spill-vgpr-to-agpr.ll
14 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
; RUN: llc -march=amdgcn -mcpu=gfx908 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX908 %s
; RUN: not llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefixes=GCN,GFX900 %s
; GCN-LABEL: {{^}}max_10_vgprs:
; GFX900-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
; GFX900-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
; GFX908-NOT: SCRATCH_RSRC
; GFX908-DAG: v_accvgpr_write_b32 a0, v{{[0-9]}}
; GFX908-DAG: v_accvgpr_write_b32 a1, v{{[0-9]}}
; GFX900: buffer_store_dword v{{[0-9]}},
; GFX900: buffer_store_dword v{{[0-9]}},
; GFX900: buffer_load_dword v{{[0-9]}},
; GFX900: buffer_load_dword v{{[0-9]}},
; GFX908-NOT: buffer_
; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a0
; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a1
; GCN: NumVgprs: 10
; GFX900: ScratchSize: 12
; GFX908: ScratchSize: 0
; GCN: VGPRBlocks: 2
; GCN: NumVGPRsForWavesPerEU: 10
define amdgpu_kernel void @max_10_vgprs(i32 addrspace(1)* %p) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%p1 = getelementptr inbounds i32, i32 addrspace(1)* %p, i32 %tid
%p2 = getelementptr inbounds i32, i32 addrspace(1)* %p1, i32 4
%p3 = getelementptr inbounds i32, i32 addrspace(1)* %p2, i32 8
%p4 = getelementptr inbounds i32, i32 addrspace(1)* %p3, i32 12
%p5 = getelementptr inbounds i32, i32 addrspace(1)* %p4, i32 16
%p6 = getelementptr inbounds i32, i32 addrspace(1)* %p5, i32 20
%p7 = getelementptr inbounds i32, i32 addrspace(1)* %p6, i32 24
%p8 = getelementptr inbounds i32, i32 addrspace(1)* %p7, i32 28
%p9 = getelementptr inbounds i32, i32 addrspace(1)* %p8, i32 32
%p10 = getelementptr inbounds i32, i32 addrspace(1)* %p9, i32 36
%v1 = load volatile i32, i32 addrspace(1)* %p1
%v2 = load volatile i32, i32 addrspace(1)* %p2
%v3 = load volatile i32, i32 addrspace(1)* %p3
%v4 = load volatile i32, i32 addrspace(1)* %p4
%v5 = load volatile i32, i32 addrspace(1)* %p5
%v6 = load volatile i32, i32 addrspace(1)* %p6
%v7 = load volatile i32, i32 addrspace(1)* %p7
%v8 = load volatile i32, i32 addrspace(1)* %p8
%v9 = load volatile i32, i32 addrspace(1)* %p9
%v10 = load volatile i32, i32 addrspace(1)* %p10
call void asm sideeffect "", "v,v,v,v,v,v,v,v,v,v"(i32 %v1, i32 %v2, i32 %v3, i32 %v4, i32 %v5, i32 %v6, i32 %v7, i32 %v8, i32 %v9, i32 %v10)
store volatile i32 %v1, i32 addrspace(1)* undef
store volatile i32 %v2, i32 addrspace(1)* undef
store volatile i32 %v3, i32 addrspace(1)* undef
store volatile i32 %v4, i32 addrspace(1)* undef
store volatile i32 %v5, i32 addrspace(1)* undef
store volatile i32 %v6, i32 addrspace(1)* undef
store volatile i32 %v7, i32 addrspace(1)* undef
store volatile i32 %v8, i32 addrspace(1)* undef
store volatile i32 %v9, i32 addrspace(1)* undef
store volatile i32 %v10, i32 addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}max_10_vgprs_used_9a:
; GFX908-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
; GFX908-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
; GFX908-DAG: v_accvgpr_write_b32 a9, v{{[0-9]}}
; GFX908: buffer_store_dword v{{[0-9]}},
; GFX908-NOT: buffer_
; GFX908: v_accvgpr_read_b32 v{{[0-9]}}, a9
; GFX908: buffer_load_dword v{{[0-9]}},
; GFX908-NOT: buffer_
; GFX900: couldn't allocate input reg for constraint 'a'
; GFX908: NumVgprs: 10
; GFX908: ScratchSize: 8
; GFX908: VGPRBlocks: 2
; GFX908: NumVGPRsForWavesPerEU: 10
