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
| ;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
;CHECK-LABEL: {{^}}buffer_load:
;CHECK: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen
;CHECK: buffer_load_dwordx4 v[4:7], {{v[0-9]+}}, s[0:3], 0 idxen glc
;CHECK: buffer_load_dwordx4 v[8:11], {{v[0-9]+}}, s[0:3], 0 idxen slc
;CHECK: s_waitcnt
define amdgpu_ps {<4 x float>, <4 x float>, <4 x float>} @buffer_load(<4 x i32> inreg) {
main_body:
%data = call <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 0)
%data_glc = call <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 1)
%data_slc = call <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 2)
%r0 = insertvalue {<4 x float>, <4 x float>, <4 x float>} undef, <4 x float> %data, 0
%r1 = insertvalue {<4 x float>, <4 x float>, <4 x float>} %r0, <4 x float> %data_glc, 1
%r2 = insertvalue {<4 x float>, <4 x float>, <4 x float>} %r1, <4 x float> %data_slc, 2
ret {<4 x float>, <4 x float>, <4 x float>} %r2
}
;CHECK-LABEL: {{^}}buffer_load_immoffs:
;CHECK: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:40
;CHECK: s_waitcnt
define amdgpu_ps <4 x float> @buffer_load_immoffs(<4 x i32> inreg) {
main_body:
%data = call <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 40, i32 0, i32 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_immoffs_large:
;CHECK: s_movk_i32 [[OFFSET:s[0-9]+]], 0x1ffc
;CHECK: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], [[OFFSET]] idxen offset:4
;CHECK: s_waitcnt
define amdgpu_ps <4 x float> @buffer_load_immoffs_large(<4 x i32> inreg) {
main_body:
%data = call <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 4, i32 8188, i32 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_idx:
;CHECK: buffer_load_dwordx4 v[0:3], v0, s[0:3], 0 idxen
;CHECK: s_waitcnt
define amdgpu_ps <4 x float> @buffer_load_idx(<4 x i32> inreg, i32) {
main_body:
%data = call <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32> %0, i32 %1, i32 0, i32 0, i32 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_ofs:
;CHECK: buffer_load_dwordx4 v[0:3], v[0:1], s[0:3], 0 idxen offen
;CHECK: s_waitcnt
define amdgpu_ps <4 x float> @buffer_load_ofs(<4 x i32> inreg, i32) {
main_body:
%data = call <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 %1, i32 0, i32 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_ofs_imm:
;CHECK: buffer_load_dwordx4 v[0:3], v[0:1], s[0:3], 0 idxen offen offset:60
;CHECK: s_waitcnt
define amdgpu_ps <4 x float> @buffer_load_ofs_imm(<4 x i32> inreg, i32) {
main_body:
%ofs = add i32 %1, 60
%data = call <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 %ofs, i32 0, i32 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_both:
;CHECK: buffer_load_dwordx4 v[0:3], v[0:1], s[0:3], 0 idxen offen
;CHECK: s_waitcnt
define amdgpu_ps <4 x float> @buffer_load_both(<4 x i32> inreg, i32, i32) {
main_body:
%data = call <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32> %0, i32 %1, i32 %2, i32 0, i32 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_both_reversed:
;CHECK: v_mov_b32_e32 v2, v0
;CHECK: buffer_load_dwordx4 v[0:3], v[1:2], s[0:3], 0 idxen offen
;CHECK: s_waitcnt
define amdgpu_ps <4 x float> @buffer_load_both_reversed(<4 x i32> inreg, i32, i32) {
main_body:
%data = call <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32> %0, i32 %2, i32 %1, i32 0, i32 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_x1:
;CHECK: buffer_load_dword v0, v[0:1], s[0:3], 0 idxen offen
;CHECK: s_waitcnt
define amdgpu_ps float @buffer_load_x1(<4 x i32> inreg %rsrc, i32 %idx, i32 %ofs) {
main_body:
%data = call float @llvm.amdgcn.struct.buffer.load.f32(<4 x i32> %rsrc, i32 %idx, i32 %ofs, i32 0, i32 0)
ret float %data
}
;CHECK-LABEL: {{^}}buffer_load_x2:
;CHECK: buffer_load_dwordx2 v[0:1], v[0:1], s[0:3], 0 idxen offen
;CHECK: s_waitcnt
define amdgpu_ps <2 x float> @buffer_load_x2(<4 x i32> inreg %rsrc, i32 %idx, i32 %ofs) {
main_body:
%data = call <2 x float> @llvm.amdgcn.struct.buffer.load.v2f32(<4 x i32> %rsrc, i32 %idx, i32 %ofs, i32 0, i32 0)
ret <2 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_negative_offset:
;CHECK: v_add_{{[iu]}}32_e32 {{v[0-9]+}}, vcc, -16, v0
;CHECK: buffer_load_dwordx4 v[0:3], {{v\[[0-9]+:[0-9]+\]}}, s[0:3], 0 idxen offen
define amdgpu_ps <4 x float> @buffer_load_negative_offset(<4 x i32> inreg, i32 %ofs) {
main_body:
%ofs.1 = add i32 %ofs, -16
%data = call <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 %ofs.1, i32 0, i32 0)
ret <4 x float> %data
}
; SI won't merge ds memory operations, because of the signed offset bug, so
; we only have check lines for VI.
