File: cp-async-bulk-tensor-g2s.ll

package info (click to toggle)
llvm-toolchain-21 1%3A21.1.6-2
  • links: PTS, VCS
  • area: main
  • in suites: forky
  • size: 2,245,044 kB
  • sloc: cpp: 7,619,726; ansic: 1,434,018; asm: 1,058,748; python: 252,740; f90: 94,671; objc: 70,685; lisp: 42,813; pascal: 18,401; sh: 8,601; ml: 5,111; perl: 4,720; makefile: 3,666; awk: 3,523; javascript: 2,409; xml: 892; fortran: 770
file content (459 lines) | stat: -rw-r--r-- 39,435 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
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
 
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80| FileCheck --check-prefixes=CHECK-PTX64 %s
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80 --nvptx-short-ptr| FileCheck --check-prefixes=CHECK-PTX-SHARED32 %s
; RUN: %if ptxas-12.3 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80| %ptxas-verify -arch=sm_90 %}
; RUN: %if ptxas-12.3 %{ llc < %s -mtriple=nvptx64 -mcpu=sm_90 -mattr=+ptx80 --nvptx-short-ptr| %ptxas-verify -arch=sm_90 %}

target triple = "nvptx64-nvidia-cuda"

declare void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.1d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tm, i32 %d0, i16 %mc, i64 %ch, i1 %f1, i1 %f2);
declare void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.2d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tm, i32 %d0, i32 %d1, i16 %mc, i64 %ch, i1 %f1, i1 %f2);
declare void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i16 %mc, i64 %ch, i1 %f1, i1 %f2);
declare void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %mc, i64 %ch, i1 %f1, i1 %f2);
declare void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %mc, i64 %ch, i1 %f1, i1 %f2);

declare void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i16 %im2col0, i16 %mc, i64 %ch, i1 %f1, i1 %f2);
declare void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %im2col0, i16 %im2col1, i16 %mc, i64 %ch, i1 %f1, i1 %f2);
declare void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tm, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %im2col0, i16 %im2col1, i16 %im2col2, i16 %mc, i64 %ch, i1 %f1, i1 %f2);

; CHECK-LABEL: cp_async_bulk_tensor_g2s_tile_1d
define void @cp_async_bulk_tensor_g2s_tile_1d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i16 %mc, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_g2s_tile_1d(
; CHECK-PTX64:       {
; CHECK-PTX64-NEXT:    .reg .b16 %rs<2>;
; CHECK-PTX64-NEXT:    .reg .b32 %r<2>;
; CHECK-PTX64-NEXT:    .reg .b64 %rd<5>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT:  // %bb.0:
; CHECK-PTX64-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_tile_1d_param_0];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_tile_1d_param_1];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd3, [cp_async_bulk_tensor_g2s_tile_1d_param_2];
; CHECK-PTX64-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_tile_1d_param_3];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.1d.shared::cluster.global.tile.mbarrier::complete_tx::bytes [%rd1], [%rd3, {%r1}], [%rd2];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd4, [cp_async_bulk_tensor_g2s_tile_1d_param_5];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.1d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.L2::cache_hint [%rd1], [%rd3, {%r1}], [%rd2], %rd4;
; CHECK-PTX64-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_tile_1d_param_4];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.1d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster [%rd1], [%rd3, {%r1}], [%rd2], %rs1;
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.1d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%rd1], [%rd3, {%r1}], [%rd2], %rs1, %rd4;
; CHECK-PTX64-NEXT:    ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_g2s_tile_1d(
; CHECK-PTX-SHARED32:       {
; CHECK-PTX-SHARED32-NEXT:    .reg .b16 %rs<2>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b32 %r<4>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT:  // %bb.0:
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_tile_1d_param_0];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_tile_1d_param_1];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_tile_1d_param_2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_tile_1d_param_3];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.1d.shared::cluster.global.tile.mbarrier::complete_tx::bytes [%r1], [%rd1, {%r3}], [%r2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_tile_1d_param_5];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.1d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.L2::cache_hint [%r1], [%rd1, {%r3}], [%r2], %rd2;
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_tile_1d_param_4];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.1d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster [%r1], [%rd1, {%r3}], [%r2], %rs1;
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.1d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%r1], [%rd1, {%r3}], [%r2], %rs1, %rd2;
; CHECK-PTX-SHARED32-NEXT:    ret;
  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.1d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i16 %mc, i64 %ch, i1 0, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.1d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i16 %mc, i64 %ch, i1 0, i1 1)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.1d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i16 %mc, i64 %ch, i1 1, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.1d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i16 %mc, i64 %ch, i1 1, i1 1)
  ret void
}

