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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mattr=-flat-for-global -verify-machineinstrs | FileCheck %s --check-prefix=SI
; RUN: llc < %s -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs | FileCheck %s --check-prefixes=GFX89,VI
; RUN: llc < %s -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs -| FileCheck %s --check-prefixes=GFX89,GFX9
; XXX - Why the packing?
define amdgpu_kernel void @scalar_to_vector_v2i32(ptr addrspace(1) %out, ptr addrspace(1) %in) nounwind {
; SI-LABEL: scalar_to_vector_v2i32:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x9
; SI-NEXT: s_mov_b32 s7, 0xf000
; SI-NEXT: s_mov_b32 s6, -1
; SI-NEXT: s_mov_b32 s10, s6
; SI-NEXT: s_mov_b32 s11, s7
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_mov_b32 s8, s2
; SI-NEXT: s_mov_b32 s9, s3
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
; SI-NEXT: s_waitcnt vmcnt(0)
; SI-NEXT: v_lshrrev_b32_e32 v1, 16, v0
; SI-NEXT: v_alignbit_b32 v0, v1, v0, 16
; SI-NEXT: s_mov_b32 s4, s0
; SI-NEXT: s_mov_b32 s5, s1
; SI-NEXT: v_mov_b32_e32 v1, v0
; SI-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: scalar_to_vector_v2i32:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x24
; VI-NEXT: s_mov_b32 s7, 0xf000
; VI-NEXT: s_mov_b32 s6, -1
; VI-NEXT: s_mov_b32 s10, s6
; VI-NEXT: s_mov_b32 s11, s7
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_mov_b32 s8, s2
; VI-NEXT: s_mov_b32 s9, s3
; VI-NEXT: buffer_load_dword v0, off, s[8:11], 0
; VI-NEXT: s_mov_b32 s4, s0
; VI-NEXT: s_mov_b32 s5, s1
; VI-NEXT: s_waitcnt vmcnt(0)
; VI-NEXT: v_lshrrev_b32_e32 v1, 16, v0
; VI-NEXT: v_alignbit_b32 v0, v1, v0, 16
; VI-NEXT: v_mov_b32_e32 v1, v0
; VI-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
; VI-NEXT: s_endpgm
;
; GFX9-LABEL: scalar_to_vector_v2i32:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x24
; GFX9-NEXT: s_mov_b32 s7, 0xf000
; GFX9-NEXT: s_mov_b32 s6, -1
; GFX9-NEXT: s_mov_b32 s10, s6
; GFX9-NEXT: s_mov_b32 s11, s7
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: s_mov_b32 s8, s2
; GFX9-NEXT: s_mov_b32 s9, s3
; GFX9-NEXT: buffer_load_dword v0, off, s[8:11], 0
; GFX9-NEXT: v_mov_b32_e32 v2, 0xffff0000
; GFX9-NEXT: s_mov_b32 s4, s0
; GFX9-NEXT: s_mov_b32 s5, s1
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: v_lshrrev_b32_e32 v1, 16, v0
; GFX9-NEXT: v_and_or_b32 v0, v0, v2, v1
; GFX9-NEXT: v_mov_b32_e32 v1, v0
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
; GFX9-NEXT: s_endpgm
%tmp1 = load i32, ptr addrspace(1) %in, align 4
%bc = bitcast i32 %tmp1 to <2 x i16>
%tmp2 = shufflevector <2 x i16> %bc, <2 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
store <4 x i16> %tmp2, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @scalar_to_vector_v2f32(ptr addrspace(1) %out, ptr addrspace(1) %in) nounwind {
; SI-LABEL: scalar_to_vector_v2f32:
; SI: ; %bb.0:
; SI-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x9
; SI-NEXT: s_mov_b32 s7, 0xf000
; SI-NEXT: s_mov_b32 s6, -1
; SI-NEXT: s_mov_b32 s10, s6
; SI-NEXT: s_mov_b32 s11, s7
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_mov_b32 s8, s2
