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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -global-isel=0 | FileCheck %s -check-prefixes=CHECK,CHECK-SDAG-TRUE16
; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -global-isel=0 | FileCheck %s -check-prefixes=CHECK,CHECK-FAKE16
; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -global-isel=1 | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL-TRUE16
; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -global-isel=1 | FileCheck %s -check-prefixes=CHECK,CHECK-FAKE16
define amdgpu_kernel void @raw_ptr_atomic_buffer_ptr_load_i32(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_ptr_load_i32:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB0_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: buffer_load_b32 v1, off, s[0:3], 0 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_cmp_ne_u32_e32 vcc_lo, v1, v0
; CHECK-NEXT: s_or_b32 s4, vcc_lo, s4
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-NEXT: s_and_not1_b32 exec_lo, exec_lo, s4
; CHECK-NEXT: s_cbranch_execnz .LBB0_1
; CHECK-NEXT: ; %bb.2: ; %bb2
; CHECK-NEXT: s_endpgm
bb:
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
br label %bb1
bb1:
%load = call i32 @llvm.amdgcn.raw.ptr.atomic.buffer.load.i32(ptr addrspace(8) %ptr, i32 0, i32 0, i32 1)
%cmp = icmp eq i32 %load, %id
br i1 %cmp, label %bb1, label %bb2
bb2:
ret void
}
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_i32_off(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_i32_off:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB1_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: buffer_load_b32 v1, off, s[0:3], 0 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_cmp_ne_u32_e32 vcc_lo, v1, v0
; CHECK-NEXT: s_or_b32 s4, vcc_lo, s4
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-NEXT: s_and_not1_b32 exec_lo, exec_lo, s4
; CHECK-NEXT: s_cbranch_execnz .LBB1_1
; CHECK-NEXT: ; %bb.2: ; %bb2
; CHECK-NEXT: s_endpgm
bb:
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
br label %bb1
bb1:
%load = call i32 @llvm.amdgcn.raw.ptr.atomic.buffer.load.i32(ptr addrspace(8) %ptr, i32 0, i32 0, i32 1)
%cmp = icmp eq i32 %load, %id
br i1 %cmp, label %bb1, label %bb2
bb2:
ret void
}
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_i32_soff(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_i32_soff:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB2_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: buffer_load_b32 v1, off, s[0:3], 4 offset:4 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_cmp_ne_u32_e32 vcc_lo, v1, v0
; CHECK-NEXT: s_or_b32 s4, vcc_lo, s4
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-NEXT: s_and_not1_b32 exec_lo, exec_lo, s4
; CHECK-NEXT: s_cbranch_execnz .LBB2_1
; CHECK-NEXT: ; %bb.2: ; %bb2
; CHECK-NEXT: s_endpgm
bb:
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
br label %bb1
bb1:
%load = call i32 @llvm.amdgcn.raw.ptr.atomic.buffer.load.i32(ptr addrspace(8) %ptr, i32 4, i32 4, i32 1)
%cmp = icmp eq i32 %load, %id
br i1 %cmp, label %bb1, label %bb2
bb2:
ret void
}
