File: kernels-have-spir-cc-by-default.cl

package info (click to toggle)
llvm-toolchain-13 1%3A13.0.1-11
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,418,840 kB
  • sloc: cpp: 5,290,826; ansic: 996,570; asm: 544,593; python: 188,212; objc: 72,027; lisp: 30,291; f90: 25,395; sh: 24,898; javascript: 9,780; pascal: 9,398; perl: 7,484; ml: 5,432; awk: 3,523; makefile: 2,913; xml: 953; cs: 573; fortran: 539
file content (65 lines) | stat: -rw-r--r-- 2,043 bytes parent folder | download | duplicates (3)
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
// RUN: %clang_cc1 %s -cl-std=CL1.2 -emit-llvm -triple x86_64-unknown-unknown -o - | FileCheck %s
// RUN: %clang_cc1 %s -cl-std=CL1.2 -emit-llvm -triple amdgcn-unknown-unknown -o - | FileCheck -check-prefixes=AMDGCN %s
// Test that the kernels always use the SPIR calling convention
// to have unambiguous mapping of arguments to feasibly implement
// clSetKernelArg().

typedef struct int_single {
    int a;
} int_single;

typedef struct int_pair {
    long a;
    long b;
} int_pair;

typedef struct test_struct {
    int elementA;
    int elementB;
    long elementC;
    char elementD;
    long elementE;
    float elementF;
    short elementG;
    double elementH;
} test_struct;

kernel void test_single(int_single input, global int* output) {
// CHECK: spir_kernel
// AMDGCN: define{{.*}} amdgpu_kernel void @test_single
// CHECK: struct.int_single* nocapture {{.*}} byval(%struct.int_single)
// CHECK: i32* nocapture %output
 output[0] = input.a;
}

kernel void test_pair(int_pair input, global int* output) {
// CHECK: spir_kernel
// AMDGCN: define{{.*}} amdgpu_kernel void @test_pair
// CHECK: struct.int_pair* nocapture {{.*}} byval(%struct.int_pair)
// CHECK: i32* nocapture %output
 output[0] = (int)input.a;
 output[1] = (int)input.b;
}

kernel void test_kernel(test_struct input, global int* output) {
// CHECK: spir_kernel
// AMDGCN: define{{.*}} amdgpu_kernel void @test_kernel
// CHECK: struct.test_struct* nocapture {{.*}} byval(%struct.test_struct)
// CHECK: i32* nocapture %output
 output[0] = input.elementA;
 output[1] = input.elementB;
 output[2] = (int)input.elementC;
 output[3] = (int)input.elementD;
 output[4] = (int)input.elementE;
 output[5] = (int)input.elementF;
 output[6] = (int)input.elementG;
 output[7] = (int)input.elementH;
};

void test_function(int_pair input, global int* output) {
// CHECK-NOT: spir_kernel
// AMDGCN-NOT: define{{.*}} amdgpu_kernel void @test_function
// CHECK: i64 %input.coerce0, i64 %input.coerce1, i32* nocapture %output
 output[0] = (int)input.a;
 output[1] = (int)input.b;
}