File: llvm.amdgcn.sched.group.barrier.gfx12.ll

package info (click to toggle)
llvm-toolchain-19 1%3A19.1.7-3~deb12u1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm-proposed-updates
  • size: 1,998,492 kB
  • sloc: cpp: 6,951,680; ansic: 1,486,157; asm: 913,598; python: 232,024; f90: 80,126; objc: 75,281; lisp: 37,276; pascal: 16,990; sh: 10,009; ml: 5,058; perl: 4,724; awk: 3,523; makefile: 3,167; javascript: 2,504; xml: 892; fortran: 664; cs: 573
file content (339 lines) | stat: -rw-r--r-- 20,216 bytes parent folder | download | duplicates (3) 
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
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
 
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -misched-cluster=0 < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -misched-cluster=0 -amdgpu-igrouplp-exact-solver-max-branches=250000 < %s | FileCheck -check-prefix=EXACTCUTOFF %s

declare <8 x half> @llvm.amdgcn.swmmac.f16.16x16x32.f16.v8f16.v8f16.v16f16..i16(<8 x half>, <16 x half>, <8 x half>, i16)

define amdgpu_kernel void @test_sched_group_barrier_pipeline_SWMMAC_cluster(ptr addrspace(3) noalias %in, ptr addrspace(3) noalias %out) #0 {
; GCN-LABEL: test_sched_group_barrier_pipeline_SWMMAC_cluster:
; GCN:       ; %bb.0: ; %entry
; GCN-NEXT:    s_load_b64 s[0:1], s[2:3], 0x24
; GCN-NEXT:    v_lshlrev_b32_e32 v0, 4, v0
; GCN-NEXT:    v_mov_b32_e32 v48, 0
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_1)
; GCN-NEXT:    v_and_b32_e32 v28, 0x3ff0, v0
; GCN-NEXT:    s_wait_kmcnt 0x0
; GCN-NEXT:    v_add_nc_u32_e32 v0, s0, v28
; GCN-NEXT:    v_dual_mov_b32 v50, s1 :: v_dual_add_nc_u32 v49, s1, v28
; GCN-NEXT:    ds_load_b128 v[8:11], v0
; GCN-NEXT:    ds_load_b128 v[12:15], v0 offset:512
; GCN-NEXT:    ds_load_b128 v[16:19], v0 offset:1536
; GCN-NEXT:    ds_load_b128 v[20:23], v0 offset:3072
; GCN-NEXT:    ds_load_b128 v[24:27], v0 offset:5120
; GCN-NEXT:    ds_load_b128 v[4:7], v0 offset:11280
; GCN-NEXT:    ds_load_b128 v[0:3], v0 offset:11264
; GCN-NEXT:    ; sched_group_barrier mask(0x00000100) size(7) SyncID(0)
; GCN-NEXT:    s_wait_dscnt 0x6
; GCN-NEXT:    v_mov_b32_e32 v31, v11
; GCN-NEXT:    s_wait_dscnt 0x5
; GCN-NEXT:    v_mov_b32_e32 v35, v15
; GCN-NEXT:    s_wait_dscnt 0x4
; GCN-NEXT:    v_mov_b32_e32 v39, v19
; GCN-NEXT:    s_wait_dscnt 0x3
; GCN-NEXT:    v_mov_b32_e32 v43, v23
; GCN-NEXT:    s_wait_dscnt 0x2
; GCN-NEXT:    v_dual_mov_b32 v47, v27 :: v_dual_mov_b32 v30, v10
; GCN-NEXT:    v_dual_mov_b32 v29, v9 :: v_dual_mov_b32 v28, v8
; GCN-NEXT:    v_dual_mov_b32 v34, v14 :: v_dual_mov_b32 v33, v13
; GCN-NEXT:    v_mov_b32_e32 v32, v12
; GCN-NEXT:    v_dual_mov_b32 v38, v18 :: v_dual_mov_b32 v37, v17
; GCN-NEXT:    v_mov_b32_e32 v36, v16
; GCN-NEXT:    v_dual_mov_b32 v42, v22 :: v_dual_mov_b32 v41, v21
; GCN-NEXT:    v_mov_b32_e32 v40, v20
; GCN-NEXT:    v_dual_mov_b32 v46, v26 :: v_dual_mov_b32 v45, v25
; GCN-NEXT:    v_mov_b32_e32 v44, v24
; GCN-NEXT:    s_wait_dscnt 0x0
; GCN-NEXT:    v_swmmac_f16_16x16x32_f16 v[28:31], v[8:11], v[0:7], v48
