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
362
363
364
365
366
367
368
369
370
371
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -mattr=+real-true16 < %s | FileCheck -check-prefixes=CHECK,CHECK-TRUE16 %s
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -mattr=-real-true16 < %s | FileCheck -check-prefixes=CHECK,CHECK-FAKE16 %s
; Make sure we use a stack pointer and allocate 112 * 4 bytes at the beginning of the stack.
define amdgpu_cs void @amdgpu_cs() #0 {
; CHECK-LABEL: amdgpu_cs:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-NEXT: s_cmp_lg_u32 0, s33
; CHECK-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-NEXT: s_alloc_vgpr 0
; CHECK-NEXT: s_endpgm
ret void
}
define amdgpu_kernel void @kernel() #0 {
; CHECK-LABEL: kernel:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-NEXT: s_cmp_lg_u32 0, s33
; CHECK-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-NEXT: s_alloc_vgpr 0
; CHECK-NEXT: s_endpgm
ret void
}
define amdgpu_cs void @with_local() #0 {
; CHECK-TRUE16-LABEL: with_local:
; CHECK-TRUE16: ; %bb.0:
; CHECK-TRUE16-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-TRUE16-NEXT: v_mov_b16_e32 v0.l, 13
; CHECK-TRUE16-NEXT: s_cmp_lg_u32 0, s33
; CHECK-TRUE16-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-TRUE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-TRUE16-NEXT: s_wait_storecnt 0x0
; CHECK-TRUE16-NEXT: s_alloc_vgpr 0
; CHECK-TRUE16-NEXT: s_endpgm
;
; CHECK-FAKE16-LABEL: with_local:
; CHECK-FAKE16: ; %bb.0:
; CHECK-FAKE16-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-FAKE16-NEXT: v_mov_b32_e32 v0, 13
; CHECK-FAKE16-NEXT: s_cmp_lg_u32 0, s33
; CHECK-FAKE16-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-FAKE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-FAKE16-NEXT: s_wait_storecnt 0x0
; CHECK-FAKE16-NEXT: s_alloc_vgpr 0
; CHECK-FAKE16-NEXT: s_endpgm
%local = alloca i32, addrspace(5)
store volatile i8 13, ptr addrspace(5) %local
ret void
}
; Check that we generate s_cselect for SP if we can fit
; the offset in an inline constant.
define amdgpu_cs void @with_calls_inline_const() #0 {
; CHECK-TRUE16-LABEL: with_calls_inline_const:
; CHECK-TRUE16: ; %bb.0:
; CHECK-TRUE16-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-TRUE16-NEXT: v_mov_b16_e32 v0.l, 15
; CHECK-TRUE16-NEXT: s_cmp_lg_u32 0, s33
; CHECK-TRUE16-NEXT: s_mov_b32 s1, callee@abs32@hi
; CHECK-TRUE16-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-TRUE16-NEXT: s_mov_b32 s0, callee@abs32@lo
; CHECK-TRUE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-TRUE16-NEXT: s_wait_storecnt 0x0
; CHECK-TRUE16-NEXT: v_mov_b32_e32 v0, 0x47
; CHECK-TRUE16-NEXT: s_cselect_b32 s32, 0x1d0, 16
; CHECK-TRUE16-NEXT: s_swappc_b64 s[30:31], s[0:1]
; CHECK-TRUE16-NEXT: s_alloc_vgpr 0
; CHECK-TRUE16-NEXT: s_endpgm
;
; CHECK-FAKE16-LABEL: with_calls_inline_const:
; CHECK-FAKE16: ; %bb.0:
; CHECK-FAKE16-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-FAKE16-NEXT: v_mov_b32_e32 v0, 15
; CHECK-FAKE16-NEXT: s_cmp_lg_u32 0, s33
; CHECK-FAKE16-NEXT: s_mov_b32 s1, callee@abs32@hi
; CHECK-FAKE16-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-FAKE16-NEXT: s_mov_b32 s0, callee@abs32@lo
; CHECK-FAKE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-FAKE16-NEXT: s_wait_storecnt 0x0
; CHECK-FAKE16-NEXT: v_mov_b32_e32 v0, 0x47
; CHECK-FAKE16-NEXT: s_cselect_b32 s32, 0x1d0, 16
; CHECK-FAKE16-NEXT: s_swappc_b64 s[30:31], s[0:1]
; CHECK-FAKE16-NEXT: s_alloc_vgpr 0
; CHECK-FAKE16-NEXT: s_endpgm
%local = alloca i32, addrspace(5)
store volatile i8 15, ptr addrspace(5) %local
call amdgpu_gfx void @callee(i32 71)
ret void
}
; Check that we generate s_mov + s_cmovk if we can't
; fit the offset for SP in an inline constant.
