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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --check-attributes --check-globals --include-generated-funcs
; RUN: opt -data-layout=A5 -amdgpu-lower-enqueued-block -S < %s | FileCheck %s
%struct.ndrange_t = type { i32 }
%opencl.queue_t = type opaque
define amdgpu_kernel void @non_caller(ptr addrspace(1) %a, i8 %b, ptr addrspace(1) %c, i64 %d) {
ret void
}
define amdgpu_kernel void @caller(ptr addrspace(1) %a, i8 %b, ptr addrspace(1) %c, i64 %d) {
entry:
%block = alloca <{ i32, i32, ptr addrspace(1), i8 }>, align 8, addrspace(5)
%inst = alloca %struct.ndrange_t, align 4, addrspace(5)
%block2 = alloca <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
%inst3 = alloca %struct.ndrange_t, align 4, addrspace(5)
%block.size = getelementptr inbounds <{ i32, i32, ptr addrspace(1), i8 }>, ptr addrspace(5) %block, i32 0, i32 0
store i32 25, ptr addrspace(5) %block.size, align 8
%block.align = getelementptr inbounds <{ i32, i32, ptr addrspace(1), i8 }>, ptr addrspace(5) %block, i32 0, i32 1
store i32 8, ptr addrspace(5) %block.align, align 4
%block.captured = getelementptr inbounds <{ i32, i32, ptr addrspace(1), i8 }>, ptr addrspace(5) %block, i32 0, i32 2
store ptr addrspace(1) %a, ptr addrspace(5) %block.captured, align 8
%block.captured1 = getelementptr inbounds <{ i32, i32, ptr addrspace(1), i8 }>, ptr addrspace(5) %block, i32 0, i32 3
store i8 %b, ptr addrspace(5) %block.captured1, align 8
%inst4 = addrspacecast ptr addrspace(5) %block to ptr
%inst5 = call i32 @__enqueue_kernel_basic(ptr addrspace(1) undef, i32 0, ptr addrspace(5) byval(%struct.ndrange_t) nonnull %inst,
ptr @__test_block_invoke_kernel, ptr nonnull %inst4) #2
%inst10 = call i32 @__enqueue_kernel_basic(ptr addrspace(1) undef, i32 0, ptr addrspace(5) byval(%struct.ndrange_t) nonnull %inst,
ptr @__test_block_invoke_kernel, ptr nonnull %inst4) #2
%inst11 = call i32 @__enqueue_kernel_basic(ptr addrspace(1) undef, i32 0, ptr addrspace(5) byval(%struct.ndrange_t) nonnull %inst,
ptr @0, ptr nonnull %inst4) #2
%inst12 = call i32 @__enqueue_kernel_basic(ptr addrspace(1) undef, i32 0, ptr addrspace(5) byval(%struct.ndrange_t) nonnull %inst,
ptr @1, ptr nonnull %inst4) #2
%block.size4 = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) %block2, i32 0, i32 0
store i32 41, ptr addrspace(5) %block.size4, align 8
%block.align5 = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) %block2, i32 0, i32 1
store i32 8, ptr addrspace(5) %block.align5, align 4
%block.captured7 = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) %block2, i32 0, i32 2
store ptr addrspace(1) %a, ptr addrspace(5) %block.captured7, align 8
%block.captured8 = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) %block2, i32 0, i32 5
store i8 %b, ptr addrspace(5) %block.captured8, align 8
%block.captured9 = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) %block2, i32 0, i32 3
store ptr addrspace(1) %c, ptr addrspace(5) %block.captured9, align 8
%block.captured10 = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) %block2, i32 0, i32 4
store i64 %d, ptr addrspace(5) %block.captured10, align 8
%inst8 = addrspacecast ptr addrspace(5) %block2 to ptr
%inst9 = call i32 @__enqueue_kernel_basic(ptr addrspace(1) undef, i32 0, ptr addrspace(5) byval(%struct.ndrange_t) nonnull %inst3,
