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
| ; RUN: llc -march=amdgcn -mcpu=tahiti < %s | FileCheck -check-prefixes=GCN,SICI,SI %s
; RUN: llc -march=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefixes=GCN,SICI %s
; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck -check-prefixes=GCN,VIGFX9 %s
; RUN: llc -march=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN,VIGFX9 %s
; GCN-LABEL: {{^}}load_i32:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dword s{{[0-9]}}, s[0:1], 0x0
; SICI-DAG: s_load_dword s{{[0-9]}}, s[2:3], 0x2
; VIGFX9-DAG: s_load_dword s{{[0-9]}}, s[0:1], 0x0
; VIGFX9-DAG: s_load_dword s{{[0-9]}}, s[2:3], 0x8
define amdgpu_vs float @load_i32(i32 addrspace(6)* inreg %p0, i32 addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr inbounds i32, i32 addrspace(6)* %p1, i32 2
%r0 = load i32, i32 addrspace(6)* %p0
%r1 = load i32, i32 addrspace(6)* %gep1
%r = add i32 %r0, %r1
%r2 = bitcast i32 %r to float
ret float %r2
}
; GCN-LABEL: {{^}}load_v2i32:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx2 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx2 s[{{.*}}], s[2:3], 0x4
; VIGFX9-DAG: s_load_dwordx2 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx2 s[{{.*}}], s[2:3], 0x10
define amdgpu_vs <2 x float> @load_v2i32(<2 x i32> addrspace(6)* inreg %p0, <2 x i32> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr inbounds <2 x i32>, <2 x i32> addrspace(6)* %p1, i32 2
%r0 = load <2 x i32>, <2 x i32> addrspace(6)* %p0
%r1 = load <2 x i32>, <2 x i32> addrspace(6)* %gep1
%r = add <2 x i32> %r0, %r1
%r2 = bitcast <2 x i32> %r to <2 x float>
ret <2 x float> %r2
}
; GCN-LABEL: {{^}}load_v4i32:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx4 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx4 s[{{.*}}], s[2:3], 0x8
; VIGFX9-DAG: s_load_dwordx4 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx4 s[{{.*}}], s[2:3], 0x20
define amdgpu_vs <4 x float> @load_v4i32(<4 x i32> addrspace(6)* inreg %p0, <4 x i32> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(6)* %p1, i32 2
%r0 = load <4 x i32>, <4 x i32> addrspace(6)* %p0
%r1 = load <4 x i32>, <4 x i32> addrspace(6)* %gep1
%r = add <4 x i32> %r0, %r1
%r2 = bitcast <4 x i32> %r to <4 x float>
ret <4 x float> %r2
}
; GCN-LABEL: {{^}}load_v8i32:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx8 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx8 s[{{.*}}], s[2:3], 0x10
; VIGFX9-DAG: s_load_dwordx8 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx8 s[{{.*}}], s[2:3], 0x40
define amdgpu_vs <8 x float> @load_v8i32(<8 x i32> addrspace(6)* inreg %p0, <8 x i32> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr inbounds <8 x i32>, <8 x i32> addrspace(6)* %p1, i32 2
%r0 = load <8 x i32>, <8 x i32> addrspace(6)* %p0
%r1 = load <8 x i32>, <8 x i32> addrspace(6)* %gep1
%r = add <8 x i32> %r0, %r1
%r2 = bitcast <8 x i32> %r to <8 x float>
ret <8 x float> %r2
}
; GCN-LABEL: {{^}}load_v16i32:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx16 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx16 s[{{.*}}], s[2:3], 0x20
; VIGFX9-DAG: s_load_dwordx16 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx16 s[{{.*}}], s[2:3], 0x80
define amdgpu_vs <16 x float> @load_v16i32(<16 x i32> addrspace(6)* inreg %p0, <16 x i32> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr inbounds <16 x i32>, <16 x i32> addrspace(6)* %p1, i32 2