define amdgpu_cs void @with_calls_no_inline_const() #0 {
; CHECK-TRUE16-LABEL: with_calls_no_inline_const:
; CHECK-TRUE16: ; %bb.0:
; CHECK-TRUE16-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-TRUE16-NEXT: v_mov_b16_e32 v0.l, 15
; CHECK-TRUE16-NEXT: s_cmp_lg_u32 0, s33
; CHECK-TRUE16-NEXT: s_mov_b32 s1, callee@abs32@hi
; CHECK-TRUE16-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-TRUE16-NEXT: s_mov_b32 s0, callee@abs32@lo
; CHECK-TRUE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-TRUE16-NEXT: s_wait_storecnt 0x0
; CHECK-TRUE16-NEXT: v_mov_b32_e32 v0, 0x47
; CHECK-TRUE16-NEXT: s_movk_i32 s32, 0x100
; CHECK-TRUE16-NEXT: s_cmovk_i32 s32, 0x2c0
; CHECK-TRUE16-NEXT: s_swappc_b64 s[30:31], s[0:1]
; CHECK-TRUE16-NEXT: s_alloc_vgpr 0
; CHECK-TRUE16-NEXT: s_endpgm
;
; CHECK-FAKE16-LABEL: with_calls_no_inline_const:
; CHECK-FAKE16: ; %bb.0:
; CHECK-FAKE16-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-FAKE16-NEXT: v_mov_b32_e32 v0, 15
; CHECK-FAKE16-NEXT: s_cmp_lg_u32 0, s33
; CHECK-FAKE16-NEXT: s_mov_b32 s1, callee@abs32@hi
; CHECK-FAKE16-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-FAKE16-NEXT: s_mov_b32 s0, callee@abs32@lo
; CHECK-FAKE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-FAKE16-NEXT: s_wait_storecnt 0x0
; CHECK-FAKE16-NEXT: v_mov_b32_e32 v0, 0x47
; CHECK-FAKE16-NEXT: s_movk_i32 s32, 0x100
; CHECK-FAKE16-NEXT: s_cmovk_i32 s32, 0x2c0
; CHECK-FAKE16-NEXT: s_swappc_b64 s[30:31], s[0:1]
; CHECK-FAKE16-NEXT: s_alloc_vgpr 0
; CHECK-FAKE16-NEXT: s_endpgm
%local = alloca i32, i32 61, addrspace(5)
store volatile i8 15, ptr addrspace(5) %local
call amdgpu_gfx void @callee(i32 71)
ret void
}
define amdgpu_cs void @with_spills() #0 {
; CHECK-LABEL: with_spills:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; CHECK-NEXT: s_cmp_lg_u32 0, s33
; CHECK-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-NEXT: s_alloc_vgpr 0
; CHECK-NEXT: s_endpgm
call void asm "; spills", "~{v40},~{v42}"()
ret void
}
define amdgpu_cs void @realign_stack(<32 x i32> %x) #0 {
; CHECK-LABEL: realign_stack:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-NEXT: s_mov_b32 s1, callee@abs32@hi
; CHECK-NEXT: s_cmp_lg_u32 0, s33
; CHECK-NEXT: s_mov_b32 s0, callee@abs32@lo
; CHECK-NEXT: s_cmovk_i32 s33, 0x200
; CHECK-NEXT: s_movk_i32 s32, 0x100
; CHECK-NEXT: s_clause 0x7
; CHECK-NEXT: scratch_store_b128 off, v[28:31], s33 offset:112
; CHECK-NEXT: scratch_store_b128 off, v[24:27], s33 offset:96
; CHECK-NEXT: scratch_store_b128 off, v[20:23], s33 offset:80
; CHECK-NEXT: scratch_store_b128 off, v[16:19], s33 offset:64