; CHECK-LABEL: buffer_load_mmo:
; VI: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0
; VI: ds_write2_b32 v{{[0-9]+}}, [[ZERO]], [[ZERO]] offset1:4
define amdgpu_ps float @buffer_load_mmo(<4 x i32> inreg %rsrc, float addrspace(3)* %lds) {
entry:
store float 0.0, float addrspace(3)* %lds
%val = call float @llvm.amdgcn.struct.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%tmp2 = getelementptr float, float addrspace(3)* %lds, i32 4
store float 0.0, float addrspace(3)* %tmp2
ret float %val
}
;CHECK-LABEL: {{^}}buffer_load_int:
;CHECK: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen
;CHECK: buffer_load_dwordx2 v[4:5], {{v[0-9]+}}, s[0:3], 0 idxen glc
;CHECK: buffer_load_dword v6, {{v[0-9]+}}, s[0:3], 0 idxen slc
;CHECK: s_waitcnt
define amdgpu_ps {<4 x float>, <2 x float>, float} @buffer_load_int(<4 x i32> inreg) {
main_body:
%data = call <4 x i32> @llvm.amdgcn.struct.buffer.load.v4i32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 0)
%data_glc = call <2 x i32> @llvm.amdgcn.struct.buffer.load.v2i32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 1)
%data_slc = call i32 @llvm.amdgcn.struct.buffer.load.i32(<4 x i32> %0, i32 0, i32 0, i32 0, i32 2)
%fdata = bitcast <4 x i32> %data to <4 x float>
%fdata_glc = bitcast <2 x i32> %data_glc to <2 x float>
%fdata_slc = bitcast i32 %data_slc to float
%r0 = insertvalue {<4 x float>, <2 x float>, float} undef, <4 x float> %fdata, 0
%r1 = insertvalue {<4 x float>, <2 x float>, float} %r0, <2 x float> %fdata_glc, 1
%r2 = insertvalue {<4 x float>, <2 x float>, float} %r1, float %fdata_slc, 2
ret {<4 x float>, <2 x float>, float} %r2
}
;CHECK-LABEL: {{^}}struct_buffer_load_ubyte:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_ubyte v{{[0-9]}}, v[0:1], s[0:3], 0 idxen offen
;CHECK: s_waitcnt vmcnt(0)
;CHECK-NEXT: v_cvt_f32_ubyte0_e32 v0, v0
;CHECK-NEXT: ; return to shader part epilog
define amdgpu_ps float @struct_buffer_load_ubyte(<4 x i32> inreg %rsrc, i32 %idx, i32 %ofs) {
main_body:
%tmp = call i8 @llvm.amdgcn.struct.buffer.load.i8(<4 x i32> %rsrc, i32 %idx, i32 %ofs, i32 0, i32 0)
%tmp2 = zext i8 %tmp to i32
%val = uitofp i32 %tmp2 to float
ret float %val
}
;CHECK-LABEL: {{^}}struct_buffer_load_ushort:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_ushort v{{[0-9]}}, v[0:1], s[0:3], 0 idxen offen
;CHECK-NEXT: s_waitcnt vmcnt(0)
;CHECK-NEXT: v_cvt_f32_u32_e32 v0, v0
;CHECK-NEXT: ; return to shader part epilog
define amdgpu_ps float @struct_buffer_load_ushort(<4 x i32> inreg %rsrc, i32 %idx, i32 %ofs) {
main_body:
%tmp = call i16 @llvm.amdgcn.struct.buffer.load.i16(<4 x i32> %rsrc, i32 %idx, i32 %ofs, i32 0, i32 0)
