FindCUDAToolkit — CMake 4.1.0-rc1 Documentation (original) (raw)

Added in version 3.17.

This script locates the NVIDIA CUDA toolkit and the associated libraries, but does not require the CUDA language be enabled for a given project. This module does not search for the NVIDIA CUDA Samples.

Added in version 3.19: QNX support.

Search Behavior¶

The CUDA Toolkit search behavior uses the following order:

1. If the CUDA language has been enabled we will use the directory containing the compiler as the first search location for nvcc.
2. If the variable CMAKE_CUDA_COMPILER or the environment variable CUDACXX is defined, it will be used as the path to the nvcc executable.
3. If the CUDAToolkit_ROOT cmake configuration variable (e.g.,-DCUDAToolkit_ROOT=/some/path) or environment variable is defined, it will be searched. If both an environment variable and a configuration variable are specified, the configuration variable takes precedence.
   The directory specified here must be such that the executable nvcc or the appropriate version.txt or version.json file can be found underneath the specified directory.
4. If the CUDA_PATH environment variable is defined, it will be searched for nvcc.
5. The user's path is searched for nvcc using find_program(). If this is found, no subsequent search attempts are performed. Users are responsible for ensuring that the first nvcc to show up in the path is the desired path in the event that multiple CUDA Toolkits are installed.
6. On Unix systems, if the symbolic link /usr/local/cuda exists, this is used. No subsequent search attempts are performed. No default symbolic link location exists for the Windows platform.
7. The platform specific default install locations are searched. If exactly one candidate is found, this is used. The default CUDA Toolkit install locations searched are:

   Platform	Search Pattern
   macOS	/Developer/NVIDIA/CUDA-X.Y
   Other Unix	/usr/local/cuda-X.Y
   Windows	C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\vX.Y
   Where X.Y would be a specific version of the CUDA Toolkit, such as/usr/local/cuda-9.0 orC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0
   Note
   When multiple CUDA Toolkits are installed in the default location of a system (e.g., both /usr/local/cuda-9.0 and /usr/local/cuda-10.0exist but the /usr/local/cuda symbolic link does not exist), this package is marked as not found.
   There are too many factors involved in making an automatic decision in the presence of multiple CUDA Toolkits being installed. In this situation, users are encouraged to either (1) set CUDAToolkit_ROOT or (2) ensure that the correct nvcc executable shows up in $PATH forfind_program() to find.

Arguments¶

[<version>]

The [<version>] argument requests a version with which the package found should be compatible. See find_package version formatfor more details.

Options¶

REQUIRED

If specified, configuration will error if a suitable CUDA Toolkit is not found.

QUIET

If specified, the search for a suitable CUDA Toolkit will not produce any messages.

EXACT

If specified, the CUDA Toolkit is considered found only if the exactVERSION specified is recovered.

Imported Targets¶

An imported target named CUDA::toolkit is provided.

This module defines IMPORTED targets for each of the following libraries that are part of the CUDAToolkit:

• CUDA Runtime Library
• CUDA Driver Library
• cuBLAS
• cuDLA
• cuFile
• cuFFT
• cuRAND
• cuSOLVER
• cuSPARSE
• cuPTI
• NPP
• nvBLAS
• nvGRAPH
• nvJPEG
• nvidia-ML
• nvPTX Compiler
• nvRTC
• nvJitLink
• nvFatBin
• nvToolsExt
• nvtx3
• OpenCL
• cuLIBOS

CUDA Runtime Library¶

The CUDA Runtime library (cudart) are what most applications will typically need to link against to make any calls such as cudaMalloc, and cudaFree.

Targets Created:

• CUDA::cudart
• CUDA::cudart_static

CUDA Driver Library¶

The CUDA Driver library (cuda) are used by applications that use calls such as cuMemAlloc, and cuMemFree.

Targets Created:

• CUDA::cuda_driver

cuBLAS¶

The CUDA Basic Linear Algebra Subroutine library.