; SI-NEXT: s_mov_b32 s9, s3
; SI-NEXT: buffer_load_dword v0, off, s[8:11], 0
; SI-NEXT: s_waitcnt vmcnt(0)
; SI-NEXT: v_lshrrev_b32_e32 v1, 16, v0
; SI-NEXT: v_alignbit_b32 v0, v1, v0, 16
; SI-NEXT: s_mov_b32 s4, s0
; SI-NEXT: s_mov_b32 s5, s1
; SI-NEXT: v_mov_b32_e32 v1, v0
; SI-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: scalar_to_vector_v2f32:
; VI: ; %bb.0:
; VI-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x24
; VI-NEXT: s_mov_b32 s7, 0xf000
; VI-NEXT: s_mov_b32 s6, -1
; VI-NEXT: s_mov_b32 s10, s6
; VI-NEXT: s_mov_b32 s11, s7
; VI-NEXT: s_waitcnt lgkmcnt(0)
; VI-NEXT: s_mov_b32 s8, s2
; VI-NEXT: s_mov_b32 s9, s3
; VI-NEXT: buffer_load_dword v0, off, s[8:11], 0
; VI-NEXT: s_mov_b32 s4, s0
; VI-NEXT: s_mov_b32 s5, s1
; VI-NEXT: s_waitcnt vmcnt(0)
; VI-NEXT: v_lshrrev_b32_e32 v1, 16, v0
; VI-NEXT: v_alignbit_b32 v0, v1, v0, 16
; VI-NEXT: v_mov_b32_e32 v1, v0
; VI-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
; VI-NEXT: s_endpgm
;
; GFX9-LABEL: scalar_to_vector_v2f32:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x24
; GFX9-NEXT: s_mov_b32 s7, 0xf000
; GFX9-NEXT: s_mov_b32 s6, -1
; GFX9-NEXT: s_mov_b32 s10, s6
; GFX9-NEXT: s_mov_b32 s11, s7
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: s_mov_b32 s8, s2
; GFX9-NEXT: s_mov_b32 s9, s3
; GFX9-NEXT: buffer_load_dword v0, off, s[8:11], 0
; GFX9-NEXT: v_mov_b32_e32 v2, 0xffff0000
; GFX9-NEXT: s_mov_b32 s4, s0
; GFX9-NEXT: s_mov_b32 s5, s1
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: v_lshrrev_b32_e32 v1, 16, v0
; GFX9-NEXT: v_and_or_b32 v0, v0, v2, v1
; GFX9-NEXT: v_mov_b32_e32 v1, v0
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[4:7], 0
; GFX9-NEXT: s_endpgm
%tmp1 = load float, ptr addrspace(1) %in, align 4
%bc = bitcast float %tmp1 to <2 x i16>
%tmp2 = shufflevector <2 x i16> %bc, <2 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
store <4 x i16> %tmp2, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @scalar_to_vector_v4i16() {
; SI-LABEL: scalar_to_vector_v4i16:
; SI: ; %bb.0: ; %bb
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: buffer_load_ubyte v0, off, s[0:3], 0
; SI-NEXT: s_waitcnt vmcnt(0)
; SI-NEXT: v_lshlrev_b32_e32 v1, 8, v0
; SI-NEXT: v_or_b32_e32 v2, v1, v0
; SI-NEXT: v_and_b32_e32 v1, 0xff00, v2
; SI-NEXT: v_or_b32_e32 v0, v0, v1
; SI-NEXT: v_lshlrev_b32_e32 v3, 16, v0
; SI-NEXT: v_or_b32_e32 v1, v0, v3
; SI-NEXT: v_or_b32_e32 v0, v2, v3
; SI-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: scalar_to_vector_v4i16:
; VI: ; %bb.0: ; %bb
; VI-NEXT: s_mov_b32 s3, 0xf000
; VI-NEXT: s_mov_b32 s2, -1
; VI-NEXT: buffer_load_ubyte v0, off, s[0:3], 0
; VI-NEXT: s_waitcnt vmcnt(0)
; VI-NEXT: v_readfirstlane_b32 s0, v0
; VI-NEXT: s_lshl_b32 s1, s0, 8
; VI-NEXT: s_or_b32 s0, s0, s1
; VI-NEXT: s_lshl_b32 s1, s0, 16
; VI-NEXT: s_and_b32 s0, s0, 0xffff
; VI-NEXT: s_or_b32 s0, s0, s1
; VI-NEXT: v_mov_b32_e32 v0, s0
; VI-NEXT: v_mov_b32_e32 v1, s0
; VI-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
; VI-NEXT: s_endpgm
;
; GFX9-LABEL: scalar_to_vector_v4i16:
; GFX9: ; %bb.0: ; %bb
; GFX9-NEXT: s_mov_b32 s3, 0xf000
; GFX9-NEXT: s_mov_b32 s2, -1
; GFX9-NEXT: buffer_load_ubyte v0, off, s[0:3], 0
