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
|
// Tests the driver when targeting the NVPTX architecture directly without a
// host toolchain to perform CUDA mappings.
//
// Test the generated phases when targeting NVPTX.
//
// RUN: %clang -target nvptx64-nvidia-cuda -ccc-print-phases %s 2>&1 \
// RUN: | FileCheck -check-prefix=PHASES %s
// PHASES: 0: input, "[[INPUT:.+]]", c
// PHASES-NEXT: 1: preprocessor, {0}, cpp-output
// PHASES-NEXT: 2: compiler, {1}, ir
// PHASES-NEXT: 3: backend, {2}, assembler
// PHASES-NEXT: 4: assembler, {3}, object
// PHASES-NEXT: 5: linker, {4}, image
//
// Test the generated bindings when targeting NVPTX.
//
// RUN: %clang -target nvptx64-nvidia-cuda -ccc-print-bindings %s 2>&1 \
// RUN: | FileCheck -check-prefix=BINDINGS %s
// BINDINGS: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[PTX:.+]].s"
// BINDINGS-NEXT: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[PTX]].s"], output: "[[CUBIN:.+]].o"
// BINDINGS-NEXT: "nvptx64-nvidia-cuda" - "NVPTX::Linker", inputs: ["[[CUBIN]].o"], output: "a.out"
//
// Test the generated arguments to the CUDA binary utils when targeting NVPTX.
// Ensure that the '.o' files are converted to '.cubin' if produced internally.
//
// RUN: %clang -target nvptx64-nvidia-cuda -march=sm_61 -### %s 2>&1 \
// RUN: | FileCheck -check-prefix=ARGS %s
// ARGS: -cc1" "-triple" "nvptx64-nvidia-cuda" "-S" {{.*}} "-target-cpu" "sm_61" "-target-feature" "+ptx{{[0-9]+}}" {{.*}} "-o" "[[PTX:.+]].s"
// ARGS-NEXT: ptxas{{.*}}"-m64" "-O0" "--gpu-name" "sm_61" "--output-file" "[[CUBIN:.+]].o" "[[PTX]].s" "-c"
// ARGS-NEXT: clang-nvlink-wrapper{{.*}}"-o" "a.out" "-arch" "sm_61"{{.*}}"[[CUBIN]].o"
//
// Test the generated arguments to the CUDA binary utils when targeting NVPTX.
// Ensure that we emit '.o' files if compiled with '-c'
//
// RUN: %clang -target nvptx64-nvidia-cuda -march=sm_61 -c -### %s 2>&1 \
// RUN: | FileCheck -check-prefix=OBJECT %s
// RUN: %clang -target nvptx64-nvidia-cuda -save-temps -march=sm_61 -c -### %s 2>&1 \
// RUN: | FileCheck -check-prefix=OBJECT %s
// OBJECT: -cc1" "-triple" "nvptx64-nvidia-cuda" "-S" {{.*}} "-target-cpu" "sm_61" "-target-feature" "+ptx{{[0-9]+}}" {{.*}} "-o" "[[PTX:.+]].s"
// OBJECT-NEXT: ptxas{{.*}}"-m64" "-O0" "--gpu-name" "sm_61" "--output-file" "[[OBJ:.+]].o" "[[PTX]].s" "-c"
//
// Test the generated arguments to the CUDA binary utils when targeting NVPTX.
// Ensure that we copy input '.o' files to '.cubin' files when linking.
//
// RUN: touch %t.o
// RUN: %clang -target nvptx64-nvidia-cuda -march=sm_61 -### %t.o 2>&1 \
// RUN: | FileCheck -check-prefix=LINK %s
// LINK: clang-nvlink-wrapper{{.*}}"-o" "a.out" "-arch" "sm_61"{{.*}}[[CUBIN:.+]].o
//
// Test to ensure that we enable handling global constructors in a freestanding
// Nvidia compilation.
//
// RUN: %clang -target nvptx64-nvidia-cuda -march=sm_70 %s -### 2>&1 \
// RUN: | FileCheck -check-prefix=LOWERING %s
// LOWERING: -cc1" "-triple" "nvptx64-nvidia-cuda" {{.*}} "-mllvm" "--nvptx-lower-global-ctor-dtor"
//
// Test passing arguments directly to nvlink.
//
// RUN: %clang -target nvptx64-nvidia-cuda -Wl,-v -Wl,a,b -march=sm_52 -### %s 2>&1 \
// RUN: | FileCheck -check-prefix=LINKER-ARGS %s
// LINKER-ARGS: clang-nvlink-wrapper{{.*}}"-v"{{.*}}"a" "b"
// Tests for handling a missing architecture.
//
// RUN: not %clang -target nvptx64-nvidia-cuda %s -### 2>&1 \
// RUN: | FileCheck -check-prefix=MISSING %s
// RUN: not %clang -target nvptx64-nvidia-cuda -march=generic %s -### 2>&1 \
// RUN: | FileCheck -check-prefix=MISSING %s
// MISSING: error: must pass in an explicit nvptx64 gpu architecture to 'ptxas'
// MISSING: error: must pass in an explicit nvptx64 gpu architecture to 'nvlink'
// RUN: %clang -target nvptx64-nvidia-cuda -flto -c %s -### 2>&1 \
// RUN: | FileCheck -check-prefix=GENERIC %s
// RUN: %clang -target nvptx64-nvidia-cuda -march=sm_52 -march=generic -flto -c %s -### 2>&1 \
// RUN: | FileCheck -check-prefix=GENERIC %s
// GENERIC-NOT: -cc1" "-triple" "nvptx64-nvidia-cuda" {{.*}} "-target-cpu"
|
