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
|
;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck -check-prefix=VERDE %s
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s
;CHECK-LABEL: {{^}}buffer_store:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx4 v[0:3], off, s[0:3], 0
;CHECK: buffer_store_dwordx4 v[4:7], off, s[0:3], 0 glc
;CHECK: buffer_store_dwordx4 v[8:11], off, s[0:3], 0 slc
define amdgpu_ps void @buffer_store(<4 x i32> inreg, <4 x float>, <4 x float>, <4 x float>) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 0, i32 0, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %2, <4 x i32> %0, i32 0, i32 0, i1 1, i1 0)
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %3, <4 x i32> %0, i32 0, i32 0, i1 0, i1 1)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_immoffs:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx4 v[0:3], off, s[0:3], 0 offset:42
define amdgpu_ps void @buffer_store_immoffs(<4 x i32> inreg, <4 x float>) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 0, i32 42, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_idx:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx4 v[0:3], v4, s[0:3], 0 idxen
define amdgpu_ps void @buffer_store_idx(<4 x i32> inreg, <4 x float>, i32) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 %2, i32 0, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_ofs:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx4 v[0:3], v4, s[0:3], 0 offen
define amdgpu_ps void @buffer_store_ofs(<4 x i32> inreg, <4 x float>, i32) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 0, i32 %2, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_both:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx4 v[0:3], v[4:5], s[0:3], 0 idxen offen
define amdgpu_ps void @buffer_store_both(<4 x i32> inreg, <4 x float>, i32, i32) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 %2, i32 %3, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_both_reversed:
;CHECK: v_mov_b32_e32 v6, v4
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx4 v[0:3], v[5:6], s[0:3], 0 idxen offen
define amdgpu_ps void @buffer_store_both_reversed(<4 x i32> inreg, <4 x float>, i32, i32) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 %3, i32 %2, i1 0, i1 0)
ret void
}
; Ideally, the register allocator would avoid the wait here
;
;CHECK-LABEL: {{^}}buffer_store_wait:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx4 v[0:3], v4, s[0:3], 0 idxen
;VERDE: s_waitcnt expcnt(0)
;CHECK: buffer_load_dwordx4 v[0:3], v5, s[0:3], 0 idxen
;CHECK: s_waitcnt vmcnt(0)
;CHECK: buffer_store_dwordx4 v[0:3], v6, s[0:3], 0 idxen
define amdgpu_ps void @buffer_store_wait(<4 x i32> inreg, <4 x float>, i32, i32, i32) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 %2, i32 0, i1 0, i1 0)
%data = call <4 x float> @llvm.amdgcn.buffer.load.v4f32(<4 x i32> %0, i32 %3, i32 0, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %data, <4 x i32> %0, i32 %4, i32 0, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x1:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dword v0, v1, s[0:3], 0 idxen
define amdgpu_ps void @buffer_store_x1(<4 x i32> inreg %rsrc, float %data, i32 %index) {
main_body:
call void @llvm.amdgcn.buffer.store.f32(float %data, <4 x i32> %rsrc, i32 %index, i32 0, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x2:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx2 v[0:1], v2, s[0:3], 0 idxen
define amdgpu_ps void @buffer_store_x2(<4 x i32> inreg %rsrc, <2 x float> %data, i32 %index) #0 {
main_body:
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %data, <4 x i32> %rsrc, i32 %index, i32 0, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x1_offen_merged:
;CHECK-NOT: s_waitcnt
;CHECK-DAG: buffer_store_dwordx4 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:4
;CHECK-DAG: buffer_store_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:28
define amdgpu_ps void @buffer_store_x1_offen_merged(<4 x i32> inreg %rsrc, i32 %a, float %v1, float %v2, float %v3, float %v4, float %v5, float %v6) {