; GCN-NEXT:    v_swmmac_f16_16x16x32_f16 v[32:35], v[12:15], v[0:7], v48
; GCN-NEXT:    v_swmmac_f16_16x16x32_f16 v[36:39], v[16:19], v[0:7], v48
; GCN-NEXT:    v_swmmac_f16_16x16x32_f16 v[40:43], v[20:23], v[0:7], v48
; GCN-NEXT:    v_swmmac_f16_16x16x32_f16 v[44:47], v[24:27], v[0:7], v48
; GCN-NEXT:    ds_store_b128 v49, v[28:31]
; GCN-NEXT:    ds_store_b128 v50, v[32:35] offset:512
; GCN-NEXT:    ds_store_b128 v50, v[36:39] offset:1024
; GCN-NEXT:    ds_store_b128 v50, v[40:43] offset:1536
; GCN-NEXT:    ds_store_b128 v50, v[44:47] offset:2048
; GCN-NEXT:    ; sched_group_barrier mask(0x00000008) size(5) SyncID(0)
; GCN-NEXT:    ; sched_group_barrier mask(0x00000200) size(5) SyncID(0)
; GCN-NEXT:    s_endpgm
;
; EXACTCUTOFF-LABEL: test_sched_group_barrier_pipeline_SWMMAC_cluster:
; EXACTCUTOFF:       ; %bb.0: ; %entry
; EXACTCUTOFF-NEXT:    s_load_b64 s[0:1], s[2:3], 0x24
; EXACTCUTOFF-NEXT:    v_lshlrev_b32_e32 v0, 4, v0
; EXACTCUTOFF-NEXT:    v_mov_b32_e32 v48, 0
; EXACTCUTOFF-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_1)
; EXACTCUTOFF-NEXT:    v_and_b32_e32 v28, 0x3ff0, v0
; EXACTCUTOFF-NEXT:    s_wait_kmcnt 0x0
; EXACTCUTOFF-NEXT:    v_add_nc_u32_e32 v0, s0, v28
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v50, s1 :: v_dual_add_nc_u32 v49, s1, v28
; EXACTCUTOFF-NEXT:    ds_load_b128 v[8:11], v0
; EXACTCUTOFF-NEXT:    ds_load_b128 v[12:15], v0 offset:512
; EXACTCUTOFF-NEXT:    ds_load_b128 v[16:19], v0 offset:1536
; EXACTCUTOFF-NEXT:    ds_load_b128 v[20:23], v0 offset:3072
; EXACTCUTOFF-NEXT:    ds_load_b128 v[24:27], v0 offset:5120
; EXACTCUTOFF-NEXT:    ds_load_b128 v[4:7], v0 offset:11280
; EXACTCUTOFF-NEXT:    ds_load_b128 v[0:3], v0 offset:11264
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000100) size(7) SyncID(0)
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x6
; EXACTCUTOFF-NEXT:    v_mov_b32_e32 v31, v11
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x5
; EXACTCUTOFF-NEXT:    v_mov_b32_e32 v35, v15
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x4
; EXACTCUTOFF-NEXT:    v_mov_b32_e32 v39, v19
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x3
; EXACTCUTOFF-NEXT:    v_mov_b32_e32 v43, v23
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x2
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v47, v27 :: v_dual_mov_b32 v30, v10
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v29, v9 :: v_dual_mov_b32 v28, v8
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v34, v14 :: v_dual_mov_b32 v33, v13
; EXACTCUTOFF-NEXT:    v_mov_b32_e32 v32, v12
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v38, v18 :: v_dual_mov_b32 v37, v17
; EXACTCUTOFF-NEXT:    v_mov_b32_e32 v36, v16
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v42, v22 :: v_dual_mov_b32 v41, v21
; EXACTCUTOFF-NEXT:    v_mov_b32_e32 v40, v20
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v46, v26 :: v_dual_mov_b32 v45, v25
; EXACTCUTOFF-NEXT:    v_mov_b32_e32 v44, v24
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x0
