forked from OSchip/llvm-project
75 lines
3.2 KiB
LLVM
75 lines
3.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp -enable-arm-maskedldst -tail-predication=force-enabled %s -o - | FileCheck %s
|
|
|
|
define arm_aapcs_vfpcc void @gather_inc_v4i32_simple(i32* noalias nocapture readonly %data, i32* noalias nocapture %dst, i32 %n) {
|
|
; CHECK-LABEL: gather_inc_v4i32_simple:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: .save {r4, lr}
|
|
; CHECK-NEXT: push {r4, lr}
|
|
; CHECK-NEXT: cmp r2, #1
|
|
; CHECK-NEXT: it lt
|
|
; CHECK-NEXT: poplt {r4, pc}
|
|
; CHECK-NEXT: .LBB0_1: @ %vector.ph.preheader
|
|
; CHECK-NEXT: bic r12, r2, #3
|
|
; CHECK-NEXT: movs r3, #1
|
|
; CHECK-NEXT: sub.w lr, r12, #4
|
|
; CHECK-NEXT: add.w r4, r3, lr, lsr #2
|
|
; CHECK-NEXT: adr r3, .LCPI0_0
|
|
; CHECK-NEXT: vldrw.u32 q0, [r3]
|
|
; CHECK-NEXT: vadd.i32 q0, q0, r0
|
|
; CHECK-NEXT: .LBB0_2: @ %vector.ph
|
|
; CHECK-NEXT: @ =>This Loop Header: Depth=1
|
|
; CHECK-NEXT: @ Child Loop BB0_3 Depth 2
|
|
; CHECK-NEXT: mov r0, r1
|
|
; CHECK-NEXT: vmov q1, q0
|
|
; CHECK-NEXT: dls lr, r4
|
|
; 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 q2, [q1, #16]!
|
|
; CHECK-NEXT: vstrb.8 q2, [r0], #16
|
|
; CHECK-NEXT: le lr, .LBB0_3
|
|
; CHECK-NEXT: @ %bb.4: @ %middle.block
|
|
; CHECK-NEXT: @ in Loop: Header=BB0_2 Depth=1
|
|
; CHECK-NEXT: cmp r12, r2
|
|
; CHECK-NEXT: bne .LBB0_2
|
|
; CHECK-NEXT: @ %bb.5: @ %for.cond.cleanup
|
|
; CHECK-NEXT: pop {r4, pc}
|
|
; CHECK-NEXT: .p2align 4
|
|
; CHECK-NEXT: @ %bb.6:
|
|
; CHECK-NEXT: .LCPI0_0:
|
|
; CHECK-NEXT: .long 4294967280 @ 0xfffffff0
|
|
; CHECK-NEXT: .long 4294967284 @ 0xfffffff4
|
|
; CHECK-NEXT: .long 4294967288 @ 0xfffffff8
|
|
; CHECK-NEXT: .long 4294967292 @ 0xfffffffc
|
|
entry:
|
|
%cmp22 = icmp sgt i32 %n, 0
|
|
br i1 %cmp22, label %vector.ph, label %for.cond.cleanup
|
|
|
|
vector.ph: ; preds = %for.body.preheader
|
|
%n.vec = and i32 %n, -4
|
|
br label %vector.body
|
|
|
|
vector.body: ; preds = %vector.body, %vector.ph
|
|
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
|
|
%vec.ind = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %vector.ph ], [ %vec.ind.next, %vector.body ]
|
|
%0 = getelementptr inbounds i32, i32* %data, <4 x i32> %vec.ind
|
|
%wide.masked.gather = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %0, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef)
|
|
%1 = getelementptr inbounds i32, i32* %dst, i32 %index
|
|
%2 = bitcast i32* %1 to <4 x i32>*
|
|
store <4 x i32> %wide.masked.gather, <4 x i32>* %2, align 4
|
|
%index.next = add i32 %index, 4
|
|
%vec.ind.next = add <4 x i32> %vec.ind, <i32 4, i32 4, i32 4, i32 4>
|
|
%3 = icmp eq i32 %index.next, %n.vec
|
|
br i1 %3, label %middle.block, label %vector.body
|
|
|
|
middle.block: ; preds = %vector.body
|
|
%cmp.n = icmp eq i32 %n.vec, %n
|
|
br i1 %cmp.n, label %for.cond.cleanup, label %vector.ph
|
|
|
|
for.cond.cleanup: ; preds = %for.body, %middle.block, %entry
|
|
ret void
|
|
}
|
|
|
|
declare <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*>, i32, <4 x i1>, <4 x i32>)
|