widen-smrd-loads.ll
16.8 KB
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
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -amdgpu-codegenprepare-widen-constant-loads=0 -mtriple=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI %s
; RUN: llc -amdgpu-codegenprepare-widen-constant-loads=0 -mtriple=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI %s
define amdgpu_kernel void @widen_i16_constant_load(i16 addrspace(4)* %arg) {
; SI-LABEL: widen_i16_constant_load:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_load_dword s1, s[0:1], 0x0
; SI-NEXT: s_mov_b32 s0, 0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_addk_i32 s1, 0x3e7
; SI-NEXT: s_or_b32 s4, s1, 4
; SI-NEXT: s_mov_b32 s1, s0
; SI-NEXT: v_mov_b32_e32 v0, s4
; SI-NEXT: buffer_store_short v0, off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: widen_i16_constant_load:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_load_dword s0, s[0:1], 0x0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_addk_i32 s0, 0x3e7
; VI-NEXT: s_or_b32 s0, s0, 4
; VI-NEXT: v_mov_b32_e32 v2, s0
; VI-NEXT: flat_store_short v[0:1], v2
; VI-NEXT: s_endpgm
%load = load i16, i16 addrspace(4)* %arg, align 4
%add = add i16 %load, 999
%or = or i16 %add, 4
store i16 %or, i16 addrspace(1)* null
ret void
}
define amdgpu_kernel void @widen_i16_constant_load_zext_i32(i16 addrspace(4)* %arg) {
; SI-LABEL: widen_i16_constant_load_zext_i32:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_load_dword s1, s[0:1], 0x0
; SI-NEXT: s_mov_b32 s0, 0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_and_b32 s1, s1, 0xffff
; SI-NEXT: s_addk_i32 s1, 0x3e7
; SI-NEXT: s_or_b32 s4, s1, 4
; SI-NEXT: s_mov_b32 s1, s0
; SI-NEXT: v_mov_b32_e32 v0, s4
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: widen_i16_constant_load_zext_i32:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_load_dword s0, s[0:1], 0x0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_and_b32 s0, s0, 0xffff
; VI-NEXT: s_addk_i32 s0, 0x3e7
; VI-NEXT: s_or_b32 s0, s0, 4
; VI-NEXT: v_mov_b32_e32 v2, s0
; VI-NEXT: flat_store_dword v[0:1], v2
; VI-NEXT: s_endpgm
%load = load i16, i16 addrspace(4)* %arg, align 4
%ext = zext i16 %load to i32
%add = add i32 %ext, 999
%or = or i32 %add, 4
store i32 %or, i32 addrspace(1)* null
ret void
}
define amdgpu_kernel void @widen_i16_constant_load_sext_i32(i16 addrspace(4)* %arg) {
; SI-LABEL: widen_i16_constant_load_sext_i32:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_load_dword s1, s[0:1], 0x0
; SI-NEXT: s_mov_b32 s0, 0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_sext_i32_i16 s1, s1
; SI-NEXT: s_addk_i32 s1, 0x3e7
; SI-NEXT: s_or_b32 s4, s1, 4
; SI-NEXT: s_mov_b32 s1, s0
; SI-NEXT: v_mov_b32_e32 v0, s4
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: widen_i16_constant_load_sext_i32:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_load_dword s0, s[0:1], 0x0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_sext_i32_i16 s0, s0
; VI-NEXT: s_addk_i32 s0, 0x3e7
; VI-NEXT: s_or_b32 s0, s0, 4
; VI-NEXT: v_mov_b32_e32 v2, s0
; VI-NEXT: flat_store_dword v[0:1], v2
; VI-NEXT: s_endpgm
%load = load i16, i16 addrspace(4)* %arg, align 4
%ext = sext i16 %load to i32
%add = add i32 %ext, 999
%or = or i32 %add, 4
store i32 %or, i32 addrspace(1)* null
ret void
}
define amdgpu_kernel void @widen_i17_constant_load(i17 addrspace(4)* %arg) {
; SI-LABEL: widen_i17_constant_load:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[6:7], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s0, 0
