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
| ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=kaveri -mattr=-code-object-v3 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,HSA %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -mattr=-code-object-v3 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,MESA %s
; GCN-LABEL: {{^}}kernel_implicitarg_ptr_empty:
; GCN: enable_sgpr_kernarg_segment_ptr = 1
; HSA: kernarg_segment_byte_size = 0
; MESA: kernarg_segment_byte_size = 16
; HSA: s_load_dword s0, s[4:5], 0x0
define amdgpu_kernel void @kernel_implicitarg_ptr_empty() #0 {
%implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
%cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
%load = load volatile i32, i32 addrspace(4)* %cast
ret void
}
; GCN-LABEL: {{^}}opencl_kernel_implicitarg_ptr_empty:
; GCN: enable_sgpr_kernarg_segment_ptr = 1
; HSA: kernarg_segment_byte_size = 48
; MESA: kernarg_segment_byte_size = 16
; HSA: s_load_dword s0, s[4:5], 0x0
define amdgpu_kernel void @opencl_kernel_implicitarg_ptr_empty() #1 {
%implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
%cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
%load = load volatile i32, i32 addrspace(4)* %cast
ret void
}
; GCN-LABEL: {{^}}kernel_implicitarg_ptr:
; GCN: enable_sgpr_kernarg_segment_ptr = 1
; HSA: kernarg_segment_byte_size = 112
; MESA: kernarg_segment_byte_size = 128
; HSA: s_load_dword s0, s[4:5], 0x1c
define amdgpu_kernel void @kernel_implicitarg_ptr([112 x i8]) #0 {
%implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
%cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
%load = load volatile i32, i32 addrspace(4)* %cast
ret void
}
; GCN-LABEL: {{^}}opencl_kernel_implicitarg_ptr:
; GCN: enable_sgpr_kernarg_segment_ptr = 1
; HSA: kernarg_segment_byte_size = 160
; MESA: kernarg_segment_byte_size = 128
; HSA: s_load_dword s0, s[4:5], 0x1c
define amdgpu_kernel void @opencl_kernel_implicitarg_ptr([112 x i8]) #1 {
%implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
%cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
%load = load volatile i32, i32 addrspace(4)* %cast
ret void
}
; GCN-LABEL: {{^}}func_implicitarg_ptr:
; GCN: s_waitcnt
; MESA: v_mov_b32_e32 v0, s4
; MESA: v_mov_b32_e32 v1, s5
; MESA: buffer_load_dword v0, v[0:1], s[8:11], 0 addr64
; HSA: v_mov_b32_e32 v0, s4
; HSA: v_mov_b32_e32 v1, s5
; HSA: flat_load_dword v0, v[0:1]
; GCN-NEXT: s_waitcnt
; GCN-NEXT: s_setpc_b64
define void @func_implicitarg_ptr() #0 {
%implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
%cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
%load = load volatile i32, i32 addrspace(4)* %cast
ret void
}
; GCN-LABEL: {{^}}opencl_func_implicitarg_ptr:
; GCN: s_waitcnt
; MESA: v_mov_b32_e32 v0, s4
; MESA: v_mov_b32_e32 v1, s5
; MESA: buffer_load_dword v0, v[0:1], s[8:11], 0 addr64
; HSA: v_mov_b32_e32 v0, s4
; HSA: v_mov_b32_e32 v1, s5
; HSA: flat_load_dword v0, v[0:1]
; GCN-NEXT: s_waitcnt
; GCN-NEXT: s_setpc_b64
define void @opencl_func_implicitarg_ptr() #0 {
%implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
%cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
%load = load volatile i32, i32 addrspace(4)* %cast
ret void
}
; GCN-LABEL: {{^}}kernel_call_implicitarg_ptr_func_empty:
; GCN: enable_sgpr_kernarg_segment_ptr = 1
; HSA: kernarg_segment_byte_size = 0
; MESA: kernarg_segment_byte_size = 16
; GCN-NOT: s[4:5]
; GCN-NOT: s4
; GCN-NOT: s5
; GCN: s_swappc_b64
define amdgpu_kernel void @kernel_call_implicitarg_ptr_func_empty() #0 {
call void @func_implicitarg_ptr()
ret void
}
; GCN-LABEL: {{^}}opencl_kernel_call_implicitarg_ptr_func_empty:
; GCN: enable_sgpr_kernarg_segment_ptr = 1
; HSA: kernarg_segment_byte_size = 48
; MESA: kernarg_segment_byte_size = 16
; GCN-NOT: s[4:5]
; GCN-NOT: s4
; GCN-NOT: s5
; GCN: s_swappc_b64
define amdgpu_kernel void @opencl_kernel_call_implicitarg_ptr_func_empty() #1 {
call void @func_implicitarg_ptr()
ret void
}
; GCN-LABEL: {{^}}kernel_call_implicitarg_ptr_func:
; GCN: enable_sgpr_kernarg_segment_ptr = 1
; HSA: kernarg_segment_byte_size = 112
; MESA: kernarg_segment_byte_size = 128
