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
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
|
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX7LESS %s
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8MORE %s
declare i32 @llvm.amdgcn.workitem.id.x()
; Show that what the atomic optimization pass will do for global pointers.
; GCN-LABEL: add_i32_constant:
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
; GCN: {{flat|buffer|global}}_atomic_add v[[value]]
define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
entry:
%old = atomicrmw add i32 addrspace(1)* %inout, i32 5 acq_rel
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: add_i32_uniform:
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
; GCN: {{flat|buffer|global}}_atomic_add v[[value]]
define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, i32 addrspace(1)* %inout, i32 %additive) {
entry:
%old = atomicrmw add i32 addrspace(1)* %inout, i32 %additive acq_rel
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: add_i32_varying:
; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
; GFX7LESS-NOT: s_bcnt1_i32_b64
; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
; GFX8MORE: v_add_u32_dpp
; GFX8MORE: v_add_u32_dpp
; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
; GFX8MORE: buffer_atomic_add v[[value]]
define amdgpu_kernel void @add_i32_varying(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
entry:
%lane = call i32 @llvm.amdgcn.workitem.id.x()
%old = atomicrmw add i32 addrspace(1)* %inout, i32 %lane acq_rel
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: add_i64_constant:
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: v_mul_hi_u32_u24{{(_e[0-9]+)?}} v[[value_hi:[0-9]+]], s[[popcount]], 5
; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value_lo:[0-9]+]], s[[popcount]], 5
; GCN: {{flat|buffer|global}}_atomic_add_x2 v{{\[}}[[value_lo]]:[[value_hi]]{{\]}}
define amdgpu_kernel void @add_i64_constant(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
entry:
%old = atomicrmw add i64 addrspace(1)* %inout, i64 5 acq_rel
store i64 %old, i64 addrspace(1)* %out
ret void
}
; GCN-LABEL: add_i64_uniform:
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
; GCN: s_bcnt1_i32_b64 s{{[0-9]+}}, s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: {{flat|buffer|global}}_atomic_add_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
define amdgpu_kernel void @add_i64_uniform(i64 addrspace(1)* %out, i64 addrspace(1)* %inout, i64 %additive) {
entry:
%old = atomicrmw add i64 addrspace(1)* %inout, i64 %additive acq_rel
store i64 %old, i64 addrspace(1)* %out
ret void
}
; GCN-LABEL: add_i64_varying:
; GCN-NOT: v_mbcnt_lo_u32_b32
; GCN-NOT: v_mbcnt_hi_u32_b32
; GCN-NOT: s_bcnt1_i32_b64
; GCN: {{flat|buffer|global}}_atomic_add_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
define amdgpu_kernel void @add_i64_varying(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
entry:
%lane = call i32 @llvm.amdgcn.workitem.id.x()
%zext = zext i32 %lane to i64
%old = atomicrmw add i64 addrspace(1)* %inout, i64 %zext acq_rel
store i64 %old, i64 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i32_constant:
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
; GCN: {{flat|buffer|global}}_atomic_sub v[[value]]
define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
entry:
%old = atomicrmw sub i32 addrspace(1)* %inout, i32 5 acq_rel
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i32_uniform:
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
; GCN: {{flat|buffer|global}}_atomic_sub v[[value]]
define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, i32 addrspace(1)* %inout, i32 %subitive) {
entry:
%old = atomicrmw sub i32 addrspace(1)* %inout, i32 %subitive acq_rel
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i32_varying:
; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
; GFX7LESS-NOT: s_bcnt1_i32_b64
; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
; GFX8MORE: v_sub{{(rev)?}}_u32_dpp
; GFX8MORE: v_sub{{(rev)?}}_u32_dpp
; GFX8MORE: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
; GFX8MORE: buffer_atomic_sub v[[value]]
define amdgpu_kernel void @sub_i32_varying(i32 addrspace(1)* %out, i32 addrspace(1)* %inout) {
entry:
%lane = call i32 @llvm.amdgcn.workitem.id.x()
%old = atomicrmw sub i32 addrspace(1)* %inout, i32 %lane acq_rel
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i64_constant:
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
; GCN: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: v_mul_hi_u32_u24{{(_e[0-9]+)?}} v[[value_hi:[0-9]+]], s[[popcount]], 5
; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value_lo:[0-9]+]], s[[popcount]], 5
; GCN: {{flat|buffer|global}}_atomic_sub_x2 v{{\[}}[[value_lo]]:[[value_hi]]{{\]}}
define amdgpu_kernel void @sub_i64_constant(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
entry:
%old = atomicrmw sub i64 addrspace(1)* %inout, i64 5 acq_rel
store i64 %old, i64 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i64_uniform:
; GCN: v_cmp_ne_u32_e64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, 1, 0
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_lo:[0-9]+]], s[[exec_lo]], 0
; GCN: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt_hi:[0-9]+]], s[[exec_hi]], v[[mbcnt_lo]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc, 0, v[[mbcnt_hi]]
; GCN: s_bcnt1_i32_b64 s{{[0-9]+}}, s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: {{flat|buffer|global}}_atomic_sub_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
define amdgpu_kernel void @sub_i64_uniform(i64 addrspace(1)* %out, i64 addrspace(1)* %inout, i64 %subitive) {
entry:
%old = atomicrmw sub i64 addrspace(1)* %inout, i64 %subitive acq_rel
store i64 %old, i64 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i64_varying:
; GCN-NOT: v_mbcnt_lo_u32_b32
; GCN-NOT: v_mbcnt_hi_u32_b32
; GCN-NOT: s_bcnt1_i32_b64
; GCN: {{flat|buffer|global}}_atomic_sub_x2 v{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}
define amdgpu_kernel void @sub_i64_varying(i64 addrspace(1)* %out, i64 addrspace(1)* %inout) {
entry:
%lane = call i32 @llvm.amdgcn.workitem.id.x()
%zext = zext i32 %lane to i64
%old = atomicrmw sub i64 addrspace(1)* %inout, i64 %zext acq_rel
store i64 %old, i64 addrspace(1)* %out
ret void
}
|
