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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck %s
; Check that nofpclass attributes on call returns are used in
; selectiondag.
define internal float @func_f32(ptr addrspace(1) %ptr) {
; CHECK-LABEL: func_f32:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: global_load_dword v0, v[0:1], off glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
%ld = load volatile float, ptr addrspace(1) %ptr
ret float %ld
}
define float @call_nofpclass_funcs_f32(ptr addrspace(1) %ptr) {
; CHECK-LABEL: call_nofpclass_funcs_f32:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: s_mov_b32 s18, s33
; CHECK-NEXT: s_mov_b32 s33, s32
; CHECK-NEXT: s_xor_saveexec_b64 s[16:17], -1
; CHECK-NEXT: buffer_store_dword v4, off, s[0:3], s33 ; 4-byte Folded Spill
; CHECK-NEXT: s_mov_b64 exec, s[16:17]
; CHECK-NEXT: s_addk_i32 s32, 0x400
; CHECK-NEXT: v_writelane_b32 v4, s30, 0
; CHECK-NEXT: s_getpc_b64 s[16:17]
; CHECK-NEXT: s_add_u32 s16, s16, func_f32@rel32@lo+4
; CHECK-NEXT: s_addc_u32 s17, s17, func_f32@rel32@hi+12
; CHECK-NEXT: v_writelane_b32 v4, s31, 1
; CHECK-NEXT: v_mov_b32_e32 v2, v0
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_mov_b32_e32 v3, v0
; CHECK-NEXT: v_mov_b32_e32 v0, v2
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_min_f32_e32 v0, v3, v0
; CHECK-NEXT: v_readlane_b32 s31, v4, 1
; CHECK-NEXT: v_readlane_b32 s30, v4, 0
; CHECK-NEXT: s_mov_b32 s32, s33
; CHECK-NEXT: s_xor_saveexec_b64 s[4:5], -1
; CHECK-NEXT: buffer_load_dword v4, off, s[0:3], s33 ; 4-byte Folded Reload
; CHECK-NEXT: s_mov_b64 exec, s[4:5]
; CHECK-NEXT: s_mov_b32 s33, s18
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
%call0 = call nofpclass(nan) float @func_f32(ptr addrspace(1) %ptr)
%call1 = call nofpclass(nan) float @func_f32(ptr addrspace(1) %ptr)
%min = call float @llvm.minnum.f32(float %call0, float %call1)
ret float %min
}
define internal <2 x float> @func_v2f32(ptr addrspace(1) %ptr) {
; CHECK-LABEL: func_v2f32:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: global_load_dwordx2 v[0:1], v[0:1], off glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
%ld = load volatile <2 x float>, ptr addrspace(1) %ptr
ret <2 x float> %ld
}
define <2 x float> @call_nofpclass_funcs_v2f32(ptr addrspace(1) %ptr) {
; CHECK-LABEL: call_nofpclass_funcs_v2f32:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: s_mov_b32 s18, s33
; CHECK-NEXT: s_mov_b32 s33, s32
; CHECK-NEXT: s_xor_saveexec_b64 s[16:17], -1
; CHECK-NEXT: buffer_store_dword v6, off, s[0:3], s33 ; 4-byte Folded Spill
; CHECK-NEXT: s_mov_b64 exec, s[16:17]
; CHECK-NEXT: s_addk_i32 s32, 0x400
; CHECK-NEXT: v_writelane_b32 v6, s30, 0
; CHECK-NEXT: s_getpc_b64 s[16:17]
; CHECK-NEXT: s_add_u32 s16, s16, func_v2f32@rel32@lo+4
; CHECK-NEXT: s_addc_u32 s17, s17, func_v2f32@rel32@hi+12
; CHECK-NEXT: v_writelane_b32 v6, s31, 1
; CHECK-NEXT: v_mov_b32_e32 v2, v1
; CHECK-NEXT: v_mov_b32_e32 v3, v0
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_mov_b32_e32 v4, v0
; CHECK-NEXT: v_mov_b32_e32 v5, v1
; CHECK-NEXT: v_mov_b32_e32 v0, v3
; CHECK-NEXT: v_mov_b32_e32 v1, v2
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_min_f32_e32 v0, v4, v0
; CHECK-NEXT: v_min_f32_e32 v1, v5, v1
; CHECK-NEXT: v_readlane_b32 s31, v6, 1