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_i32_dlc(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_i32_dlc:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB3_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: buffer_load_b32 v1, off, s[0:3], 0 offset:4 dlc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_cmp_ne_u32_e32 vcc_lo, v1, v0
; CHECK-NEXT: s_or_b32 s4, vcc_lo, s4
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-NEXT: s_and_not1_b32 exec_lo, exec_lo, s4
; CHECK-NEXT: s_cbranch_execnz .LBB3_1
; CHECK-NEXT: ; %bb.2: ; %bb2
; CHECK-NEXT: s_endpgm
bb:
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
br label %bb1
bb1:
%load = call i32 @llvm.amdgcn.raw.ptr.atomic.buffer.load.i32(ptr addrspace(8) %ptr, i32 4, i32 0, i32 4)
%cmp = icmp eq i32 %load, %id
br i1 %cmp, label %bb1, label %bb2
bb2:
ret void
}
define amdgpu_kernel void @raw_nonptr_atomic_buffer_load_i32(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_nonptr_atomic_buffer_load_i32:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: buffer_load_b32 v1, off, s[0:3], 0 offset:4 glc
; CHECK-NEXT: s_mov_b32 s0, 0
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_cmp_ne_u32_e32 vcc_lo, v1, v0
; CHECK-NEXT: .LBB4_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: s_and_b32 s1, exec_lo, vcc_lo
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
; CHECK-NEXT: s_or_b32 s0, s1, s0
; CHECK-NEXT: s_and_not1_b32 exec_lo, exec_lo, s0
; CHECK-NEXT: s_cbranch_execnz .LBB4_1
; CHECK-NEXT: ; %bb.2: ; %bb2
; CHECK-NEXT: s_endpgm
bb:
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
br label %bb1
bb1:
%load = call i32 @llvm.amdgcn.raw.ptr.buffer.load.i32(ptr addrspace(8) %ptr, i32 4, i32 0, i32 1)
%cmp = icmp eq i32 %load, %id
br i1 %cmp, label %bb1, label %bb2
bb2:
ret void
}
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_i64(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_i64:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-NEXT: v_dual_mov_b32 v1, 0 :: v_dual_and_b32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB5_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: buffer_load_b64 v[2:3], off, s[0:3], 0 offset:4 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_cmp_ne_u64_e32 vcc_lo, v[2:3], v[0:1]
; CHECK-NEXT: s_or_b32 s4, vcc_lo, s4
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-NEXT: s_and_not1_b32 exec_lo, exec_lo, s4
; CHECK-NEXT: s_cbranch_execnz .LBB5_1
; CHECK-NEXT: ; %bb.2: ; %bb2
; CHECK-NEXT: s_endpgm
bb:
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
%id.zext = zext i32 %id to i64
br label %bb1
bb1:
%load = call i64 @llvm.amdgcn.raw.ptr.atomic.buffer.load.i64(ptr addrspace(8) %ptr, i32 4, i32 0, i32 1)
%cmp = icmp eq i64 %load, %id.zext
br i1 %cmp, label %bb1, label %bb2
bb2:
ret void
}
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_v2i16(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_v2i16:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB6_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: buffer_load_b32 v1, off, s[0:3], 0 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_cmp_ne_u32_e32 vcc_lo, v1, v0
; CHECK-NEXT: s_or_b32 s4, vcc_lo, s4
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-NEXT: s_and_not1_b32 exec_lo, exec_lo, s4
; CHECK-NEXT: s_cbranch_execnz .LBB6_1
; CHECK-NEXT: ; %bb.2: ; %bb2
; CHECK-NEXT: s_endpgm
bb:
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
br label %bb1
