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
|
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=verde -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,SI,SIVI,MUBUF %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx803 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,VI,SIVI,MUBUF %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,MUBUF,GFX9-MUBUF,GFX9_10-MUBUF %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx900 -filetype=obj -amdgpu-use-divergent-register-indexing < %s | llvm-readobj -r - | FileCheck --check-prefix=RELS %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx1010 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,MUBUF,GFX10_W32-MUBUF,GFX9_10-MUBUF %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx1010 -mattr=-flat-for-global,+wavefrontsize64 -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,MUBUF,GFX10_W64-MUBUF,GFX9_10-MUBUF %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -amdgpu-enable-flat-scratch -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,FLATSCR,GFX9-FLATSCR %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx1030 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -amdgpu-enable-flat-scratch -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,FLATSCR,GFX10-FLATSCR %s
; RUN: llc -march=amdgcn -mtriple=amdgcn--amdpal -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -amdgpu-enable-flat-scratch -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,FLATSCR,GFX9-FLATSCR-PAL %s
; RUN: llc -march=amdgcn -mtriple=amdgcn--amdpal -mcpu=gfx1030 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -amdgpu-enable-flat-scratch -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,FLATSCR,GFX10-FLATSCR-PAL %s
; RELS: R_AMDGPU_ABS32_LO SCRATCH_RSRC_DWORD0
; RELS: R_AMDGPU_ABS32_LO SCRATCH_RSRC_DWORD1
; This used to fail due to a v_add_i32 instruction with an illegal immediate
; operand that was created during Local Stack Slot Allocation. Test case derived
; from https://bugs.freedesktop.org/show_bug.cgi?id=96602
;
; GCN-LABEL: {{^}}ps_main:
; GFX9-FLATSCR-DAG: s_add_u32 flat_scratch_lo, s0, s2
; GFX9-FLATSCR-DAG: s_addc_u32 flat_scratch_hi, s1, 0
; GFX9-FLATSCR-DAG: v_and_b32_e32 [[CLAMP_IDX:v[0-9]+]], 0x1fc, v0
; GFX10-FLATSCR: s_add_u32 s0, s0, s2
; GFX10-FLATSCR: s_addc_u32 s1, s1, 0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s1
; GFX9-FLATSCR-PAL-DAG: s_getpc_b64 s[2:3]
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 s2, s0
; GFX9-FLATSCR-PAL-DAG: s_load_dwordx2 s[2:3], s[2:3], 0x0
; GFX9-FLATSCR-PAL-DAG: v_lshlrev_b32_e32 v0, 2, v0
; GFX9-FLATSCR-PAL-DAG: v_mov_b32_e32 v0, 0xbf20e7f4
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 vcc_hi, 0
; GFX9-FLATSCR-PAL-DAG: s_waitcnt lgkmcnt(0)
; GFX9-FLATSCR-PAL-DAG: s_and_b32 s3, s3, 0xffff
; GFX9-FLATSCR-PAL-DAG: s_add_u32 flat_scratch_lo, s2, s0
; GFX9-FLATSCR-PAL-DAG: s_addc_u32 flat_scratch_hi, s3, 0
; GFX9-FLATSCR-PAL-DAG: v_and_b32_e32 [[CLAMP_IDX:v[0-9]+]], 0x1fc, v0
; GFX10-FLATSCR-PAL: s_getpc_b64 s[2:3]
; GFX10-FLATSCR-PAL: s_mov_b32 s2, s0
; GFX10-FLATSCR-PAL: s_load_dwordx2 s[2:3], s[2:3], 0x0
; GFX10-FLATSCR-PAL: s_waitcnt lgkmcnt(0)
