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
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 < %s | FileCheck -check-prefixes=GFX12 %s
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1100 < %s | FileCheck -check-prefixes=GFX11 %s
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 < %s | FileCheck -check-prefixes=GFX9 %s
; --------------------------------------------------------------------
; i32
; --------------------------------------------------------------------
define i32 @buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory(ptr addrspace(7) inreg %ptr, i32 %val) #0 {
; GFX12-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory:
; GFX12: ; %bb.0:
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: s_wait_expcnt 0x0
; GFX12-NEXT: s_wait_samplecnt 0x0
; GFX12-NEXT: s_wait_bvhcnt 0x0
; GFX12-NEXT: s_wait_kmcnt 0x0
; GFX12-NEXT: v_mov_b32_e32 v1, s16
; GFX12-NEXT: s_wait_storecnt 0x0
; GFX12-NEXT: buffer_atomic_sub_clamp_u32 v0, v1, s[0:3], null offen offset:1024 th:TH_ATOMIC_RETURN
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_inv scope:SCOPE_DEV
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory:
; GFX11: ; %bb.0:
; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX11-NEXT: v_mov_b32_e32 v1, s16
; GFX11-NEXT: s_waitcnt_vscnt null, 0x0
; GFX11-NEXT: buffer_atomic_csub_u32 v0, v1, s[0:3], 0 offen offset:1024 glc
; GFX11-NEXT: s_waitcnt vmcnt(0)
; GFX11-NEXT: buffer_gl1_inv
; GFX11-NEXT: buffer_gl0_inv
; GFX11-NEXT: s_setpc_b64 s[30:31]
;
; GFX9-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_mov_b32_e32 v2, v0
; GFX9-NEXT: v_mov_b32_e32 v0, s20
; GFX9-NEXT: buffer_load_dword v0, v0, s[16:19], 0 offen offset:1024
; GFX9-NEXT: s_mov_b64 s[4:5], 0
; GFX9-NEXT: v_mov_b32_e32 v3, s20
; GFX9-NEXT: .LBB0_1: ; %atomicrmw.start
; GFX9-NEXT: ; =>This Inner Loop Header: Depth=1
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: v_mov_b32_e32 v5, v0
; GFX9-NEXT: v_sub_u32_e64 v4, v5, v2 clamp
; GFX9-NEXT: v_mov_b32_e32 v0, v4
; GFX9-NEXT: v_mov_b32_e32 v1, v5
; GFX9-NEXT: buffer_atomic_cmpswap v[0:1], v3, s[16:19], 0 offen offset:1024 glc
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: buffer_wbinvl1
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, v0, v5
; GFX9-NEXT: s_or_b64 s[4:5], vcc, s[4:5]
; GFX9-NEXT: s_andn2_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_cbranch_execnz .LBB0_1
; GFX9-NEXT: ; %bb.2: ; %atomicrmw.end
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_setpc_b64 s[30:31]
%gep = getelementptr i32, ptr addrspace(7) %ptr, i32 256
%result = atomicrmw usub_sat ptr addrspace(7) %gep, i32 %val syncscope("agent") seq_cst, !amdgpu.no.fine.grained.memory !0
ret i32 %result
}
define void @buffer_fat_ptr_agent_atomic_usub_sat_noret_u32__offset__amdgpu_no_fine_grained_memory(ptr addrspace(7) inreg %ptr, i32 %val) #0 {
; GFX12-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_noret_u32__offset__amdgpu_no_fine_grained_memory:
; GFX12: ; %bb.0:
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: s_wait_expcnt 0x0
; GFX12-NEXT: s_wait_samplecnt 0x0
; GFX12-NEXT: s_wait_bvhcnt 0x0