; CHECK-LABEL: cp_async_bulk_tensor_g2s_tile_2d
define void @cp_async_bulk_tensor_g2s_tile_2d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i16 %mc, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_g2s_tile_2d(
; CHECK-PTX64:       {
; CHECK-PTX64-NEXT:    .reg .b16 %rs<2>;
; CHECK-PTX64-NEXT:    .reg .b32 %r<3>;
; CHECK-PTX64-NEXT:    .reg .b64 %rd<5>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT:  // %bb.0:
; CHECK-PTX64-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_tile_2d_param_0];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_tile_2d_param_1];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd3, [cp_async_bulk_tensor_g2s_tile_2d_param_2];
; CHECK-PTX64-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_tile_2d_param_3];
; CHECK-PTX64-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_tile_2d_param_4];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.2d.shared::cluster.global.tile.mbarrier::complete_tx::bytes [%rd1], [%rd3, {%r1, %r2}], [%rd2];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd4, [cp_async_bulk_tensor_g2s_tile_2d_param_6];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.2d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.L2::cache_hint [%rd1], [%rd3, {%r1, %r2}], [%rd2], %rd4;
; CHECK-PTX64-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_tile_2d_param_5];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.2d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster [%rd1], [%rd3, {%r1, %r2}], [%rd2], %rs1;
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.2d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%rd1], [%rd3, {%r1, %r2}], [%rd2], %rs1, %rd4;
; CHECK-PTX64-NEXT:    ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_g2s_tile_2d(
; CHECK-PTX-SHARED32:       {
; CHECK-PTX-SHARED32-NEXT:    .reg .b16 %rs<2>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b32 %r<5>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT:  // %bb.0:
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_tile_2d_param_0];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_tile_2d_param_1];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_tile_2d_param_2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_tile_2d_param_3];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r4, [cp_async_bulk_tensor_g2s_tile_2d_param_4];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.2d.shared::cluster.global.tile.mbarrier::complete_tx::bytes [%r1], [%rd1, {%r3, %r4}], [%r2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_tile_2d_param_6];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.2d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.L2::cache_hint [%r1], [%rd1, {%r3, %r4}], [%r2], %rd2;
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_tile_2d_param_5];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.2d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster [%r1], [%rd1, {%r3, %r4}], [%r2], %rs1;
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.2d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%r1], [%rd1, {%r3, %r4}], [%r2], %rs1, %rd2;
; CHECK-PTX-SHARED32-NEXT:    ret;
  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.2d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i16 %mc, i64 %ch, i1 0, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.2d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i16 %mc, i64 %ch, i1 0, i1 1)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.2d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i16 %mc, i64 %ch, i1 1, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.2d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i16 %mc, i64 %ch, i1 1, i1 1)
  ret void
}