; CHECK-NEXT: scratch_store_b128 off, v[12:15], s33 offset:48
; CHECK-NEXT: scratch_store_b128 off, v[8:11], s33 offset:32
; CHECK-NEXT: scratch_store_b128 off, v[4:7], s33 offset:16
; CHECK-NEXT: scratch_store_b128 off, v[0:3], s33
; CHECK-NEXT: v_mov_b32_e32 v0, 0x47
; CHECK-NEXT: s_cmovk_i32 s32, 0x300
; CHECK-NEXT: s_swappc_b64 s[30:31], s[0:1]
; CHECK-NEXT: s_alloc_vgpr 0
; CHECK-NEXT: s_endpgm
%v = alloca <32 x i32>, align 128, addrspace(5)
store <32 x i32> %x, ptr addrspace(5) %v
call amdgpu_gfx void @callee(i32 71)
ret void
}
define amdgpu_cs void @frame_pointer_none() #1 {
; CHECK-TRUE16-LABEL: frame_pointer_none:
; CHECK-TRUE16: ; %bb.0:
; CHECK-TRUE16-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-TRUE16-NEXT: v_mov_b16_e32 v0.l, 13
; CHECK-TRUE16-NEXT: s_cmp_lg_u32 0, s33
; CHECK-TRUE16-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-TRUE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-TRUE16-NEXT: s_wait_storecnt 0x0
; CHECK-TRUE16-NEXT: s_alloc_vgpr 0
; CHECK-TRUE16-NEXT: s_endpgm
;
; CHECK-FAKE16-LABEL: frame_pointer_none:
; CHECK-FAKE16: ; %bb.0:
; CHECK-FAKE16-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-FAKE16-NEXT: v_mov_b32_e32 v0, 13
; CHECK-FAKE16-NEXT: s_cmp_lg_u32 0, s33
; CHECK-FAKE16-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-FAKE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-FAKE16-NEXT: s_wait_storecnt 0x0
; CHECK-FAKE16-NEXT: s_alloc_vgpr 0
; CHECK-FAKE16-NEXT: s_endpgm
%local = alloca i32, addrspace(5)
store volatile i8 13, ptr addrspace(5) %local
ret void
}
define amdgpu_cs void @frame_pointer_all() #2 {
; CHECK-TRUE16-LABEL: frame_pointer_all:
; CHECK-TRUE16: ; %bb.0:
; CHECK-TRUE16-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-TRUE16-NEXT: v_mov_b16_e32 v0.l, 13
; CHECK-TRUE16-NEXT: s_cmp_lg_u32 0, s33
; CHECK-TRUE16-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-TRUE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-TRUE16-NEXT: s_wait_storecnt 0x0
; CHECK-TRUE16-NEXT: s_alloc_vgpr 0
; CHECK-TRUE16-NEXT: s_endpgm
;
; CHECK-FAKE16-LABEL: frame_pointer_all:
; CHECK-FAKE16: ; %bb.0:
; CHECK-FAKE16-NEXT: s_getreg_b32 s33, hwreg(HW_REG_HW_ID2, 8, 2)
; CHECK-FAKE16-NEXT: v_mov_b32_e32 v0, 13
; CHECK-FAKE16-NEXT: s_cmp_lg_u32 0, s33
; CHECK-FAKE16-NEXT: s_cmovk_i32 s33, 0x1c0
; CHECK-FAKE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-FAKE16-NEXT: s_wait_storecnt 0x0
; CHECK-FAKE16-NEXT: s_alloc_vgpr 0
; CHECK-FAKE16-NEXT: s_endpgm
%local = alloca i32, addrspace(5)
store volatile i8 13, ptr addrspace(5) %local
ret void
}
; Non-entry functions and graphics shaders don't need to worry about CWSR.