; GFX12-NEXT: s_wait_kmcnt 0x0
; GFX12-NEXT: v_mov_b32_e32 v1, s16
; GFX12-NEXT: s_wait_storecnt 0x0
; GFX12-NEXT: buffer_atomic_sub_clamp_u32 v0, v1, s[0:3], null offen offset:1024 th:TH_ATOMIC_RETURN
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_inv scope:SCOPE_DEV
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_noret_u32__offset__amdgpu_no_fine_grained_memory:
; GFX11: ; %bb.0:
; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX11-NEXT: v_mov_b32_e32 v1, s16
; GFX11-NEXT: s_waitcnt_vscnt null, 0x0
; GFX11-NEXT: buffer_atomic_csub_u32 v0, v1, s[0:3], 0 offen offset:1024 glc
; GFX11-NEXT: s_waitcnt vmcnt(0)
; GFX11-NEXT: buffer_gl1_inv
; GFX11-NEXT: buffer_gl0_inv
; GFX11-NEXT: s_setpc_b64 s[30:31]
;
; GFX9-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_noret_u32__offset__amdgpu_no_fine_grained_memory:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_mov_b32_e32 v1, s20
; GFX9-NEXT: buffer_load_dword v2, v1, s[16:19], 0 offen offset:1024
; GFX9-NEXT: s_mov_b64 s[4:5], 0
; GFX9-NEXT: v_mov_b32_e32 v3, s20
; GFX9-NEXT: .LBB1_1: ; %atomicrmw.start
; GFX9-NEXT: ; =>This Inner Loop Header: Depth=1
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: v_sub_u32_e64 v1, v2, v0 clamp
; GFX9-NEXT: v_mov_b32_e32 v5, v2
; GFX9-NEXT: v_mov_b32_e32 v4, v1
; GFX9-NEXT: buffer_atomic_cmpswap v[4:5], v3, s[16:19], 0 offen offset:1024 glc
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: buffer_wbinvl1
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, v4, v2
; GFX9-NEXT: s_or_b64 s[4:5], vcc, s[4:5]
; GFX9-NEXT: v_mov_b32_e32 v2, v4
; GFX9-NEXT: s_andn2_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_cbranch_execnz .LBB1_1
; GFX9-NEXT: ; %bb.2: ; %atomicrmw.end
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_setpc_b64 s[30:31]
%gep = getelementptr i32, ptr addrspace(7) %ptr, i32 256
%unused = atomicrmw usub_sat ptr addrspace(7) %gep, i32 %val syncscope("agent") seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define i32 @buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_remote_memory(ptr addrspace(7) inreg %ptr, i32 %val) #0 {
; GFX12-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_remote_memory:
; GFX12: ; %bb.0:
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: s_wait_expcnt 0x0
; GFX12-NEXT: s_wait_samplecnt 0x0
; GFX12-NEXT: s_wait_bvhcnt 0x0
; GFX12-NEXT: s_wait_kmcnt 0x0
; GFX12-NEXT: v_mov_b32_e32 v1, s16
; GFX12-NEXT: s_wait_storecnt 0x0
; GFX12-NEXT: buffer_atomic_sub_clamp_u32 v0, v1, s[0:3], null offen offset:1024 th:TH_ATOMIC_RETURN
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_inv scope:SCOPE_DEV
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_remote_memory:
; GFX11: ; %bb.0:
; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX11-NEXT: v_mov_b32_e32 v1, s16
; GFX11-NEXT: s_waitcnt_vscnt null, 0x0
; GFX11-NEXT: buffer_atomic_csub_u32 v0, v1, s[0:3], 0 offen offset:1024 glc
; GFX11-NEXT: s_waitcnt vmcnt(0)
; GFX11-NEXT: buffer_gl1_inv
; GFX11-NEXT: buffer_gl0_inv
; GFX11-NEXT: s_setpc_b64 s[30:31]
;
; GFX9-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_remote_memory:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_mov_b32_e32 v2, v0