bb1:
%load = call <2 x i16> @llvm.amdgcn.raw.ptr.atomic.buffer.load.v2i16(ptr addrspace(8) %ptr, i32 0, i32 0, i32 1)
%bitcast = bitcast <2 x i16> %load to i32
%cmp = icmp eq i32 %bitcast, %id
br i1 %cmp, label %bb1, label %bb2
bb2:
ret void
}
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_v4i16(ptr addrspace(8) %ptr) {
; CHECK-SDAG-TRUE16-LABEL: raw_ptr_atomic_buffer_load_v4i16:
; CHECK-SDAG-TRUE16: ; %bb.0: ; %bb
; CHECK-SDAG-TRUE16-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-SDAG-TRUE16-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-SDAG-TRUE16-NEXT: s_mov_b32 s4, 0
; CHECK-SDAG-TRUE16-NEXT: .LBB7_1: ; %bb1
; CHECK-SDAG-TRUE16-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-SDAG-TRUE16-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-SDAG-TRUE16-NEXT: buffer_load_b64 v[1:2], off, s[0:3], 0 offset:4 glc
; CHECK-SDAG-TRUE16-NEXT: s_waitcnt vmcnt(0)
; CHECK-SDAG-TRUE16-NEXT: v_and_b32_e32 v1, 0xffff, v1
; CHECK-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
; CHECK-SDAG-TRUE16-NEXT: v_lshl_or_b32 v1, v2, 16, v1
; CHECK-SDAG-TRUE16-NEXT: v_cmp_ne_u32_e32 vcc_lo, v1, v0
; CHECK-SDAG-TRUE16-NEXT: s_or_b32 s4, vcc_lo, s4
; CHECK-SDAG-TRUE16-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-SDAG-TRUE16-NEXT: s_and_not1_b32 exec_lo, exec_lo, s4
; CHECK-SDAG-TRUE16-NEXT: s_cbranch_execnz .LBB7_1
; CHECK-SDAG-TRUE16-NEXT: ; %bb.2: ; %bb2
; CHECK-SDAG-TRUE16-NEXT: s_endpgm
;
; CHECK-FAKE16-LABEL: raw_ptr_atomic_buffer_load_v4i16:
; CHECK-FAKE16: ; %bb.0: ; %bb
; CHECK-FAKE16-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-FAKE16-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-FAKE16-NEXT: s_mov_b32 s4, 0
; CHECK-FAKE16-NEXT: .LBB7_1: ; %bb1
; CHECK-FAKE16-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-FAKE16-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-FAKE16-NEXT: buffer_load_b64 v[1:2], off, s[0:3], 0 offset:4 glc
; CHECK-FAKE16-NEXT: s_waitcnt vmcnt(0)
; CHECK-FAKE16-NEXT: v_and_b32_e32 v1, 0xffff, v1
; CHECK-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
; CHECK-FAKE16-NEXT: v_lshl_or_b32 v1, v2, 16, v1
; CHECK-FAKE16-NEXT: v_cmp_ne_u32_e32 vcc_lo, v1, v0
; CHECK-FAKE16-NEXT: s_or_b32 s4, vcc_lo, s4
; CHECK-FAKE16-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-FAKE16-NEXT: s_and_not1_b32 exec_lo, exec_lo, s4
; CHECK-FAKE16-NEXT: s_cbranch_execnz .LBB7_1
; CHECK-FAKE16-NEXT: ; %bb.2: ; %bb2
; CHECK-FAKE16-NEXT: s_endpgm
;
; CHECK-GISEL-TRUE16-LABEL: raw_ptr_atomic_buffer_load_v4i16:
; CHECK-GISEL-TRUE16: ; %bb.0: ; %bb
; CHECK-GISEL-TRUE16-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-GISEL-TRUE16-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-GISEL-TRUE16-NEXT: s_mov_b32 s4, 0
; CHECK-GISEL-TRUE16-NEXT: .LBB7_1: ; %bb1
; CHECK-GISEL-TRUE16-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-GISEL-TRUE16-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-GISEL-TRUE16-NEXT: buffer_load_b64 v[1:2], off, s[0:3], 0 offset:4 glc
; CHECK-GISEL-TRUE16-NEXT: s_waitcnt vmcnt(0)
; CHECK-GISEL-TRUE16-NEXT: v_mov_b16_e32 v1.h, v2.l
; CHECK-GISEL-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(SALU_CYCLE_1)
; CHECK-GISEL-TRUE16-NEXT: v_cmp_ne_u32_e32 vcc_lo, v1, v0
; CHECK-GISEL-TRUE16-NEXT: s_or_b32 s4, vcc_lo, s4