; CHECK-NEXT: v_readlane_b32 s30, v6, 0
; CHECK-NEXT: s_mov_b32 s32, s33
; CHECK-NEXT: s_xor_saveexec_b64 s[4:5], -1
; CHECK-NEXT: buffer_load_dword v6, off, s[0:3], s33 ; 4-byte Folded Reload
; CHECK-NEXT: s_mov_b64 exec, s[4:5]
; CHECK-NEXT: s_mov_b32 s33, s18
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
%call0 = call nofpclass(nan) <2 x float> @func_v2f32(ptr addrspace(1) %ptr)
%call1 = call nofpclass(nan) <2 x float> @func_v2f32(ptr addrspace(1) %ptr)
%min = call <2 x float> @llvm.minnum.v2f32(<2 x float> %call0, <2 x float> %call1)
ret <2 x float> %min
}
define internal double @func_f64(ptr addrspace(1) %ptr) {
; CHECK-LABEL: func_f64:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: global_load_dwordx2 v[0:1], v[0:1], off glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
%ld = load volatile double, ptr addrspace(1) %ptr
ret double %ld
}
define double @call_nofpclass_funcs_f64(ptr addrspace(1) %ptr) {
; CHECK-LABEL: call_nofpclass_funcs_f64:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: s_mov_b32 s18, s33
; CHECK-NEXT: s_mov_b32 s33, s32
; CHECK-NEXT: s_xor_saveexec_b64 s[16:17], -1
; CHECK-NEXT: buffer_store_dword v6, off, s[0:3], s33 ; 4-byte Folded Spill
; CHECK-NEXT: s_mov_b64 exec, s[16:17]
; CHECK-NEXT: s_addk_i32 s32, 0x400
; CHECK-NEXT: v_writelane_b32 v6, s30, 0
; CHECK-NEXT: s_getpc_b64 s[16:17]
; CHECK-NEXT: s_add_u32 s16, s16, func_f64@rel32@lo+4
; CHECK-NEXT: s_addc_u32 s17, s17, func_f64@rel32@hi+12
; CHECK-NEXT: v_writelane_b32 v6, s31, 1
; CHECK-NEXT: v_mov_b32_e32 v4, v1
; CHECK-NEXT: v_mov_b32_e32 v5, v0
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_mov_b32_e32 v2, v0
; CHECK-NEXT: v_mov_b32_e32 v3, v1
; CHECK-NEXT: v_mov_b32_e32 v0, v5
; CHECK-NEXT: v_mov_b32_e32 v1, v4
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_min_f64 v[0:1], v[2:3], v[0:1]
; CHECK-NEXT: v_readlane_b32 s31, v6, 1
; CHECK-NEXT: v_readlane_b32 s30, v6, 0
; CHECK-NEXT: s_mov_b32 s32, s33
; CHECK-NEXT: s_xor_saveexec_b64 s[4:5], -1
; CHECK-NEXT: buffer_load_dword v6, off, s[0:3], s33 ; 4-byte Folded Reload
; CHECK-NEXT: s_mov_b64 exec, s[4:5]
; CHECK-NEXT: s_mov_b32 s33, s18
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
%call0 = call nofpclass(nan) double @func_f64(ptr addrspace(1) %ptr)
%call1 = call nofpclass(nan) double @func_f64(ptr addrspace(1) %ptr)
%min = call double @llvm.minnum.f64(double %call0, double %call1)
ret double %min
}
define float @call_nofpclass_intrinsic_f32(float %x, float %y, float %z) {
; CHECK-LABEL: call_nofpclass_intrinsic_f32:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: v_sqrt_f32_e32 v0, v0
; CHECK-NEXT: v_sqrt_f32_e32 v1, v1
; CHECK-NEXT: v_cmp_lt_f32_e32 vcc, v0, v1
; CHECK-NEXT: v_cndmask_b32_e32 v0, v1, v0, vcc
; CHECK-NEXT: s_setpc_b64 s[30:31]
%call0 = call nofpclass(nan) float @llvm.amdgcn.sqrt.f32(float %x)
%call1 = call nofpclass(nan) float @llvm.amdgcn.sqrt.f32(float %y)
%lt = fcmp olt float %call0, %call1
%min = select nsz i1 %lt, float %call0, float %call1
ret float %min
}
define <2 x half> @call_nofpclass_intrinsic_v2f16(float %x, float %y, float %z, float %w) {
; CHECK-LABEL: call_nofpclass_intrinsic_v2f16:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: v_cvt_pkrtz_f16_f32 v0, v0, v1
; CHECK-NEXT: v_cvt_pkrtz_f16_f32 v1, v2, v3
; CHECK-NEXT: v_lshrrev_b32_e32 v2, 16, v1
