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
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
| ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -verify-machineinstrs -O0 < %s
; GCN-LABEL: {{^}}test_loop:
; GCN: s_and_b64 vcc, exec, -1
; GCN: [[LABEL:BB[0-9+]_[0-9]+]]: ; %for.body{{$}}
; GCN: ds_read_b32
; GCN: ds_write_b32
; GCN: s_cbranch_vccnz [[LABEL]]
; GCN: s_endpgm
define amdgpu_kernel void @test_loop(float addrspace(3)* %ptr, i32 %n) nounwind {
entry:
%cmp = icmp eq i32 %n, -1
br i1 %cmp, label %for.exit, label %for.body
for.exit:
ret void
for.body:
%indvar = phi i32 [ %inc, %for.body ], [ 0, %entry ]
%tmp = add i32 %indvar, 32
%arrayidx = getelementptr float, float addrspace(3)* %ptr, i32 %tmp
%vecload = load float, float addrspace(3)* %arrayidx, align 4
%add = fadd float %vecload, 1.0
store float %add, float addrspace(3)* %arrayidx, align 8
%inc = add i32 %indvar, 1
br label %for.body
}
; GCN-LABEL: @loop_const_true
; GCN: [[LABEL:BB[0-9+]_[0-9]+]]:
; GCN: ds_read_b32
; GCN: ds_write_b32
; GCN: s_branch [[LABEL]]
define amdgpu_kernel void @loop_const_true(float addrspace(3)* %ptr, i32 %n) nounwind {
entry:
br label %for.body
for.exit:
ret void
for.body:
%indvar = phi i32 [ %inc, %for.body ], [ 0, %entry ]
%tmp = add i32 %indvar, 32
%arrayidx = getelementptr float, float addrspace(3)* %ptr, i32 %tmp
%vecload = load float, float addrspace(3)* %arrayidx, align 4
%add = fadd float %vecload, 1.0
store float %add, float addrspace(3)* %arrayidx, align 8
%inc = add i32 %indvar, 1
br i1 true, label %for.body, label %for.exit
}
; GCN-LABEL: {{^}}loop_const_false:
; GCN-NOT: s_branch
; GCN: s_endpgm
define amdgpu_kernel void @loop_const_false(float addrspace(3)* %ptr, i32 %n) nounwind {
entry:
br label %for.body
for.exit:
ret void
; XXX - Should there be an S_ENDPGM?
for.body:
%indvar = phi i32 [ %inc, %for.body ], [ 0, %entry ]
%tmp = add i32 %indvar, 32
%arrayidx = getelementptr float, float addrspace(3)* %ptr, i32 %tmp
%vecload = load float, float addrspace(3)* %arrayidx, align 4
%add = fadd float %vecload, 1.0
store float %add, float addrspace(3)* %arrayidx, align 8
%inc = add i32 %indvar, 1
br i1 false, label %for.body, label %for.exit
}
; GCN-LABEL: {{^}}loop_const_undef:
; GCN-NOT: s_branch
; GCN: s_endpgm
define amdgpu_kernel void @loop_const_undef(float addrspace(3)* %ptr, i32 %n) nounwind {
entry:
br label %for.body
for.exit:
ret void
; XXX - Should there be an s_endpgm?
for.body:
%indvar = phi i32 [ %inc, %for.body ], [ 0, %entry ]
%tmp = add i32 %indvar, 32
%arrayidx = getelementptr float, float addrspace(3)* %ptr, i32 %tmp
%vecload = load float, float addrspace(3)* %arrayidx, align 4
%add = fadd float %vecload, 1.0
store float %add, float addrspace(3)* %arrayidx, align 8
%inc = add i32 %indvar, 1
br i1 undef, label %for.body, label %for.exit
}
; GCN-LABEL: {{^}}loop_arg_0:
; GCN: v_and_b32_e32 v{{[0-9]+}}, 1, v{{[0-9]+}}
; GCN: v_cmp_eq_u32{{[^,]*}}, 1,
; GCN: [[LOOPBB:BB[0-9]+_[0-9]+]]
; GCN: s_add_i32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80
; GCN: s_add_i32 s{{[0-9]+}}, s{{[0-9]+}}, 4
; GCN: s_cbranch_vccnz [[LOOPBB]]
; GCN-NEXT: ; %bb.2
; GCN-NEXT: s_endpgm
define amdgpu_kernel void @loop_arg_0(float addrspace(3)* %ptr, i32 %n) nounwind {
entry:
%cond = load volatile i1, i1 addrspace(3)* null
br label %for.body
for.exit:
ret void
for.body:
%indvar = phi i32 [ %inc, %for.body ], [ 0, %entry ]
%tmp = add i32 %indvar, 32
%arrayidx = getelementptr float, float addrspace(3)* %ptr, i32 %tmp
%vecload = load float, float addrspace(3)* %arrayidx, align 4
%add = fadd float %vecload, 1.0
store float %add, float addrspace(3)* %arrayidx, align 8
%inc = add i32 %indvar, 1
br i1 %cond, label %for.body, label %for.exit
}
|