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
|
// RUN: %clang_cc1 %s -triple nvptx-unknown-unknown -fcuda-is-device -emit-llvm -o - | FileCheck %s
#include "Inputs/cuda.h"
#define MAX_THREADS_PER_BLOCK 256
#define MIN_BLOCKS_PER_MP 2
// Test both max threads per block and Min cta per sm.
extern "C" {
__global__ void
__launch_bounds__( MAX_THREADS_PER_BLOCK, MIN_BLOCKS_PER_MP )
Kernel1()
{
}
}
// CHECK: !{{[0-9]+}} = !{void ()* @Kernel1, !"maxntidx", i32 256}
// CHECK: !{{[0-9]+}} = !{void ()* @Kernel1, !"minctasm", i32 2}
// Test only max threads per block. Min cta per sm defaults to 0, and
// CodeGen doesn't output a zero value for minctasm.
extern "C" {
__global__ void
__launch_bounds__( MAX_THREADS_PER_BLOCK )
Kernel2()
{
}
}
// CHECK: !{{[0-9]+}} = !{void ()* @Kernel2, !"maxntidx", i32 256}
template <int max_threads_per_block>
__global__ void
__launch_bounds__(max_threads_per_block)
Kernel3()
{
}
template void Kernel3<MAX_THREADS_PER_BLOCK>();
// CHECK: !{{[0-9]+}} = !{void ()* @{{.*}}Kernel3{{.*}}, !"maxntidx", i32 256}
template <int max_threads_per_block, int min_blocks_per_mp>
__global__ void
__launch_bounds__(max_threads_per_block, min_blocks_per_mp)
Kernel4()
{
}
template void Kernel4<MAX_THREADS_PER_BLOCK, MIN_BLOCKS_PER_MP>();
// CHECK: !{{[0-9]+}} = !{void ()* @{{.*}}Kernel4{{.*}}, !"maxntidx", i32 256}
// CHECK: !{{[0-9]+}} = !{void ()* @{{.*}}Kernel4{{.*}}, !"minctasm", i32 2}
const int constint = 100;
template <int max_threads_per_block, int min_blocks_per_mp>
__global__ void
__launch_bounds__(max_threads_per_block + constint,
min_blocks_per_mp + max_threads_per_block)
Kernel5()
{
}
template void Kernel5<MAX_THREADS_PER_BLOCK, MIN_BLOCKS_PER_MP>();
// CHECK: !{{[0-9]+}} = !{void ()* @{{.*}}Kernel5{{.*}}, !"maxntidx", i32 356}
// CHECK: !{{[0-9]+}} = !{void ()* @{{.*}}Kernel5{{.*}}, !"minctasm", i32 258}
// Make sure we don't emit negative launch bounds values.
__global__ void
__launch_bounds__( -MAX_THREADS_PER_BLOCK, MIN_BLOCKS_PER_MP )
Kernel6()
{
}
// CHECK-NOT: !{{[0-9]+}} = !{void ()* @{{.*}}Kernel6{{.*}}, !"maxntidx",
// CHECK: !{{[0-9]+}} = !{void ()* @{{.*}}Kernel6{{.*}}, !"minctasm",
__global__ void
__launch_bounds__( MAX_THREADS_PER_BLOCK, -MIN_BLOCKS_PER_MP )
Kernel7()
{
}
// CHECK: !{{[0-9]+}} = !{void ()* @{{.*}}Kernel7{{.*}}, !"maxntidx",
// CHECK-NOT: !{{[0-9]+}} = !{void ()* @{{.*}}Kernel7{{.*}}, !"minctasm",
|