%a1 = add i32 %a, 4
%a2 = add i32 %a, 8
%a3 = add i32 %a, 12
%a4 = add i32 %a, 16
%a5 = add i32 %a, 28
%a6 = add i32 %a, 32
call void @llvm.amdgcn.buffer.store.f32(float %v1, <4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v2, <4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v3, <4 x i32> %rsrc, i32 0, i32 %a3, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v4, <4 x i32> %rsrc, i32 0, i32 %a4, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v5, <4 x i32> %rsrc, i32 0, i32 %a5, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v6, <4 x i32> %rsrc, i32 0, i32 %a6, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x1_offen_merged_glc_slc:
;CHECK-NOT: s_waitcnt
;CHECK-DAG: buffer_store_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:4{{$}}
;CHECK-DAG: buffer_store_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:12 glc{{$}}
;CHECK-DAG: buffer_store_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:28 glc slc{{$}}
define amdgpu_ps void @buffer_store_x1_offen_merged_glc_slc(<4 x i32> inreg %rsrc, i32 %a, float %v1, float %v2, float %v3, float %v4, float %v5, float %v6) {
%a1 = add i32 %a, 4
%a2 = add i32 %a, 8
%a3 = add i32 %a, 12
%a4 = add i32 %a, 16
%a5 = add i32 %a, 28
%a6 = add i32 %a, 32
call void @llvm.amdgcn.buffer.store.f32(float %v1, <4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v2, <4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v3, <4 x i32> %rsrc, i32 0, i32 %a3, i1 1, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v4, <4 x i32> %rsrc, i32 0, i32 %a4, i1 1, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v5, <4 x i32> %rsrc, i32 0, i32 %a5, i1 1, i1 1)
call void @llvm.amdgcn.buffer.store.f32(float %v6, <4 x i32> %rsrc, i32 0, i32 %a6, i1 1, i1 1)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x2_offen_merged:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx4 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:4
define amdgpu_ps void @buffer_store_x2_offen_merged(<4 x i32> inreg %rsrc, i32 %a, <2 x float> %v1, <2 x float> %v2) {
%a1 = add i32 %a, 4
%a2 = add i32 %a, 12
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v1, <4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v2, <4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x3_offen_merged:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx3 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:28
define amdgpu_ps void @buffer_store_x3_offen_merged(<4 x i32> inreg %rsrc, i32 %a, float %v1, float %v2, float %v3) {
%a1 = add i32 %a, 28
%a2 = add i32 %a, 32
%a3 = add i32 %a, 36
call void @llvm.amdgcn.buffer.store.f32(float %v1, <4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v2, <4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v3, <4 x i32> %rsrc, i32 0, i32 %a3, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x3_offen_merged2:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx3 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:4
define amdgpu_ps void @buffer_store_x3_offen_merged2(<4 x i32> inreg %rsrc, i32 %a, <2 x float> %v1, float %v2) {
%a1 = add i32 %a, 4
%a2 = add i32 %a, 12
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v1, <4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v2, <4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x3_offen_merged3:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx3 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:4
define amdgpu_ps void @buffer_store_x3_offen_merged3(<4 x i32> inreg %rsrc, i32 %a, float %v1, <2 x float> %v2) {
%a1 = add i32 %a, 4
%a2 = add i32 %a, 8
call void @llvm.amdgcn.buffer.store.f32(float %v1, <4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v2, <4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x1_offset_merged:
;CHECK-NOT: s_waitcnt
;CHECK-DAG: buffer_store_dwordx4 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:4
;CHECK-DAG: buffer_store_dwordx2 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:28