ptr @__test_block_invoke_2_kernel, ptr nonnull %inst8) #2
ret void
}
; __enqueue_kernel* functions may get inlined
define amdgpu_kernel void @inlined_caller(ptr addrspace(1) %a, i8 %b, ptr addrspace(1) %c, i64 %d) {
entry:
%inst = load i64, ptr addrspace(1) addrspacecast (ptr @__test_block_invoke_kernel to ptr addrspace(1))
store i64 %inst, ptr addrspace(1) %c
ret void
}
define internal amdgpu_kernel void @__test_block_invoke_kernel(<{ i32, i32, ptr addrspace(1), i8 }> %arg) #0 {
entry:
%.fca.3.extract = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> %arg, 2
%.fca.4.extract = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> %arg, 3
store i8 %.fca.4.extract, ptr addrspace(1) %.fca.3.extract, align 1
ret void
}
declare i32 @__enqueue_kernel_basic(ptr addrspace(1), i32, ptr addrspace(5), ptr, ptr) local_unnamed_addr
define internal amdgpu_kernel void @__test_block_invoke_2_kernel(<{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> %arg) #0 {
entry:
%.fca.3.extract = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> %arg, 2
%.fca.4.extract = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> %arg, 3
%.fca.5.extract = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> %arg, 4
%.fca.6.extract = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> %arg, 5
store i8 %.fca.6.extract, ptr addrspace(1) %.fca.3.extract, align 1
store i64 %.fca.5.extract, ptr addrspace(1) %.fca.4.extract, align 8
ret void
}
@kernel_address_user = global [1 x ptr] [ ptr @block_has_used_kernel_address ]
define internal amdgpu_kernel void @block_has_used_kernel_address(<{ i32, i32, ptr addrspace(1), i8 }> %arg) #0 {
entry:
%.fca.3.extract = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> %arg, 2
%.fca.4.extract = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> %arg, 3
store i8 %.fca.4.extract, ptr addrspace(1) %.fca.3.extract, align 1
ret void
}
define amdgpu_kernel void @user_of_kernel_address(ptr addrspace(1) %arg) {
store ptr @block_has_used_kernel_address, ptr addrspace(1) %arg
ret void
}
define internal amdgpu_kernel void @0(<{ i32, i32, ptr addrspace(1), i8 }> %arg) #0 {
ret void
}
define internal amdgpu_kernel void @1(<{ i32, i32, ptr addrspace(1), i8 }> %arg) #0 {
ret void
}
attributes #0 = { "enqueued-block" }
;.
; CHECK: @[[KERNEL_ADDRESS_USER:[a-zA-Z0-9_$"\\.-]+]] = global [1 x ptr] [ptr addrspacecast (ptr addrspace(1) @block_has_used_kernel_address.runtime_handle to ptr)]
; CHECK: @[[__TEST_BLOCK_INVOKE_KERNEL_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) externally_initialized constant [[BLOCK_RUNTIME_HANDLE_T:%.*]] zeroinitializer
; CHECK: @[[__TEST_BLOCK_INVOKE_2_KERNEL_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) externally_initialized constant [[BLOCK_RUNTIME_HANDLE_T:%.*]] zeroinitializer
; CHECK: @[[BLOCK_HAS_USED_KERNEL_ADDRESS_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) externally_initialized constant [[BLOCK_RUNTIME_HANDLE_T:%.*]] zeroinitializer
; CHECK: @[[__AMDGPU_ENQUEUED_KERNEL_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) externally_initialized constant [[BLOCK_RUNTIME_HANDLE_T:%.*]] zeroinitializer
; CHECK: @[[__AMDGPU_ENQUEUED_KERNEL_1_RUNTIME_HANDLE:[a-zA-Z0-9_$"\\.-]+]] = addrspace(1) externally_initialized constant [[BLOCK_RUNTIME_HANDLE_T:%.*]] zeroinitializer
;.
