1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
|
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
; RUN: llc -global-isel -mtriple=amdgcn -mcpu=fiji -O0 -stop-after=irtranslator -o - %s | FileCheck %s
define float @test_atomicrmw_fadd(ptr addrspace(3) %addr) {
; CHECK-LABEL: name: test_atomicrmw_fadd
; CHECK: bb.1 (%ir-block.0):
; CHECK-NEXT: liveins: $vgpr0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p3) = COPY $vgpr0
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
; CHECK-NEXT: [[ATOMICRMW_FADD:%[0-9]+]]:_(s32) = G_ATOMICRMW_FADD [[COPY]](p3), [[C]] :: (load store seq_cst (s32) on %ir.addr, addrspace 3)
; CHECK-NEXT: $vgpr0 = COPY [[ATOMICRMW_FADD]](s32)
; CHECK-NEXT: SI_RETURN implicit $vgpr0
%oldval = atomicrmw fadd ptr addrspace(3) %addr, float 1.0 seq_cst
ret float %oldval
}
define float @test_atomicrmw_fsub(ptr addrspace(3) %addr) {
; CHECK-LABEL: name: test_atomicrmw_fsub
; CHECK: bb.1 (%ir-block.0):
; CHECK-NEXT: successors: %bb.2(0x80000000)
; CHECK-NEXT: liveins: $vgpr0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p3) = COPY $vgpr0
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
; CHECK-NEXT: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[COPY]](p3) :: (load (s32) from %ir.addr, addrspace 3)
; CHECK-NEXT: G_BR %bb.2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.2.atomicrmw.start:
; CHECK-NEXT: successors: %bb.3(0x40000000), %bb.2(0x40000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[PHI:%[0-9]+]]:_(s64) = G_PHI %15(s64), %bb.2, [[C1]](s64), %bb.1
; CHECK-NEXT: [[PHI1:%[0-9]+]]:_(s32) = G_PHI [[LOAD]](s32), %bb.1, %13(s32), %bb.2
; CHECK-NEXT: [[FSUB:%[0-9]+]]:_(s32) = G_FSUB [[PHI1]], [[C]]
; CHECK-NEXT: [[ATOMIC_CMPXCHG_WITH_SUCCESS:%[0-9]+]]:_(s32), [[ATOMIC_CMPXCHG_WITH_SUCCESS1:%[0-9]+]]:_(s1) = G_ATOMIC_CMPXCHG_WITH_SUCCESS [[COPY]](p3), [[PHI1]], [[FSUB]] :: (load store seq_cst seq_cst (s32) on %ir.addr, addrspace 3)
; CHECK-NEXT: [[INTRINSIC_CONVERGENT:%[0-9]+]]:_(s64) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.if.break), [[ATOMIC_CMPXCHG_WITH_SUCCESS1]](s1), [[PHI]](s64)
; CHECK-NEXT: [[INTRINSIC_CONVERGENT_W_SIDE_EFFECTS:%[0-9]+]]:_(s1) = G_INTRINSIC_CONVERGENT_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.loop), [[INTRINSIC_CONVERGENT]](s64)
; CHECK-NEXT: G_BRCOND [[INTRINSIC_CONVERGENT_W_SIDE_EFFECTS]](s1), %bb.3
; CHECK-NEXT: G_BR %bb.2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.3.atomicrmw.end:
; CHECK-NEXT: [[PHI2:%[0-9]+]]:_(s32) = G_PHI [[ATOMIC_CMPXCHG_WITH_SUCCESS]](s32), %bb.2
; CHECK-NEXT: [[PHI3:%[0-9]+]]:_(s64) = G_PHI [[INTRINSIC_CONVERGENT]](s64), %bb.2
; CHECK-NEXT: G_INTRINSIC_CONVERGENT_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.end.cf), [[PHI3]](s64)
; CHECK-NEXT: $vgpr0 = COPY [[PHI2]](s32)
; CHECK-NEXT: SI_RETURN implicit $vgpr0
%oldval = atomicrmw fsub ptr addrspace(3) %addr, float 1.0 seq_cst
ret float %oldval
}
!llvm.module.flags = !{!0}
!0 = !{i32 1, !"amdgpu_code_object_version", i32 500}
|