; CHECK-LABEL: cp_async_bulk_tensor_g2s_tile_3d
define void @cp_async_bulk_tensor_g2s_tile_3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i16 %mc, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_g2s_tile_3d(
; CHECK-PTX64:       {
; CHECK-PTX64-NEXT:    .reg .b16 %rs<2>;
; CHECK-PTX64-NEXT:    .reg .b32 %r<4>;
; CHECK-PTX64-NEXT:    .reg .b64 %rd<5>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT:  // %bb.0:
; CHECK-PTX64-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_tile_3d_param_0];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_tile_3d_param_1];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd3, [cp_async_bulk_tensor_g2s_tile_3d_param_2];
; CHECK-PTX64-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_tile_3d_param_3];
; CHECK-PTX64-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_tile_3d_param_4];
; CHECK-PTX64-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_tile_3d_param_5];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.tile.mbarrier::complete_tx::bytes [%rd1], [%rd3, {%r1, %r2, %r3}], [%rd2];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd4, [cp_async_bulk_tensor_g2s_tile_3d_param_7];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3}], [%rd2], %rd4;
; CHECK-PTX64-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_tile_3d_param_6];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster [%rd1], [%rd3, {%r1, %r2, %r3}], [%rd2], %rs1;
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3}], [%rd2], %rs1, %rd4;
; CHECK-PTX64-NEXT:    ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_g2s_tile_3d(
; CHECK-PTX-SHARED32:       {
; CHECK-PTX-SHARED32-NEXT:    .reg .b16 %rs<2>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b32 %r<6>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT:  // %bb.0:
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_tile_3d_param_0];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_tile_3d_param_1];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_tile_3d_param_2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_tile_3d_param_3];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r4, [cp_async_bulk_tensor_g2s_tile_3d_param_4];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r5, [cp_async_bulk_tensor_g2s_tile_3d_param_5];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.tile.mbarrier::complete_tx::bytes [%r1], [%rd1, {%r3, %r4, %r5}], [%r2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_tile_3d_param_7];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5}], [%r2], %rd2;
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_tile_3d_param_6];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster [%r1], [%rd1, {%r3, %r4, %r5}], [%r2], %rs1;
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5}], [%r2], %rs1, %rd2;
; CHECK-PTX-SHARED32-NEXT:    ret;
  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i16 %mc, i64 %ch, i1 0, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i16 %mc, i64 %ch, i1 0, i1 1)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i16 %mc, i64 %ch, i1 1, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i16 %mc, i64 %ch, i1 1, i1 1)
  ret void
}

; CHECK-LABEL: cp_async_bulk_tensor_g2s_tile_4d
define void @cp_async_bulk_tensor_g2s_tile_4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %mc, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_g2s_tile_4d(
; CHECK-PTX64:       {
; CHECK-PTX64-NEXT:    .reg .b16 %rs<2>;
; CHECK-PTX64-NEXT:    .reg .b32 %r<5>;
; CHECK-PTX64-NEXT:    .reg .b64 %rd<5>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT:  // %bb.0:
; CHECK-PTX64-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_tile_4d_param_0];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_tile_4d_param_1];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd3, [cp_async_bulk_tensor_g2s_tile_4d_param_2];
; CHECK-PTX64-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_tile_4d_param_3];
; CHECK-PTX64-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_tile_4d_param_4];
; CHECK-PTX64-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_tile_4d_param_5];
; CHECK-PTX64-NEXT:    ld.param.b32 %r4, [cp_async_bulk_tensor_g2s_tile_4d_param_6];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.tile.mbarrier::complete_tx::bytes [%rd1], [%rd3, {%r1, %r2, %r3, %r4}], [%rd2];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd4, [cp_async_bulk_tensor_g2s_tile_4d_param_8];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3, %r4}], [%rd2], %rd4;
; CHECK-PTX64-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_tile_4d_param_7];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster [%rd1], [%rd3, {%r1, %r2, %r3, %r4}], [%rd2], %rs1;
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3, %r4}], [%rd2], %rs1, %rd4;
; CHECK-PTX64-NEXT:    ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_g2s_tile_4d(
; CHECK-PTX-SHARED32:       {
; CHECK-PTX-SHARED32-NEXT:    .reg .b16 %rs<2>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b32 %r<7>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT:  // %bb.0:
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_tile_4d_param_0];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_tile_4d_param_1];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_tile_4d_param_2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_tile_4d_param_3];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r4, [cp_async_bulk_tensor_g2s_tile_4d_param_4];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r5, [cp_async_bulk_tensor_g2s_tile_4d_param_5];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r6, [cp_async_bulk_tensor_g2s_tile_4d_param_6];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.tile.mbarrier::complete_tx::bytes [%r1], [%rd1, {%r3, %r4, %r5, %r6}], [%r2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_tile_4d_param_8];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5, %r6}], [%r2], %rd2;
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_tile_4d_param_7];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster [%r1], [%rd1, {%r3, %r4, %r5, %r6}], [%r2], %rs1;
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5, %r6}], [%r2], %rs1, %rd2;
; CHECK-PTX-SHARED32-NEXT:    ret;
  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %mc, i64 %ch, i1 0, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %mc, i64 %ch, i1 0, i1 1)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %mc, i64 %ch, i1 1, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %mc, i64 %ch, i1 1, i1 1)
  ret void
}