; GFX10-FLATSCR-PAL: s_and_b32 s3, s3, 0xffff
; GFX10-FLATSCR-PAL: s_add_u32 s2, s2, s0
; GFX10-FLATSCR-PAL: s_addc_u32 s3, s3, 0
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s2
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s3
; MUBUF-DAG: s_mov_b32 s0, SCRATCH_RSRC_DWORD0
; MUBUF-DAG: s_mov_b32 s1, SCRATCH_RSRC_DWORD1
; MUBUF-DAG: s_mov_b32 s2, -1
; SI-DAG: s_mov_b32 s3, 0xe8f000
; VI-DAG: s_mov_b32 s3, 0xe80000
; GFX9-MUBUF-DAG: s_mov_b32 s3, 0xe00000
; GFX10_W32-MUBUF-DAG: s_mov_b32 s3, 0x31c16000
; GFX10_W64-MUBUF-DAG: s_mov_b32 s3, 0x31e16000
; FLATSCR-NOT: SCRATCH_RSRC_DWORD
; GFX9-FLATSCR: s_mov_b32 [[SP:[^,]+]], 0
; GFX9-FLATSCR: scratch_store_dwordx4 off, v[{{[0-9:]+}}], [[SP]] offset:
; GFX10-FLATSCR: scratch_store_dwordx4 off, v[{{[0-9:]+}}], off offset:
; MUBUF-DAG: v_lshlrev_b32_e32 [[BYTES:v[0-9]+]], 2, v0
; MUBUF-DAG: v_and_b32_e32 [[CLAMP_IDX:v[0-9]+]], 0x1fc, [[BYTES]]
; GFX10-FLATSCR: v_and_b32_e32 [[CLAMP_IDX:v[0-9]+]], 0x1fc, v0
; GFX10-FLATSCR-PAL: v_and_b32_e32 [[CLAMP_IDX:v[0-9]+]], 0x1fc, v0
; GCN-NOT: s_mov_b32 s0
; GCN-DAG: v_add{{_|_nc_}}{{i|u}}32_e32 [[HI_OFF:v[0-9]+]],{{.*}} 0x280, [[CLAMP_IDX]]
; GCN-DAG: v_add{{_|_nc_}}{{i|u}}32_e32 [[LO_OFF:v[0-9]+]],{{.*}} {{v2|0x80}}, [[CLAMP_IDX]]
; MUBUF: buffer_load_dword {{v[0-9]+}}, [[LO_OFF]], {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; MUBUF: buffer_load_dword {{v[0-9]+}}, [[HI_OFF]], {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; FLATSCR: scratch_load_dword {{v[0-9]+}}, [[LO_OFF]], off
define amdgpu_ps float @ps_main(i32 %idx) {
%v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
%v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
%r = fadd float %v1, %v2
ret float %r
}
; GCN-LABEL: {{^}}vs_main:
; GFX9-FLATSCR: s_add_u32 flat_scratch_lo, s0, s2
; GFX9-FLATSCR: s_addc_u32 flat_scratch_hi, s1, 0
; GFX10-FLATSCR: s_add_u32 s0, s0, s2
; GFX10-FLATSCR: s_addc_u32 s1, s1, 0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s1
; GFX9-FLATSCR-PAL-DAG: s_getpc_b64 s[2:3]
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 s2, s0
; GFX9-FLATSCR-PAL-DAG: s_load_dwordx2 s[2:3], s[2:3], 0x0
; GFX9-FLATSCR-PAL-DAG: v_lshlrev_b32_e32 v0, 2, v0
; GFX9-FLATSCR-PAL-DAG: v_mov_b32_e32 v0, 0xbf20e7f4
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 vcc_hi, 0
; GFX9-FLATSCR-PAL-DAG: s_waitcnt lgkmcnt(0)
; GFX9-FLATSCR-PAL-DAG: s_and_b32 s3, s3, 0xffff
; GFX9-FLATSCR-PAL-DAG: s_add_u32 flat_scratch_lo, s2, s0
; GFX9-FLATSCR-PAL-DAG: s_addc_u32 flat_scratch_hi, s3, 0
; GFX10-FLATSCR-PAL: s_getpc_b64 s[2:3]
; GFX10-FLATSCR-PAL: s_mov_b32 s2, s0
; GFX10-FLATSCR-PAL: s_load_dwordx2 s[2:3], s[2:3], 0x0
; GFX10-FLATSCR-PAL: s_waitcnt lgkmcnt(0)
; GFX10-FLATSCR-PAL: s_and_b32 s3, s3, 0xffff
; GFX10-FLATSCR-PAL: s_add_u32 s2, s2, s0
; GFX10-FLATSCR-PAL: s_addc_u32 s3, s3, 0
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s2
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s3
; MUBUF-DAG: s_mov_b32 s0, SCRATCH_RSRC_DWORD0
; GCN-NOT: s_mov_b32 s0
; FLATSCR-NOT: SCRATCH_RSRC_DWORD
; MUBUF: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; MUBUF: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; GFX9-FLATSCR: s_mov_b32 [[SP:[^,]+]], 0