; GFX9-NEXT: v_mov_b32_e32 v0, s20
; GFX9-NEXT: buffer_load_dword v0, v0, s[16:19], 0 offen offset:1024
; GFX9-NEXT: s_mov_b64 s[4:5], 0
; GFX9-NEXT: v_mov_b32_e32 v3, s20
; GFX9-NEXT: .LBB2_1: ; %atomicrmw.start
; GFX9-NEXT: ; =>This Inner Loop Header: Depth=1
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: v_mov_b32_e32 v5, v0
; GFX9-NEXT: v_sub_u32_e64 v4, v5, v2 clamp
; GFX9-NEXT: v_mov_b32_e32 v0, v4
; GFX9-NEXT: v_mov_b32_e32 v1, v5
; GFX9-NEXT: buffer_atomic_cmpswap v[0:1], v3, s[16:19], 0 offen offset:1024 glc
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: buffer_wbinvl1
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, v0, v5
; GFX9-NEXT: s_or_b64 s[4:5], vcc, s[4:5]
; GFX9-NEXT: s_andn2_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_cbranch_execnz .LBB2_1
; GFX9-NEXT: ; %bb.2: ; %atomicrmw.end
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_setpc_b64 s[30:31]
%gep = getelementptr i32, ptr addrspace(7) %ptr, i32 256
%result = atomicrmw usub_sat ptr addrspace(7) %gep, i32 %val syncscope("agent") seq_cst, !amdgpu.no.remote.memory !0
ret i32 %result
}
define i32 @buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory__amdgpu_no_remote_memory(ptr addrspace(7) inreg %ptr, i32 %val) #0 {
; GFX12-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory__amdgpu_no_remote_memory:
; GFX12: ; %bb.0:
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: s_wait_expcnt 0x0
; GFX12-NEXT: s_wait_samplecnt 0x0
; GFX12-NEXT: s_wait_bvhcnt 0x0
; GFX12-NEXT: s_wait_kmcnt 0x0
; GFX12-NEXT: v_mov_b32_e32 v1, s16
; GFX12-NEXT: s_wait_storecnt 0x0
; GFX12-NEXT: buffer_atomic_sub_clamp_u32 v0, v1, s[0:3], null offen offset:1024 th:TH_ATOMIC_RETURN
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_inv scope:SCOPE_DEV
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory__amdgpu_no_remote_memory:
; GFX11: ; %bb.0:
; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX11-NEXT: v_mov_b32_e32 v1, s16
; GFX11-NEXT: s_waitcnt_vscnt null, 0x0
; GFX11-NEXT: buffer_atomic_csub_u32 v0, v1, s[0:3], 0 offen offset:1024 glc
; GFX11-NEXT: s_waitcnt vmcnt(0)
; GFX11-NEXT: buffer_gl1_inv
; GFX11-NEXT: buffer_gl0_inv
; GFX11-NEXT: s_setpc_b64 s[30:31]
;
; GFX9-LABEL: buffer_fat_ptr_agent_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory__amdgpu_no_remote_memory:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_mov_b32_e32 v2, v0
; GFX9-NEXT: v_mov_b32_e32 v0, s20
; GFX9-NEXT: buffer_load_dword v0, v0, s[16:19], 0 offen offset:1024
; GFX9-NEXT: s_mov_b64 s[4:5], 0
; GFX9-NEXT: v_mov_b32_e32 v3, s20
; GFX9-NEXT: .LBB3_1: ; %atomicrmw.start
; GFX9-NEXT: ; =>This Inner Loop Header: Depth=1
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: v_mov_b32_e32 v5, v0
; GFX9-NEXT: v_sub_u32_e64 v4, v5, v2 clamp
; GFX9-NEXT: v_mov_b32_e32 v0, v4
; GFX9-NEXT: v_mov_b32_e32 v1, v5
; GFX9-NEXT: buffer_atomic_cmpswap v[0:1], v3, s[16:19], 0 offen offset:1024 glc
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: buffer_wbinvl1
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, v0, v5