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_mov_b32 s1, s0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_load_dword s7, s[6:7], 0x0
; SI-NEXT: s_mov_b32 s4, 2
; SI-NEXT: s_mov_b32 s5, s0
; SI-NEXT: s_mov_b32 s6, s2
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_add_i32 s7, s7, 34
; SI-NEXT: s_or_b32 s7, s7, 4
; SI-NEXT: v_mov_b32_e32 v0, s7
; SI-NEXT: s_bfe_u32 s8, s7, 0x10010
; SI-NEXT: buffer_store_short v0, off, s[0:3], 0
; SI-NEXT: s_mov_b32 s7, s3
; SI-NEXT: s_waitcnt expcnt(0)
; SI-NEXT: v_mov_b32_e32 v0, s8
; SI-NEXT: buffer_store_byte v0, off, s[4:7], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: widen_i17_constant_load:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v2, 2
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: v_mov_b32_e32 v3, 0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_load_dword s0, s[0:1], 0x0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_add_i32 s0, s0, 34
; VI-NEXT: s_or_b32 s0, s0, 4
; VI-NEXT: v_mov_b32_e32 v4, s0
; VI-NEXT: s_bfe_u32 s0, s0, 0x10010
; VI-NEXT: flat_store_short v[0:1], v4
; VI-NEXT: v_mov_b32_e32 v0, s0
; VI-NEXT: flat_store_byte v[2:3], v0
; VI-NEXT: s_endpgm
%load = load i17, i17 addrspace(4)* %arg, align 4
%add = add i17 %load, 34
%or = or i17 %add, 4
store i17 %or, i17 addrspace(1)* null
ret void
}
define amdgpu_kernel void @widen_f16_constant_load(half addrspace(4)* %arg) {
; SI-LABEL: widen_f16_constant_load:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_load_dword s0, s[0:1], 0x0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: v_cvt_f32_f16_e32 v0, s0
; SI-NEXT: s_mov_b32 s0, 0
; SI-NEXT: s_mov_b32 s1, s0
; SI-NEXT: v_add_f32_e32 v0, 4.0, v0
; SI-NEXT: v_cvt_f16_f32_e32 v0, v0
; SI-NEXT: buffer_store_short v0, off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: widen_f16_constant_load:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_load_dword s0, s[0:1], 0x0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: v_add_f16_e64 v2, s0, 4.0
; VI-NEXT: flat_store_short v[0:1], v2
; VI-NEXT: s_endpgm
%load = load half, half addrspace(4)* %arg, align 4
%add = fadd half %load, 4.0
store half %add, half addrspace(1)* null
ret void
}
; FIXME: valu usage on VI
define amdgpu_kernel void @widen_v2i8_constant_load(<2 x i8> addrspace(4)* %arg) {
; SI-LABEL: widen_v2i8_constant_load:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s0, 0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_load_dword s1, s[2:3], 0x0
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_and_b32 s4, s1, 0xff00
; SI-NEXT: s_add_i32 s1, s1, 12
; SI-NEXT: s_or_b32 s1, s1, 4
; SI-NEXT: s_and_b32 s1, s1, 0xff
; SI-NEXT: s_or_b32 s1, s4, s1
; SI-NEXT: s_addk_i32 s1, 0x2c00
; SI-NEXT: s_or_b32 s4, s1, 0x300
; SI-NEXT: s_mov_b32 s1, s0
; SI-NEXT: v_mov_b32_e32 v0, s4
; SI-NEXT: buffer_store_short v0, off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: widen_v2i8_constant_load:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: v_mov_b32_e32 v0, 44
; VI-NEXT: v_mov_b32_e32 v1, 3
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_load_dword s0, s[0:1], 0x0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_and_b32 s1, s0, 0xffff
; VI-NEXT: v_mov_b32_e32 v2, s0
; VI-NEXT: s_add_i32 s1, s1, 12
; VI-NEXT: v_add_u32_sdwa v0, vcc, v0, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_1
; VI-NEXT: s_or_b32 s0, s1, 4
; VI-NEXT: v_or_b32_sdwa v0, v0, v1 dst_sel:BYTE_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
; VI-NEXT: s_and_b32 s0, s0, 0xff