; CHECK-LABEL: define {{[^@]+}}@non_caller
; CHECK-SAME: (ptr addrspace(1) [[A:%.*]], i8 [[B:%.*]], ptr addrspace(1) [[C:%.*]], i64 [[D:%.*]]) {
; CHECK-NEXT: ret void
;
;
; CHECK-LABEL: define {{[^@]+}}@caller
; CHECK-SAME: (ptr addrspace(1) [[A:%.*]], i8 [[B:%.*]], ptr addrspace(1) [[C:%.*]], i64 [[D:%.*]]) {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[BLOCK:%.*]] = alloca <{ i32, i32, ptr addrspace(1), i8 }>, align 8, addrspace(5)
; CHECK-NEXT: [[INST:%.*]] = alloca [[STRUCT_NDRANGE_T:%.*]], align 4, addrspace(5)
; CHECK-NEXT: [[BLOCK2:%.*]] = alloca <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, align 8, addrspace(5)
; CHECK-NEXT: [[INST3:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4, addrspace(5)
; CHECK-NEXT: [[BLOCK_SIZE:%.*]] = getelementptr inbounds <{ i32, i32, ptr addrspace(1), i8 }>, ptr addrspace(5) [[BLOCK]], i32 0, i32 0
; CHECK-NEXT: store i32 25, ptr addrspace(5) [[BLOCK_SIZE]], align 8
; CHECK-NEXT: [[BLOCK_ALIGN:%.*]] = getelementptr inbounds <{ i32, i32, ptr addrspace(1), i8 }>, ptr addrspace(5) [[BLOCK]], i32 0, i32 1
; CHECK-NEXT: store i32 8, ptr addrspace(5) [[BLOCK_ALIGN]], align 4
; CHECK-NEXT: [[BLOCK_CAPTURED:%.*]] = getelementptr inbounds <{ i32, i32, ptr addrspace(1), i8 }>, ptr addrspace(5) [[BLOCK]], i32 0, i32 2
; CHECK-NEXT: store ptr addrspace(1) [[A]], ptr addrspace(5) [[BLOCK_CAPTURED]], align 8
; CHECK-NEXT: [[BLOCK_CAPTURED1:%.*]] = getelementptr inbounds <{ i32, i32, ptr addrspace(1), i8 }>, ptr addrspace(5) [[BLOCK]], i32 0, i32 3
; CHECK-NEXT: store i8 [[B]], ptr addrspace(5) [[BLOCK_CAPTURED1]], align 8
; CHECK-NEXT: [[INST4:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK]] to ptr
; CHECK-NEXT: [[INST5:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) undef, i32 0, ptr addrspace(5) nonnull byval([[STRUCT_NDRANGE_T]]) [[INST]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_kernel.runtime_handle to ptr), ptr nonnull [[INST4]])
; CHECK-NEXT: [[INST10:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) undef, i32 0, ptr addrspace(5) nonnull byval([[STRUCT_NDRANGE_T]]) [[INST]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_kernel.runtime_handle to ptr), ptr nonnull [[INST4]])
; CHECK-NEXT: [[INST11:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) undef, i32 0, ptr addrspace(5) nonnull byval([[STRUCT_NDRANGE_T]]) [[INST]], ptr addrspacecast (ptr addrspace(1) @__amdgpu_enqueued_kernel.runtime_handle to ptr), ptr nonnull [[INST4]])
; CHECK-NEXT: [[INST12:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) undef, i32 0, ptr addrspace(5) nonnull byval([[STRUCT_NDRANGE_T]]) [[INST]], ptr addrspacecast (ptr addrspace(1) @__amdgpu_enqueued_kernel.1.runtime_handle to ptr), ptr nonnull [[INST4]])
; CHECK-NEXT: [[BLOCK_SIZE4:%.*]] = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK2]], i32 0, i32 0
; CHECK-NEXT: store i32 41, ptr addrspace(5) [[BLOCK_SIZE4]], align 8
; CHECK-NEXT: [[BLOCK_ALIGN5:%.*]] = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK2]], i32 0, i32 1
; CHECK-NEXT: store i32 8, ptr addrspace(5) [[BLOCK_ALIGN5]], align 4
; CHECK-NEXT: [[BLOCK_CAPTURED7:%.*]] = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK2]], i32 0, i32 2
; CHECK-NEXT: store ptr addrspace(1) [[A]], ptr addrspace(5) [[BLOCK_CAPTURED7]], align 8
; CHECK-NEXT: [[BLOCK_CAPTURED8:%.*]] = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK2]], i32 0, i32 5
; CHECK-NEXT: store i8 [[B]], ptr addrspace(5) [[BLOCK_CAPTURED8]], align 8
; CHECK-NEXT: [[BLOCK_CAPTURED9:%.*]] = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK2]], i32 0, i32 3
; CHECK-NEXT: store ptr addrspace(1) [[C]], ptr addrspace(5) [[BLOCK_CAPTURED9]], align 8