; EXACTCUTOFF-NEXT:    v_swmmac_f16_16x16x32_f16 v[28:31], v[8:11], v[0:7], v48
; EXACTCUTOFF-NEXT:    v_swmmac_f16_16x16x32_f16 v[32:35], v[12:15], v[0:7], v48
; EXACTCUTOFF-NEXT:    v_swmmac_f16_16x16x32_f16 v[36:39], v[16:19], v[0:7], v48
; EXACTCUTOFF-NEXT:    v_swmmac_f16_16x16x32_f16 v[40:43], v[20:23], v[0:7], v48
; EXACTCUTOFF-NEXT:    v_swmmac_f16_16x16x32_f16 v[44:47], v[24:27], v[0:7], v48
; EXACTCUTOFF-NEXT:    ds_store_b128 v49, v[28:31]
; EXACTCUTOFF-NEXT:    ds_store_b128 v50, v[32:35] offset:512
; EXACTCUTOFF-NEXT:    ds_store_b128 v50, v[36:39] offset:1024
; EXACTCUTOFF-NEXT:    ds_store_b128 v50, v[40:43] offset:1536
; EXACTCUTOFF-NEXT:    ds_store_b128 v50, v[44:47] offset:2048
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000008) size(5) SyncID(0)
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000200) size(5) SyncID(0)
; EXACTCUTOFF-NEXT:    s_endpgm
entry:
  %idx = call i32 @llvm.amdgcn.workitem.id.x()
  %load.0.addr = getelementptr <8 x half>, ptr addrspace(3) %in, i32 %idx
  %load.0 = load <8 x half>, ptr addrspace(3) %load.0.addr
  %load.1.addr = getelementptr <8 x half>, ptr addrspace(3) %load.0.addr, i32 32
  %load.1 = load <8 x half>, ptr addrspace(3) %load.1.addr
  %load.2.addr = getelementptr <8 x half>, ptr addrspace(3) %load.1.addr, i32 64
  %load.2 = load <8 x half>, ptr addrspace(3) %load.2.addr
  %load.3.addr = getelementptr <8 x half>, ptr addrspace(3) %load.2.addr, i32 96
  %load.3 = load <8 x half>, ptr addrspace(3) %load.3.addr
  %load.4.addr = getelementptr <8 x half>, ptr addrspace(3) %load.3.addr, i32 128
  %load.4 = load <8 x half>, ptr addrspace(3) %load.4.addr
  %load.b.addr = getelementptr <16 x half>, ptr addrspace(3) %load.4.addr, i32 192
  %load.b = load <16 x half>, ptr addrspace(3) %load.b.addr
  %mai.0 = call <8 x half> @llvm.amdgcn.swmmac.f16.16x16x32.f16.v8f16.v8f16.v16f16.i16(<8 x half> %load.0, <16 x half> %load.b, <8 x half> %load.0, i1 0)
  %mai.1 = call <8 x half> @llvm.amdgcn.swmmac.f16.16x16x32.f16.v8f16.v8f16.v16f16.i16(<8 x half> %load.1, <16 x half> %load.b, <8 x half> %load.1, i1 0)
  %mai.2 = call <8 x half> @llvm.amdgcn.swmmac.f16.16x16x32.f16.v8f16.v8f16.v16f16.i16(<8 x half> %load.2, <16 x half> %load.b, <8 x half> %load.2, i1 0)
  %mai.3 = call <8 x half> @llvm.amdgcn.swmmac.f16.16x16x32.f16.v8f16.v8f16.v16f16.i16(<8 x half> %load.3, <16 x half> %load.b, <8 x half> %load.3, i1 0)
  %mai.4 = call <8 x half> @llvm.amdgcn.swmmac.f16.16x16x32.f16.v8f16.v8f16.v16f16.i16(<8 x half> %load.4, <16 x half> %load.b, <8 x half> %load.4, i1 0)
  %store.0.addr = getelementptr <8 x half>, ptr addrspace(3) %out, i32 %idx
  store <8 x half> %mai.0, ptr addrspace(3) %store.0.addr
  %store.1.addr = getelementptr <8 x half>, ptr addrspace(3) %out, i32 32
  store <8 x half> %mai.1, ptr addrspace(3) %store.1.addr
  %store.2.addr = getelementptr <8 x half>, ptr addrspace(3) %out, i32 64
  store <8 x half> %mai.2, ptr addrspace(3) %store.2.addr
  %store.3.addr = getelementptr <8 x half>, ptr addrspace(3) %out, i32 96