; VI-NEXT: v_or_b32_e32 v2, s0, v0
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: flat_store_short v[0:1], v2
; VI-NEXT: s_endpgm
%load = load <2 x i8>, <2 x i8> addrspace(4)* %arg, align 4
%add = add <2 x i8> %load, <i8 12, i8 44>
%or = or <2 x i8> %add, <i8 4, i8 3>
store <2 x i8> %or, <2 x i8> addrspace(1)* null
ret void
}
define amdgpu_kernel void @no_widen_i16_constant_divergent_load(i16 addrspace(4)* %arg) {
; SI-LABEL: no_widen_i16_constant_divergent_load:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s2, 0
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: v_lshlrev_b32_e32 v0, 1, v0
; SI-NEXT: v_mov_b32_e32 v1, 0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: buffer_load_ushort v0, v[0:1], s[0:3], 0 addr64
; SI-NEXT: s_mov_b32 s6, -1
; SI-NEXT: s_mov_b32 s4, s2
; SI-NEXT: s_mov_b32 s5, s2
; SI-NEXT: s_mov_b32 s7, s3
; SI-NEXT: s_waitcnt vmcnt(0)
; SI-NEXT: v_add_i32_e32 v0, vcc, 0x3e7, v0
; SI-NEXT: v_or_b32_e32 v0, 4, v0
; SI-NEXT: buffer_store_short v0, off, s[4:7], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: no_widen_i16_constant_divergent_load:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: v_lshlrev_b32_e32 v0, 1, v0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: v_mov_b32_e32 v1, s1
; VI-NEXT: v_add_u32_e32 v0, vcc, s0, v0
; VI-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
; VI-NEXT: flat_load_ushort v0, v[0:1]
; VI-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; VI-NEXT: v_add_u16_e32 v0, 0x3e7, v0
; VI-NEXT: v_or_b32_e32 v2, 4, v0
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: flat_store_short v[0:1], v2
; VI-NEXT: s_endpgm
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = zext i32 %tid to i64
%gep.arg = getelementptr inbounds i16, i16 addrspace(4)* %arg, i64 %tid.ext
%load = load i16, i16 addrspace(4)* %gep.arg, align 4
%add = add i16 %load, 999
%or = or i16 %add, 4
store i16 %or, i16 addrspace(1)* null
ret void
}
define amdgpu_kernel void @widen_i1_constant_load(i1 addrspace(4)* %arg) {
; SI-LABEL: widen_i1_constant_load:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_load_dword s1, s[0:1], 0x0
; SI-NEXT: s_mov_b32 s0, 0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_and_b32 s4, s1, 1
; SI-NEXT: s_mov_b32 s1, s0
; SI-NEXT: v_mov_b32_e32 v0, s4
; SI-NEXT: buffer_store_byte v0, off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: widen_i1_constant_load:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_load_dword s0, s[0:1], 0x0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_and_b32 s0, s0, 1
; VI-NEXT: v_mov_b32_e32 v2, s0
; VI-NEXT: flat_store_byte v[0:1], v2
; VI-NEXT: s_endpgm
%load = load i1, i1 addrspace(4)* %arg, align 4
%and = and i1 %load, true
store i1 %and, i1 addrspace(1)* null
ret void
}
define amdgpu_kernel void @widen_i16_zextload_i64_constant_load(i16 addrspace(4)* %arg) {
; SI-LABEL: widen_i16_zextload_i64_constant_load:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_load_dword s1, s[0:1], 0x0
; SI-NEXT: s_mov_b32 s0, 0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_and_b32 s1, s1, 0xffff
; SI-NEXT: s_addk_i32 s1, 0x3e7
; SI-NEXT: s_or_b32 s4, s1, 4
; SI-NEXT: s_mov_b32 s1, s0
; SI-NEXT: v_mov_b32_e32 v0, s4
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: widen_i16_zextload_i64_constant_load:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_load_dword s0, s[0:1], 0x0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_and_b32 s0, s0, 0xffff
; VI-NEXT: s_addk_i32 s0, 0x3e7
; VI-NEXT: s_or_b32 s0, s0, 4