define amdgpu_ps void @buffer_store_x1_offset_merged(<4 x i32> inreg %rsrc, float %v1, float %v2, float %v3, float %v4, float %v5, float %v6) {
call void @llvm.amdgcn.buffer.store.f32(float %v1, <4 x i32> %rsrc, i32 0, i32 4, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v2, <4 x i32> %rsrc, i32 0, i32 8, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v3, <4 x i32> %rsrc, i32 0, i32 12, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v4, <4 x i32> %rsrc, i32 0, i32 16, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v5, <4 x i32> %rsrc, i32 0, i32 28, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v6, <4 x i32> %rsrc, i32 0, i32 32, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x2_offset_merged:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx4 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:4
define amdgpu_ps void @buffer_store_x2_offset_merged(<4 x i32> inreg %rsrc, <2 x float> %v1, <2 x float> %v2) {
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v1, <4 x i32> %rsrc, i32 0, i32 4, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v2, <4 x i32> %rsrc, i32 0, i32 12, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x3_offset_merged:
;CHECK-NOT: s_waitcnt
;CHECK-DAG: buffer_store_dwordx3 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:4
define amdgpu_ps void @buffer_store_x3_offset_merged(<4 x i32> inreg %rsrc, float %v1, float %v2, float %v3) {
call void @llvm.amdgcn.buffer.store.f32(float %v1, <4 x i32> %rsrc, i32 0, i32 4, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v2, <4 x i32> %rsrc, i32 0, i32 8, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v3, <4 x i32> %rsrc, i32 0, i32 12, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x3_offset_merged2:
;CHECK-NOT: s_waitcnt
;CHECK-DAG: buffer_store_dwordx3 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:4
define amdgpu_ps void @buffer_store_x3_offset_merged2(<4 x i32> inreg %rsrc, float %v1, <2 x float> %v2) {
call void @llvm.amdgcn.buffer.store.f32(float %v1, <4 x i32> %rsrc, i32 0, i32 4, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v2, <4 x i32> %rsrc, i32 0, i32 8, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x3_offset_merged3:
;CHECK-NOT: s_waitcnt
;CHECK-DAG: buffer_store_dwordx3 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:8
define amdgpu_ps void @buffer_store_x3_offset_merged3(<4 x i32> inreg %rsrc, <2 x float> %v1, float %v2) {
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v1, <4 x i32> %rsrc, i32 0, i32 8, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v2, <4 x i32> %rsrc, i32 0, i32 16, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_byte:
;CHECK-NOT: s_waitcnt
;CHECK-NEXT: %bb.
;CHECK: buffer_store_byte v{{[0-9]}}, off, s[0:3], 0 offset:8
define amdgpu_ps void @buffer_store_byte(<4 x i32> inreg %rsrc, float %v1) {
main_body:
%v2 = fptoui float %v1 to i32
%v3 = trunc i32 %v2 to i8
call void @llvm.amdgcn.buffer.store.i8(i8 %v3, <4 x i32> %rsrc, i32 0, i32 8, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_short:
;CHECK-NOT: s_waitcnt
;CHECK-NEXT: %bb.
;CHECK: buffer_store_short v{{[0-9]}}, off, s[0:3], 0 offset:16
define amdgpu_ps void @buffer_store_short(<4 x i32> inreg %rsrc, float %v1) {
main_body:
%v2 = fptoui float %v1 to i32
%v3 = trunc i32 %v2 to i16
call void @llvm.amdgcn.buffer.store.i16(i16 %v3, <4 x i32> %rsrc, i32 0, i32 16, i1 0, i1 0)
ret void
}
declare void @llvm.amdgcn.buffer.store.f32(float, <4 x i32>, i32, i32, i1, i1) #0
declare void @llvm.amdgcn.buffer.store.v2f32(<2 x float>, <4 x i32>, i32, i32, i1, i1) #0
declare void @llvm.amdgcn.buffer.store.v4f32(<4 x float>, <4 x i32>, i32, i32, i1, i1) #0
declare void @llvm.amdgcn.buffer.store.i8(i8, <4 x i32>, i32, i32, i1, i1) #0
declare void @llvm.amdgcn.buffer.store.i16(i16, <4 x i32>, i32, i32, i1, i1) #0
declare <4 x float> @llvm.amdgcn.buffer.load.v4f32(<4 x i32>, i32, i32, i1, i1) #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readonly }
|
