File: amdgpu-demote-scc-branches.ll

package info (click to toggle)
llvm-toolchain-20 1%3A20.1.6-1~exp1
  • links: PTS, VCS
  • area: main
  • in suites: experimental
  • size: 2,111,304 kB
  • sloc: cpp: 7,438,677; ansic: 1,393,822; asm: 1,012,926; python: 241,650; f90: 86,635; objc: 75,479; lisp: 42,144; pascal: 17,286; sh: 10,027; ml: 5,082; perl: 4,730; awk: 3,523; makefile: 3,349; javascript: 2,251; xml: 892; fortran: 672
file content (361 lines) | stat: -rw-r--r-- 14,313 bytes parent folder | download | duplicates (2)
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
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn -mcpu=gfx90a < %s | FileCheck -check-prefixes=GFX9 %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck -check-prefixes=GFX10,GFX1010 %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1030 < %s | FileCheck -check-prefixes=GFX10,GFX1030 %s

define void @uniform_br_no_metadata(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef inreg %flag) {
; GFX9-LABEL: uniform_br_no_metadata:
; GFX9:       ; %bb.0: ; %entry
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    s_cmp_lt_i32 s23, 1
; GFX9-NEXT:    s_cbranch_scc1 .LBB0_2
; GFX9-NEXT:  ; %bb.1: ; %if.then
; GFX9-NEXT:    s_mov_b32 s7, s20
; GFX9-NEXT:    s_mov_b32 s6, s19
; GFX9-NEXT:    s_mov_b32 s5, s18
; GFX9-NEXT:    s_mov_b32 s4, s17
; GFX9-NEXT:    v_mov_b32_e32 v0, s16
; GFX9-NEXT:    v_mov_b32_e32 v1, s21
; GFX9-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX9-NEXT:  .LBB0_2: ; %if.end
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    s_setpc_b64 s[30:31]
;
; GFX10-LABEL: uniform_br_no_metadata:
; GFX10:       ; %bb.0: ; %entry
; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT:    s_cmp_lt_i32 s23, 1
; GFX10-NEXT:    s_cbranch_scc1 .LBB0_2
; GFX10-NEXT:  ; %bb.1: ; %if.then
; GFX10-NEXT:    v_mov_b32_e32 v0, s16
; GFX10-NEXT:    v_mov_b32_e32 v1, s21
; GFX10-NEXT:    s_mov_b32 s7, s20
; GFX10-NEXT:    s_mov_b32 s6, s19
; GFX10-NEXT:    s_mov_b32 s5, s18
; GFX10-NEXT:    s_mov_b32 s4, s17
; GFX10-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX10-NEXT:  .LBB0_2: ; %if.end
; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT:    s_setpc_b64 s[30:31]
entry:
  %cmp = icmp sgt i32 %flag, 0
  br i1 %cmp, label %if.then, label %if.end

if.then:
  tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
  br label %if.end

if.end:
  call void @llvm.amdgcn.s.waitcnt(i32 0)
  ret void
}

define void @uniform_br_unprofitable(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef inreg %flag) {
; GFX9-LABEL: uniform_br_unprofitable:
; GFX9:       ; %bb.0: ; %entry
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    s_cmp_lt_i32 s23, 1
; GFX9-NEXT:    s_cbranch_scc1 .LBB1_2
; GFX9-NEXT:  ; %bb.1: ; %if.then
; GFX9-NEXT:    s_mov_b32 s7, s20
; GFX9-NEXT:    s_mov_b32 s6, s19
; GFX9-NEXT:    s_mov_b32 s5, s18
; GFX9-NEXT:    s_mov_b32 s4, s17
; GFX9-NEXT:    v_mov_b32_e32 v0, s16
; GFX9-NEXT:    v_mov_b32_e32 v1, s21
; GFX9-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX9-NEXT:  .LBB1_2: ; %if.end
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    s_setpc_b64 s[30:31]
;
; GFX10-LABEL: uniform_br_unprofitable:
; GFX10:       ; %bb.0: ; %entry
; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT:    s_cmp_lt_i32 s23, 1
; GFX10-NEXT:    s_cbranch_scc1 .LBB1_2
; GFX10-NEXT:  ; %bb.1: ; %if.then
; GFX10-NEXT:    v_mov_b32_e32 v0, s16
; GFX10-NEXT:    v_mov_b32_e32 v1, s21
; GFX10-NEXT:    s_mov_b32 s7, s20
; GFX10-NEXT:    s_mov_b32 s6, s19
; GFX10-NEXT:    s_mov_b32 s5, s18
; GFX10-NEXT:    s_mov_b32 s4, s17
; GFX10-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX10-NEXT:  .LBB1_2: ; %if.end
; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT:    s_setpc_b64 s[30:31]
entry:
  %cmp = icmp sgt i32 %flag, 0
  br i1 %cmp, label %if.then, label %if.end, !prof !0