; GFX9-FLATSCR: scratch_store_dwordx4 off, v[{{[0-9:]+}}], [[SP]] offset:
; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
define amdgpu_vs float @vs_main(i32 %idx) {
%v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
%v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
%r = fadd float %v1, %v2
ret float %r
}
; GCN-LABEL: {{^}}cs_main:
; GFX9-FLATSCR: s_add_u32 flat_scratch_lo, s0, s2
; GFX9-FLATSCR: s_addc_u32 flat_scratch_hi, s1, 0
; GFX10-FLATSCR: s_add_u32 s0, s0, s2
; GFX10-FLATSCR: s_addc_u32 s1, s1, 0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s1
; GFX9-FLATSCR-PAL-DAG: s_getpc_b64 s[2:3]
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 s2, s0
; GFX9-FLATSCR-PAL-DAG: s_load_dwordx2 s[2:3], s[2:3], 0x10
; GFX9-FLATSCR-PAL-DAG: v_lshlrev_b32_e32 v0, 2, v0
; GFX9-FLATSCR-PAL-DAG: v_mov_b32_e32 v0, 0xbf20e7f4
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 vcc_hi, 0
; GFX9-FLATSCR-PAL-DAG: s_waitcnt lgkmcnt(0)
; GFX9-FLATSCR-PAL-DAG: s_and_b32 s3, s3, 0xffff
; GFX9-FLATSCR-PAL-DAG: s_add_u32 flat_scratch_lo, s2, s0
; GFX9-FLATSCR-PAL-DAG: s_addc_u32 flat_scratch_hi, s3, 0
; GFX10-FLATSCR-PAL: s_getpc_b64 s[2:3]
; GFX10-FLATSCR-PAL: s_mov_b32 s2, s0
; GFX10-FLATSCR-PAL: s_load_dwordx2 s[2:3], s[2:3], 0x10
; GFX10-FLATSCR-PAL: s_waitcnt lgkmcnt(0)
; GFX10-FLATSCR-PAL: s_and_b32 s3, s3, 0xffff
; GFX10-FLATSCR-PAL: s_add_u32 s2, s2, s0
; GFX10-FLATSCR-PAL: s_addc_u32 s3, s3, 0
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s2
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s3
; MUBUF-DAG: s_mov_b32 s0, SCRATCH_RSRC_DWORD0
; FLATSCR-NOT: SCRATCH_RSRC_DWORD
; MUBUF: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; MUBUF: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
define amdgpu_cs float @cs_main(i32 %idx) {
%v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
%v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
%r = fadd float %v1, %v2
ret float %r
}
; GCN-LABEL: {{^}}hs_main:
; GFX9-FLATSCR: s_add_u32 flat_scratch_lo, s0, s5
; GFX9-FLATSCR: s_addc_u32 flat_scratch_hi, s1, 0
; GFX10-FLATSCR: s_add_u32 s0, s0, s5
; GFX10-FLATSCR: s_addc_u32 s1, s1, 0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s1
; SIVI: s_mov_b32 s0, SCRATCH_RSRC_DWORD0
; SIVI-NOT: s_mov_b32 s0
; SIVI: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; SIVI: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; GFX9_10-MUBUF: s_mov_b32 s0, SCRATCH_RSRC_DWORD0
; GFX9_10-NOT: s_mov_b32 s5
; GFX9_10-MUBUF: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; GFX9_10-MUBUF: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; FLATSCR-NOT: SCRATCH_RSRC_DWORD
; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
define amdgpu_hs float @hs_main(i32 %idx) {
%v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
%v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
%r = fadd float %v1, %v2
ret float %r
}
; GCN-LABEL: {{^}}gs_main:
; GFX9-FLATSCR: s_add_u32 flat_scratch_lo, s0, s5
; GFX9-FLATSCR: s_addc_u32 flat_scratch_hi, s1, 0
; GFX10-FLATSCR: s_add_u32 s0, s0, s5
; GFX10-FLATSCR: s_addc_u32 s1, s1, 0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s1
; GFX9-FLATSCR-PAL-DAG: s_getpc_b64 s[0:1]
