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
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --check-attributes --check-globals all --include-generated-funcs --version 5
// RUN: %clang_cc1 -fno-ident -no-enable-noundef-analysis %s -cl-std=CL2.0 -ffake-address-space-map -O0 -emit-llvm -o - -triple "spir-unknown-unknown" -fdenormal-fp-math-f32=preserve-sign -cl-uniform-work-group-size | FileCheck --check-prefix=SPIR32 %s
// RUN: %clang_cc1 -fno-ident -ffp-exception-behavior=strict -fexperimental-strict-floating-point -no-enable-noundef-analysis %s -cl-std=CL2.0 -ffake-address-space-map -O0 -emit-llvm -o - -triple "spir-unknown-unknown" | FileCheck --check-prefix=STRICTFP %s
// Test that attributes are correctly applied to functions introduced for
// enqueued blocks
typedef void (^bl_t)(local void *);
typedef struct {int a;} ndrange_t;
kernel void device_side_enqueue(global float *a, global float *b, int i) {
queue_t default_queue;
unsigned flags = 0;
ndrange_t ndrange;
enqueue_kernel(default_queue, flags, ndrange,
^(void) {
a[i] = 4.0f * b[i] + 1.0f;
});
}
// SPIR32: Function Attrs: convergent noinline norecurse nounwind optnone
// SPIR32-LABEL: define dso_local spir_kernel void @device_side_enqueue(
// SPIR32-SAME: ptr addrspace(1) align 4 [[A:%.*]], ptr addrspace(1) align 4 [[B:%.*]], i32 [[I:%.*]]) #[[ATTR0:[0-9]+]] !kernel_arg_addr_space [[META2:![0-9]+]] !kernel_arg_access_qual [[META3:![0-9]+]] !kernel_arg_type [[META4:![0-9]+]] !kernel_arg_base_type [[META4]] !kernel_arg_type_qual [[META5:![0-9]+]] {
// SPIR32-NEXT: [[ENTRY:.*:]]
// SPIR32-NEXT: [[A_ADDR:%.*]] = alloca ptr addrspace(1), align 4
// SPIR32-NEXT: [[B_ADDR:%.*]] = alloca ptr addrspace(1), align 4
// SPIR32-NEXT: [[I_ADDR:%.*]] = alloca i32, align 4
// SPIR32-NEXT: store ptr addrspace(1) [[A]], ptr [[A_ADDR]], align 4
// SPIR32-NEXT: store ptr addrspace(1) [[B]], ptr [[B_ADDR]], align 4
// SPIR32-NEXT: store i32 [[I]], ptr [[I_ADDR]], align 4
// SPIR32-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr [[A_ADDR]], align 4
// SPIR32-NEXT: [[TMP1:%.*]] = load ptr addrspace(1), ptr [[B_ADDR]], align 4
// SPIR32-NEXT: [[TMP2:%.*]] = load i32, ptr [[I_ADDR]], align 4
// SPIR32-NEXT: call spir_func void @__clang_ocl_kern_imp_device_side_enqueue(ptr addrspace(1) align 4 [[TMP0]], ptr addrspace(1) align 4 [[TMP1]], i32 [[TMP2]]) #[[ATTR5:[0-9]+]]
// SPIR32-NEXT: ret void
//
//
// SPIR32: Function Attrs: convergent noinline norecurse nounwind optnone
// SPIR32-LABEL: define dso_local spir_func void @__clang_ocl_kern_imp_device_side_enqueue(
// SPIR32-SAME: ptr addrspace(1) align 4 [[A:%.*]], ptr addrspace(1) align 4 [[B:%.*]], i32 [[I:%.*]]) #[[ATTR0]] !kernel_arg_addr_space [[META2]] !kernel_arg_access_qual [[META3]] !kernel_arg_type [[META4]] !kernel_arg_base_type [[META4]] !kernel_arg_type_qual [[META5]] {
// SPIR32-NEXT: [[ENTRY:.*:]]
// SPIR32-NEXT: [[A_ADDR:%.*]] = alloca ptr addrspace(1), align 4
// SPIR32-NEXT: [[B_ADDR:%.*]] = alloca ptr addrspace(1), align 4
// SPIR32-NEXT: [[I_ADDR:%.*]] = alloca i32, align 4
// SPIR32-NEXT: [[DEFAULT_QUEUE:%.*]] = alloca target("spirv.Queue"), align 4
// SPIR32-NEXT: [[FLAGS:%.*]] = alloca i32, align 4
// SPIR32-NEXT: [[NDRANGE:%.*]] = alloca [[STRUCT_NDRANGE_T:%.*]], align 4
// SPIR32-NEXT: [[TMP:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4
// SPIR32-NEXT: [[BLOCK:%.*]] = alloca <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, align 4