  store <8 x half> %mai.3, ptr addrspace(3) %store.3.addr
  %store.4.addr = getelementptr <8 x half>, ptr addrspace(3) %out, i32 128
  store <8 x half> %mai.4, ptr addrspace(3) %store.4.addr
  ; 7 DS read
  call void @llvm.amdgcn.sched.group.barrier(i32 256, i32 7, i32 0)
  ; 5 SWMMAC
  call void @llvm.amdgcn.sched.group.barrier(i32 8, i32 5, i32 0)
  ; 5 DS write
  call void @llvm.amdgcn.sched.group.barrier(i32 512, i32 5, i32 0)
  ret void
}

define amdgpu_kernel void @test_sched_group_barrier_pipeline_SWMMAC_interleaved(ptr addrspace(3) noalias %in, ptr addrspace(3) noalias %out) #0 {
; GCN-LABEL: test_sched_group_barrier_pipeline_SWMMAC_interleaved:
; GCN:       ; %bb.0: ; %entry
; GCN-NEXT:    s_load_b64 s[0:1], s[2:3], 0x24
; GCN-NEXT:    v_and_b32_e32 v16, 0x3ff, v0
; GCN-NEXT:    v_mov_b32_e32 v18, 0
; GCN-NEXT:    s_wait_kmcnt 0x0
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_2)
; GCN-NEXT:    v_lshl_add_u32 v17, v16, 5, s0
; GCN-NEXT:    v_lshl_add_u32 v16, v16, 4, s1
; GCN-NEXT:    ds_load_b128 v[8:11], v17 offset:1024
; GCN-NEXT:    ds_load_b128 v[0:3], v17
; GCN-NEXT:    ds_load_b128 v[4:7], v17 offset:16
; GCN-NEXT:    ; sched_group_barrier mask(0x00000100) size(3) SyncID(0)
; GCN-NEXT:    s_wait_dscnt 0x2
; GCN-NEXT:    v_dual_mov_b32 v15, v11 :: v_dual_mov_b32 v14, v10
; GCN-NEXT:    v_dual_mov_b32 v13, v9 :: v_dual_mov_b32 v12, v8
; GCN-NEXT:    s_wait_dscnt 0x0
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT:    v_swmmac_f16_16x16x32_f16 v[12:15], v[8:11], v[0:7], v18
; GCN-NEXT:    ; sched_group_barrier mask(0x00000008) size(1) SyncID(0)
; GCN-NEXT:    ds_store_b128 v16, v[12:15]
; GCN-NEXT:    ds_load_b128 v[8:11], v17 offset:2560
; GCN-NEXT:    v_mov_b32_e32 v16, s1
; GCN-NEXT:    ; sched_group_barrier mask(0x00000200) size(1) SyncID(0)
; GCN-NEXT:    ; sched_group_barrier mask(0x00000100) size(1) SyncID(0)
; GCN-NEXT:    s_wait_dscnt 0x0
; GCN-NEXT:    v_dual_mov_b32 v15, v11 :: v_dual_mov_b32 v14, v10
; GCN-NEXT:    v_dual_mov_b32 v13, v9 :: v_dual_mov_b32 v12, v8
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT:    v_swmmac_f16_16x16x32_f16 v[12:15], v[8:11], v[0:7], v18
; GCN-NEXT:    ; sched_group_barrier mask(0x00000008) size(1) SyncID(0)
; GCN-NEXT:    ds_store_b128 v16, v[12:15] offset:512
; GCN-NEXT:    ds_load_b128 v[8:11], v17 offset:4608
; GCN-NEXT:    ; sched_group_barrier mask(0x00000200) size(1) SyncID(0)
; GCN-NEXT:    ; sched_group_barrier mask(0x00000100) size(1) SyncID(0)
; GCN-NEXT:    s_wait_dscnt 0x0
; GCN-NEXT:    v_dual_mov_b32 v15, v11 :: v_dual_mov_b32 v14, v10
; GCN-NEXT:    v_dual_mov_b32 v13, v9 :: v_dual_mov_b32 v12, v8
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT:    v_swmmac_f16_16x16x32_f16 v[12:15], v[8:11], v[0:7], v18
; GCN-NEXT:    ; sched_group_barrier mask(0x00000008) size(1) SyncID(0)
; GCN-NEXT:    ds_store_b128 v16, v[12:15] offset:1024
; GCN-NEXT:    ds_load_b128 v[8:11], v17 offset:7168
; GCN-NEXT:    ; sched_group_barrier mask(0x00000200) size(1) SyncID(0)