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 s0, s8
; GFX9-FLATSCR-PAL-DAG: s_load_dwordx2 s[0:1], s[0:1], 0x0
; GFX9-FLATSCR-PAL-DAG: v_lshlrev_b32_e32 v0, 2, v0
; GFX9-FLATSCR-PAL-DAG: v_mov_b32_e32 v0, 0xbf20e7f4
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 vcc_hi, 0
; GFX9-FLATSCR-PAL-DAG: s_waitcnt lgkmcnt(0)
; GFX9-FLATSCR-PAL-DAG: s_and_b32 s1, s1, 0xffff
; GFX9-FLATSCR-PAL-DAG: s_add_u32 flat_scratch_lo, s0, s5
; GFX9-FLATSCR-PAL-DAG: s_addc_u32 flat_scratch_hi, s1, 0
; GFX10-FLATSCR-PAL: s_getpc_b64 s[0:1]
; GFX10-FLATSCR-PAL: s_mov_b32 s0, s8
; GFX10-FLATSCR-PAL: s_load_dwordx2 s[0:1], s[0:1], 0x0
; GFX10-FLATSCR-PAL: s_waitcnt lgkmcnt(0)
; GFX10-FLATSCR-PAL: s_and_b32 s1, s1, 0xffff
; GFX10-FLATSCR-PAL: s_add_u32 s0, s0, s5
; GFX10-FLATSCR-PAL: s_addc_u32 s1, s1, 0
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s0
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s1
; SIVI: s_mov_b32 s0, SCRATCH_RSRC_DWORD0
; SIVI: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; SIVI: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; GFX9_10-MUBUF: s_mov_b32 s0, SCRATCH_RSRC_DWORD0
; GFX9_10-MUBUF: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; GFX9_10-MUBUF: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; FLATSCR-NOT: SCRATCH_RSRC_DWORD
; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
define amdgpu_gs float @gs_main(i32 %idx) {
%v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
%v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
%r = fadd float %v1, %v2
ret float %r
}
; Mesa GS and HS shaders have the preloaded scratch wave offset SGPR fixed at
; SGPR5, and the inreg implementation is used to reference it in the IR. The
; following tests confirm the shader and anything inserted after the return
; (i.e. SI_RETURN_TO_EPILOG) can access the scratch wave offset.
; GCN-LABEL: {{^}}hs_ir_uses_scratch_offset:
; GFX9-FLATSCR: s_add_u32 flat_scratch_lo, s0, s5
; GFX9-FLATSCR: s_addc_u32 flat_scratch_hi, s1, 0
; GFX10-FLATSCR: s_add_u32 s0, s0, s5
; GFX10-FLATSCR: s_addc_u32 s1, s1, 0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s1
; GFX9-FLATSCR-PAL-DAG: s_getpc_b64 s[0:1]
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 s0, s8
; GFX9-FLATSCR-PAL-DAG: s_load_dwordx2 s[0:1], s[0:1], 0x0
; GFX9-FLATSCR-PAL-DAG: v_lshlrev_b32_e32 v0, 2, v0
; GFX9-FLATSCR-PAL-DAG: v_mov_b32_e32 v0, 0xbf20e7f4
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 vcc_hi, 0
; GFX9-FLATSCR-PAL-DAG: s_waitcnt lgkmcnt(0)
; GFX9-FLATSCR-PAL-DAG: s_and_b32 s1, s1, 0xffff
; GFX9-FLATSCR-PAL-DAG: s_add_u32 flat_scratch_lo, s0, s5
; GFX9-FLATSCR-PAL-DAG: s_addc_u32 flat_scratch_hi, s1, 0
; GFX10-FLATSCR-PAL: s_getpc_b64 s[0:1]
; GFX10-FLATSCR-PAL: s_mov_b32 s0, s8
; GFX10-FLATSCR-PAL: s_load_dwordx2 s[0:1], s[0:1], 0x0
; GFX10-FLATSCR-PAL: s_waitcnt lgkmcnt(0)
; GFX10-FLATSCR-PAL: s_and_b32 s1, s1, 0xffff
; GFX10-FLATSCR-PAL: s_add_u32 s0, s0, s5
; GFX10-FLATSCR-PAL: s_addc_u32 s1, s1, 0
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s0
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s1
; MUBUF: s_mov_b32 s8, SCRATCH_RSRC_DWORD0
; FLATSCR-NOT: SCRATCH_RSRC_DWORD
; SIVI-NOT: s_mov_b32 s6