%tmp2 = zext i16 %tmp to i32
%val = uitofp i32 %tmp2 to float
ret float %val
}
;CHECK-LABEL: {{^}}struct_buffer_load_sbyte:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_sbyte v{{[0-9]}}, v[0:1], s[0:3], 0 idxen offen
;CHECK-NEXT: s_waitcnt vmcnt(0)
;CHECK-NEXT: v_cvt_f32_i32_e32 v0, v0
;CHECK-NEXT: ; return to shader part epilog
define amdgpu_ps float @struct_buffer_load_sbyte(<4 x i32> inreg %rsrc, i32 %idx, i32 %ofs) {
main_body:
%tmp = call i8 @llvm.amdgcn.struct.buffer.load.i8(<4 x i32> %rsrc, i32 %idx, i32 %ofs, i32 0, i32 0)
%tmp2 = sext i8 %tmp to i32
%val = sitofp i32 %tmp2 to float
ret float %val
}
;CHECK-LABEL: {{^}}struct_buffer_load_sshort:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_sshort v{{[0-9]}}, v[0:1], s[0:3], 0 idxen offen
;CHECK-NEXT: s_waitcnt vmcnt(0)
;CHECK-NEXT: v_cvt_f32_i32_e32 v0, v0
;CHECK-NEXT: ; return to shader part epilog
define amdgpu_ps float @struct_buffer_load_sshort(<4 x i32> inreg %rsrc, i32 %idx, i32 %ofs) {
main_body:
%tmp = call i16 @llvm.amdgcn.struct.buffer.load.i16(<4 x i32> %rsrc, i32 %idx, i32 %ofs, i32 0, i32 0)
%tmp2 = sext i16 %tmp to i32
%val = sitofp i32 %tmp2 to float
ret float %val
}
;CHECK-LABEL: {{^}}struct_buffer_load_f16:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_ushort [[VAL:v[0-9]+]], v1, s[0:3], 0 idxen
;CHECK: s_waitcnt vmcnt(0)
;CHECK: ds_write_b16 v0, [[VAL]]
define amdgpu_ps void @struct_buffer_load_f16(<4 x i32> inreg %rsrc, half addrspace(3)* %ptr, i32 %idx) {
main_body:
%val = call half @llvm.amdgcn.struct.buffer.load.f16(<4 x i32> %rsrc, i32 %idx, i32 0, i32 0, i32 0)
store half %val, half addrspace(3)* %ptr
ret void
}
;CHECK-LABEL: {{^}}struct_buffer_load_v2f16:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_dword [[VAL:v[0-9]+]], v1, s[0:3], 0 idxen
;CHECK: s_waitcnt vmcnt(0)
;CHECK: ds_write_b32 v0, [[VAL]]
define amdgpu_ps void @struct_buffer_load_v2f16(<4 x i32> inreg %rsrc, <2 x half> addrspace(3)* %ptr, i32 %idx) {
main_body:
%val = call <2 x half> @llvm.amdgcn.struct.buffer.load.v2f16(<4 x i32> %rsrc, i32 %idx, i32 0, i32 0, i32 0)
store <2 x half> %val, <2 x half> addrspace(3)* %ptr
ret void
}
;CHECK-LABEL: {{^}}struct_buffer_load_v4f16:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]], v1, s[0:3], 0 idxen
;CHECK: s_waitcnt vmcnt(0)
;CHECK: ds_write_b64 v0, [[VAL]]
define amdgpu_ps void @struct_buffer_load_v4f16(<4 x i32> inreg %rsrc, <4 x half> addrspace(3)* %ptr, i32 %idx) {
main_body:
%val = call <4 x half> @llvm.amdgcn.struct.buffer.load.v4f16(<4 x i32> %rsrc, i32 %idx, i32 0, i32 0, i32 0)
store <4 x half> %val, <4 x half> addrspace(3)* %ptr
ret void
}