if.then:
  tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
  br label %if.end

if.end:
  call void @llvm.amdgcn.s.waitcnt(i32 0)
  ret void
}

define void @uniform_br_profitable(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef inreg %flag) {
; GFX9-LABEL: uniform_br_profitable:
; GFX9:       ; %bb.0: ; %entry
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    s_cmp_lt_i32 s23, 1
; GFX9-NEXT:    s_cbranch_scc1 .LBB2_2
; GFX9-NEXT:  ; %bb.1: ; %if.then
; GFX9-NEXT:    s_mov_b32 s7, s20
; GFX9-NEXT:    s_mov_b32 s6, s19
; GFX9-NEXT:    s_mov_b32 s5, s18
; GFX9-NEXT:    s_mov_b32 s4, s17
; GFX9-NEXT:    v_mov_b32_e32 v0, s16
; GFX9-NEXT:    v_mov_b32_e32 v1, s21
; GFX9-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX9-NEXT:  .LBB2_2: ; %if.end
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    s_setpc_b64 s[30:31]
;
; GFX10-LABEL: uniform_br_profitable:
; GFX10:       ; %bb.0: ; %entry
; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT:    s_cmp_lt_i32 s23, 1
; GFX10-NEXT:    s_cbranch_scc1 .LBB2_2
; GFX10-NEXT:  ; %bb.1: ; %if.then
; GFX10-NEXT:    v_mov_b32_e32 v0, s16
; GFX10-NEXT:    v_mov_b32_e32 v1, s21
; GFX10-NEXT:    s_mov_b32 s7, s20
; GFX10-NEXT:    s_mov_b32 s6, s19
; GFX10-NEXT:    s_mov_b32 s5, s18
; GFX10-NEXT:    s_mov_b32 s4, s17
; GFX10-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX10-NEXT:  .LBB2_2: ; %if.end
; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT:    s_setpc_b64 s[30:31]
entry:
  %cmp = icmp sgt i32 %flag, 0
  br i1 %cmp, label %if.then, label %if.end, !prof !1

if.then:
  tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
  br label %if.end

if.end:
  call void @llvm.amdgcn.s.waitcnt(i32 0)
  ret void
}

define void @divergent_br_no_metadata(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef %flag) {
; GFX9-LABEL: divergent_br_no_metadata:
; GFX9:       ; %bb.0: ; %entry
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    v_cmp_lt_i32_e32 vcc, 0, v0
; GFX9-NEXT:    s_and_saveexec_b64 s[8:9], vcc
; GFX9-NEXT:    s_cbranch_execz .LBB3_2
; GFX9-NEXT:  ; %bb.1: ; %if.then
; GFX9-NEXT:    s_mov_b32 s7, s20
; GFX9-NEXT:    s_mov_b32 s6, s19
; GFX9-NEXT:    s_mov_b32 s5, s18
; GFX9-NEXT:    s_mov_b32 s4, s17
; GFX9-NEXT:    v_mov_b32_e32 v0, s16
; GFX9-NEXT:    v_mov_b32_e32 v1, s21
; GFX9-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX9-NEXT:  .LBB3_2: ; %if.end
; GFX9-NEXT:    s_or_b64 exec, exec, s[8:9]
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    s_setpc_b64 s[30:31]
;
; GFX1010-LABEL: divergent_br_no_metadata:
; GFX1010:       ; %bb.0: ; %entry
; GFX1010-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT:    v_cmp_lt_i32_e32 vcc_lo, 0, v0
; GFX1010-NEXT:    s_and_saveexec_b32 s8, vcc_lo
; GFX1010-NEXT:    s_cbranch_execz .LBB3_2
; GFX1010-NEXT:  ; %bb.1: ; %if.then
; GFX1010-NEXT:    v_mov_b32_e32 v0, s16
; GFX1010-NEXT:    v_mov_b32_e32 v1, s21
; GFX1010-NEXT:    s_mov_b32 s7, s20
; GFX1010-NEXT:    s_mov_b32 s6, s19
; GFX1010-NEXT:    s_mov_b32 s5, s18
; GFX1010-NEXT:    s_mov_b32 s4, s17
; GFX1010-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX1010-NEXT:  .LBB3_2: ; %if.end
; GFX1010-NEXT:    s_waitcnt_depctr 0xffe3
; GFX1010-NEXT:    s_or_b32 exec_lo, exec_lo, s8
; GFX1010-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT:    s_setpc_b64 s[30:31]
;
; GFX1030-LABEL: divergent_br_no_metadata:
; GFX1030:       ; %bb.0: ; %entry
; GFX1030-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT:    s_mov_b32 s8, exec_lo
; GFX1030-NEXT:    v_cmpx_lt_i32_e32 0, v0
; GFX1030-NEXT:    s_cbranch_execz .LBB3_2
; GFX1030-NEXT:  ; %bb.1: ; %if.then
; GFX1030-NEXT:    v_mov_b32_e32 v0, s16
; GFX1030-NEXT:    v_mov_b32_e32 v1, s21
; GFX1030-NEXT:    s_mov_b32 s7, s20
; GFX1030-NEXT:    s_mov_b32 s6, s19
; GFX1030-NEXT:    s_mov_b32 s5, s18
; GFX1030-NEXT:    s_mov_b32 s4, s17
; GFX1030-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX1030-NEXT:  .LBB3_2: ; %if.end
; GFX1030-NEXT:    s_or_b32 exec_lo, exec_lo, s8
; GFX1030-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT:    s_setpc_b64 s[30:31]
entry:
  %cmp = icmp sgt i32 %flag, 0
  br i1 %cmp, label %if.then, label %if.end