; CHECK-LABEL: cp_async_bulk_tensor_g2s_tile_5d
define void @cp_async_bulk_tensor_g2s_tile_5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %mc, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_g2s_tile_5d(
; CHECK-PTX64:       {
; CHECK-PTX64-NEXT:    .reg .b16 %rs<2>;
; CHECK-PTX64-NEXT:    .reg .b32 %r<6>;
; CHECK-PTX64-NEXT:    .reg .b64 %rd<5>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT:  // %bb.0:
; CHECK-PTX64-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_tile_5d_param_0];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_tile_5d_param_1];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd3, [cp_async_bulk_tensor_g2s_tile_5d_param_2];
; CHECK-PTX64-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_tile_5d_param_3];
; CHECK-PTX64-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_tile_5d_param_4];
; CHECK-PTX64-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_tile_5d_param_5];
; CHECK-PTX64-NEXT:    ld.param.b32 %r4, [cp_async_bulk_tensor_g2s_tile_5d_param_6];
; CHECK-PTX64-NEXT:    ld.param.b32 %r5, [cp_async_bulk_tensor_g2s_tile_5d_param_7];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.tile.mbarrier::complete_tx::bytes [%rd1], [%rd3, {%r1, %r2, %r3, %r4, %r5}], [%rd2];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd4, [cp_async_bulk_tensor_g2s_tile_5d_param_9];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3, %r4, %r5}], [%rd2], %rd4;
; CHECK-PTX64-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_tile_5d_param_8];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster [%rd1], [%rd3, {%r1, %r2, %r3, %r4, %r5}], [%rd2], %rs1;
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3, %r4, %r5}], [%rd2], %rs1, %rd4;
; CHECK-PTX64-NEXT:    ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_g2s_tile_5d(
; CHECK-PTX-SHARED32:       {
; CHECK-PTX-SHARED32-NEXT:    .reg .b16 %rs<2>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b32 %r<8>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT:  // %bb.0:
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_tile_5d_param_0];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_tile_5d_param_1];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_tile_5d_param_2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_tile_5d_param_3];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r4, [cp_async_bulk_tensor_g2s_tile_5d_param_4];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r5, [cp_async_bulk_tensor_g2s_tile_5d_param_5];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r6, [cp_async_bulk_tensor_g2s_tile_5d_param_6];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r7, [cp_async_bulk_tensor_g2s_tile_5d_param_7];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.tile.mbarrier::complete_tx::bytes [%r1], [%rd1, {%r3, %r4, %r5, %r6, %r7}], [%r2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_tile_5d_param_9];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5, %r6, %r7}], [%r2], %rd2;
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_tile_5d_param_8];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster [%r1], [%rd1, {%r3, %r4, %r5, %r6, %r7}], [%r2], %rs1;
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.tile.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5, %r6, %r7}], [%r2], %rs1, %rd2;
; CHECK-PTX-SHARED32-NEXT:    ret;
  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %mc, i64 %ch, i1 0, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %mc, i64 %ch, i1 0, i1 1)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %mc, i64 %ch, i1 1, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.tile.5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %mc, i64 %ch, i1 1, i1 1)
  ret void
}