; GCN-NEXT:    ; sched_group_barrier mask(0x00000100) size(1) SyncID(0)
; GCN-NEXT:    s_wait_dscnt 0x0
; GCN-NEXT:    v_dual_mov_b32 v15, v11 :: v_dual_mov_b32 v14, v10
; GCN-NEXT:    v_dual_mov_b32 v13, v9 :: v_dual_mov_b32 v12, v8
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT:    v_swmmac_f16_16x16x32_f16 v[12:15], v[8:11], v[0:7], v18
; GCN-NEXT:    ; sched_group_barrier mask(0x00000008) size(1) SyncID(0)
; GCN-NEXT:    ds_store_b128 v16, v[12:15] offset:1536
; GCN-NEXT:    ds_load_b128 v[8:11], v17 offset:10240
; GCN-NEXT:    ; sched_group_barrier mask(0x00000200) size(1) SyncID(0)
; GCN-NEXT:    ; sched_group_barrier mask(0x00000100) size(1) SyncID(0)
; GCN-NEXT:    s_wait_dscnt 0x0
; GCN-NEXT:    v_dual_mov_b32 v15, v11 :: v_dual_mov_b32 v14, v10
; GCN-NEXT:    v_dual_mov_b32 v13, v9 :: v_dual_mov_b32 v12, v8
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT:    v_swmmac_f16_16x16x32_f16 v[12:15], v[8:11], v[0:7], v18
; GCN-NEXT:    ; sched_group_barrier mask(0x00000008) size(1) SyncID(0)
; GCN-NEXT:    ds_store_b128 v16, v[12:15] offset:2048
; GCN-NEXT:    ; sched_group_barrier mask(0x00000200) size(1) SyncID(0)
; GCN-NEXT:    s_endpgm
;
; EXACTCUTOFF-LABEL: test_sched_group_barrier_pipeline_SWMMAC_interleaved:
; EXACTCUTOFF:       ; %bb.0: ; %entry
; EXACTCUTOFF-NEXT:    s_load_b64 s[0:1], s[2:3], 0x24
; EXACTCUTOFF-NEXT:    v_and_b32_e32 v16, 0x3ff, v0
; EXACTCUTOFF-NEXT:    v_mov_b32_e32 v18, 0
; EXACTCUTOFF-NEXT:    s_wait_kmcnt 0x0
; EXACTCUTOFF-NEXT:    s_delay_alu instid0(VALU_DEP_2)
; EXACTCUTOFF-NEXT:    v_lshl_add_u32 v17, v16, 5, s0
; EXACTCUTOFF-NEXT:    v_lshl_add_u32 v16, v16, 4, s1
; EXACTCUTOFF-NEXT:    ds_load_b128 v[8:11], v17 offset:1024
; EXACTCUTOFF-NEXT:    ds_load_b128 v[0:3], v17
; EXACTCUTOFF-NEXT:    ds_load_b128 v[4:7], v17 offset:16
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000100) size(3) SyncID(0)
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x2
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v15, v11 :: v_dual_mov_b32 v14, v10
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v13, v9 :: v_dual_mov_b32 v12, v8
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x0
; EXACTCUTOFF-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; EXACTCUTOFF-NEXT:    v_swmmac_f16_16x16x32_f16 v[12:15], v[8:11], v[0:7], v18
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000008) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    ds_store_b128 v16, v[12:15]
; EXACTCUTOFF-NEXT:    ds_load_b128 v[8:11], v17 offset:2560
; EXACTCUTOFF-NEXT:    v_mov_b32_e32 v16, s1
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000200) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000100) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x0
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v15, v11 :: v_dual_mov_b32 v14, v10
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v13, v9 :: v_dual_mov_b32 v12, v8
; EXACTCUTOFF-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; EXACTCUTOFF-NEXT:    v_swmmac_f16_16x16x32_f16 v[12:15], v[8:11], v[0:7], v18
