cudarc 0.19.6

Safe and minimal CUDA bindings
Documentation 
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
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243

//! Safe CUDA wrappers for:
//!
//! | library | dynamic load | dynamic link | static link |
//! | --- | --- | --- | --- |
//! | [CUDA driver](https://docs.nvidia.com/cuda/cuda-driver-api/index.html) | ✅ | ✅ | ❌ |
//! | [NVRTC](https://docs.nvidia.com/cuda/nvrtc/index.html) | ✅ | ✅ | ✅ |
//! | [cuRAND](https://docs.nvidia.com/cuda/curand/index.html) | ✅ | ✅ | ✅ |
//! | [cuBLAS](https://docs.nvidia.com/cuda/cublas/index.html) | ✅ | ✅ | ✅ |
//! | [cuBLASLt](https://docs.nvidia.com/cuda/cublas/#using-the-cublaslt-api) | ✅ | ✅ | ✅ |
//! | [NCCL](https://docs.nvidia.com/deeplearning/nccl/user-guide/docs/) | ✅ | ✅ | ✅ |
//! | [cuDNN](https://docs.nvidia.com/deeplearning/cudnn/backend/latest/api/overview.html) | ✅ | ✅ | ✅ |
//! | [cuSPARSE](https://docs.nvidia.com/cuda/cusparse/) | ✅ | ✅ | ✅ |
//! | [cuSOLVER](https://docs.nvidia.com/cuda/cusolver/) | ✅ | ✅ | ❌ |
//! | [cuFILE](https://docs.nvidia.com/gpudirect-storage/api-reference-guide/index.html#introduction) | ✅ | ✅ | ✅ |
//! | [CUPTI](https://docs.nvidia.com/cupti/) | ✅ | ✅ | ✅ |
//! | [nvtx](https://nvidia.github.io/NVTX/) | ✅ | ✅ | ❌ |
//! | [cuTENSOR](https://docs.nvidia.com/cuda/cutensor/index.html) | ✅ | ✅ | ❌ |
//!
//! CUDA Versions supported
//! - 11.4-11.8
//! - 12.0-12.9
//! - 13.0
//!
//! CUDNN versions supported:
//! - 9.12.0
//!
//! NCCL versions supported:
//! - 2.28.3
//!
//! # Configuring CUDA version
//!
//! Select cuda version with one of:
//! - `-F cuda-version-from-build-system`: At build time will get the cuda toolkit version using `nvcc`
//!     - `-F fallback-latest`: can be used to control behavior if this fails. default is not enabled, which will cause the build
//!       script to panic. if `-F fallback-latest` is enabled, we will use the highest bindings we have.
//! - `-F cuda-<major>0<minor>0` to build for a specific version of cuda
//!
//! # Configuring linking
//!
//! By default we use `-F dynamic-loading`, which will not require any libraries to be present at build time.
//!
//! You can also enable `-F dynamic-linking` or `-F static-linking` for your use case.
//!
//! # Getting started
//!
//! **See [driver] for more examples**
//!
//! At the core is the [driver] API, which exposes a bunch of structs, but the main ones are:
//!
//! 1. [`driver::CudaContext`] is a handle to a specific device ordinal (e.g. 0, 1, 2, ...)
//! 2. [`driver::CudaStream`] is how you submit work to a device
//! 3. [`driver::CudaSlice<T>`], which represents a [`Vec<T>`] on the device, can be allocated
//!    using the aforementioned [`driver::CudaStream`].
//!
//! Here is a table of similar concepts between CPU and Cuda:
//!
//! | Concept | CPU | Cuda |
//! | --- | --- | --- |
//! | Memory allocator | [`std::alloc::GlobalAlloc`] | [`driver::CudaContext`] |
//! | List of values on heap | [`Vec<T>`] | [`driver::CudaSlice<T>`] |
//! | Slice | `&[T]` | [`driver::CudaView<T>`] |
//! | Mutable Slice  | `&mut [T]` | [`driver::CudaViewMut<T>`] |
//! | Function | [`Fn`] | [`driver::CudaFunction`] |
//! | Calling a function | `my_function(a, b, c)` | [`driver::LaunchArgs::launch()`] |
//! | Thread | [`std::thread::Thread`] | [`driver::CudaStream`] |
//!
//! # Combining the different APIs
//!
//! All the highest level apis have been designed to work together.
//!
//! ## nvrtc
//!
//! [`nvrtc::compile_ptx()`] outputs a [`nvrtc::Ptx`], which can
//! be loaded into a device with [`driver::CudaContext::load_module()`].
//!
//! ## cublas
//!
//! [cublas::CudaBlas] can perform gemm operations using [`cublas::Gemm<T>`],
//! and [`cublas::Gemv<T>`]. Both of these traits can generically accept memory
//! allocated by the driver in the form of: [`driver::CudaSlice<T>`],
//! [`driver::CudaView<T>`], and [`driver::CudaViewMut<T>`].
//!
//! ## curand
//!
//! [curand::CudaRng] can fill a [`driver::CudaSlice<T>`] with random data, based on
//! one of its available distributions.
//!
//! # Combining safe/result/sys
//!
//! The result and sys levels are very inter-changeable for each API. However,
//! the safe apis don't necessarily allow you to mix in the result level. This
//! is to encourage going through the safe API when possible.
//!
//! **If you need some functionality that isn't present in the safe api, please
//! open a ticket.**
//!
//! # crate organization
//!
//! Each of the modules for the above is organized into three levels:
//! 1. A `safe` module which provides safe abstractions over the `result` module
//! 2. A `result` which is a thin wrapper around the `sys` module to ensure all functions return [Result]
//! 3. A `sys` module which contains the raw FFI bindings
//!
//! | API | Safe | Result | Sys |
//! | --- | --- | --- | --- |
//! | driver | [driver::safe] | [driver::result] | [driver::sys] |
//! | cublas | [cublas::safe] | [cublas::result] | [cublas::sys] |
//! | cublaslt | [cublaslt::safe] | [cublaslt::result] | [cublaslt::sys] |
//! | nvrtc | [nvrtc::safe] | [nvrtc::result] | [nvrtc::sys] |
//! | curand | [curand::safe] | [curand::result] | [curand::sys] |
//! | cudnn | [cudnn::safe] | [cudnn::result] | [cudnn::sys] |
//! | cufft | [cufft::safe] | [cufft::result] | [cufft::sys] |
//! | cusparse | - | [cusparse::result] | [cusparse::sys] |
//! | cusolver | [cusolver::safe] | [cusolver::result] | [cusolver::sys] |
//! | cusolvermg | [cusolvermg::safe] | [cusolvermg::result] | [cusolvermg::sys] |
//! | cupti | - | [cupti::result] | [cupti::sys] |
//! | nvtx | [nvtx::safe] | [nvtx::result] | [nvtx::sys] |
//! | cutensor | [cutensor::safe] | [cutensor::result] | [cutensor::sys] |