// SPIR32-NEXT: store ptr addrspace(1) [[A]], ptr [[A_ADDR]], align 4
// SPIR32-NEXT: store ptr addrspace(1) [[B]], ptr [[B_ADDR]], align 4
// SPIR32-NEXT: store i32 [[I]], ptr [[I_ADDR]], align 4
// SPIR32-NEXT: store i32 0, ptr [[FLAGS]], align 4
// SPIR32-NEXT: [[TMP0:%.*]] = load target("spirv.Queue"), ptr [[DEFAULT_QUEUE]], align 4
// SPIR32-NEXT: [[TMP1:%.*]] = load i32, ptr [[FLAGS]], align 4
// SPIR32-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 [[TMP]], ptr align 4 [[NDRANGE]], i32 4, i1 false)
// SPIR32-NEXT: [[BLOCK_SIZE:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 0
// SPIR32-NEXT: store i32 24, ptr [[BLOCK_SIZE]], align 4
// SPIR32-NEXT: [[BLOCK_ALIGN:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 1
// SPIR32-NEXT: store i32 4, ptr [[BLOCK_ALIGN]], align 4
// SPIR32-NEXT: [[BLOCK_INVOKE:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 2
// SPIR32-NEXT: store ptr addrspace(4) addrspacecast (ptr @__device_side_enqueue_block_invoke to ptr addrspace(4)), ptr [[BLOCK_INVOKE]], align 4
// SPIR32-NEXT: [[BLOCK_CAPTURED:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 3
// SPIR32-NEXT: [[TMP2:%.*]] = load ptr addrspace(1), ptr [[A_ADDR]], align 4
// SPIR32-NEXT: store ptr addrspace(1) [[TMP2]], ptr [[BLOCK_CAPTURED]], align 4
// SPIR32-NEXT: [[BLOCK_CAPTURED1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 4
// SPIR32-NEXT: [[TMP3:%.*]] = load i32, ptr [[I_ADDR]], align 4
// SPIR32-NEXT: store i32 [[TMP3]], ptr [[BLOCK_CAPTURED1]], align 4
// SPIR32-NEXT: [[BLOCK_CAPTURED2:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 5
// SPIR32-NEXT: [[TMP4:%.*]] = load ptr addrspace(1), ptr [[B_ADDR]], align 4
// SPIR32-NEXT: store ptr addrspace(1) [[TMP4]], ptr [[BLOCK_CAPTURED2]], align 4
// SPIR32-NEXT: [[TMP5:%.*]] = addrspacecast ptr [[BLOCK]] to ptr addrspace(4)
// SPIR32-NEXT: [[TMP6:%.*]] = call spir_func i32 @__enqueue_kernel_basic(target("spirv.Queue") [[TMP0]], i32 [[TMP1]], ptr [[TMP]], ptr addrspace(4) addrspacecast (ptr @__device_side_enqueue_block_invoke_kernel to ptr addrspace(4)), ptr addrspace(4) [[TMP5]])
// SPIR32-NEXT: ret void
//
//
// SPIR32: Function Attrs: convergent noinline nounwind optnone
// SPIR32-LABEL: define internal spir_func void @__device_side_enqueue_block_invoke(
// SPIR32-SAME: ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR2:[0-9]+]] {
// SPIR32-NEXT: [[ENTRY:.*:]]
// SPIR32-NEXT: [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr addrspace(4), align 4
// SPIR32-NEXT: [[BLOCK_ADDR:%.*]] = alloca ptr addrspace(4), align 4
// SPIR32-NEXT: store ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR]], align 4
// SPIR32-NEXT: store ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], ptr [[BLOCK_ADDR]], align 4
// SPIR32-NEXT: [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 5
// SPIR32-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[BLOCK_CAPTURE_ADDR]], align 4
// SPIR32-NEXT: [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// SPIR32-NEXT: [[TMP1:%.*]] = load i32, ptr addrspace(4) [[BLOCK_CAPTURE_ADDR1]], align 4
// SPIR32-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr addrspace(1) [[TMP0]], i32 [[TMP1]]
// SPIR32-NEXT: [[TMP2:%.*]] = load float, ptr addrspace(1) [[ARRAYIDX]], align 4
// SPIR32-NEXT: [[TMP3:%.*]] = call float @llvm.fmuladd.f32(float 4.000000e+00, float [[TMP2]], float 1.000000e+00)