; VI-NEXT: v_mov_b32_e32 v2, s0
; VI-NEXT: flat_store_dword v[0:1], v2
; VI-NEXT: s_endpgm
%load = load i16, i16 addrspace(4)* %arg, align 4
%zext = zext i16 %load to i32
%add = add i32 %zext, 999
%or = or i32 %add, 4
store i32 %or, i32 addrspace(1)* null
ret void
}
define amdgpu_kernel void @widen_i1_zext_to_i64_constant_load(i1 addrspace(4)* %arg) {
; SI-LABEL: widen_i1_zext_to_i64_constant_load:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_load_dword s1, s[0:1], 0x0
; SI-NEXT: s_mov_b32 s0, 0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_and_b32 s1, s1, 1
; SI-NEXT: s_add_u32 s4, s1, 0x3e7
; SI-NEXT: s_addc_u32 s5, 0, 0
; SI-NEXT: v_mov_b32_e32 v0, s4
; SI-NEXT: s_mov_b32 s1, s0
; SI-NEXT: v_mov_b32_e32 v1, s5
; SI-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: widen_i1_zext_to_i64_constant_load:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_load_dword s0, s[0:1], 0x0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_and_b32 s0, s0, 1
; VI-NEXT: s_add_u32 s0, s0, 0x3e7
; VI-NEXT: s_addc_u32 s1, 0, 0
; VI-NEXT: v_mov_b32_e32 v3, s1
; VI-NEXT: v_mov_b32_e32 v2, s0
; VI-NEXT: flat_store_dwordx2 v[0:1], v[2:3]
; VI-NEXT: s_endpgm
%load = load i1, i1 addrspace(4)* %arg, align 4
%zext = zext i1 %load to i64
%add = add i64 %zext, 999
store i64 %add, i64 addrspace(1)* null
ret void
}
define amdgpu_kernel void @widen_i16_constant32_load(i16 addrspace(6)* %arg) {
; SI-LABEL: widen_i16_constant32_load:
; SI: ; %bb.0:
; SI-NEXT: s_load_dword s0, s[0:1], 0x9
; SI-NEXT: s_mov_b32 s1, 0
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_load_dword s0, s[0:1], 0x0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_addk_i32 s0, 0x3e7
; SI-NEXT: s_or_b32 s4, s0, 4
; SI-NEXT: s_mov_b32 s0, s1
; SI-NEXT: v_mov_b32_e32 v0, s4
; SI-NEXT: buffer_store_short v0, off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: widen_i16_constant32_load:
; VI: ; %bb.0:
; VI-NEXT: s_load_dword s0, s[0:1], 0x24
; VI-NEXT: s_mov_b32 s1, 0
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_load_dword s0, s[0:1], 0x0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_addk_i32 s0, 0x3e7
; VI-NEXT: s_or_b32 s0, s0, 4
; VI-NEXT: v_mov_b32_e32 v2, s0
; VI-NEXT: flat_store_short v[0:1], v2
; VI-NEXT: s_endpgm
%load = load i16, i16 addrspace(6)* %arg, align 4
%add = add i16 %load, 999
%or = or i16 %add, 4
store i16 %or, i16 addrspace(1)* null
ret void
}
define amdgpu_kernel void @widen_i16_global_invariant_load(i16 addrspace(1)* %arg) {
; SI-LABEL: widen_i16_global_invariant_load:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_load_dword s1, s[0:1], 0x0
; SI-NEXT: s_mov_b32 s0, 0
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_addk_i32 s1, 0x3e7
; SI-NEXT: s_or_b32 s4, s1, 1
; SI-NEXT: s_mov_b32 s1, s0
; SI-NEXT: v_mov_b32_e32 v0, s4
; SI-NEXT: buffer_store_short v0, off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: widen_i16_global_invariant_load:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; VI-NEXT: v_mov_b32_e32 v0, 0
; VI-NEXT: v_mov_b32_e32 v1, 0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_load_dword s0, s[0:1], 0x0
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_addk_i32 s0, 0x3e7
; VI-NEXT: s_or_b32 s0, s0, 1
; VI-NEXT: v_mov_b32_e32 v2, s0
; VI-NEXT: flat_store_short v[0:1], v2
; VI-NEXT: s_endpgm
%load = load i16, i16 addrspace(1)* %arg, align 4, !invariant.load !0
%add = add i16 %load, 999
%or = or i16 %add, 1
store i16 %or, i16 addrspace(1)* null
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x()
!0 = !{}