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
|
;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], off, s[0:3], 0
;CHECK: buffer_load_dwordx4 v[4:7], off, s[0:3], 0 glc
;CHECK: buffer_load_dwordx4 v[8:11], off, s[0:3], 0 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.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 0, i1 0, i1 0)
%data_glc = call <4 x float> @llvm.amdgcn.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 0, i1 1, i1 0)
%data_slc = call <4 x float> @llvm.amdgcn.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 0, i1 0, i1 1)
%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], off, s[0:3], 0 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.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 40, i1 0, i1 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_immoffs_large:
;SICI: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 offen
;VI: s_movk_i32 [[OFFSET:s[0-9]+]], 0x1ffc
;VI: buffer_load_dwordx4 v[0:3], off, s[0:3], [[OFFSET]] 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.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 8192, i1 0, i1 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.buffer.load.v4f32(<4 x i32> %0, i32 %1, i32 0, i1 0, i1 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_ofs:
;CHECK: buffer_load_dwordx4 v[0:3], v0, s[0:3], 0 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.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 %1, i1 0, i1 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_ofs_imm:
;CHECK: buffer_load_dwordx4 v[0:3], v0, s[0:3], 0 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.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 %ofs, i1 0, i1 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.buffer.load.v4f32(<4 x i32> %0, i32 %1, i32 %2, i1 0, i1 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.buffer.load.v4f32(<4 x i32> %0, i32 %2, i32 %1, i1 0, i1 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.buffer.load.f32(<4 x i32> %rsrc, i32 %idx, i32 %ofs, i1 0, i1 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.buffer.load.v2f32(<4 x i32> %rsrc, i32 %idx, i32 %ofs, i1 0, i1 0)
ret <2 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_negative_offset:
;CHECK: v_add_{{[iu]}}32_e32 [[VOFS:v[0-9]+]], vcc, -16, v0
;CHECK: buffer_load_dwordx4 v[0:3], [[VOFS]], s[0:3], 0 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.buffer.load.v4f32(<4 x i32> %0, i32 0, i32 %ofs.1, i1 0, i1 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.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 0, i1 0, i1 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_x1_offen_merged:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_dwordx4 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:4
;CHECK-NEXT: buffer_load_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:28
;CHECK: s_waitcnt
define amdgpu_ps void @buffer_load_x1_offen_merged(<4 x i32> inreg %rsrc, i32 %a) {
main_body:
%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
%r1 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
%r2 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
%r3 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a3, i1 0, i1 0)
%r4 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a4, i1 0, i1 0)
%r5 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a5, i1 0, i1 0)
%r6 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a6, i1 0, i1 0)
call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %r1, float %r2, float %r3, float %r4, i1 true, i1 true)
call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %r5, float %r6, float undef, float undef, i1 true, i1 true)
ret void
}
;CHECK-LABEL: {{^}}buffer_load_x1_offen_merged_glc_slc:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:4{{$}}
;CHECK-NEXT: buffer_load_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:12 glc{{$}}
;CHECK-NEXT: buffer_load_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:28 glc slc{{$}}
;CHECK: s_waitcnt
define amdgpu_ps void @buffer_load_x1_offen_merged_glc_slc(<4 x i32> inreg %rsrc, i32 %a) {
main_body:
%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
%r1 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
%r2 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
%r3 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a3, i1 1, i1 0)
%r4 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a4, i1 1, i1 0)
%r5 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a5, i1 1, i1 1)
%r6 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %a6, i1 1, i1 1)
call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %r1, float %r2, float %r3, float %r4, i1 true, i1 true)
call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %r5, float %r6, float undef, float undef, i1 true, i1 true)
ret void
}
;CHECK-LABEL: {{^}}buffer_load_x2_offen_merged:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_dwordx4 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:4
;CHECK: s_waitcnt
define amdgpu_ps void @buffer_load_x2_offen_merged(<4 x i32> inreg %rsrc, i32 %a) {
main_body:
%a1 = add i32 %a, 4
%a2 = add i32 %a, 12
%vr1 = call <2 x float> @llvm.amdgcn.buffer.load.v2f32(<4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
%vr2 = call <2 x float> @llvm.amdgcn.buffer.load.v2f32(<4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
%r1 = extractelement <2 x float> %vr1, i32 0
%r2 = extractelement <2 x float> %vr1, i32 1
%r3 = extractelement <2 x float> %vr2, i32 0
%r4 = extractelement <2 x float> %vr2, i32 1
call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %r1, float %r2, float %r3, float %r4, i1 true, i1 true)
ret void
}
;CHECK-LABEL: {{^}}buffer_load_x1_offset_merged:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_dwordx4 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:4
;CHECK-NEXT: buffer_load_dwordx2 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:28
;CHECK: s_waitcnt
define amdgpu_ps void @buffer_load_x1_offset_merged(<4 x i32> inreg %rsrc) {
main_body:
%r1 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 4, i1 0, i1 0)
%r2 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 8, i1 0, i1 0)
%r3 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 12, i1 0, i1 0)
%r4 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 16, i1 0, i1 0)
%r5 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 28, i1 0, i1 0)
%r6 = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 32, i1 0, i1 0)
call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %r1, float %r2, float %r3, float %r4, i1 true, i1 true)
call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %r5, float %r6, float undef, float undef, i1 true, i1 true)
ret void
}
;CHECK-LABEL: {{^}}buffer_load_x2_offset_merged:
;CHECK-NEXT: %bb.
;CHECK-NEXT: buffer_load_dwordx4 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:4
;CHECK: s_waitcnt
define amdgpu_ps void @buffer_load_x2_offset_merged(<4 x i32> inreg %rsrc) {
main_body:
%vr1 = call <2 x float> @llvm.amdgcn.buffer.load.v2f32(<4 x i32> %rsrc, i32 0, i32 4, i1 0, i1 0)
%vr2 = call <2 x float> @llvm.amdgcn.buffer.load.v2f32(<4 x i32> %rsrc, i32 0, i32 12, i1 0, i1 0)
%r1 = extractelement <2 x float> %vr1, i32 0
%r2 = extractelement <2 x float> %vr1, i32 1
%r3 = extractelement <2 x float> %vr2, i32 0
%r4 = extractelement <2 x float> %vr2, i32 1
call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %r1, float %r2, float %r3, float %r4, i1 true, i1 true)
ret void
}
declare float @llvm.amdgcn.buffer.load.f32(<4 x i32>, i32, i32, i1, i1) #0
declare <2 x float> @llvm.amdgcn.buffer.load.v2f32(<4 x i32>, i32, i32, i1, i1) #0
declare <4 x float> @llvm.amdgcn.buffer.load.v4f32(<4 x i32>, i32, i32, i1, i1) #0
declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1) #0
attributes #0 = { nounwind readonly }
|