// SPIR32-NEXT: [[BLOCK_CAPTURE_ADDR2:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
// SPIR32-NEXT: [[TMP4:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[BLOCK_CAPTURE_ADDR2]], align 4
// SPIR32-NEXT: [[BLOCK_CAPTURE_ADDR3:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// SPIR32-NEXT: [[TMP5:%.*]] = load i32, ptr addrspace(4) [[BLOCK_CAPTURE_ADDR3]], align 4
// SPIR32-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds float, ptr addrspace(1) [[TMP4]], i32 [[TMP5]]
// SPIR32-NEXT: store float [[TMP3]], ptr addrspace(1) [[ARRAYIDX4]], align 4
// SPIR32-NEXT: ret void
//
//
// SPIR32: Function Attrs: convergent nounwind
// SPIR32-LABEL: define spir_kernel void @__device_side_enqueue_block_invoke_kernel(
// SPIR32-SAME: ptr addrspace(4) [[TMP0:%.*]]) #[[ATTR4:[0-9]+]] {
// SPIR32-NEXT: [[ENTRY:.*:]]
// SPIR32-NEXT: call spir_func void @__device_side_enqueue_block_invoke(ptr addrspace(4) [[TMP0]])
// SPIR32-NEXT: ret void
//
//
// STRICTFP: Function Attrs: convergent noinline norecurse nounwind optnone strictfp
// STRICTFP-LABEL: define dso_local spir_kernel void @device_side_enqueue(
// STRICTFP-SAME: ptr addrspace(1) align 4 [[A:%.*]], ptr addrspace(1) align 4 [[B:%.*]], i32 [[I:%.*]]) #[[ATTR0:[0-9]+]] !kernel_arg_addr_space [[META2:![0-9]+]] !kernel_arg_access_qual [[META3:![0-9]+]] !kernel_arg_type [[META4:![0-9]+]] !kernel_arg_base_type [[META4]] !kernel_arg_type_qual [[META5:![0-9]+]] {
// STRICTFP-NEXT: [[ENTRY:.*:]]
// STRICTFP-NEXT: [[A_ADDR:%.*]] = alloca ptr addrspace(1), align 4
// STRICTFP-NEXT: [[B_ADDR:%.*]] = alloca ptr addrspace(1), align 4
// STRICTFP-NEXT: [[I_ADDR:%.*]] = alloca i32, align 4
// STRICTFP-NEXT: store ptr addrspace(1) [[A]], ptr [[A_ADDR]], align 4
// STRICTFP-NEXT: store ptr addrspace(1) [[B]], ptr [[B_ADDR]], align 4
// STRICTFP-NEXT: store i32 [[I]], ptr [[I_ADDR]], align 4
// STRICTFP-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr [[A_ADDR]], align 4
// STRICTFP-NEXT: [[TMP1:%.*]] = load ptr addrspace(1), ptr [[B_ADDR]], align 4
// STRICTFP-NEXT: [[TMP2:%.*]] = load i32, ptr [[I_ADDR]], align 4
// STRICTFP-NEXT: call spir_func void @__clang_ocl_kern_imp_device_side_enqueue(ptr addrspace(1) align 4 [[TMP0]], ptr addrspace(1) align 4 [[TMP1]], i32 [[TMP2]]) #[[ATTR5:[0-9]+]]
// STRICTFP-NEXT: ret void
//
//
// STRICTFP: Function Attrs: convergent noinline norecurse nounwind optnone strictfp
// STRICTFP-LABEL: define dso_local spir_func void @__clang_ocl_kern_imp_device_side_enqueue(
// STRICTFP-SAME: ptr addrspace(1) align 4 [[A:%.*]], ptr addrspace(1) align 4 [[B:%.*]], i32 [[I:%.*]]) #[[ATTR0]] !kernel_arg_addr_space [[META2]] !kernel_arg_access_qual [[META3]] !kernel_arg_type [[META4]] !kernel_arg_base_type [[META4]] !kernel_arg_type_qual [[META5]] {
// STRICTFP-NEXT: [[ENTRY:.*:]]
// STRICTFP-NEXT: [[A_ADDR:%.*]] = alloca ptr addrspace(1), align 4
// STRICTFP-NEXT: [[B_ADDR:%.*]] = alloca ptr addrspace(1), align 4
// STRICTFP-NEXT: [[I_ADDR:%.*]] = alloca i32, align 4
// STRICTFP-NEXT: [[DEFAULT_QUEUE:%.*]] = alloca target("spirv.Queue"), align 4
// STRICTFP-NEXT: [[FLAGS:%.*]] = alloca i32, align 4
// STRICTFP-NEXT: [[NDRANGE:%.*]] = alloca [[STRUCT_NDRANGE_T:%.*]], align 4
// STRICTFP-NEXT: [[TMP:%.*]] = alloca [[STRUCT_NDRANGE_T]], align 4
// STRICTFP-NEXT: [[BLOCK:%.*]] = alloca <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, align 4