define amdgpu_gs void @amdgpu_gs() #0 {
; CHECK-TRUE16-LABEL: amdgpu_gs:
; CHECK-TRUE16: ; %bb.0:
; CHECK-TRUE16-NEXT: v_mov_b16_e32 v0.l, 15
; CHECK-TRUE16-NEXT: s_mov_b32 s1, callee@abs32@hi
; CHECK-TRUE16-NEXT: s_mov_b32 s0, callee@abs32@lo
; CHECK-TRUE16-NEXT: s_mov_b32 s32, 16
; CHECK-TRUE16-NEXT: scratch_store_b8 off, v0, off scope:SCOPE_SYS
; CHECK-TRUE16-NEXT: s_wait_storecnt 0x0
; CHECK-TRUE16-NEXT: v_mov_b32_e32 v0, 0x47
; CHECK-TRUE16-NEXT: s_swappc_b64 s[30:31], s[0:1]
; CHECK-TRUE16-NEXT: s_alloc_vgpr 0
; CHECK-TRUE16-NEXT: s_endpgm
;
; CHECK-FAKE16-LABEL: amdgpu_gs:
; CHECK-FAKE16: ; %bb.0:
; CHECK-FAKE16-NEXT: v_mov_b32_e32 v0, 15
; CHECK-FAKE16-NEXT: s_mov_b32 s1, callee@abs32@hi
; CHECK-FAKE16-NEXT: s_mov_b32 s0, callee@abs32@lo
; CHECK-FAKE16-NEXT: s_mov_b32 s32, 16
; CHECK-FAKE16-NEXT: scratch_store_b8 off, v0, off scope:SCOPE_SYS
; CHECK-FAKE16-NEXT: s_wait_storecnt 0x0
; CHECK-FAKE16-NEXT: v_mov_b32_e32 v0, 0x47
; CHECK-FAKE16-NEXT: s_swappc_b64 s[30:31], s[0:1]
; CHECK-FAKE16-NEXT: s_alloc_vgpr 0
; CHECK-FAKE16-NEXT: s_endpgm
%local = alloca i32, addrspace(5)
store volatile i8 15, ptr addrspace(5) %local
call amdgpu_gfx void @callee(i32 71)
ret void
}
define amdgpu_gfx void @amdgpu_gfx() #0 {
; CHECK-TRUE16-LABEL: amdgpu_gfx:
; CHECK-TRUE16: ; %bb.0:
; CHECK-TRUE16-NEXT: s_wait_loadcnt_dscnt 0x0
; CHECK-TRUE16-NEXT: s_wait_expcnt 0x0
; CHECK-TRUE16-NEXT: s_wait_samplecnt 0x0
; CHECK-TRUE16-NEXT: s_wait_bvhcnt 0x0
; CHECK-TRUE16-NEXT: s_wait_kmcnt 0x0
; CHECK-TRUE16-NEXT: s_mov_b32 s0, s33
; CHECK-TRUE16-NEXT: s_mov_b32 s33, s32
; CHECK-TRUE16-NEXT: s_or_saveexec_b32 s1, -1
; CHECK-TRUE16-NEXT: scratch_store_b32 off, v40, s33 offset:4 ; 4-byte Folded Spill
; CHECK-TRUE16-NEXT: s_wait_alu 0xfffe
; CHECK-TRUE16-NEXT: s_mov_b32 exec_lo, s1
; CHECK-TRUE16-NEXT: v_writelane_b32 v40, s0, 2
; CHECK-TRUE16-NEXT: v_mov_b16_e32 v0.l, 15
; CHECK-TRUE16-NEXT: s_mov_b32 s1, callee@abs32@hi
; CHECK-TRUE16-NEXT: s_mov_b32 s0, callee@abs32@lo
; CHECK-TRUE16-NEXT: s_add_co_i32 s32, s32, 16
; CHECK-TRUE16-NEXT: v_writelane_b32 v40, s30, 0
; CHECK-TRUE16-NEXT: s_wait_storecnt 0x0
; CHECK-TRUE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-TRUE16-NEXT: s_wait_storecnt 0x0
; CHECK-TRUE16-NEXT: v_mov_b32_e32 v0, 0x47
; CHECK-TRUE16-NEXT: v_writelane_b32 v40, s31, 1
; CHECK-TRUE16-NEXT: s_wait_alu 0xfffe
; CHECK-TRUE16-NEXT: s_swappc_b64 s[30:31], s[0:1]
; CHECK-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1)
; CHECK-TRUE16-NEXT: v_readlane_b32 s31, v40, 1
; CHECK-TRUE16-NEXT: v_readlane_b32 s30, v40, 0
; CHECK-TRUE16-NEXT: s_mov_b32 s32, s33
; CHECK-TRUE16-NEXT: v_readlane_b32 s0, v40, 2
; CHECK-TRUE16-NEXT: s_or_saveexec_b32 s1, -1
; CHECK-TRUE16-NEXT: scratch_load_b32 v40, off, s33 offset:4 ; 4-byte Folded Reload