; CHECK-LABEL: cp_async_bulk_tensor_g2s_im2col_3d
define void @cp_async_bulk_tensor_g2s_im2col_3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i16 %im2col0, i16 %mc, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_g2s_im2col_3d(
; CHECK-PTX64:       {
; CHECK-PTX64-NEXT:    .reg .b16 %rs<3>;
; CHECK-PTX64-NEXT:    .reg .b32 %r<4>;
; CHECK-PTX64-NEXT:    .reg .b64 %rd<5>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT:  // %bb.0:
; CHECK-PTX64-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_im2col_3d_param_0];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_im2col_3d_param_1];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd3, [cp_async_bulk_tensor_g2s_im2col_3d_param_2];
; CHECK-PTX64-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_im2col_3d_param_3];
; CHECK-PTX64-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_im2col_3d_param_4];
; CHECK-PTX64-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_im2col_3d_param_5];
; CHECK-PTX64-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_im2col_3d_param_6];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes [%rd1], [%rd3, {%r1, %r2, %r3}], [%rd2], {%rs1};
; CHECK-PTX64-NEXT:    ld.param.b64 %rd4, [cp_async_bulk_tensor_g2s_im2col_3d_param_8];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3}], [%rd2], {%rs1}, %rd4;
; CHECK-PTX64-NEXT:    ld.param.b16 %rs2, [cp_async_bulk_tensor_g2s_im2col_3d_param_7];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster [%rd1], [%rd3, {%r1, %r2, %r3}], [%rd2], {%rs1}, %rs2;
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3}], [%rd2], {%rs1}, %rs2, %rd4;
; CHECK-PTX64-NEXT:    ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_g2s_im2col_3d(
; CHECK-PTX-SHARED32:       {
; CHECK-PTX-SHARED32-NEXT:    .reg .b16 %rs<3>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b32 %r<6>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT:  // %bb.0:
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_im2col_3d_param_0];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_im2col_3d_param_1];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_im2col_3d_param_2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_im2col_3d_param_3];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r4, [cp_async_bulk_tensor_g2s_im2col_3d_param_4];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r5, [cp_async_bulk_tensor_g2s_im2col_3d_param_5];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_im2col_3d_param_6];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes [%r1], [%rd1, {%r3, %r4, %r5}], [%r2], {%rs1};
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_im2col_3d_param_8];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5}], [%r2], {%rs1}, %rd2;
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs2, [cp_async_bulk_tensor_g2s_im2col_3d_param_7];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster [%r1], [%rd1, {%r3, %r4, %r5}], [%r2], {%rs1}, %rs2;
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.3d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5}], [%r2], {%rs1}, %rs2, %rd2;
; CHECK-PTX-SHARED32-NEXT:    ret;
  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i16 %im2col0, i16 %mc, i64 %ch, i1 0, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i16 %im2col0, i16 %mc, i64 %ch, i1 0, i1 1)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i16 %im2col0, i16 %mc, i64 %ch, i1 1, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.3d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i16 %im2col0, i16 %mc, i64 %ch, i1 1, i1 1)
  ret void
}