define amdgpu_kernel void @max_10_vgprs_used_9a(i32 addrspace(1)* %p) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
call void asm sideeffect "", "a,a,a,a,a,a,a,a,a"(i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9)
%p1 = getelementptr inbounds i32, i32 addrspace(1)* %p, i32 %tid
%p2 = getelementptr inbounds i32, i32 addrspace(1)* %p1, i32 4
%p3 = getelementptr inbounds i32, i32 addrspace(1)* %p2, i32 8
%p4 = getelementptr inbounds i32, i32 addrspace(1)* %p3, i32 12
%p5 = getelementptr inbounds i32, i32 addrspace(1)* %p4, i32 16
%p6 = getelementptr inbounds i32, i32 addrspace(1)* %p5, i32 20
%p7 = getelementptr inbounds i32, i32 addrspace(1)* %p6, i32 24
%p8 = getelementptr inbounds i32, i32 addrspace(1)* %p7, i32 28
%p9 = getelementptr inbounds i32, i32 addrspace(1)* %p8, i32 32
%p10 = getelementptr inbounds i32, i32 addrspace(1)* %p9, i32 36
%v1 = load volatile i32, i32 addrspace(1)* %p1
%v2 = load volatile i32, i32 addrspace(1)* %p2
%v3 = load volatile i32, i32 addrspace(1)* %p3
%v4 = load volatile i32, i32 addrspace(1)* %p4
%v5 = load volatile i32, i32 addrspace(1)* %p5
%v6 = load volatile i32, i32 addrspace(1)* %p6
%v7 = load volatile i32, i32 addrspace(1)* %p7
%v8 = load volatile i32, i32 addrspace(1)* %p8
%v9 = load volatile i32, i32 addrspace(1)* %p9
%v10 = load volatile i32, i32 addrspace(1)* %p10
call void asm sideeffect "", "v,v,v,v,v,v,v,v,v,v"(i32 %v1, i32 %v2, i32 %v3, i32 %v4, i32 %v5, i32 %v6, i32 %v7, i32 %v8, i32 %v9, i32 %v10)
store volatile i32 %v1, i32 addrspace(1)* undef
store volatile i32 %v2, i32 addrspace(1)* undef
store volatile i32 %v3, i32 addrspace(1)* undef
store volatile i32 %v4, i32 addrspace(1)* undef
store volatile i32 %v5, i32 addrspace(1)* undef
store volatile i32 %v6, i32 addrspace(1)* undef
store volatile i32 %v7, i32 addrspace(1)* undef
store volatile i32 %v8, i32 addrspace(1)* undef
store volatile i32 %v9, i32 addrspace(1)* undef
store volatile i32 %v10, i32 addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}max_10_vgprs_used_1a_partial_spill:
; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
; GFX908-DAG: v_accvgpr_write_b32 a0, 1
; GFX908-DAG: v_accvgpr_write_b32 a1, v{{[0-9]}}
; GFX908-DAG: v_accvgpr_write_b32 a2, v{{[0-9]}}
; GFX908-DAG: v_accvgpr_write_b32 a3, v{{[0-9]}}
; GFX908-DAG: v_accvgpr_write_b32 a4, v{{[0-9]}}
; GFX908-DAG: v_accvgpr_write_b32 a5, v{{[0-9]}}
; GFX908-DAG: v_accvgpr_write_b32 a6, v{{[0-9]}}
; GFX908-DAG: v_accvgpr_write_b32 a7, v{{[0-9]}}
; GFX908-DAG: v_accvgpr_write_b32 a8, v{{[0-9]}}
; GFX908-DAG: v_accvgpr_write_b32 a9, v{{[0-9]}}
; GFX900: buffer_store_dword v{{[0-9]}},
; GCN-DAG: buffer_store_dword v{{[0-9]}},
; GFX900: buffer_load_dword v{{[0-9]}},
; GCN-DAG: buffer_load_dword v{{[0-9]}},
; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a1
; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a2
; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a3
; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a4
; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a5
; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a6
; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a7
; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a8
; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a9
; GCN: NumVgprs: 10
; GFX900: ScratchSize: 44
; GFX908: ScratchSize: 20
; GCN: VGPRBlocks: 2
; GCN: NumVGPRsForWavesPerEU: 10