%r0 = load <16 x i32>, <16 x i32> addrspace(6)* %p0
%r1 = load <16 x i32>, <16 x i32> addrspace(6)* %gep1
%r = add <16 x i32> %r0, %r1
%r2 = bitcast <16 x i32> %r to <16 x float>
ret <16 x float> %r2
}
; GCN-LABEL: {{^}}load_float:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dword s{{[0-9]}}, s[0:1], 0x0
; SICI-DAG: s_load_dword s{{[0-9]}}, s[2:3], 0x2
; VIGFX9-DAG: s_load_dword s{{[0-9]}}, s[0:1], 0x0
; VIGFX9-DAG: s_load_dword s{{[0-9]}}, s[2:3], 0x8
define amdgpu_vs float @load_float(float addrspace(6)* inreg %p0, float addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr inbounds float, float addrspace(6)* %p1, i32 2
%r0 = load float, float addrspace(6)* %p0
%r1 = load float, float addrspace(6)* %gep1
%r = fadd float %r0, %r1
ret float %r
}
; GCN-LABEL: {{^}}load_v2float:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx2 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx2 s[{{.*}}], s[2:3], 0x4
; VIGFX9-DAG: s_load_dwordx2 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx2 s[{{.*}}], s[2:3], 0x10
define amdgpu_vs <2 x float> @load_v2float(<2 x float> addrspace(6)* inreg %p0, <2 x float> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr inbounds <2 x float>, <2 x float> addrspace(6)* %p1, i32 2
%r0 = load <2 x float>, <2 x float> addrspace(6)* %p0
%r1 = load <2 x float>, <2 x float> addrspace(6)* %gep1
%r = fadd <2 x float> %r0, %r1
ret <2 x float> %r
}
; GCN-LABEL: {{^}}load_v4float:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx4 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx4 s[{{.*}}], s[2:3], 0x8
; VIGFX9-DAG: s_load_dwordx4 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx4 s[{{.*}}], s[2:3], 0x20
define amdgpu_vs <4 x float> @load_v4float(<4 x float> addrspace(6)* inreg %p0, <4 x float> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr inbounds <4 x float>, <4 x float> addrspace(6)* %p1, i32 2
%r0 = load <4 x float>, <4 x float> addrspace(6)* %p0
%r1 = load <4 x float>, <4 x float> addrspace(6)* %gep1
%r = fadd <4 x float> %r0, %r1
ret <4 x float> %r
}
; GCN-LABEL: {{^}}load_v8float:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx8 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx8 s[{{.*}}], s[2:3], 0x10
; VIGFX9-DAG: s_load_dwordx8 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx8 s[{{.*}}], s[2:3], 0x40
define amdgpu_vs <8 x float> @load_v8float(<8 x float> addrspace(6)* inreg %p0, <8 x float> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr inbounds <8 x float>, <8 x float> addrspace(6)* %p1, i32 2
%r0 = load <8 x float>, <8 x float> addrspace(6)* %p0
%r1 = load <8 x float>, <8 x float> addrspace(6)* %gep1
%r = fadd <8 x float> %r0, %r1
ret <8 x float> %r
}
; GCN-LABEL: {{^}}load_v16float:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx16 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx16 s[{{.*}}], s[2:3], 0x20
; VIGFX9-DAG: s_load_dwordx16 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx16 s[{{.*}}], s[2:3], 0x80
define amdgpu_vs <16 x float> @load_v16float(<16 x float> addrspace(6)* inreg %p0, <16 x float> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr inbounds <16 x float>, <16 x float> addrspace(6)* %p1, i32 2
%r0 = load <16 x float>, <16 x float> addrspace(6)* %p0
%r1 = load <16 x float>, <16 x float> addrspace(6)* %gep1
%r = fadd <16 x float> %r0, %r1
ret <16 x float> %r