; CHECK-LABEL: cp_async_bulk_tensor_g2s_im2col_4d
define void @cp_async_bulk_tensor_g2s_im2col_4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %im2col0, i16 %im2col1, i16 %mc, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_g2s_im2col_4d(
; CHECK-PTX64:       {
; CHECK-PTX64-NEXT:    .reg .b16 %rs<4>;
; CHECK-PTX64-NEXT:    .reg .b32 %r<5>;
; CHECK-PTX64-NEXT:    .reg .b64 %rd<5>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT:  // %bb.0:
; CHECK-PTX64-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_im2col_4d_param_0];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_im2col_4d_param_1];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd3, [cp_async_bulk_tensor_g2s_im2col_4d_param_2];
; CHECK-PTX64-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_im2col_4d_param_3];
; CHECK-PTX64-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_im2col_4d_param_4];
; CHECK-PTX64-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_im2col_4d_param_5];
; CHECK-PTX64-NEXT:    ld.param.b32 %r4, [cp_async_bulk_tensor_g2s_im2col_4d_param_6];
; CHECK-PTX64-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_im2col_4d_param_7];
; CHECK-PTX64-NEXT:    ld.param.b16 %rs2, [cp_async_bulk_tensor_g2s_im2col_4d_param_8];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes [%rd1], [%rd3, {%r1, %r2, %r3, %r4}], [%rd2], {%rs1, %rs2};
; CHECK-PTX64-NEXT:    ld.param.b64 %rd4, [cp_async_bulk_tensor_g2s_im2col_4d_param_10];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3, %r4}], [%rd2], {%rs1, %rs2}, %rd4;
; CHECK-PTX64-NEXT:    ld.param.b16 %rs3, [cp_async_bulk_tensor_g2s_im2col_4d_param_9];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster [%rd1], [%rd3, {%r1, %r2, %r3, %r4}], [%rd2], {%rs1, %rs2}, %rs3;
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3, %r4}], [%rd2], {%rs1, %rs2}, %rs3, %rd4;
; CHECK-PTX64-NEXT:    ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_g2s_im2col_4d(
; CHECK-PTX-SHARED32:       {
; CHECK-PTX-SHARED32-NEXT:    .reg .b16 %rs<4>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b32 %r<7>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT:  // %bb.0:
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_im2col_4d_param_0];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_im2col_4d_param_1];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_im2col_4d_param_2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_im2col_4d_param_3];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r4, [cp_async_bulk_tensor_g2s_im2col_4d_param_4];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r5, [cp_async_bulk_tensor_g2s_im2col_4d_param_5];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r6, [cp_async_bulk_tensor_g2s_im2col_4d_param_6];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_im2col_4d_param_7];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs2, [cp_async_bulk_tensor_g2s_im2col_4d_param_8];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes [%r1], [%rd1, {%r3, %r4, %r5, %r6}], [%r2], {%rs1, %rs2};
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_im2col_4d_param_10];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5, %r6}], [%r2], {%rs1, %rs2}, %rd2;
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs3, [cp_async_bulk_tensor_g2s_im2col_4d_param_9];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster [%r1], [%rd1, {%r3, %r4, %r5, %r6}], [%r2], {%rs1, %rs2}, %rs3;
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.4d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5, %r6}], [%r2], {%rs1, %rs2}, %rs3, %rd2;
; CHECK-PTX-SHARED32-NEXT:    ret;
  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %im2col0, i16 %im2col1, i16 %mc, i64 %ch, i1 0, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %im2col0, i16 %im2col1, i16 %mc, i64 %ch, i1 0, i1 1)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %im2col0, i16 %im2col1, i16 %mc, i64 %ch, i1 1, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.4d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i16 %im2col0, i16 %im2col1, i16 %mc, i64 %ch, i1 1, i1 1)
  ret void
}