#![cfg_attr(feature = "no-std", no_std)]

#[cfg(feature = "no-std")]
extern crate alloc;
#[cfg(feature = "no-std")]
extern crate no_std_compat as std;

#[cfg(feature = "cublas")]
pub mod cublas;
#[cfg(feature = "cublaslt")]
pub mod cublaslt;
#[cfg(any(
    feature = "cudnn-08009",
    feature = "cudnn-09010",
    feature = "cudnn-09021",
))]
pub mod cudnn;
#[cfg(all(
    feature = "cufft",
    not(any(
        feature = "cuda-11040",
        feature = "cuda-11050",
        feature = "cuda-11060",
        feature = "cuda-11070",
        feature = "cuda-11080",
    ))
))]
pub mod cufft;
#[cfg(feature = "cufile")]
pub mod cufile;
#[cfg(feature = "cupti")]
pub mod cupti;
#[cfg(feature = "curand")]
pub mod curand;
#[cfg(feature = "cusolver")]
pub mod cusolver;
#[cfg(feature = "cusolvermg")]
pub mod cusolvermg;
#[cfg(feature = "cusparse")]
pub mod cusparse;
#[cfg(all(
    any(
        feature = "cutensor-02003",
        feature = "cutensor-02004",
        feature = "cutensor-02005",
        feature = "cutensor-02006",
    ),
    not(any(
        feature = "cuda-11040",
        feature = "cuda-11050",
        feature = "cuda-11060",
        feature = "cuda-11070",
        feature = "cuda-11080",
    ))
))]
pub mod cutensor;
#[cfg(feature = "driver")]
pub mod driver;
#[cfg(any(
    feature = "nccl-02022",
    feature = "nccl-02024",
    feature = "nccl-02025",
    feature = "nccl-02026",
    feature = "nccl-02027",
    feature = "nccl-02028",
    feature = "nccl-02029",
    feature = "nccl-02030",
))]
pub mod nccl;
#[cfg(feature = "nvrtc")]
pub mod nvrtc;
#[cfg(feature = "nvtx")]
pub mod nvtx;
#[cfg(feature = "runtime")]
pub mod runtime;