;CHECK-LABEL: {{^}}struct_buffer_load_i16:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_ushort [[VAL:v[0-9]+]], v1, s[0:3], 0 idxen
;CHECK: s_waitcnt vmcnt(0)
;CHECK: ds_write_b16 v0, [[VAL]]
define amdgpu_ps void @struct_buffer_load_i16(<4 x i32> inreg %rsrc, i16 addrspace(3)* %ptr, i32 %idx) {
main_body:
%val = call i16 @llvm.amdgcn.struct.buffer.load.i16(<4 x i32> %rsrc, i32 %idx, i32 0, i32 0, i32 0)
store i16 %val, i16 addrspace(3)* %ptr
ret void
}
;CHECK-LABEL: {{^}}struct_buffer_load_v2i16:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_dword [[VAL:v[0-9]+]], v1, s[0:3], 0 idxen
;CHECK: s_waitcnt vmcnt(0)
;CHECK: ds_write_b32 v0, [[VAL]]
define amdgpu_ps void @struct_buffer_load_v2i16(<4 x i32> inreg %rsrc, <2 x i16> addrspace(3)* %ptr, i32 %idx) {
main_body:
%val = call <2 x i16> @llvm.amdgcn.struct.buffer.load.v2i16(<4 x i32> %rsrc, i32 %idx, i32 0, i32 0, i32 0)
store <2 x i16> %val, <2 x i16> addrspace(3)* %ptr
ret void
}
;CHECK-LABEL: {{^}}struct_buffer_load_v4i16:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]], v1, s[0:3], 0 idxen
;CHECK: s_waitcnt vmcnt(0)
;CHECK: ds_write_b64 v0, [[VAL]]
define amdgpu_ps void @struct_buffer_load_v4i16(<4 x i32> inreg %rsrc, <4 x i16> addrspace(3)* %ptr, i32 %idx) {
main_body:
%val = call <4 x i16> @llvm.amdgcn.struct.buffer.load.v4i16(<4 x i32> %rsrc, i32 %idx, i32 0, i32 0, i32 0)
store <4 x i16> %val, <4 x i16> addrspace(3)* %ptr
ret void
}
declare float @llvm.amdgcn.struct.buffer.load.f32(<4 x i32>, i32, i32, i32, i32) #0
declare <2 x float> @llvm.amdgcn.struct.buffer.load.v2f32(<4 x i32>, i32, i32, i32, i32) #0
declare <4 x float> @llvm.amdgcn.struct.buffer.load.v4f32(<4 x i32>, i32, i32, i32, i32) #0
declare i32 @llvm.amdgcn.struct.buffer.load.i32(<4 x i32>, i32, i32, i32, i32) #0
declare <2 x i32> @llvm.amdgcn.struct.buffer.load.v2i32(<4 x i32>, i32, i32, i32, i32) #0
declare <4 x i32> @llvm.amdgcn.struct.buffer.load.v4i32(<4 x i32>, i32, i32, i32, i32) #0
declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1) #0
declare i8 @llvm.amdgcn.struct.buffer.load.i8(<4 x i32>, i32, i32, i32, i32) #0
declare half @llvm.amdgcn.struct.buffer.load.f16(<4 x i32>, i32, i32, i32, i32) #0
declare <2 x half> @llvm.amdgcn.struct.buffer.load.v2f16(<4 x i32>, i32, i32, i32, i32) #0
declare <4 x half> @llvm.amdgcn.struct.buffer.load.v4f16(<4 x i32>, i32, i32, i32, i32) #0
declare i16 @llvm.amdgcn.struct.buffer.load.i16(<4 x i32>, i32, i32, i32, i32) #0
declare <2 x i16> @llvm.amdgcn.struct.buffer.load.v2i16(<4 x i32>, i32, i32, i32, i32) #0
declare <4 x i16> @llvm.amdgcn.struct.buffer.load.v4i16(<4 x i32>, i32, i32, i32, i32) #0
attributes #0 = { nounwind readonly }
|