; CHECK-LABEL: cp_async_bulk_tensor_g2s_im2col_5d
define void @cp_async_bulk_tensor_g2s_im2col_5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %im2col0, i16 %im2col1, i16 %im2col2, i16 %mc, i64 %ch) {
; CHECK-PTX64-LABEL: cp_async_bulk_tensor_g2s_im2col_5d(
; CHECK-PTX64:       {
; CHECK-PTX64-NEXT:    .reg .b16 %rs<5>;
; CHECK-PTX64-NEXT:    .reg .b32 %r<6>;
; CHECK-PTX64-NEXT:    .reg .b64 %rd<5>;
; CHECK-PTX64-EMPTY:
; CHECK-PTX64-NEXT:  // %bb.0:
; CHECK-PTX64-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_im2col_5d_param_0];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_im2col_5d_param_1];
; CHECK-PTX64-NEXT:    ld.param.b64 %rd3, [cp_async_bulk_tensor_g2s_im2col_5d_param_2];
; CHECK-PTX64-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_im2col_5d_param_3];
; CHECK-PTX64-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_im2col_5d_param_4];
; CHECK-PTX64-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_im2col_5d_param_5];
; CHECK-PTX64-NEXT:    ld.param.b32 %r4, [cp_async_bulk_tensor_g2s_im2col_5d_param_6];
; CHECK-PTX64-NEXT:    ld.param.b32 %r5, [cp_async_bulk_tensor_g2s_im2col_5d_param_7];
; CHECK-PTX64-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_im2col_5d_param_8];
; CHECK-PTX64-NEXT:    ld.param.b16 %rs2, [cp_async_bulk_tensor_g2s_im2col_5d_param_9];
; CHECK-PTX64-NEXT:    ld.param.b16 %rs3, [cp_async_bulk_tensor_g2s_im2col_5d_param_10];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes [%rd1], [%rd3, {%r1, %r2, %r3, %r4, %r5}], [%rd2], {%rs1, %rs2, %rs3};
; CHECK-PTX64-NEXT:    ld.param.b64 %rd4, [cp_async_bulk_tensor_g2s_im2col_5d_param_12];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3, %r4, %r5}], [%rd2], {%rs1, %rs2, %rs3}, %rd4;
; CHECK-PTX64-NEXT:    ld.param.b16 %rs4, [cp_async_bulk_tensor_g2s_im2col_5d_param_11];
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster [%rd1], [%rd3, {%r1, %r2, %r3, %r4, %r5}], [%rd2], {%rs1, %rs2, %rs3}, %rs4;
; CHECK-PTX64-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%rd1], [%rd3, {%r1, %r2, %r3, %r4, %r5}], [%rd2], {%rs1, %rs2, %rs3}, %rs4, %rd4;
; CHECK-PTX64-NEXT:    ret;
;
; CHECK-PTX-SHARED32-LABEL: cp_async_bulk_tensor_g2s_im2col_5d(
; CHECK-PTX-SHARED32:       {
; CHECK-PTX-SHARED32-NEXT:    .reg .b16 %rs<5>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b32 %r<8>;
; CHECK-PTX-SHARED32-NEXT:    .reg .b64 %rd<3>;
; CHECK-PTX-SHARED32-EMPTY:
; CHECK-PTX-SHARED32-NEXT:  // %bb.0:
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r1, [cp_async_bulk_tensor_g2s_im2col_5d_param_0];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r2, [cp_async_bulk_tensor_g2s_im2col_5d_param_1];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd1, [cp_async_bulk_tensor_g2s_im2col_5d_param_2];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r3, [cp_async_bulk_tensor_g2s_im2col_5d_param_3];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r4, [cp_async_bulk_tensor_g2s_im2col_5d_param_4];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r5, [cp_async_bulk_tensor_g2s_im2col_5d_param_5];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r6, [cp_async_bulk_tensor_g2s_im2col_5d_param_6];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b32 %r7, [cp_async_bulk_tensor_g2s_im2col_5d_param_7];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs1, [cp_async_bulk_tensor_g2s_im2col_5d_param_8];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs2, [cp_async_bulk_tensor_g2s_im2col_5d_param_9];
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs3, [cp_async_bulk_tensor_g2s_im2col_5d_param_10];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes [%r1], [%rd1, {%r3, %r4, %r5, %r6, %r7}], [%r2], {%rs1, %rs2, %rs3};
; CHECK-PTX-SHARED32-NEXT:    ld.param.b64 %rd2, [cp_async_bulk_tensor_g2s_im2col_5d_param_12];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5, %r6, %r7}], [%r2], {%rs1, %rs2, %rs3}, %rd2;
; CHECK-PTX-SHARED32-NEXT:    ld.param.b16 %rs4, [cp_async_bulk_tensor_g2s_im2col_5d_param_11];
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster [%r1], [%rd1, {%r3, %r4, %r5, %r6, %r7}], [%r2], {%rs1, %rs2, %rs3}, %rs4;
; CHECK-PTX-SHARED32-NEXT:    cp.async.bulk.tensor.5d.shared::cluster.global.im2col.mbarrier::complete_tx::bytes.multicast::cluster.L2::cache_hint [%r1], [%rd1, {%r3, %r4, %r5, %r6, %r7}], [%r2], {%rs1, %rs2, %rs3}, %rs4, %rd2;
; CHECK-PTX-SHARED32-NEXT:    ret;
  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %im2col0, i16 %im2col1, i16 %im2col2, i16 %mc, i64 %ch, i1 0, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %im2col0, i16 %im2col1, i16 %im2col2, i16 %mc, i64 %ch, i1 0, i1 1)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %im2col0, i16 %im2col1, i16 %im2col2, i16 %mc, i64 %ch, i1 1, i1 0)

  tail call void @llvm.nvvm.cp.async.bulk.tensor.g2s.im2col.5d(ptr addrspace(7) %d, ptr addrspace(3) %bar, ptr %tmap, i32 %d0, i32 %d1, i32 %d2, i32 %d3, i32 %d4, i16 %im2col0, i16 %im2col1, i16 %im2col2, i16 %mc, i64 %ch, i1 1, i1 1)
  ret void
}