pub mod types;

#[cfg(feature = "dynamic-loading")]
pub(crate) fn panic_no_lib_found<S: std::fmt::Debug>(lib_name: &str, choices: &[S]) -> ! {
    panic!("Unable to dynamically load the \"{lib_name}\" shared library - searched for library names: {choices:?}. Ensure that `LD_LIBRARY_PATH` has the correct path to the installed library. If the shared library is present on the system under a different name than one of those listed above, please open a GitHub issue.");
}

#[cfg(feature = "dynamic-loading")]
pub fn get_lib_name_candidates(lib_name: &str) -> std::vec::Vec<std::string::String> {
    use std::env::consts::{DLL_PREFIX, DLL_SUFFIX};

    let pointer_width = if cfg!(target_pointer_width = "32") {
        "32"
    } else if cfg!(target_pointer_width = "64") {
        "64"
    } else {
        panic!("Unsupported target pointer width")
    };

    let major = env!("CUDA_MAJOR_VERSION");
    let minor = env!("CUDA_MINOR_VERSION");

    [
        std::format!("{DLL_PREFIX}{lib_name}{DLL_SUFFIX}"),
        std::format!("{DLL_PREFIX}{lib_name}{pointer_width}{DLL_SUFFIX}"),
        std::format!("{DLL_PREFIX}{lib_name}{pointer_width}_{major}{DLL_SUFFIX}"),
        std::format!("{DLL_PREFIX}{lib_name}{pointer_width}_{major}{minor}{DLL_SUFFIX}"),
        std::format!("{DLL_PREFIX}{lib_name}{pointer_width}_{major}{minor}_0{DLL_SUFFIX}"),
        std::format!("{DLL_PREFIX}{lib_name}{pointer_width}_{major}0_{minor}{DLL_SUFFIX}"),
        // See issue #242
        std::format!("{DLL_PREFIX}{lib_name}{pointer_width}_10{DLL_SUFFIX}"),
        std::format!("{DLL_PREFIX}{lib_name}{pointer_width}_11{DLL_SUFFIX}"),
        std::format!("{DLL_PREFIX}{lib_name}{pointer_width}_12{DLL_SUFFIX}"),
        // See issue #246
        std::format!("{DLL_PREFIX}{lib_name}{pointer_width}_{major}0_0{DLL_SUFFIX}"),
        // See issue #260
        std::format!("{DLL_PREFIX}{lib_name}{pointer_width}_9{DLL_SUFFIX}"),
        // See issue #274
        std::format!("{DLL_PREFIX}{lib_name}{DLL_SUFFIX}.{major}"),
        std::format!("{DLL_PREFIX}{lib_name}{DLL_SUFFIX}.12"),
        std::format!("{DLL_PREFIX}{lib_name}{DLL_SUFFIX}.11"),
        std::format!("{DLL_PREFIX}{lib_name}{DLL_SUFFIX}.10"),
        std::format!("{DLL_PREFIX}{lib_name}{DLL_SUFFIX}.9"),
        // See issue #296
        std::format!("{DLL_PREFIX}{lib_name}{DLL_SUFFIX}.1"),
    ]
    .into()
}