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s0, v0
; GFX9-NEXT: s_lshl_b32 s1, s0, 8
; GFX9-NEXT: s_or_b32 s0, s0, s1
; GFX9-NEXT: s_and_b32 s1, s0, 0xffff
; GFX9-NEXT: s_lshl_b32 s0, s0, 16
; GFX9-NEXT: s_or_b32 s0, s1, s0
; GFX9-NEXT: v_mov_b32_e32 v0, s0
; GFX9-NEXT: v_mov_b32_e32 v1, s0
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
; GFX9-NEXT: s_endpgm
bb:
%tmp = load <2 x i8>, ptr addrspace(1) undef, align 1
%tmp1 = shufflevector <2 x i8> %tmp, <2 x i8> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 0, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9>
store <8 x i8> %tmp2, ptr addrspace(1) undef, align 8
ret void
}
define amdgpu_kernel void @scalar_to_vector_v4f16() {
; SI-LABEL: scalar_to_vector_v4f16:
; SI: ; %bb.0: ; %bb
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: buffer_load_ubyte v0, off, s[0:3], 0
; SI-NEXT: s_waitcnt vmcnt(0)
; SI-NEXT: v_lshlrev_b32_e32 v1, 8, v0
; SI-NEXT: v_or_b32_e32 v2, v1, v0
; SI-NEXT: v_and_b32_e32 v1, 0xff00, v2
; SI-NEXT: v_or_b32_e32 v0, v0, v1
; SI-NEXT: v_lshlrev_b32_e32 v3, 16, v0
; SI-NEXT: v_or_b32_e32 v1, v0, v3
; SI-NEXT: v_or_b32_e32 v0, v2, v3
; SI-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; VI-LABEL: scalar_to_vector_v4f16:
; VI: ; %bb.0: ; %bb
; VI-NEXT: s_mov_b32 s3, 0xf000
; VI-NEXT: s_mov_b32 s2, -1
; VI-NEXT: buffer_load_ubyte v0, off, s[0:3], 0
; VI-NEXT: s_waitcnt vmcnt(0)
; VI-NEXT: v_readfirstlane_b32 s0, v0
; VI-NEXT: s_lshl_b32 s1, s0, 8
; VI-NEXT: s_or_b32 s0, s1, s0
; VI-NEXT: s_and_b32 s1, s0, 0xff00
; VI-NEXT: s_bfe_u32 s4, s0, 0x80008
; VI-NEXT: s_or_b32 s1, s4, s1
; VI-NEXT: s_and_b32 s0, s0, 0xffff
; VI-NEXT: s_lshl_b32 s4, s1, 16
; VI-NEXT: s_and_b32 s1, s1, 0xffff
; VI-NEXT: s_or_b32 s1, s1, s4
; VI-NEXT: s_or_b32 s0, s0, s4
; VI-NEXT: v_mov_b32_e32 v0, s0
; VI-NEXT: v_mov_b32_e32 v1, s1
; VI-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
; VI-NEXT: s_endpgm
;
; GFX9-LABEL: scalar_to_vector_v4f16:
; GFX9: ; %bb.0: ; %bb
; GFX9-NEXT: s_mov_b32 s3, 0xf000
; GFX9-NEXT: s_mov_b32 s2, -1
; GFX9-NEXT: buffer_load_ubyte v0, off, s[0:3], 0
; GFX9-NEXT: s_waitcnt vmcnt(0)
; GFX9-NEXT: v_readfirstlane_b32 s0, v0
; GFX9-NEXT: s_lshl_b32 s1, s0, 8
; GFX9-NEXT: s_or_b32 s0, s1, s0
; GFX9-NEXT: s_and_b32 s1, s0, 0xff00
; GFX9-NEXT: s_bfe_u32 s4, s0, 0x80008
; GFX9-NEXT: s_or_b32 s1, s4, s1
; GFX9-NEXT: s_and_b32 s0, s0, 0xffff
; GFX9-NEXT: s_and_b32 s4, s1, 0xffff
; GFX9-NEXT: s_lshl_b32 s1, s1, 16
; GFX9-NEXT: s_or_b32 s4, s4, s1
; GFX9-NEXT: s_or_b32 s0, s0, s1
; GFX9-NEXT: v_mov_b32_e32 v0, s0
; GFX9-NEXT: v_mov_b32_e32 v1, s4
; GFX9-NEXT: buffer_store_dwordx2 v[0:1], off, s[0:3], 0
; GFX9-NEXT: s_endpgm
bb:
%load = load half, ptr addrspace(1) undef, align 1
%tmp = bitcast half %load to <2 x i8>
%tmp1 = shufflevector <2 x i8> %tmp, <2 x i8> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 0, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9>
store <8 x i8> %tmp2, ptr addrspace(1) undef, align 8
ret void
}
; Getting a SCALAR_TO_VECTOR seems to be tricky. These cases managed
; to produce one, but for some reason never made it to selection.