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000008) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    ds_store_b128 v16, v[12:15] offset:512
; EXACTCUTOFF-NEXT:    ds_load_b128 v[8:11], v17 offset:4608
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000200) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000100) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x0
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v15, v11 :: v_dual_mov_b32 v14, v10
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v13, v9 :: v_dual_mov_b32 v12, v8
; EXACTCUTOFF-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; EXACTCUTOFF-NEXT:    v_swmmac_f16_16x16x32_f16 v[12:15], v[8:11], v[0:7], v18
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000008) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    ds_store_b128 v16, v[12:15] offset:1024
; EXACTCUTOFF-NEXT:    ds_load_b128 v[8:11], v17 offset:7168
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000200) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000100) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x0
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v15, v11 :: v_dual_mov_b32 v14, v10
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v13, v9 :: v_dual_mov_b32 v12, v8
; EXACTCUTOFF-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; EXACTCUTOFF-NEXT:    v_swmmac_f16_16x16x32_f16 v[12:15], v[8:11], v[0:7], v18
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000008) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    ds_store_b128 v16, v[12:15] offset:1536
; EXACTCUTOFF-NEXT:    ds_load_b128 v[8:11], v17 offset:10240
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000200) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000100) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    s_wait_dscnt 0x0
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v15, v11 :: v_dual_mov_b32 v14, v10
; EXACTCUTOFF-NEXT:    v_dual_mov_b32 v13, v9 :: v_dual_mov_b32 v12, v8
; EXACTCUTOFF-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; EXACTCUTOFF-NEXT:    v_swmmac_f16_16x16x32_f16 v[12:15], v[8:11], v[0:7], v18
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000008) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    ds_store_b128 v16, v[12:15] offset:2048
; EXACTCUTOFF-NEXT:    ; sched_group_barrier mask(0x00000200) size(1) SyncID(0)
; EXACTCUTOFF-NEXT:    s_endpgm
entry:
  %idx = call i32 @llvm.amdgcn.workitem.id.x()
  %load.b.addr = getelementptr <16 x half>, ptr addrspace(3) %in, i32 %idx
  %load.b = load <16 x half>, ptr addrspace(3) %load.b.addr
  %load.0.addr = getelementptr <8 x half>, ptr addrspace(3) %load.b.addr, i32 64
  %load.0 = load <8 x half>, ptr addrspace(3) %load.0.addr
  %load.1.addr = getelementptr <8 x half>, ptr addrspace(3) %load.0.addr, i32 96
  %load.1 = load <8 x half>, ptr addrspace(3) %load.1.addr
  %load.2.addr = getelementptr <8 x half>, ptr addrspace(3) %load.1.addr, i32 128