define amdgpu_kernel void @max_10_vgprs_used_1a_partial_spill(i64 addrspace(1)* %p) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
call void asm sideeffect "", "a"(i32 1)
%p1 = getelementptr inbounds i64, i64 addrspace(1)* %p, i32 %tid
%p2 = getelementptr inbounds i64, i64 addrspace(1)* %p1, i32 8
%p3 = getelementptr inbounds i64, i64 addrspace(1)* %p2, i32 16
%p4 = getelementptr inbounds i64, i64 addrspace(1)* %p3, i32 24
%p5 = getelementptr inbounds i64, i64 addrspace(1)* %p4, i32 32
%v1 = load volatile i64, i64 addrspace(1)* %p1
%v2 = load volatile i64, i64 addrspace(1)* %p2
%v3 = load volatile i64, i64 addrspace(1)* %p3
%v4 = load volatile i64, i64 addrspace(1)* %p4
%v5 = load volatile i64, i64 addrspace(1)* %p5
call void asm sideeffect "", "v,v,v,v,v"(i64 %v1, i64 %v2, i64 %v3, i64 %v4, i64 %v5)
store volatile i64 %v1, i64 addrspace(1)* %p2
store volatile i64 %v2, i64 addrspace(1)* %p3
store volatile i64 %v3, i64 addrspace(1)* %p4
store volatile i64 %v4, i64 addrspace(1)* %p5
store volatile i64 %v5, i64 addrspace(1)* %p1
ret void
}
; GCN-LABEL: {{^}}max_10_vgprs_spill_v32:
; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
; GFX908-DAG: v_accvgpr_write_b32 a0,
; GFX908-DAG: v_accvgpr_write_b32 a9, v{{[0-9]}}
; GCN-NOT: a10
; GCN: buffer_store_dword v{{[0-9]}},
; GFX908: NumVgprs: 10
; GFX900: ScratchSize: 100
; GFX908: ScratchSize: 68
; GFX908: VGPRBlocks: 2
; GFX908: NumVGPRsForWavesPerEU: 10
define amdgpu_kernel void @max_10_vgprs_spill_v32(<32 x float> addrspace(1)* %p) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p, i32 %tid
%v = load volatile <32 x float>, <32 x float> addrspace(1)* %gep
store volatile <32 x float> %v, <32 x float> addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}max_256_vgprs_spill_9x32:
; GFX900-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
; GFX900-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
; GFX908-NOT: SCRATCH_RSRC
; GFX908-DAG: v_accvgpr_write_b32 a0, v
; GFX900: buffer_store_dword v
; GFX900: buffer_load_dword v
; GFX908-NOT: buffer_
; GFX908-DAG: v_accvgpr_read_b32
; GCN: NumVgprs: 256
; GFX900: ScratchSize: 148
; GFX908: ScratchSize: 0
; GCN: VGPRBlocks: 63
; GCN: NumVGPRsForWavesPerEU: 256
define amdgpu_kernel void @max_256_vgprs_spill_9x32(<32 x float> addrspace(1)* %p) #1 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%p1 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p, i32 %tid
%p2 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p1, i32 %tid
%p3 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p2, i32 %tid
%p4 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p3, i32 %tid
%p5 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p4, i32 %tid
%p6 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p5, i32 %tid
%p7 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p6, i32 %tid
%p8 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p7, i32 %tid
%p9 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p8, i32 %tid
%v1 = load volatile <32 x float>, <32 x float> addrspace(1)* %p1
%v2 = load volatile <32 x float>, <32 x float> addrspace(1)* %p2
%v3 = load volatile <32 x float>, <32 x float> addrspace(1)* %p3
%v4 = load volatile <32 x float>, <32 x float> addrspace(1)* %p4
%v5 = load volatile <32 x float>, <32 x float> addrspace(1)* %p5
%v6 = load volatile <32 x float>, <32 x float> addrspace(1)* %p6
%v7 = load volatile <32 x float>, <32 x float> addrspace(1)* %p7
