LABEL: start12:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, lr}
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    cmp r3, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    poplt {r4, pc}
; CHECK-NEXT:  .LBB0_1: @ %vector.ph
; CHECK-NEXT:    vmov r12, s0
; CHECK-NEXT:    adds r0, #48
; CHECK-NEXT:    adds r1, #48
; CHECK-NEXT:    adds r2, #48
; CHECK-NEXT:    subs r3, #12
; CHECK-NEXT:    dlstp.32 lr, r3
; CHECK-NEXT:  .LBB0_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r1], #16
; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
; CHECK-NEXT:    vfmas.f32 q1, q0, r12
; CHECK-NEXT:    vstrw.32 q1, [r2], #16
; CHECK-NEXT:    letp lr, .LBB0_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    pop {r4, pc}
entry:
  %cmp8 = icmp sgt i32 %n, 0
  br i1 %cmp8, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %n.rnd.up = add i32 %n, 3
  %n.vec = and i32 %n.rnd.up, -4
  %broadcast.splatinsert13 = insertelement <4 x float> undef, float %a, i32 0
  %broadcast.splat14 = shufflevector <4 x float> %broadcast.splatinsert13, <4 x float> undef, <4 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 12, %vector.ph ], [ %index.next, %vector.body ]
  %0 = getelementptr inbounds float, ptr %x, i32 %index
  %1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %0, i32 4, <4 x i1> %1, <4 x float> undef)
  %2 = getelementptr inbounds float, ptr %y, i32 %index
  %wide.masked.load12 = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %2, i32 4, <4 x i1> %1, <4 x float> undef)
  %3 = call fast <4 x float> @llvm.fma.v4f32(<4 x float> %wide.masked.load, <4 x float> %wide.masked.load12, <4 x float> %broadcast.splat14)
  %4 = getelementptr inbounds float, ptr %z, i32 %index
  call void @llvm.masked.store.v4f32.p0(<4 x float> %3, ptr %4, i32 4, <4 x i1> %1)
  %index.next = add i32 %index, 4
  %5 = icmp eq i32 %index.next, %n.vec
  br i1 %5, label %for.cond.cleanup, label %vector.body

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


define arm_aapcs_vfpcc void @start11(ptr nocapture readonly %x, ptr nocapture readonly %y, ptr noalias nocapture %z, float %a, i32 %n) {
; CHECK-LABEL: start11:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    cmp r3, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    bxlt lr
; CHECK-NEXT:  .LBB1_1: @ %vector.ph
; CHECK-NEXT:    .save {r4, r5, r7, lr}
; CHECK-NEXT:    push {r4, r5, r7, lr}
; CHECK-NEXT:    vmov r12, s0
; CHECK-NEXT:    adds r4, r3, #3
; CHECK-NEXT:    adr r5, .LCPI1_0
; CHECK-NEXT:    bic lr, r4, #3
; CHECK-NEXT:    adds r0, #44
; CHECK-NEXT:    adds r1, #44
; CHECK-NEXT:    adds r2, #44
; CHECK-NEXT:    vldrw.u32 q0, [r5]
; CHECK-NEXT:    movs r4, #11
; CHECK-NEXT:    vdup.32 q1, r3
; CHECK-NEXT:  .LBB1_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vqadd.u32 q2, q0, r4
; CHECK-NEXT:    adds r4, #4
; CHECK-NEXT:    cmp lr, r4
; CHECK-NEXT:    vptt.u32 hi, q1, q2
; CHECK-NEXT:    vldrwt.u32 q2, [r1], #16
; CHECK-NEXT:    vldrwt.u32 q3, [r0], #16
; CHECK-NEXT:    vfmas.f32 q3, q2, r12
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vstrwt.32 q3, [r2], #16
; CHECK-NEXT:    bne .LBB1_2
; CHECK-NEXT:  @ %bb.3:
; CHECK-NEXT:    pop.w {r4, r5, r7, lr}
; CHECK-NEXT:    bx lr
; CHECK-NEXT:    .p2align 4
; CHECK-NEXT:  @ %bb.4:
; CHECK-NEXT:  .LCPI1_0:
; CHECK-NEXT:    .long 0 @ 0x0
; CHECK-NEXT:    .long 1 @ 0x1
; CHECK-NEXT:    .long 2 @ 0x2
; CHECK-NEXT:    .long 3 @ 0x3
entry:
  %cmp8 = icmp sgt i32 %n, 0
  br i1 %cmp8, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %n.rnd.up = add i32 %n, 3
  %n.vec = and i32 %n.rnd.up, -4
  %broadcast.splatinsert13 = insertelement <4 x float> undef, float %a, i32 0
  %broadcast.splat14 = shufflevector <4 x float> %broadcast.splatinsert13, <4 x float> undef, <4 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 11, %vector.ph ], [ %index.next, %vector.body ]
  %0 = getelementptr inbounds float, ptr %x, i32 %index
  %1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %0, i32 4, <4 x i1> %1, <4 x float> undef)
  %2 = getelementptr inbounds float, ptr %y, i32 %index
  %wide.masked.load12 = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %2, i32 4, <4 x i1> %1, <4 x float> undef)
  %3 = call fast <4 x float> @llvm.fma.v4f32(<4 x float> %wide.masked.load, <4 x float> %wide.masked.load12, <4 x float> %broadcast.splat14)
  %4 = getelementptr inbounds float, ptr %z, i32 %index
  call void @llvm.masked.store.v4f32.p0(<4 x float> %3, ptr %4, i32 4, <4 x i1> %1)
  %index.next = add i32 %index, 4
  %5 = icmp eq i32 %index.next, %n.vec
  br i1 %5, label %for.cond.cleanup, label %vector.body