  %load.2 = load <8 x half>, ptr addrspace(3) %load.2.addr
  %load.3.addr = getelementptr <8 x half>, ptr addrspace(3) %load.2.addr, i32 160
  %load.3 = load <8 x half>, ptr addrspace(3) %load.3.addr
  %load.4.addr = getelementptr <8 x half>, ptr addrspace(3) %load.3.addr, i32 192
  %load.4 = load <8 x half>, ptr addrspace(3) %load.4.addr
  %mai.0 = call <8 x half> @llvm.amdgcn.swmmac.f16.16x16x32.f16.v8f16.v8f16.v16f16.i16(<8 x half> %load.0, <16 x half> %load.b, <8 x half> %load.0, i1 0)
  %mai.1 = call <8 x half> @llvm.amdgcn.swmmac.f16.16x16x32.f16.v8f16.v8f16.v16f16.i16(<8 x half> %load.1, <16 x half> %load.b, <8 x half> %load.1, i1 0)
  %mai.2 = call <8 x half> @llvm.amdgcn.swmmac.f16.16x16x32.f16.v8f16.v8f16.v16f16.i16(<8 x half> %load.2, <16 x half> %load.b, <8 x half> %load.2, i1 0)
  %mai.3 = call <8 x half> @llvm.amdgcn.swmmac.f16.16x16x32.f16.v8f16.v8f16.v16f16.i16(<8 x half> %load.3, <16 x half> %load.b, <8 x half> %load.3, i1 0)
  %mai.4 = call <8 x half> @llvm.amdgcn.swmmac.f16.16x16x32.f16.v8f16.v8f16.v16f16.i16(<8 x half> %load.4, <16 x half> %load.b, <8 x half> %load.4, i1 0)
  %store.0.addr = getelementptr <8 x half>, ptr addrspace(3) %out, i32 %idx
  store <8 x half> %mai.0, ptr addrspace(3) %store.0.addr
  %store.1.addr = getelementptr <8 x half>, ptr addrspace(3) %out, i32 32
  store <8 x half> %mai.1, ptr addrspace(3) %store.1.addr
  %store.2.addr = getelementptr <8 x half>, ptr addrspace(3) %out, i32 64
  store <8 x half> %mai.2, ptr addrspace(3) %store.2.addr
  %store.3.addr = getelementptr <8 x half>, ptr addrspace(3) %out, i32 96
  store <8 x half> %mai.3, ptr addrspace(3) %store.3.addr
  %store.4.addr = getelementptr <8 x half>, ptr addrspace(3) %out, i32 128
  store <8 x half> %mai.4, ptr addrspace(3) %store.4.addr
  ; 3 DS read
  call void @llvm.amdgcn.sched.group.barrier(i32 256, i32 3, i32 0)
  ; 1 SWMMAC
  call void @llvm.amdgcn.sched.group.barrier(i32 8, i32 1, i32 0)
  ; 1 DS write
  call void @llvm.amdgcn.sched.group.barrier(i32 512, i32 1, i32 0)
  ; 1 DS read
  call void @llvm.amdgcn.sched.group.barrier(i32 256, i32 1, i32 0)
  ; 1 SWMMAC
  call void @llvm.amdgcn.sched.group.barrier(i32 8, i32 1, i32 0)
  ; 1 DS write
  call void @llvm.amdgcn.sched.group.barrier(i32 512, i32 1, i32 0)
  ; 1 DS read
  call void @llvm.amdgcn.sched.group.barrier(i32 256, i32 1, i32 0)
  ; 1 SWMMAC
  call void @llvm.amdgcn.sched.group.barrier(i32 8, i32 1, i32 0)
  ; 1 DS write
  call void @llvm.amdgcn.sched.group.barrier(i32 512, i32 1, i32 0)
  ; 1 DS read
  call void @llvm.amdgcn.sched.group.barrier(i32 256, i32 1, i32 0)
  ; 1 SWMMAC
  call void @llvm.amdgcn.sched.group.barrier(i32 8, i32 1, i32 0)
  ; 1 DS write
  call void @llvm.amdgcn.sched.group.barrier(i32 512, i32 1, i32 0)
  ; 1 DS read
  call void @llvm.amdgcn.sched.group.barrier(i32 256, i32 1, i32 0)
  ; 1 SWMMAC
  call void @llvm.amdgcn.sched.group.barrier(i32 8, i32 1, i32 0)
  ; 1 DS write
  call void @llvm.amdgcn.sched.group.barrier(i32 512, i32 1, i32 0)
  ret void
}