Targets Created:

• CUDA::cublas
• CUDA::cublas_static
• CUDA::cublasLt starting in CUDA 10.1
• CUDA::cublasLt_static starting in CUDA 10.1

cuDLA¶

Added in version 3.27.

The NVIDIA Tegra Deep Learning Accelerator library.

Targets Created:

• CUDA::cudla starting in CUDA 11.6

cuFile¶

Added in version 3.25.

The NVIDIA GPUDirect Storage cuFile library.

Targets Created:

• CUDA::cuFile starting in CUDA 11.4
• CUDA::cuFile_static starting in CUDA 11.4
• CUDA::cuFile_rdma starting in CUDA 11.4
• CUDA::cuFile_rdma_static starting in CUDA 11.4

cuFFT¶

The CUDA Fast Fourier Transform library.

Targets Created:

• CUDA::cufft
• CUDA::cufftw
• CUDA::cufft_static
• CUDA::cufft_static_nocallback starting in CUDA 9.2, requires CMake 3.23+
• CUDA::cufftw_static

cuRAND¶

The CUDA random number generation library.

Targets Created:

• CUDA::curand
• CUDA::curand_static

cuSOLVER¶

A GPU accelerated linear system solver library.

Targets Created:

• CUDA::cusolver
• CUDA::cusolver_static

cuSPARSE¶

The CUDA sparse matrix library.

Targets Created:

• CUDA::cusparse
• CUDA::cusparse_static

cupti¶

The NVIDIA CUDA Profiling Tools Interface.

Targets Created:

• CUDA::cupti
• CUDA::cupti_static

Added in version 3.27:

• CUDA::nvperf_host starting in CUDA 10.2
• CUDA::nvperf_host_static starting in CUDA 10.2
• CUDA::nvperf_target starting in CUDA 10.2
• CUDA::pcsamplingutil starting in CUDA 11.3

NPP¶

The NVIDIA 2D Image and Signal Processing Performance Primitives libraries.

Targets Created:

• nppc:
  • CUDA::nppc
  • CUDA::nppc_static
• nppial: Arithmetic and logical operation functions in nppi_arithmetic_and_logical_operations.h
  • CUDA::nppial
  • CUDA::nppial_static
• nppicc: Color conversion and sampling functions in nppi_color_conversion.h
  • CUDA::nppicc
  • CUDA::nppicc_static
• nppicom: JPEG compression and decompression functions in nppi_compression_functions.hRemoved starting in CUDA 11.0, use nvJPEG instead.
  • CUDA::nppicom
  • CUDA::nppicom_static
• nppidei: Data exchange and initialization functions in nppi_data_exchange_and_initialization.h
  • CUDA::nppidei
  • CUDA::nppidei_static
• nppif: Filtering and computer vision functions in nppi_filter_functions.h
  • CUDA::nppif
  • CUDA::nppif_static
• nppig: Geometry transformation functions found in nppi_geometry_transforms.h
  • CUDA::nppig
  • CUDA::nppig_static
• nppim: Morphological operation functions found in nppi_morphological_operations.h
  • CUDA::nppim
  • CUDA::nppim_static
• nppist: Statistics and linear transform in nppi_statistics_functions.h and nppi_linear_transforms.h
  • CUDA::nppist
  • CUDA::nppist_static
• nppisu: Memory support functions in nppi_support_functions.h
  • CUDA::nppisu
  • CUDA::nppisu_static
• nppitc: Threshold and compare operation functions in nppi_threshold_and_compare_operations.h
  • CUDA::nppitc
  • CUDA::nppitc_static
• npps:
  • CUDA::npps
  • CUDA::npps_static

nvBLAS¶

The GPU-accelerated drop-in BLAS library. This is a shared library only.

Targets Created:

• CUDA::nvblas

nvGRAPH¶

A GPU-accelerated graph analytics library. Removed starting in CUDA 11.0

Targets Created:

• CUDA::nvgraph
• CUDA::nvgraph_static

nvJPEG¶

A GPU-accelerated JPEG codec library. Introduced in CUDA 10.

Targets Created:

• CUDA::nvjpeg
• CUDA::nvjpeg_static

nvPTX Compiler¶

Added in version 3.25.