; define amdgpu_kernel void @scalar_to_vector_test2(ptr addrspace(1) %out, ptr addrspace(1) %in) nounwind {
; %tmp1 = load i32, ptr addrspace(1) %in, align 4
; %bc = bitcast i32 %tmp1 to <4 x i8>
; %tmp2 = shufflevector <4 x i8> %bc, <4 x i8> undef, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
; store <8 x i8> %tmp2, ptr addrspace(1) %out, align 4
; ret void
; }
; define amdgpu_kernel void @scalar_to_vector_test3(ptr addrspace(1) %out) nounwind {
; %newvec0 = insertelement <2 x i64> undef, i64 12345, i32 0
; %newvec1 = insertelement <2 x i64> %newvec0, i64 undef, i32 1
; %bc = bitcast <2 x i64> %newvec1 to <4 x i32>
; %add = add <4 x i32> %bc, <i32 1, i32 2, i32 3, i32 4>
; store <4 x i32> %add, ptr addrspace(1) %out, align 16
; ret void
; }
; define amdgpu_kernel void @scalar_to_vector_test4(ptr addrspace(1) %out) nounwind {
; %newvec0 = insertelement <4 x i32> undef, i32 12345, i32 0
; %bc = bitcast <4 x i32> %newvec0 to <8 x i16>
; %add = add <8 x i16> %bc, <i16 1, i16 2, i16 3, i16 4, i16 1, i16 2, i16 3, i16 4>
; store <8 x i16> %add, ptr addrspace(1) %out, align 16
; ret void
; }
; define amdgpu_kernel void @scalar_to_vector_test5(ptr addrspace(1) %out) nounwind {
; %newvec0 = insertelement <2 x i32> undef, i32 12345, i32 0
; %bc = bitcast <2 x i32> %newvec0 to <4 x i16>
; %add = add <4 x i16> %bc, <i16 1, i16 2, i16 3, i16 4>
; store <4 x i16> %add, ptr addrspace(1) %out, align 16
; ret void
; }
define amdgpu_kernel void @scalar_to_vector_test6(ptr addrspace(1) %out, i8 zeroext %val) nounwind {
; SI-LABEL: scalar_to_vector_test6:
; SI: ; %bb.0:
; SI-NEXT: s_load_dword s6, s[4:5], 0xb
; SI-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: v_mov_b32_e32 v0, s6
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
; SI-NEXT: s_endpgm
;
; GFX89-LABEL: scalar_to_vector_test6:
; GFX89: ; %bb.0:
; GFX89-NEXT: s_load_dword s6, s[4:5], 0x2c
; GFX89-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x24
; GFX89-NEXT: s_mov_b32 s3, 0xf000
; GFX89-NEXT: s_mov_b32 s2, -1
; GFX89-NEXT: s_waitcnt lgkmcnt(0)
; GFX89-NEXT: v_mov_b32_e32 v0, s6
; GFX89-NEXT: buffer_store_dword v0, off, s[0:3], 0
; GFX89-NEXT: s_endpgm
%newvec0 = insertelement <4 x i8> undef, i8 %val, i32 0
%bc = bitcast <4 x i8> %newvec0 to <2 x half>
store <2 x half> %bc, ptr addrspace(1) %out
ret void
}
; bitcast (scalar_to_vector x) -> any_extend x
define i64 @bitcast_combine_scalar_to_vector_v4i16(i16 %arg) {
; SI-LABEL: bitcast_combine_scalar_to_vector_v4i16:
; SI: ; %bb.0:
; SI-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; SI-NEXT: v_and_b32_e32 v1, 0xffff, v0
; SI-NEXT: v_and_b32_e32 v2, 0xff00, v0
; SI-NEXT: v_bfe_u32 v0, v0, 8, 8
; SI-NEXT: v_or_b32_e32 v2, v0, v2
; SI-NEXT: v_lshlrev_b32_e32 v3, 16, v2
; SI-NEXT: v_or_b32_e32 v0, v1, v3
; SI-NEXT: v_or_b32_e32 v1, v2, v3
; SI-NEXT: s_setpc_b64 s[30:31]
;
; GFX89-LABEL: bitcast_combine_scalar_to_vector_v4i16:
; GFX89: ; %bb.0:
; GFX89-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX89-NEXT: v_and_b32_e32 v1, 0xffffff00, v0
; GFX89-NEXT: v_or_b32_sdwa v1, v0, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:BYTE_1 src1_sel:DWORD
; GFX89-NEXT: v_lshlrev_b32_e32 v2, 16, v1
; GFX89-NEXT: v_or_b32_sdwa v1, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX89-NEXT: v_or_b32_sdwa v0, v0, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
; GFX89-NEXT: s_setpc_b64 s[30:31]
%arg.cast = bitcast i16 %arg to <2 x i8>
%tmp1 = shufflevector <2 x i8> %arg.cast, <2 x i8> poison, <8 x i32> <i32 0, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> poison, <8 x i32> <i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
%cast = bitcast <8 x i8> %tmp2 to i64
ret i64 %cast
}
|