%v8 = load volatile <32 x float>, <32 x float> addrspace(1)* %p8
%v9 = load volatile <32 x float>, <32 x float> addrspace(1)* %p9
store volatile <32 x float> %v1, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v2, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v3, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v4, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v5, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v6, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v7, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v8, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v9, <32 x float> addrspace(1)* undef
ret void
}
; FIXME: adding an AReg_1024 register class for v32f32 and v32i32
; produces unnecessary copies and we still have some amount
; of conventional spilling.
; GCN-LABEL: {{^}}max_256_vgprs_spill_9x32_2bb:
; GFX900-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
; GFX900-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
; GFX908-FIXME-NOT: SCRATCH_RSRC
; GFX908-DAG: v_accvgpr_write_b32 a0, v
; GFX900: buffer_store_dword v
; GFX900: buffer_load_dword v
; GFX908-FIXME-NOT: buffer_
; GFX908-DAG: v_accvgpr_read_b32
; GCN: NumVgprs: 256
; GFX900: ScratchSize: 2052
; GFX908-FIXME: ScratchSize: 0
; GCN: VGPRBlocks: 63
; GCN: NumVGPRsForWavesPerEU: 256
define amdgpu_kernel void @max_256_vgprs_spill_9x32_2bb(<32 x float> addrspace(1)* %p) #1 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%p1 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p, i32 %tid
%p2 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p1, i32 %tid
%p3 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p2, i32 %tid
%p4 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p3, i32 %tid
%p5 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p4, i32 %tid
%p6 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p5, i32 %tid
%p7 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p6, i32 %tid
%p8 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p7, i32 %tid
%p9 = getelementptr inbounds <32 x float>, <32 x float> addrspace(1)* %p8, i32 %tid
%v1 = load volatile <32 x float>, <32 x float> addrspace(1)* %p1
%v2 = load volatile <32 x float>, <32 x float> addrspace(1)* %p2
%v3 = load volatile <32 x float>, <32 x float> addrspace(1)* %p3
%v4 = load volatile <32 x float>, <32 x float> addrspace(1)* %p4
%v5 = load volatile <32 x float>, <32 x float> addrspace(1)* %p5
%v6 = load volatile <32 x float>, <32 x float> addrspace(1)* %p6
%v7 = load volatile <32 x float>, <32 x float> addrspace(1)* %p7
%v8 = load volatile <32 x float>, <32 x float> addrspace(1)* %p8
%v9 = load volatile <32 x float>, <32 x float> addrspace(1)* %p9
br label %st
st:
store volatile <32 x float> %v1, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v2, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v3, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v4, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v5, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v6, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v7, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v8, <32 x float> addrspace(1)* undef
store volatile <32 x float> %v9, <32 x float> addrspace(1)* undef
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x()
attributes #0 = { nounwind "amdgpu-num-vgpr"="10" }
attributes #1 = { "amdgpu-flat-work-group-size"="1,256" }