if.then:
  tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
  br label %if.end

if.end:
  call void @llvm.amdgcn.s.waitcnt(i32 0)
  ret void
}

define void @divergent_br_unprofitable(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef %flag) {
; GFX9-LABEL: divergent_br_unprofitable:
; GFX9:       ; %bb.0: ; %entry
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    v_cmp_lt_i32_e32 vcc, 0, v0
; GFX9-NEXT:    s_and_saveexec_b64 s[8:9], vcc
; GFX9-NEXT:    s_cbranch_execz .LBB4_2
; GFX9-NEXT:  ; %bb.1: ; %if.then
; GFX9-NEXT:    s_mov_b32 s7, s20
; GFX9-NEXT:    s_mov_b32 s6, s19
; GFX9-NEXT:    s_mov_b32 s5, s18
; GFX9-NEXT:    s_mov_b32 s4, s17
; GFX9-NEXT:    v_mov_b32_e32 v0, s16
; GFX9-NEXT:    v_mov_b32_e32 v1, s21
; GFX9-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX9-NEXT:  .LBB4_2: ; %if.end
; GFX9-NEXT:    s_or_b64 exec, exec, s[8:9]
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    s_setpc_b64 s[30:31]
;
; GFX1010-LABEL: divergent_br_unprofitable:
; GFX1010:       ; %bb.0: ; %entry
; GFX1010-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT:    v_cmp_lt_i32_e32 vcc_lo, 0, v0
; GFX1010-NEXT:    s_and_saveexec_b32 s8, vcc_lo
; GFX1010-NEXT:    s_cbranch_execz .LBB4_2
; GFX1010-NEXT:  ; %bb.1: ; %if.then
; GFX1010-NEXT:    v_mov_b32_e32 v0, s16
; GFX1010-NEXT:    v_mov_b32_e32 v1, s21
; GFX1010-NEXT:    s_mov_b32 s7, s20
; GFX1010-NEXT:    s_mov_b32 s6, s19
; GFX1010-NEXT:    s_mov_b32 s5, s18
; GFX1010-NEXT:    s_mov_b32 s4, s17
; GFX1010-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX1010-NEXT:  .LBB4_2: ; %if.end
; GFX1010-NEXT:    s_waitcnt_depctr 0xffe3
; GFX1010-NEXT:    s_or_b32 exec_lo, exec_lo, s8
; GFX1010-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT:    s_setpc_b64 s[30:31]
;
; GFX1030-LABEL: divergent_br_unprofitable:
; GFX1030:       ; %bb.0: ; %entry
; GFX1030-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT:    s_mov_b32 s8, exec_lo
; GFX1030-NEXT:    v_cmpx_lt_i32_e32 0, v0
; GFX1030-NEXT:    s_cbranch_execz .LBB4_2
; GFX1030-NEXT:  ; %bb.1: ; %if.then
; GFX1030-NEXT:    v_mov_b32_e32 v0, s16
; GFX1030-NEXT:    v_mov_b32_e32 v1, s21
; GFX1030-NEXT:    s_mov_b32 s7, s20
; GFX1030-NEXT:    s_mov_b32 s6, s19
; GFX1030-NEXT:    s_mov_b32 s5, s18
; GFX1030-NEXT:    s_mov_b32 s4, s17
; GFX1030-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX1030-NEXT:  .LBB4_2: ; %if.end
; GFX1030-NEXT:    s_or_b32 exec_lo, exec_lo, s8
; GFX1030-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT:    s_setpc_b64 s[30:31]
entry:
  %cmp = icmp sgt i32 %flag, 0
  br i1 %cmp, label %if.then, label %if.end, !prof !0