// STRICTFP-NEXT: store ptr addrspace(1) [[A]], ptr [[A_ADDR]], align 4
// STRICTFP-NEXT: store ptr addrspace(1) [[B]], ptr [[B_ADDR]], align 4
// STRICTFP-NEXT: store i32 [[I]], ptr [[I_ADDR]], align 4
// STRICTFP-NEXT: store i32 0, ptr [[FLAGS]], align 4
// STRICTFP-NEXT: [[TMP0:%.*]] = load target("spirv.Queue"), ptr [[DEFAULT_QUEUE]], align 4
// STRICTFP-NEXT: [[TMP1:%.*]] = load i32, ptr [[FLAGS]], align 4
// STRICTFP-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 [[TMP]], ptr align 4 [[NDRANGE]], i32 4, i1 false) #[[ATTR6:[0-9]+]]
// STRICTFP-NEXT: [[BLOCK_SIZE:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 0
// STRICTFP-NEXT: store i32 24, ptr [[BLOCK_SIZE]], align 4
// STRICTFP-NEXT: [[BLOCK_ALIGN:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 1
// STRICTFP-NEXT: store i32 4, ptr [[BLOCK_ALIGN]], align 4
// STRICTFP-NEXT: [[BLOCK_INVOKE:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 2
// STRICTFP-NEXT: store ptr addrspace(4) addrspacecast (ptr @__device_side_enqueue_block_invoke to ptr addrspace(4)), ptr [[BLOCK_INVOKE]], align 4
// STRICTFP-NEXT: [[BLOCK_CAPTURED:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 3
// STRICTFP-NEXT: [[TMP2:%.*]] = load ptr addrspace(1), ptr [[A_ADDR]], align 4
// STRICTFP-NEXT: store ptr addrspace(1) [[TMP2]], ptr [[BLOCK_CAPTURED]], align 4
// STRICTFP-NEXT: [[BLOCK_CAPTURED1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 4
// STRICTFP-NEXT: [[TMP3:%.*]] = load i32, ptr [[I_ADDR]], align 4
// STRICTFP-NEXT: store i32 [[TMP3]], ptr [[BLOCK_CAPTURED1]], align 4
// STRICTFP-NEXT: [[BLOCK_CAPTURED2:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr [[BLOCK]], i32 0, i32 5
// STRICTFP-NEXT: [[TMP4:%.*]] = load ptr addrspace(1), ptr [[B_ADDR]], align 4
// STRICTFP-NEXT: store ptr addrspace(1) [[TMP4]], ptr [[BLOCK_CAPTURED2]], align 4
// STRICTFP-NEXT: [[TMP5:%.*]] = addrspacecast ptr [[BLOCK]] to ptr addrspace(4)
// STRICTFP-NEXT: [[TMP6:%.*]] = call spir_func i32 @__enqueue_kernel_basic(target("spirv.Queue") [[TMP0]], i32 [[TMP1]], ptr [[TMP]], ptr addrspace(4) addrspacecast (ptr @__device_side_enqueue_block_invoke_kernel to ptr addrspace(4)), ptr addrspace(4) [[TMP5]]) #[[ATTR6]]
// STRICTFP-NEXT: ret void
//
//
// STRICTFP: Function Attrs: convergent noinline nounwind optnone strictfp
// STRICTFP-LABEL: define internal spir_func void @__device_side_enqueue_block_invoke(
// STRICTFP-SAME: ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR2:[0-9]+]] {
// STRICTFP-NEXT: [[ENTRY:.*:]]
// STRICTFP-NEXT: [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca ptr addrspace(4), align 4
// STRICTFP-NEXT: [[BLOCK_ADDR:%.*]] = alloca ptr addrspace(4), align 4
// STRICTFP-NEXT: store ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], ptr [[DOTBLOCK_DESCRIPTOR_ADDR]], align 4
// STRICTFP-NEXT: store ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], ptr [[BLOCK_ADDR]], align 4
// STRICTFP-NEXT: [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 5
// STRICTFP-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[BLOCK_CAPTURE_ADDR]], align 4
// STRICTFP-NEXT: [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// STRICTFP-NEXT: [[TMP1:%.*]] = load i32, ptr addrspace(4) [[BLOCK_CAPTURE_ADDR1]], align 4
// STRICTFP-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr addrspace(1) [[TMP0]], i32 [[TMP1]]
// STRICTFP-NEXT: [[TMP2:%.*]] = load float, ptr addrspace(1) [[ARRAYIDX]], align 4
