This package provides a command-line tool to profile CUDA kernels. It enables the collection of a timeline of CUDA-related activities on both CPU and GPU, including kernel execution, memory transfers, memory set and CUDA API calls and events or metrics for CUDA kernels.

This package provides the CUDA C++ developers with building blocks that make it easier to write safe and efficient code. It unifies three essential former CUDA C++ libraries into a single repository:

• Thrust (former repo)

• CUB (former repo)

• libcudacxx (former repo)

This package provides a set of APIs which can be used at runtime to link together GPU devide code. It supports Link Time Optimization.

This binary extracts information from CUDA binary files (both standalone and those embedded in host binaries) and presents them in human readable format. The output of cuobjdump includes CUDA assembly code for each kernel, CUDA ELF section headers, string tables, relocators and other CUDA specific sections. It also extracts embedded ptx text from host binaries.

This package provides facilities that focus on the simple and efficient generation of high-quality pseudorandom and quasirandom numbers. A pseudorandom sequence of numbers satisfies most of the statistical properties of a truly random sequence but is generated by a deterministic algorithm. A quasirandom sequence of -dimensional points is generated by a deterministic algorithm designed to fill an -dimensional space evenly.

This package provides a binary that prunes host object files and libraries to only contain device code for the specified targets.

This package provides a set of GPU-accelerated basic linear algebra subroutines used for handling sparse matrices that perform significantly faster than CPU-only alternatives. Depending on the specific operation, the library targets matrices with sparsity ratios in the range between 70%-99.9%.

This package enables the creation of profiling and tracing tools that target CUDA applications and give insight into the CPU and GPU behavior of CUDA applications. It provides the following APIs:

• the Activity API,

• the Callback API,

• the Event API,

• the Metric API,

• the Profiling API,

• the PC Sampling API,

• the Checkpoint API.

This package provides a an interactive profiler for CUDA and NVIDIA OptiX that provides detailed performance metrics and API debugging via a user interface and command-line tool. Users can run guided analysis and compare results with a customizable and data-driven user interface, as well as post-process and analyze results in their own workflows.

This package provides a set of APIs which can be used at runtime to combine multiple CUDA objects into one CUDA fat binary (fatbin). The APIs accept inputs in multiple formats, either device cubins, PTX, or LTO-IR. The output is a fatbin that can be loaded by cuModuleLoadData of the CUDA Driver API. The functionality in this library is similar to the fatbinary offline tool in the CUDA toolkit, with the following advantages:

• Support for runtime fatbin creation.

• The clients get fine grain control over the input process.

• Supports direct input from memory, rather than requiring inputs be written to files.

This package provides a high-level library based on the cuBLAS and cuSPARSE libraries. It consists of two modules corresponding to two sets of API: the cuSolver API on a single GPU; and the cuSolverMG API on a single node multiGPU. Each of these can be used independently or in concert with other toolkit libraries. The intent of cuSolver is to provide useful LAPACK-like features, such as common matrix factorization and triangular solve routines for dense matrices, a sparse least-squares solver and an eigenvalue solver. In addition, cuSolver provides a new refactorization library useful for solving sequences of matrices with a shared sparsity pattern.

This package provides the CUDA compiler and the CUDA run-time support libraries for NVIDIA GPUs, all of which are proprietary.

This package provides a high-performance, GPU accelerated JPEG decoding functionality for image formats commonly used in deep learning and hyperscale multimedia applications. The library offers single and batched JPEG decoding capabilities which efficiently utilize the available GPU resources for optimum performance; and the flexibility for users to manage the memory allocation needed for decoding.

The nvJPEG library enables the following functions: use the JPEG image data stream as input; retrieve the width and height of the image from the data stream, and use this retrieved information to manage the GPU memory allocation and the decoding. A dedicated API is provided for retrieving the image information from the raw JPEG image data stream.

The encoding functions of the nvJPEG library perform GPU-accelerated compression of user’s image data to the JPEG bitstream. User can provide input data in a number of formats and colorspaces, and control the encoding process with parameters. Encoding functionality will allocate temporary buffers using user-provided memory allocator.

This package provides a minimal low-level profiling API for CUDA.

This package provides a GPU-accelerated library of primitives for deep neural networks, with highly tuned implementations for standard routines such as forward and backward convolution, attention, matmul, pooling, and normalization.

The NVIDIA Management Library Headers (NVML) is a C-based API for monitoring and managing various states of the NVIDIA GPU devices. It provides a direct access to the queries and commands exposed via nvidia-smi.

This package provides the CUDA compiler and the CUDA run-time support libraries for NVIDIA GPUs, all of which are proprietary.

This package provides the NVIDIA cuBLAS library. It includes several API extensions for providing drop-in industry standard BLAS APIs and GEMM APIs with support for fusions that are highly optimized for NVIDIA GPUs. The cuBLAS library also contains extensions for batched operations, execution across multiple GPUs, and mixed- and low-precision execution with additional tuning for the best performance.

This package decodes (demangles) low-level identifiers that have been mangled by CUDA C++ into user readable names. For every input alphanumeric word, the output of cu++filt is either the demangled name if the name decodes to a CUDA C++ name, or the original name itself.

This package provides Python low-level bindings for NVIDIA CUDA toolkit.

This package provides an interface for generating PTX code from both binary and text NVVM IR inputs.

This package provides a library of functions for performing CUDA accelerated 2D image and signal processing.

The primary library focuses on image processing and is widely applicable for developers in these areas. NPP will evolve over time to encompass more of the compute heavy tasks in a variety of problem domains. The NPP library is written to maximize flexibility, while maintaining high performance.

GDRCopy is a low-latency GPU memory copy library based on GPUDirect RDMA technology that allows the CPU to directly map and access GPU memory.

Unified Communication X (UCX) provides an optimized communication layer for message passing (MPI), portable global address space (PGAS) languages and run-time support libraries, as well as RPC and data-centric applications.

UCX utilizes high-speed networks for inter-node communication, and shared memory mechanisms for efficient intra-node communication.

This package adds CUDA support for NVIDIA GPUs.