; CHECK-GISEL-TRUE16-NEXT: s_and_not1_b32 exec_lo, exec_lo, s4
; CHECK-GISEL-TRUE16-NEXT: s_cbranch_execnz .LBB7_1
; CHECK-GISEL-TRUE16-NEXT: ; %bb.2: ; %bb2
; CHECK-GISEL-TRUE16-NEXT: s_endpgm
bb:
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
br label %bb1
bb1:
%load = call <4 x i16> @llvm.amdgcn.raw.ptr.atomic.buffer.load.v4i16(ptr addrspace(8) %ptr, i32 4, i32 0, i32 1)
%shortened = shufflevector <4 x i16> %load, <4 x i16> poison, <2 x i32> <i32 0, i32 2>
%bitcast = bitcast <2 x i16> %shortened to i32
%cmp = icmp eq i32 %bitcast, %id
br i1 %cmp, label %bb1, label %bb2
bb2:
ret void
}
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_v4i32(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_v4i32:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB8_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: buffer_load_b128 v[1:4], off, s[0:3], 0 offset:4 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: v_cmp_ne_u32_e32 vcc_lo, v4, v0
; CHECK-NEXT: s_or_b32 s4, vcc_lo, s4
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-NEXT: s_and_not1_b32 exec_lo, exec_lo, s4
; CHECK-NEXT: s_cbranch_execnz .LBB8_1
; CHECK-NEXT: ; %bb.2: ; %bb2
; CHECK-NEXT: s_endpgm
bb:
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
br label %bb1
bb1:
%load = call <4 x i32> @llvm.amdgcn.raw.ptr.atomic.buffer.load.v4i32(ptr addrspace(8) %ptr, i32 4, i32 0, i32 1)
%extracted = extractelement <4 x i32> %load, i32 3
%cmp = icmp eq i32 %extracted, %id
br i1 %cmp, label %bb1, label %bb2
bb2:
ret void
}
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_ptr(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_ptr:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB9_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: buffer_load_b64 v[1:2], off, s[0:3], 0 offset:4 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: flat_load_b32 v1, v[1:2]
; CHECK-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; CHECK-NEXT: v_cmp_ne_u32_e32 vcc_lo, v1, v0
; CHECK-NEXT: s_or_b32 s4, vcc_lo, s4
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-NEXT: s_and_not1_b32 exec_lo, exec_lo, s4
; CHECK-NEXT: s_cbranch_execnz .LBB9_1
; CHECK-NEXT: ; %bb.2: ; %bb2
; CHECK-NEXT: s_endpgm
bb:
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
br label %bb1
bb1:
%load = call ptr @llvm.amdgcn.raw.ptr.atomic.buffer.load.ptr(ptr addrspace(8) %ptr, i32 4, i32 0, i32 1)
%elem = load i32, ptr %load
%cmp = icmp eq i32 %elem, %id
br i1 %cmp, label %bb1, label %bb2
bb2:
ret void
}
; Function Attrs: nounwind readonly
declare i32 @llvm.amdgcn.raw.ptr.atom.buffer.load.i32(ptr addrspace(8), i32, i32, i32 immarg)
declare i64 @llvm.amdgcn.raw.ptr.atom.buffer.load.i64(ptr addrspace(8), i32, i32, i32 immarg)
declare <2 x i16> @llvm.amdgcn.raw.ptr.atom.buffer.load.v2i16(ptr addrspace(8), i32, i32, i32 immarg)
declare <4 x i16> @llvm.amdgcn.raw.ptr.atom.buffer.load.v4i16(ptr addrspace(8), i32, i32, i32 immarg)
declare <4 x i32> @llvm.amdgcn.raw.ptr.atom.buffer.load.v4i32(ptr addrspace(8), i32, i32, i32 immarg)
declare ptr @llvm.amdgcn.raw.ptr.atom.buffer.load.ptr(ptr addrspace(8), i32, i32, i32 immarg)
declare i32 @llvm.amdgcn.raw.ptr.buffer.load.i32(ptr addrspace(8), i32, i32, i32 immarg)
declare i32 @llvm.amdgcn.workitem.id.x()
|