; CHECK-NEXT: v_lshrrev_b32_e32 v3, 16, v0
; CHECK-NEXT: v_cmp_lt_f16_e32 vcc, v0, v1
; CHECK-NEXT: v_cndmask_b32_e32 v0, v1, v0, vcc
; CHECK-NEXT: v_cmp_lt_f16_e32 vcc, v3, v2
; CHECK-NEXT: v_cndmask_b32_e32 v1, v2, v3, vcc
; CHECK-NEXT: s_mov_b32 s4, 0x5040100
; CHECK-NEXT: v_perm_b32 v0, v1, v0, s4
; CHECK-NEXT: s_setpc_b64 s[30:31]
%call0 = call nofpclass(nan) <2 x half> @llvm.amdgcn.cvt.pkrtz(float %x, float %y)
%call1 = call nofpclass(nan) <2 x half> @llvm.amdgcn.cvt.pkrtz(float %z, float %w)
%lt = fcmp olt <2 x half> %call0, %call1
%min = select nsz <2 x i1> %lt, <2 x half> %call0, <2 x half> %call1
ret <2 x half> %min
}
define nofpclass(nan inf) { double, double } @aggregate() {
; CHECK-LABEL: aggregate:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: s_mov_b32 s16, s33
; CHECK-NEXT: s_mov_b32 s33, s32
; CHECK-NEXT: s_or_saveexec_b64 s[18:19], -1
; CHECK-NEXT: buffer_store_dword v40, off, s[0:3], s33 ; 4-byte Folded Spill
; CHECK-NEXT: s_mov_b64 exec, s[18:19]
; CHECK-NEXT: s_addk_i32 s32, 0x400
; CHECK-NEXT: v_writelane_b32 v40, s16, 2
; CHECK-NEXT: s_getpc_b64 s[16:17]
; CHECK-NEXT: s_add_u32 s16, s16, aggregate@gotpcrel32@lo+4
; CHECK-NEXT: s_addc_u32 s17, s17, aggregate@gotpcrel32@hi+12
; CHECK-NEXT: s_load_dwordx2 s[16:17], s[16:17], 0x0
; CHECK-NEXT: v_writelane_b32 v40, s30, 0
; CHECK-NEXT: v_writelane_b32 v40, s31, 1
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_readlane_b32 s31, v40, 1
; CHECK-NEXT: v_readlane_b32 s30, v40, 0
; CHECK-NEXT: s_mov_b32 s32, s33
; CHECK-NEXT: v_readlane_b32 s4, v40, 2
; CHECK-NEXT: s_or_saveexec_b64 s[6:7], -1
; CHECK-NEXT: buffer_load_dword v40, off, s[0:3], s33 ; 4-byte Folded Reload
; CHECK-NEXT: s_mov_b64 exec, s[6:7]
; CHECK-NEXT: s_mov_b32 s33, s4
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
entry:
%call.i.i = call { double, double } @aggregate()
ret { double, double } %call.i.i
}
declare hidden nofpclass(nan inf) { float, float } @aggregate_f32()
define { float, float } @aggregate_use(float %z) {
; CHECK-LABEL: aggregate_use:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: s_mov_b32 s16, s33
; CHECK-NEXT: s_mov_b32 s33, s32
; CHECK-NEXT: s_or_saveexec_b64 s[18:19], -1
; CHECK-NEXT: buffer_store_dword v41, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
; CHECK-NEXT: s_mov_b64 exec, s[18:19]
; CHECK-NEXT: v_writelane_b32 v41, s16, 2
; CHECK-NEXT: s_addk_i32 s32, 0x400
; CHECK-NEXT: v_writelane_b32 v41, s30, 0
; CHECK-NEXT: s_getpc_b64 s[16:17]
; CHECK-NEXT: s_add_u32 s16, s16, aggregate_f32@rel32@lo+4
; CHECK-NEXT: s_addc_u32 s17, s17, aggregate_f32@rel32@hi+12
; CHECK-NEXT: buffer_store_dword v40, off, s[0:3], s33 ; 4-byte Folded Spill
; CHECK-NEXT: v_writelane_b32 v41, s31, 1
; CHECK-NEXT: v_mov_b32_e32 v40, v0
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_max_f32_e32 v2, v40, v40
; CHECK-NEXT: buffer_load_dword v40, off, s[0:3], s33 ; 4-byte Folded Reload
; CHECK-NEXT: v_min_f32_e32 v0, v0, v2
; CHECK-NEXT: v_min_f32_e32 v1, v1, v2
; CHECK-NEXT: v_readlane_b32 s31, v41, 1
; CHECK-NEXT: v_readlane_b32 s30, v41, 0
; CHECK-NEXT: s_mov_b32 s32, s33
; CHECK-NEXT: v_readlane_b32 s4, v41, 2
; CHECK-NEXT: s_or_saveexec_b64 s[6:7], -1
; CHECK-NEXT: buffer_load_dword v41, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