}
; GCN-LABEL: {{^}}load_i32_hi0:
; GCN: s_mov_b32 s1, 0
; GCN-NEXT: s_load_dword s0, s[0:1], 0x0
define amdgpu_vs i32 @load_i32_hi0(i32 addrspace(6)* inreg %p) #1 {
%r0 = load i32, i32 addrspace(6)* %p
ret i32 %r0
}
; GCN-LABEL: {{^}}load_i32_hi1:
; GCN: s_mov_b32 s1, 1
; GCN-NEXT: s_load_dword s0, s[0:1], 0x0
define amdgpu_vs i32 @load_i32_hi1(i32 addrspace(6)* inreg %p) #2 {
%r0 = load i32, i32 addrspace(6)* %p
ret i32 %r0
}
; GCN-LABEL: {{^}}load_i32_hiffff8000:
; GCN: s_movk_i32 s1, 0x8000
; GCN-NEXT: s_load_dword s0, s[0:1], 0x0
define amdgpu_vs i32 @load_i32_hiffff8000(i32 addrspace(6)* inreg %p) #3 {
%r0 = load i32, i32 addrspace(6)* %p
ret i32 %r0
}
; GCN-LABEL: {{^}}load_i32_hifffffff0:
; GCN: s_mov_b32 s1, -16
; GCN-NEXT: s_load_dword s0, s[0:1], 0x0
define amdgpu_vs i32 @load_i32_hifffffff0(i32 addrspace(6)* inreg %p) #4 {
%r0 = load i32, i32 addrspace(6)* %p
ret i32 %r0
}
; GCN-LABEL: {{^}}load_sampler
; GCN: v_readfirstlane_b32
; GCN-NEXT: v_readfirstlane_b32
; SI: s_nop
; GCN: s_load_dwordx8
; GCN-NEXT: s_load_dwordx4
; GCN: image_sample
define amdgpu_ps <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> @load_sampler([0 x <4 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <8 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <4 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <8 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), float inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, i32, i32, float, i32) #5 {
main_body:
%22 = call nsz float @llvm.amdgcn.interp.mov(i32 2, i32 0, i32 0, i32 %5) #8
%23 = bitcast float %22 to i32
%24 = shl i32 %23, 1
%25 = getelementptr inbounds [0 x <8 x i32>], [0 x <8 x i32>] addrspace(6)* %1, i32 0, i32 %24, !amdgpu.uniform !0
%26 = load <8 x i32>, <8 x i32> addrspace(6)* %25, align 32, !invariant.load !0
%27 = shl i32 %23, 2
%28 = or i32 %27, 3
%29 = bitcast [0 x <8 x i32>] addrspace(6)* %1 to [0 x <4 x i32>] addrspace(6)*
%30 = getelementptr inbounds [0 x <4 x i32>], [0 x <4 x i32>] addrspace(6)* %29, i32 0, i32 %28, !amdgpu.uniform !0
%31 = load <4 x i32>, <4 x i32> addrspace(6)* %30, align 16, !invariant.load !0
%32 = call nsz <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float 0.0, <8 x i32> %26, <4 x i32> %31, i1 0, i32 0, i32 0) #8
%33 = extractelement <4 x float> %32, i32 0
%34 = extractelement <4 x float> %32, i32 1
%35 = extractelement <4 x float> %32, i32 2
%36 = extractelement <4 x float> %32, i32 3
%37 = bitcast float %4 to i32
%38 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> undef, i32 %37, 4
%39 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %38, float %33, 5
%40 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %39, float %34, 6
%41 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %40, float %35, 7
%42 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %41, float %36, 8
%43 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %42, float %20, 19
ret <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %43
}
; GCN-LABEL: {{^}}load_sampler_nouniform
; GCN: v_readfirstlane_b32
; GCN-NEXT: v_readfirstlane_b32
; SI: s_nop
; GCN: s_load_dwordx8
; GCN-NEXT: s_load_dwordx4
; GCN: image_sample