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

define arm_aapcs_vfpcc void @startS(i32 %S, ptr nocapture readonly %x, ptr nocapture readonly %y, ptr noalias nocapture %z, float %a, i32 %n) {
; CHECK-LABEL: startS:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, r5, r7, lr}
; CHECK-NEXT:    push {r4, r5, r7, lr}
; CHECK-NEXT:    ldr r5, [sp, #16]
; CHECK-NEXT:    cmp r5, #1
; CHECK-NEXT:    blt .LBB2_3
; CHECK-NEXT:  @ %bb.1: @ %vector.ph
; CHECK-NEXT:    vmov r12, s0
; CHECK-NEXT:    adds r4, r5, #3
; CHECK-NEXT:    bic lr, r4, #3
; CHECK-NEXT:    adr r4, .LCPI2_0
; CHECK-NEXT:    add.w r1, r1, r0, lsl #2
; CHECK-NEXT:    add.w r2, r2, r0, lsl #2
; CHECK-NEXT:    add.w r3, r3, r0, lsl #2
; CHECK-NEXT:    vldrw.u32 q0, [r4]
; CHECK-NEXT:    vdup.32 q1, r5
; CHECK-NEXT:  .LBB2_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vqadd.u32 q2, q0, r0
; CHECK-NEXT:    adds r0, #4
; CHECK-NEXT:    cmp lr, r0
; CHECK-NEXT:    vptt.u32 hi, q1, q2
; CHECK-NEXT:    vldrwt.u32 q2, [r2], #16
; CHECK-NEXT:    vldrwt.u32 q3, [r1], #16
; CHECK-NEXT:    vfmas.f32 q3, q2, r12
; CHECK-NEXT:    vpst
; CHECK-NEXT:    vstrwt.32 q3, [r3], #16
; CHECK-NEXT:    bne .LBB2_2
; CHECK-NEXT:  .LBB2_3: @ %for.cond.cleanup
; CHECK-NEXT:    pop {r4, r5, r7, pc}
; CHECK-NEXT:    .p2align 4
; CHECK-NEXT:  @ %bb.4:
; CHECK-NEXT:  .LCPI2_0:
; CHECK-NEXT:    .long 0 @ 0x0
; CHECK-NEXT:    .long 1 @ 0x1
; CHECK-NEXT:    .long 2 @ 0x2
; CHECK-NEXT:    .long 3 @ 0x3
entry:
  %cmp8 = icmp sgt i32 %n, 0
  br i1 %cmp8, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %n.rnd.up = add i32 %n, 3
  %n.vec = and i32 %n.rnd.up, -4
  %broadcast.splatinsert13 = insertelement <4 x float> undef, float %a, i32 0
  %broadcast.splat14 = shufflevector <4 x float> %broadcast.splatinsert13, <4 x float> undef, <4 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ %S, %vector.ph ], [ %index.next, %vector.body ]
  %0 = getelementptr inbounds float, ptr %x, i32 %index
  %1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %0, i32 4, <4 x i1> %1, <4 x float> undef)
  %2 = getelementptr inbounds float, ptr %y, i32 %index
  %wide.masked.load12 = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %2, i32 4, <4 x i1> %1, <4 x float> undef)
  %3 = call fast <4 x float> @llvm.fma.v4f32(<4 x float> %wide.masked.load, <4 x float> %wide.masked.load12, <4 x float> %broadcast.splat14)
  %4 = getelementptr inbounds float, ptr %z, i32 %index
  call void @llvm.masked.store.v4f32.p0(<4 x float> %3, ptr %4, i32 4, <4 x i1> %1)
  %index.next = add i32 %index, 4
  %5 = icmp eq i32 %index.next, %n.vec
  br i1 %5, label %for.cond.cleanup, label %vector.body