The PTX Compiler APIs. These are a set of APIs which can be used to compile a PTX program into GPU assembly code. Introduced in CUDA 11.1 This is a static library only.

Targets Created:

• CUDA::nvptxcompiler_static starting in CUDA 11.1

nvRTC¶

A runtime compilation library for CUDA.

Targets Created:

• CUDA::nvrtc

Added in version 3.26:

• CUDA::nvrtc_builtins
• CUDA::nvrtc_static starting in CUDA 11.5
• CUDA::nvrtc_builtins_static starting in CUDA 11.5

nvJitLink¶

The JIT Link APIs.

Targets Created:

• CUDA::nvJitLink starting in CUDA 12.0
• CUDA::nvJitLink_static starting in CUDA 12.0

nvFatBin¶

Added in version 3.30.

The Fatbin Creator APIs.

Targets Created:

• CUDA::nvfatbin starting in CUDA 12.4
• CUDA::nvfatbin_static starting in CUDA 12.4

nvidia-ML¶

The NVIDIA Management Library.

Targets Created:

• CUDA::nvml
• CUDA::nvml_static starting in CUDA 12.4

Added in version 3.31: Added CUDA::nvml_static.

nvToolsExt¶

Deprecated since version 3.25: With CUDA 10.0+, use nvtx3. Starting in CUDA 12.9 the nvToolsExt library no longer exists

The legacy NVIDIA Tools Extension. This is a shared library only.

Targets Created:

• CUDA::nvToolsExt

nvtx3¶

Added in version 3.25.

The header-only NVIDIA Tools Extension library. Introduced in CUDA 10.0.

Targets created:

• CUDA::nvtx3
• CUDA::nvtx3_interop
  Added in version 4.1.
  This is provided by CUDA 12.9 and above for use by languages that cannot consume C++ header-only libraries, such as Fortran.

OpenCL¶

The NVIDIA Open Computing Language library. This is a shared library only.

Targets Created:

• CUDA::OpenCL

cuLIBOS¶

The cuLIBOS library is a backend thread abstraction layer library which is static only. The CUDA::cublas_static, CUDA::cusparse_static,CUDA::cufft_static, CUDA::curand_static, and (when implemented) NPP libraries all automatically have this dependency linked.

Target Created:

• CUDA::culibos

Note: direct usage of this target by consumers should not be necessary.

Result variables¶

CUDAToolkit_FOUND

A boolean specifying whether or not the CUDA Toolkit was found.

CUDAToolkit_VERSION

The exact version of the CUDA Toolkit found (as reported bynvcc --version, version.txt, or version.json).

CUDAToolkit_VERSION_MAJOR

The major version of the CUDA Toolkit.

CUDAToolkit_VERSION_MINOR

The minor version of the CUDA Toolkit.

CUDAToolkit_VERSION_PATCH

The patch version of the CUDA Toolkit.

CUDAToolkit_BIN_DIR

The path to the CUDA Toolkit library directory that contains the CUDA executable nvcc.

CUDAToolkit_INCLUDE_DIRS

List of paths to all the CUDA Toolkit folders containing header files required to compile a project linking against CUDA.

CUDAToolkit_LIBRARY_DIR

The path to the CUDA Toolkit library directory that contains the CUDA Runtime library cudart.

CUDAToolkit_LIBRARY_ROOT

Added in version 3.18.

The path to the CUDA Toolkit directory containing the nvvm directory and either version.txt or version.json.

CUDAToolkit_TARGET_DIR

The path to the CUDA Toolkit directory including the target architecture when cross-compiling. When not cross-compiling this will be equivalent to the parent directory of CUDAToolkit_BIN_DIR.

CUDAToolkit_NVCC_EXECUTABLE

The path to the NVIDIA CUDA compiler nvcc. Note that this path maynot be the same asCMAKE_CUDA_COMPILER. nvcc must be found to determine the CUDA Toolkit version as well as determining other features of the Toolkit. This variable is set for the convenience of modules that depend on this one.