define amdgpu_ps <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> @load_sampler_nouniform([0 x <4 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <8 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <4 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <8 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), float inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, i32, i32, float, i32) #5 {
main_body:
%22 = call nsz float @llvm.amdgcn.interp.mov(i32 2, i32 0, i32 0, i32 %5) #8
%23 = bitcast float %22 to i32
%24 = shl i32 %23, 1
%25 = getelementptr inbounds [0 x <8 x i32>], [0 x <8 x i32>] addrspace(6)* %1, i32 0, i32 %24
%26 = load <8 x i32>, <8 x i32> addrspace(6)* %25, align 32, !invariant.load !0
%27 = shl i32 %23, 2
%28 = or i32 %27, 3
%29 = bitcast [0 x <8 x i32>] addrspace(6)* %1 to [0 x <4 x i32>] addrspace(6)*
%30 = getelementptr inbounds [0 x <4 x i32>], [0 x <4 x i32>] addrspace(6)* %29, i32 0, i32 %28
%31 = load <4 x i32>, <4 x i32> addrspace(6)* %30, align 16, !invariant.load !0
%32 = call nsz <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float 0.0, <8 x i32> %26, <4 x i32> %31, i1 0, i32 0, i32 0) #8
%33 = extractelement <4 x float> %32, i32 0
%34 = extractelement <4 x float> %32, i32 1
%35 = extractelement <4 x float> %32, i32 2
%36 = extractelement <4 x float> %32, i32 3
%37 = bitcast float %4 to i32
%38 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> undef, i32 %37, 4
%39 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %38, float %33, 5
%40 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %39, float %34, 6
%41 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %40, float %35, 7
%42 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %41, float %36, 8
%43 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %42, float %20, 19
ret <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %43
}
; GCN-LABEL: {{^}}load_addr_no_fold:
; GCN-DAG: s_add_i32 s0, s0, 4
; GCN-DAG: s_mov_b32 s1, 0
; GCN: s_load_dword s{{[0-9]}}, s[0:1], 0x0
define amdgpu_vs float @load_addr_no_fold(i32 addrspace(6)* inreg noalias %p0) #0 {
%gep1 = getelementptr i32, i32 addrspace(6)* %p0, i32 1
%r1 = load i32, i32 addrspace(6)* %gep1
%r2 = bitcast i32 %r1 to float
ret float %r2
}
; CHECK-LABEL: {{^}}vgpr_arg_src:
; CHECK: v_readfirstlane_b32 s[[READLANE:[0-9]+]], v0
; CHECK: s_mov_b32 s[[ZERO:[0-9]+]]
; CHECK: s_load_dwordx4 s{{\[[0-9]+:[0-9]+\]}}, s{{\[}}[[READLANE]]:[[ZERO]]{{\]}}
define amdgpu_vs float @vgpr_arg_src(<4 x i32> addrspace(6)* %arg) {
main_body:
%tmp9 = load <4 x i32>, <4 x i32> addrspace(6)* %arg
%tmp10 = call nsz float @llvm.amdgcn.struct.buffer.load.format.f32(<4 x i32> %tmp9, i32 undef, i32 0, i32 0, i32 0) #1
ret float %tmp10
}
; Function Attrs: nounwind readnone speculatable
declare float @llvm.amdgcn.interp.mov(i32, i32, i32, i32) #6
; Function Attrs: nounwind readonly
declare <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32, float, <8 x i32>, <4 x i32>, i1, i32, i32) #7
declare float @llvm.amdgcn.struct.buffer.load.format.f32(<4 x i32>, i32, i32, i32, i32) #7
!0 = !{}
attributes #0 = { nounwind }
attributes #1 = { nounwind "amdgpu-32bit-address-high-bits"="0" }
attributes #2 = { nounwind "amdgpu-32bit-address-high-bits"="1" }
attributes #3 = { nounwind "amdgpu-32bit-address-high-bits"="0xffff8000" }
attributes #4 = { nounwind "amdgpu-32bit-address-high-bits"="0xfffffff0" }
attributes #5 = { "InitialPSInputAddr"="45175" }
attributes #6 = { nounwind readnone speculatable }
attributes #7 = { nounwind readonly }
attributes #8 = { nounwind readnone }
|