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

define arm_aapcs_vfpcc void @startSmod4(i32 %S, ptr nocapture readonly %x, ptr nocapture readonly %y, ptr noalias nocapture %z, float %a, i32 %n) {
; CHECK-LABEL: startSmod4:
; CHECK:       @ %bb.0: @ %entry
; CHECK-NEXT:    .save {r4, lr}
; CHECK-NEXT:    push {r4, lr}
; CHECK-NEXT:    ldr.w lr, [sp, #8]
; CHECK-NEXT:    cmp.w lr, #1
; CHECK-NEXT:    it lt
; CHECK-NEXT:    poplt {r4, pc}
; CHECK-NEXT:  .LBB3_1: @ %vector.ph
; CHECK-NEXT:    vmov r12, s0
; CHECK-NEXT:    mvn r4, #12
; CHECK-NEXT:    and.w r4, r4, r0, lsl #2
; CHECK-NEXT:    add r1, r4
; CHECK-NEXT:    add r2, r4
; CHECK-NEXT:    add r3, r4
; CHECK-NEXT:    sub.w r0, lr, #4
; CHECK-NEXT:    dlstp.32 lr, r0
; CHECK-NEXT:  .LBB3_2: @ %vector.body
; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    vldrw.u32 q0, [r2], #16
; CHECK-NEXT:    vldrw.u32 q1, [r1], #16
; CHECK-NEXT:    vfmas.f32 q1, q0, r12
; CHECK-NEXT:    vstrw.32 q1, [r3], #16
; CHECK-NEXT:    letp lr, .LBB3_2
; CHECK-NEXT:  @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT:    pop {r4, pc}
entry:
  %cmp8 = icmp sgt i32 %n, 0
  br i1 %cmp8, label %vector.ph, label %for.cond.cleanup

vector.ph:                                        ; preds = %entry
  %Sm = and i32 %S, -4
  %n.rnd.up = add i32 %n, 3
  %n.vec = and i32 %n.rnd.up, -4
  %broadcast.splatinsert13 = insertelement <4 x float> undef, float %a, i32 0
  %broadcast.splat14 = shufflevector <4 x float> %broadcast.splatinsert13, <4 x float> undef, <4 x i32> zeroinitializer
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ %Sm, %vector.ph ], [ %index.next, %vector.body ]
  %0 = getelementptr inbounds float, ptr %x, i32 %index
  %1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
  %wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %0, i32 4, <4 x i1> %1, <4 x float> undef)
  %2 = getelementptr inbounds float, ptr %y, i32 %index
  %wide.masked.load12 = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %2, i32 4, <4 x i1> %1, <4 x float> undef)
  %3 = call fast <4 x float> @llvm.fma.v4f32(<4 x float> %wide.masked.load, <4 x float> %wide.masked.load12, <4 x float> %broadcast.splat14)
  %4 = getelementptr inbounds float, ptr %z, i32 %index
  call void @llvm.masked.store.v4f32.p0(<4 x float> %3, ptr %4, i32 4, <4 x i1> %1)
  %index.next = add i32 %index, 4
  %5 = icmp eq i32 %index.next, %n.vec
  br i1 %5, label %for.cond.cleanup, label %vector.body

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


declare <4 x float> @llvm.masked.load.v4f32.p0(ptr, i32 immarg, <4 x i1>, <4 x float>)
declare <4 x float> @llvm.fma.v4f32(<4 x float>, <4 x float>, <4 x float>)
declare void @llvm.masked.store.v4f32.p0(<4 x float>, ptr, i32 immarg, <4 x i1>)
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)