; CHECK-NEXT: [[BLOCK_CAPTURED10:%.*]] = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK2]], i32 0, i32 4
; CHECK-NEXT: store i64 [[D]], ptr addrspace(5) [[BLOCK_CAPTURED10]], align 8
; CHECK-NEXT: [[INST8:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK2]] to ptr
; CHECK-NEXT: [[INST9:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) undef, i32 0, ptr addrspace(5) nonnull byval([[STRUCT_NDRANGE_T]]) [[INST3]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_2_kernel.runtime_handle to ptr), ptr nonnull [[INST8]])
; CHECK-NEXT: ret void
;
;
; CHECK-LABEL: define {{[^@]+}}@inlined_caller
; CHECK-SAME: (ptr addrspace(1) [[A:%.*]], i8 [[B:%.*]], ptr addrspace(1) [[C:%.*]], i64 [[D:%.*]]) {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[INST:%.*]] = load i64, ptr addrspace(1) @__test_block_invoke_kernel.runtime_handle, align 4
; CHECK-NEXT: store i64 [[INST]], ptr addrspace(1) [[C]], align 4
; CHECK-NEXT: ret void
;
;
; CHECK-LABEL: define {{[^@]+}}@__test_block_invoke_kernel
; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTFCA_3_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> [[ARG]], 2
; CHECK-NEXT: [[DOTFCA_4_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> [[ARG]], 3
; CHECK-NEXT: store i8 [[DOTFCA_4_EXTRACT]], ptr addrspace(1) [[DOTFCA_3_EXTRACT]], align 1
; CHECK-NEXT: ret void
;
;
; CHECK-LABEL: define {{[^@]+}}@__test_block_invoke_2_kernel
; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[ARG:%.*]]) #[[ATTR1:[0-9]+]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTFCA_3_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[ARG]], 2
; CHECK-NEXT: [[DOTFCA_4_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[ARG]], 3
; CHECK-NEXT: [[DOTFCA_5_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[ARG]], 4
; CHECK-NEXT: [[DOTFCA_6_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[ARG]], 5
; CHECK-NEXT: store i8 [[DOTFCA_6_EXTRACT]], ptr addrspace(1) [[DOTFCA_3_EXTRACT]], align 1
; CHECK-NEXT: store i64 [[DOTFCA_5_EXTRACT]], ptr addrspace(1) [[DOTFCA_4_EXTRACT]], align 8
; CHECK-NEXT: ret void
;
;
; CHECK-LABEL: define {{[^@]+}}@block_has_used_kernel_address
; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR2:[0-9]+]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTFCA_3_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> [[ARG]], 2
; CHECK-NEXT: [[DOTFCA_4_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> [[ARG]], 3
; CHECK-NEXT: store i8 [[DOTFCA_4_EXTRACT]], ptr addrspace(1) [[DOTFCA_3_EXTRACT]], align 1
; CHECK-NEXT: ret void
;
;
; CHECK-LABEL: define {{[^@]+}}@user_of_kernel_address
; CHECK-SAME: (ptr addrspace(1) [[ARG:%.*]]) {
; CHECK-NEXT: store ptr addrspacecast (ptr addrspace(1) @block_has_used_kernel_address.runtime_handle to ptr), ptr addrspace(1) [[ARG]], align 8
; CHECK-NEXT: ret void
;
;
; CHECK-LABEL: define {{[^@]+}}@__amdgpu_enqueued_kernel
; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR3:[0-9]+]] {
; CHECK-NEXT: ret void
;
;
; CHECK-LABEL: define {{[^@]+}}@__amdgpu_enqueued_kernel.1
; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR4:[0-9]+]] {
; CHECK-NEXT: ret void
;
;.
; CHECK: attributes #[[ATTR0]] = { "enqueued-block" "runtime-handle"="__test_block_invoke_kernel.runtime_handle" }
; CHECK: attributes #[[ATTR1]] = { "enqueued-block" "runtime-handle"="__test_block_invoke_2_kernel.runtime_handle" }
; CHECK: attributes #[[ATTR2]] = { "enqueued-block" "runtime-handle"="block_has_used_kernel_address.runtime_handle" }
; CHECK: attributes #[[ATTR3]] = { "enqueued-block" "runtime-handle"="__amdgpu_enqueued_kernel.runtime_handle" }
; CHECK: attributes #[[ATTR4]] = { "enqueued-block" "runtime-handle"="__amdgpu_enqueued_kernel.1.runtime_handle" }
;.
|