; CHECK-NEXT: s_mov_b64 exec, s[6:7]
; CHECK-NEXT: s_mov_b32 s33, s4
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
%call = call nofpclass(nan inf) { float, float } @aggregate_f32()
%i = extractvalue { float, float } %call, 0
%i1 = extractvalue { float, float } %call, 1
%min0 = call float @llvm.minnum.f32(float %i, float %z)
%min1 = call float @llvm.minnum.f32(float %i1, float %z)
%insert.0 = insertvalue { float, float } poison, float %min0, 0
%insert.1 = insertvalue { float, float } %insert.0, float %min1, 1
ret { float, float } %insert.1
}
define internal <5 x double> @func_v5f64(ptr addrspace(1) %ptr) {
; CHECK-LABEL: func_v5f64:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: v_mov_b32_e32 v11, v1
; CHECK-NEXT: v_mov_b32_e32 v10, v0
; CHECK-NEXT: global_load_dwordx4 v[0:3], v[10:11], off glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_load_dwordx4 v[4:7], v[10:11], off offset:16 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_load_dwordx2 v[8:9], v[10:11], off offset:32 glc
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
%ld = load volatile <5 x double>, ptr addrspace(1) %ptr
ret <5 x double> %ld
}
define <5 x double> @call_nofpclass_funcs_v5f64_non_mvt_vector(ptr addrspace(1) %ptr) {
; CHECK-LABEL: call_nofpclass_funcs_v5f64_non_mvt_vector:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: s_mov_b32 s18, s33
; CHECK-NEXT: s_mov_b32 s33, s32
; CHECK-NEXT: s_xor_saveexec_b64 s[16:17], -1
; CHECK-NEXT: buffer_store_dword v24, off, s[0:3], s33 ; 4-byte Folded Spill
; CHECK-NEXT: s_mov_b64 exec, s[16:17]
; CHECK-NEXT: s_addk_i32 s32, 0x400
; CHECK-NEXT: v_writelane_b32 v24, s30, 0
; CHECK-NEXT: s_getpc_b64 s[16:17]
; CHECK-NEXT: s_add_u32 s16, s16, func_v5f64@rel32@lo+4
; CHECK-NEXT: s_addc_u32 s17, s17, func_v5f64@rel32@hi+12
; CHECK-NEXT: v_writelane_b32 v24, s31, 1
; CHECK-NEXT: v_mov_b32_e32 v22, v1
; CHECK-NEXT: v_mov_b32_e32 v23, v0
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_mov_b32_e32 v12, v0
; CHECK-NEXT: v_mov_b32_e32 v13, v1
; CHECK-NEXT: v_mov_b32_e32 v0, v23
; CHECK-NEXT: v_mov_b32_e32 v1, v22
; CHECK-NEXT: v_mov_b32_e32 v14, v2
; CHECK-NEXT: v_mov_b32_e32 v15, v3
; CHECK-NEXT: v_mov_b32_e32 v16, v4
; CHECK-NEXT: v_mov_b32_e32 v17, v5
; CHECK-NEXT: v_mov_b32_e32 v18, v6
; CHECK-NEXT: v_mov_b32_e32 v19, v7
; CHECK-NEXT: v_mov_b32_e32 v20, v8
; CHECK-NEXT: v_mov_b32_e32 v21, v9
; CHECK-NEXT: s_swappc_b64 s[30:31], s[16:17]
; CHECK-NEXT: v_min_f64 v[0:1], v[12:13], v[0:1]
; CHECK-NEXT: v_min_f64 v[2:3], v[14:15], v[2:3]
; CHECK-NEXT: v_min_f64 v[4:5], v[16:17], v[4:5]
; CHECK-NEXT: v_min_f64 v[6:7], v[18:19], v[6:7]
; CHECK-NEXT: v_min_f64 v[8:9], v[20:21], v[8:9]
; CHECK-NEXT: v_readlane_b32 s31, v24, 1
; CHECK-NEXT: v_readlane_b32 s30, v24, 0
; CHECK-NEXT: s_mov_b32 s32, s33
; CHECK-NEXT: s_xor_saveexec_b64 s[4:5], -1
; CHECK-NEXT: buffer_load_dword v24, off, s[0:3], s33 ; 4-byte Folded Reload
; CHECK-NEXT: s_mov_b64 exec, s[4:5]
; CHECK-NEXT: s_mov_b32 s33, s18
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: s_setpc_b64 s[30:31]
%call0 = call nofpclass(nan) <5 x double> @func_v5f64(ptr addrspace(1) %ptr)
%call1 = call nofpclass(nan) <5 x double> @func_v5f64(ptr addrspace(1) %ptr)
%min = call <5 x double> @llvm.minnum.v5f64(<5 x double> %call0, <5 x double> %call1)
ret <5 x double> %min
}
|