; GFX9-NEXT: s_or_b64 s[4:5], vcc, s[4:5]
; GFX9-NEXT: s_andn2_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_cbranch_execnz .LBB3_1
; GFX9-NEXT: ; %bb.2: ; %atomicrmw.end
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_setpc_b64 s[30:31]
%gep = getelementptr i32, ptr addrspace(7) %ptr, i32 256
%result = atomicrmw usub_sat ptr addrspace(7) %gep, i32 %val syncscope("agent") seq_cst, !amdgpu.no.fine.grained.memory !0, !amdgpu.no.remote.memory !0
ret i32 %result
}
; --------------------------------------------------------------------
; misc
; --------------------------------------------------------------------
define i32 @buffer_fat_ptr_system_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory(ptr addrspace(7) inreg %ptr, i32 %val) #0 {
; GFX12-LABEL: buffer_fat_ptr_system_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory:
; GFX12: ; %bb.0:
; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT: s_wait_expcnt 0x0
; GFX12-NEXT: s_wait_samplecnt 0x0
; GFX12-NEXT: s_wait_bvhcnt 0x0
; GFX12-NEXT: s_wait_kmcnt 0x0
; GFX12-NEXT: v_mov_b32_e32 v1, s16
; GFX12-NEXT: global_wb scope:SCOPE_SYS
; GFX12-NEXT: s_wait_storecnt 0x0
; GFX12-NEXT: buffer_atomic_sub_clamp_u32 v0, v1, s[0:3], null offen offset:1024 th:TH_ATOMIC_RETURN
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: global_inv scope:SCOPE_SYS
; GFX12-NEXT: s_wait_loadcnt 0x0
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: buffer_fat_ptr_system_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory:
; GFX11: ; %bb.0:
; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX11-NEXT: v_mov_b32_e32 v1, s16
; GFX11-NEXT: s_waitcnt_vscnt null, 0x0
; GFX11-NEXT: buffer_atomic_csub_u32 v0, v1, s[0:3], 0 offen offset:1024 glc
; GFX11-NEXT: s_waitcnt vmcnt(0)
; GFX11-NEXT: buffer_gl1_inv
; GFX11-NEXT: buffer_gl0_inv
; GFX11-NEXT: s_setpc_b64 s[30:31]
;
; GFX9-LABEL: buffer_fat_ptr_system_atomic_usub_sat_ret_u32__offset__amdgpu_no_fine_grained_memory:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_mov_b32_e32 v2, v0
; GFX9-NEXT: v_mov_b32_e32 v0, s20
; GFX9-NEXT: buffer_load_dword v0, v0, s[16:19], 0 offen offset:1024
; GFX9-NEXT: s_mov_b64 s[4:5], 0
; GFX9-NEXT: v_mov_b32_e32 v3, s20
; GFX9-NEXT: .LBB4_1: ; %atomicrmw.start
; GFX9-NEXT: ; =>This Inner Loop Header: Depth=1
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: v_mov_b32_e32 v5, v0
; GFX9-NEXT: v_sub_u32_e64 v4, v5, v2 clamp
; GFX9-NEXT: v_mov_b32_e32 v0, v4
; GFX9-NEXT: v_mov_b32_e32 v1, v5
; GFX9-NEXT: buffer_atomic_cmpswap v[0:1], v3, s[16:19], 0 offen offset:1024 glc
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: buffer_wbinvl1
; GFX9-NEXT: v_cmp_eq_u32_e32 vcc, v0, v5
; GFX9-NEXT: s_or_b64 s[4:5], vcc, s[4:5]
; GFX9-NEXT: s_andn2_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_cbranch_execnz .LBB4_1
; GFX9-NEXT: ; %bb.2: ; %atomicrmw.end
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_setpc_b64 s[30:31]
%gep = getelementptr i32, ptr addrspace(7) %ptr, i32 256
%result = atomicrmw usub_sat ptr addrspace(7) %gep, i32 %val seq_cst, !amdgpu.no.fine.grained.memory !0
ret i32 %result
}
attributes #0 = { nounwind }
!0 = !{}
|