if.then:
  tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
  br label %if.end

if.end:
  call void @llvm.amdgcn.s.waitcnt(i32 0)
  ret void
}

define void @divergent_br_profitable(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef %flag) {
; GFX9-LABEL: divergent_br_profitable:
; GFX9:       ; %bb.0: ; %entry
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    v_cmp_lt_i32_e32 vcc, 0, v0
; GFX9-NEXT:    s_and_saveexec_b64 s[8:9], vcc
; GFX9-NEXT:  ; %bb.1: ; %if.then
; GFX9-NEXT:    s_mov_b32 s7, s20
; GFX9-NEXT:    s_mov_b32 s6, s19
; GFX9-NEXT:    s_mov_b32 s5, s18
; GFX9-NEXT:    s_mov_b32 s4, s17
; GFX9-NEXT:    v_mov_b32_e32 v0, s16
; GFX9-NEXT:    v_mov_b32_e32 v1, s21
; GFX9-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX9-NEXT:  ; %bb.2: ; %if.end
; GFX9-NEXT:    s_or_b64 exec, exec, s[8:9]
; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT:    s_setpc_b64 s[30:31]
;
; GFX1010-LABEL: divergent_br_profitable:
; GFX1010:       ; %bb.0: ; %entry
; GFX1010-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT:    v_cmp_lt_i32_e32 vcc_lo, 0, v0
; GFX1010-NEXT:    s_and_saveexec_b32 s8, vcc_lo
; GFX1010-NEXT:  ; %bb.1: ; %if.then
; GFX1010-NEXT:    v_mov_b32_e32 v0, s16
; GFX1010-NEXT:    v_mov_b32_e32 v1, s21
; GFX1010-NEXT:    s_mov_b32 s7, s20
; GFX1010-NEXT:    s_mov_b32 s6, s19
; GFX1010-NEXT:    s_mov_b32 s5, s18
; GFX1010-NEXT:    s_mov_b32 s4, s17
; GFX1010-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX1010-NEXT:  ; %bb.2: ; %if.end
; GFX1010-NEXT:    s_waitcnt_depctr 0xffe3
; GFX1010-NEXT:    s_or_b32 exec_lo, exec_lo, s8
; GFX1010-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT:    s_setpc_b64 s[30:31]
;
; GFX1030-LABEL: divergent_br_profitable:
; GFX1030:       ; %bb.0: ; %entry
; GFX1030-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT:    s_mov_b32 s8, exec_lo
; GFX1030-NEXT:    v_cmpx_lt_i32_e32 0, v0
; GFX1030-NEXT:  ; %bb.1: ; %if.then
; GFX1030-NEXT:    v_mov_b32_e32 v0, s16
; GFX1030-NEXT:    v_mov_b32_e32 v1, s21
; GFX1030-NEXT:    s_mov_b32 s7, s20
; GFX1030-NEXT:    s_mov_b32 s6, s19
; GFX1030-NEXT:    s_mov_b32 s5, s18
; GFX1030-NEXT:    s_mov_b32 s4, s17
; GFX1030-NEXT:    buffer_store_dword v0, v1, s[4:7], 0 offen
; GFX1030-NEXT:  ; %bb.2: ; %if.end
; GFX1030-NEXT:    s_or_b32 exec_lo, exec_lo, s8
; GFX1030-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT:    s_setpc_b64 s[30:31]
entry:
  %cmp = icmp sgt i32 %flag, 0
  br i1 %cmp, label %if.then, label %if.end, !prof !1

if.then:
  tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
  br label %if.end

if.end:
  call void @llvm.amdgcn.s.waitcnt(i32 0)
  ret void
}

declare void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32, ptr addrspace(8) nocapture writeonly, i32, i32, i32 immarg)
declare void @llvm.amdgcn.s.waitcnt(i32)

!0 = !{!"branch_weights", i32 1000, i32 1000}
!1 = !{!"branch_weights", i32 2000, i32 1}