; CHECK-TRUE16-NEXT: s_wait_alu 0xfffe
; CHECK-TRUE16-NEXT: s_mov_b32 exec_lo, s1
; CHECK-TRUE16-NEXT: s_mov_b32 s33, s0
; CHECK-TRUE16-NEXT: s_wait_loadcnt 0x0
; CHECK-TRUE16-NEXT: s_wait_alu 0xfffe
; CHECK-TRUE16-NEXT: s_setpc_b64 s[30:31]
;
; CHECK-FAKE16-LABEL: amdgpu_gfx:
; CHECK-FAKE16: ; %bb.0:
; CHECK-FAKE16-NEXT: s_wait_loadcnt_dscnt 0x0
; CHECK-FAKE16-NEXT: s_wait_expcnt 0x0
; CHECK-FAKE16-NEXT: s_wait_samplecnt 0x0
; CHECK-FAKE16-NEXT: s_wait_bvhcnt 0x0
; CHECK-FAKE16-NEXT: s_wait_kmcnt 0x0
; CHECK-FAKE16-NEXT: s_mov_b32 s0, s33
; CHECK-FAKE16-NEXT: s_mov_b32 s33, s32
; CHECK-FAKE16-NEXT: s_or_saveexec_b32 s1, -1
; CHECK-FAKE16-NEXT: scratch_store_b32 off, v40, s33 offset:4 ; 4-byte Folded Spill
; CHECK-FAKE16-NEXT: s_wait_alu 0xfffe
; CHECK-FAKE16-NEXT: s_mov_b32 exec_lo, s1
; CHECK-FAKE16-NEXT: v_writelane_b32 v40, s0, 2
; CHECK-FAKE16-NEXT: v_mov_b32_e32 v0, 15
; CHECK-FAKE16-NEXT: s_mov_b32 s1, callee@abs32@hi
; CHECK-FAKE16-NEXT: s_mov_b32 s0, callee@abs32@lo
; CHECK-FAKE16-NEXT: s_add_co_i32 s32, s32, 16
; CHECK-FAKE16-NEXT: v_writelane_b32 v40, s30, 0
; CHECK-FAKE16-NEXT: s_wait_storecnt 0x0
; CHECK-FAKE16-NEXT: scratch_store_b8 off, v0, s33 scope:SCOPE_SYS
; CHECK-FAKE16-NEXT: s_wait_storecnt 0x0
; CHECK-FAKE16-NEXT: v_mov_b32_e32 v0, 0x47
; CHECK-FAKE16-NEXT: v_writelane_b32 v40, s31, 1
; CHECK-FAKE16-NEXT: s_wait_alu 0xfffe
; CHECK-FAKE16-NEXT: s_swappc_b64 s[30:31], s[0:1]
; CHECK-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1)
; CHECK-FAKE16-NEXT: v_readlane_b32 s31, v40, 1
; CHECK-FAKE16-NEXT: v_readlane_b32 s30, v40, 0
; CHECK-FAKE16-NEXT: s_mov_b32 s32, s33
; CHECK-FAKE16-NEXT: v_readlane_b32 s0, v40, 2
; CHECK-FAKE16-NEXT: s_or_saveexec_b32 s1, -1
; CHECK-FAKE16-NEXT: scratch_load_b32 v40, off, s33 offset:4 ; 4-byte Folded Reload
; CHECK-FAKE16-NEXT: s_wait_alu 0xfffe
; CHECK-FAKE16-NEXT: s_mov_b32 exec_lo, s1
; CHECK-FAKE16-NEXT: s_mov_b32 s33, s0
; CHECK-FAKE16-NEXT: s_wait_loadcnt 0x0
; CHECK-FAKE16-NEXT: s_wait_alu 0xfffe
; CHECK-FAKE16-NEXT: s_setpc_b64 s[30:31]
%local = alloca i32, addrspace(5)
store volatile i8 15, ptr addrspace(5) %local
call amdgpu_gfx void @callee(i32 71)
ret void
}
define void @default() #0 {
; CHECK-LABEL: default:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_wait_loadcnt_dscnt 0x0
; CHECK-NEXT: s_wait_expcnt 0x0
; CHECK-NEXT: s_wait_samplecnt 0x0
; CHECK-NEXT: s_wait_bvhcnt 0x0
; CHECK-NEXT: s_wait_kmcnt 0x0
; CHECK-NEXT: s_setpc_b64 s[30:31]
ret void
}
declare amdgpu_gfx void @callee(i32) #0
attributes #0 = { nounwind "amdgpu-dynamic-vgpr-block-size"="16" }
attributes #1 = { nounwind "frame-pointer"="none" "amdgpu-dynamic-vgpr-block-size"="16" }
attributes #2 = { nounwind "frame-pointer"="all" "amdgpu-dynamic-vgpr-block-size"="16" }
|