; HSA: s_add_u32 s4, s4, 0x70
; MESA: s_add_u32 s4, s4, 0x70
; GCN: s_addc_u32 s5, s5, 0{{$}}
; GCN: s_swappc_b64
define amdgpu_kernel void @kernel_call_implicitarg_ptr_func([112 x i8]) #0 {
call void @func_implicitarg_ptr()
ret void
}
; GCN-LABEL: {{^}}opencl_kernel_call_implicitarg_ptr_func:
; GCN: enable_sgpr_kernarg_segment_ptr = 1
; HSA: kernarg_segment_byte_size = 160
; MESA: kernarg_segment_byte_size = 128
; GCN: s_add_u32 s4, s4, 0x70
; GCN: s_addc_u32 s5, s5, 0{{$}}
; GCN: s_swappc_b64
define amdgpu_kernel void @opencl_kernel_call_implicitarg_ptr_func([112 x i8]) #1 {
call void @func_implicitarg_ptr()
ret void
}
; GCN-LABEL: {{^}}func_call_implicitarg_ptr_func:
; GCN-NOT: s4
; GCN-NOT: s5
; GCN-NOT: s[4:5]
define void @func_call_implicitarg_ptr_func() #0 {
call void @func_implicitarg_ptr()
ret void
}
; GCN-LABEL: {{^}}opencl_func_call_implicitarg_ptr_func:
; GCN-NOT: s4
; GCN-NOT: s5
; GCN-NOT: s[4:5]
define void @opencl_func_call_implicitarg_ptr_func() #0 {
call void @func_implicitarg_ptr()
ret void
}
; GCN-LABEL: {{^}}func_kernarg_implicitarg_ptr:
; GCN: s_waitcnt
; MESA-DAG: v_mov_b32_e32 v0, s4
; MESA-DAG: v_mov_b32_e32 v1, s5
; MESA-DAG: buffer_load_dword v0, v[0:1], s[8:11], 0 addr64
; MESA: v_mov_b32_e32 v0, s6
; MESA: v_mov_b32_e32 v1, s7
; MESA: buffer_load_dword v0, v[0:1], s[8:11], 0 addr64
; HSA: v_mov_b32_e32 v0, s4
; HSA: v_mov_b32_e32 v1, s5
; HSA: flat_load_dword v0, v[0:1]
; HSA: v_mov_b32_e32 v0, s6
; HSA: v_mov_b32_e32 v1, s7
; HSA: flat_load_dword v0, v[0:1]
; GCN: s_waitcnt vmcnt(0)
define void @func_kernarg_implicitarg_ptr() #0 {
%kernarg.segment.ptr = call i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr()
%implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
%cast.kernarg.segment.ptr = bitcast i8 addrspace(4)* %kernarg.segment.ptr to i32 addrspace(4)*
%cast.implicitarg = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
%load0 = load volatile i32, i32 addrspace(4)* %cast.kernarg.segment.ptr
%load1 = load volatile i32, i32 addrspace(4)* %cast.implicitarg
ret void
}
; GCN-LABEL: {{^}}opencl_func_kernarg_implicitarg_ptr:
; GCN: s_waitcnt
; MESA-DAG: v_mov_b32_e32 v0, s4
; MESA-DAG: v_mov_b32_e32 v1, s5
; MESA: buffer_load_dword v0, v[0:1], s[8:11], 0 addr64
; MESA-DAG: v_mov_b32_e32 v0, s6
; MESA-DAG: v_mov_b32_e32 v1, s7
; MESA: buffer_load_dword v0, v[0:1], s[8:11], 0 addr64
; HSA: v_mov_b32_e32 v0, s4
; HSA: v_mov_b32_e32 v1, s5
; HSA: flat_load_dword v0, v[0:1]
; HSA: v_mov_b32_e32 v0, s6
; HSA: v_mov_b32_e32 v1, s7
; HSA: flat_load_dword v0, v[0:1]
; GCN: s_waitcnt vmcnt(0)
define void @opencl_func_kernarg_implicitarg_ptr() #0 {
%kernarg.segment.ptr = call i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr()
%implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
%cast.kernarg.segment.ptr = bitcast i8 addrspace(4)* %kernarg.segment.ptr to i32 addrspace(4)*
%cast.implicitarg = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
%load0 = load volatile i32, i32 addrspace(4)* %cast.kernarg.segment.ptr
%load1 = load volatile i32, i32 addrspace(4)* %cast.implicitarg
ret void
}
; GCN-LABEL: {{^}}kernel_call_kernarg_implicitarg_ptr_func:
; GCN: s_add_u32 s6, s4, 0x70
; GCN: s_addc_u32 s7, s5, 0
; GCN: s_swappc_b64
define amdgpu_kernel void @kernel_call_kernarg_implicitarg_ptr_func([112 x i8]) #0 {
call void @func_kernarg_implicitarg_ptr()
ret void
}
; GCN-LABEL: {{^}}kernel_implicitarg_no_struct_align_padding:
; HSA: kernarg_segment_byte_size = 120
; MESA: kernarg_segment_byte_size = 84
; GCN: kernarg_segment_alignment = 6
define amdgpu_kernel void @kernel_implicitarg_no_struct_align_padding(<16 x i32>, i32) #1 {
%implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
%cast = bitcast i8 addrspace(4)* %implicitarg.ptr to i32 addrspace(4)*
%load = load volatile i32, i32 addrspace(4)* %cast
ret void
}
declare i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() #2
declare i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr() #2
attributes #0 = { nounwind noinline }
attributes #1 = { nounwind noinline "amdgpu-implicitarg-num-bytes"="48" }
attributes #2 = { nounwind readnone speculatable }
|