// STRICTFP-NEXT: [[TMP3:%.*]] = call float @llvm.experimental.constrained.fmuladd.f32(float 4.000000e+00, float [[TMP2]], float 1.000000e+00, metadata !"round.tonearest", metadata !"fpexcept.strict") #[[ATTR6]]
// STRICTFP-NEXT: [[BLOCK_CAPTURE_ADDR2:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 3
// STRICTFP-NEXT: [[TMP4:%.*]] = load ptr addrspace(1), ptr addrspace(4) [[BLOCK_CAPTURE_ADDR2]], align 4
// STRICTFP-NEXT: [[BLOCK_CAPTURE_ADDR3:%.*]] = getelementptr inbounds nuw <{ i32, i32, ptr addrspace(4), ptr addrspace(1), i32, ptr addrspace(1) }>, ptr addrspace(4) [[DOTBLOCK_DESCRIPTOR]], i32 0, i32 4
// STRICTFP-NEXT: [[TMP5:%.*]] = load i32, ptr addrspace(4) [[BLOCK_CAPTURE_ADDR3]], align 4
// STRICTFP-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds float, ptr addrspace(1) [[TMP4]], i32 [[TMP5]]
// STRICTFP-NEXT: store float [[TMP3]], ptr addrspace(1) [[ARRAYIDX4]], align 4
// STRICTFP-NEXT: ret void
//
//
// STRICTFP: Function Attrs: convergent nounwind
// STRICTFP-LABEL: define spir_kernel void @__device_side_enqueue_block_invoke_kernel(
// STRICTFP-SAME: ptr addrspace(4) [[TMP0:%.*]]) #[[ATTR4:[0-9]+]] {
// STRICTFP-NEXT: [[ENTRY:.*:]]
// STRICTFP-NEXT: call spir_func void @__device_side_enqueue_block_invoke(ptr addrspace(4) [[TMP0]]) #[[ATTR6]]
// STRICTFP-NEXT: ret void
//
//.
// SPIR32: attributes #[[ATTR0]] = { convergent noinline norecurse nounwind optnone "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }
// SPIR32: attributes #[[ATTR1:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
// SPIR32: attributes #[[ATTR2]] = { convergent noinline nounwind optnone "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
// SPIR32: attributes #[[ATTR3:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
// SPIR32: attributes #[[ATTR4]] = { convergent nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
// SPIR32: attributes #[[ATTR5]] = { convergent nounwind "uniform-work-group-size"="true" }
//.
// STRICTFP: attributes #[[ATTR0]] = { convergent noinline norecurse nounwind optnone strictfp "stack-protector-buffer-size"="8" "uniform-work-group-size"="false" }
// STRICTFP: attributes #[[ATTR1:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
// STRICTFP: attributes #[[ATTR2]] = { convergent noinline nounwind optnone strictfp "stack-protector-buffer-size"="8" }
// STRICTFP: attributes #[[ATTR3:[0-9]+]] = { nocallback nofree nosync nounwind strictfp willreturn memory(inaccessiblemem: readwrite) }
// STRICTFP: attributes #[[ATTR4]] = { convergent nounwind "stack-protector-buffer-size"="8" }
// STRICTFP: attributes #[[ATTR5]] = { convergent nounwind strictfp "uniform-work-group-size"="false" }
// STRICTFP: attributes #[[ATTR6]] = { strictfp }
//.
// SPIR32: [[META0:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
// SPIR32: [[META1:![0-9]+]] = !{i32 2, i32 0}
// SPIR32: [[META2]] = !{i32 1, i32 1, i32 0}
// SPIR32: [[META3]] = !{!"none", !"none", !"none"}
// SPIR32: [[META4]] = !{!"float*", !"float*", !"int"}
// SPIR32: [[META5]] = !{!"", !"", !""}
//.
// STRICTFP: [[META0:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
// STRICTFP: [[META1:![0-9]+]] = !{i32 2, i32 0}
// STRICTFP: [[META2]] = !{i32 1, i32 1, i32 0}
// STRICTFP: [[META3]] = !{!"none", !"none", !"none"}
// STRICTFP: [[META4]] = !{!"float*", !"float*", !"int"}
// STRICTFP: [[META5]] = !{!"", !"", !""}
//.
|