; SIVI: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; SIVI: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; GFX9_10-NOT: s_mov_b32 s5
; GFX9_10-MUBUF-DAG: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; GFX9_10-MUBUF-DAG: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; MUBUF-DAG: s_mov_b32 s2, s5
; FLATSCR-DAG: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
; FLATSCR-DAG: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
define amdgpu_hs <{i32, i32, i32, float}> @hs_ir_uses_scratch_offset(i32 inreg, i32 inreg, i32 inreg, i32 inreg, i32 inreg, i32 inreg %swo, i32 %idx) {
%v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
%v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
%f = fadd float %v1, %v2
%r1 = insertvalue <{i32, i32, i32, float}> undef, i32 %swo, 2
%r2 = insertvalue <{i32, i32, i32, float}> %r1, float %f, 3
ret <{i32, i32, i32, float}> %r2
}
; GCN-LABEL: {{^}}gs_ir_uses_scratch_offset:
; GFX9-FLATSCR: s_add_u32 flat_scratch_lo, s0, s5
; GFX9-FLATSCR: s_addc_u32 flat_scratch_hi, s1, 0
; GFX10-FLATSCR: s_add_u32 s0, s0, s5
; GFX10-FLATSCR: s_addc_u32 s1, s1, 0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s0
; GFX10-FLATSCR: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s1
; GFX9-FLATSCR-PAL-DAG: s_getpc_b64 s[0:1]
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 s0, s8
; GFX9-FLATSCR-PAL-DAG: s_load_dwordx2 s[0:1], s[0:1], 0x0
; GFX9-FLATSCR-PAL-DAG: v_lshlrev_b32_e32 v0, 2, v0
; GFX9-FLATSCR-PAL-DAG: v_mov_b32_e32 v0, 0xbf20e7f4
; GFX9-FLATSCR-PAL-DAG: s_mov_b32 vcc_hi, 0
; GFX9-FLATSCR-PAL-DAG: s_waitcnt lgkmcnt(0)
; GFX9-FLATSCR-PAL-DAG: s_and_b32 s1, s1, 0xffff
; GFX9-FLATSCR-PAL-DAG: s_add_u32 flat_scratch_lo, s0, s5
; GFX9-FLATSCR-PAL-DAG: s_addc_u32 flat_scratch_hi, s1, 0
; GFX10-FLATSCR-PAL: s_getpc_b64 s[0:1]
; GFX10-FLATSCR-PAL: s_mov_b32 s0, s8
; GFX10-FLATSCR-PAL: s_load_dwordx2 s[0:1], s[0:1], 0x0
; GFX10-FLATSCR-PAL: s_waitcnt lgkmcnt(0)
; GFX10-FLATSCR-PAL: s_and_b32 s1, s1, 0xffff
; GFX10-FLATSCR-PAL: s_add_u32 s0, s0, s5
; GFX10-FLATSCR-PAL: s_addc_u32 s1, s1, 0
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s0
; GFX10-FLATSCR-PAL: s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s1
; MUBUF: s_mov_b32 s8, SCRATCH_RSRC_DWORD0
; FLATSCR-NOT: SCRATCH_RSRC_DWORD
; SIVI: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; SIVI: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; GFX9_10-MUBUF-DAG: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; GFX9_10-MUBUF-DAG: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
; MUBUF-DAG: s_mov_b32 s2, s5
; FLATSCR-DAG: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
; FLATSCR-DAG: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
define amdgpu_gs <{i32, i32, i32, float}> @gs_ir_uses_scratch_offset(i32 inreg, i32 inreg, i32 inreg, i32 inreg, i32 inreg, i32 inreg %swo, i32 %idx) {
%v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
%v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
%f = fadd float %v1, %v2
%r1 = insertvalue <{i32, i32, i32, float}> undef, i32 %swo, 2
%r2 = insertvalue <{i32, i32, i32, float}> %r1, float %f, 3
ret <{i32, i32, i32, float}> %r2
}
|
