Package: blimps-examples Description-md5: 18ddc9ff8aab78bc1efd53cccc24389d Description-en: blocks database improved searcher (example data) BLIMPS (BLocks IMProved Searcher) is a searching tool that scores a protein sequence against blocks or a block against sequences. . This package contains example data. Package: blimps-utils Description-md5: 1afe4567b883b39e7050a4f604a91e17 Description-en: blocks database improved searcher BLIMPS (BLocks IMProved Searcher) is a searching tool that scores a protein sequence against blocks or a block against sequences. . This package contains the binaries. Package: firmware-qcom-dragonboard845c Description-md5: 3507088ed94312d44b4d5f5207d7374f Description-en: Binary firmware for various Qualcomm drivers used on Dragonboard 845c This package contains the binary firmware for GPU, USB, Venus, DSP hardware coprocessors found on SDM845, which is the main SoC on the Dragonboard 845c. Package: firmware-qcom-rb5 Description-md5: 0abf8cbedf59bff7af0b4696550319c7 Description-en: Binary firmware for various Qualcomm drivers used on Robotics RB5 This package contains the binary firmware for the SM8250, which is the main SoC on the Robotics RB5. Package: gds-tools Description-md5: 0967df359a764acf59e06afe6602e1b5 Description-en: GPUDirect Storage - tools GPUDirect Storage (GDS) enables a direct data path for direct memory access (DMA) transfers between GPU memory and storage, which avoids a bounce buffer through the CPU. . This package contains the GDS tools. Package: gitaly-installer Description-md5: a0db51942a7c98ec821bffaf2b5a8789 Description-en: Git RPC service for handling all the git calls made by GitLab Gitaly makes the git data storage tier of large GitLab instances fast. This is achieved by moving git operations as close to the data as possible and Optimizing git services using caching. Gitaly is a core service of gitlab. This package installs Gitaly from pre-built binaries from Gitlab artifacts. Package: gitlab-common Description-md5: ccb3bd8dfffd14a6e75d53315368861a Description-en: git powered software platform to collaborate on code (common) gitlab provides web based interface to host source code and track issues. It allows anyone for fork a repository and send merge requests. Code review is possible using merge request workflow. Using groups and roles project access can be controlled. . This package includes configurations common to gitlab and gitaly. Package: libaccinj64-12.3 Description-md5: 404daeb74b9a29243e00b395f84c5ada Description-en: NVIDIA ACCINJ Library (64-bit) The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . ACCINJ is the OpenACC internal library for profiling. . This package contains the 64-bit ACCINJ runtime library. Package: libblimps3 Description-md5: a1ad50ab461eca726e0a4e957f1a2ffa Description-en: blocks database improved searcher library BLIMPS (BLocks IMProved Searcher) is a searching tool that scores a protein sequence against blocks or a block against sequences. . This package provides the shared library. Package: libblimps3-dev Description-md5: 4d04b155f279229d68533b0ec59a8e4f Description-en: blocks database improved searcher library (development) BLIMPS (BLocks IMProved Searcher) is a searching tool that scores a protein sequence against blocks or a block against sequences. . This package provides the library development headers and the static library. Package: libcublas12 Description-md5: 5d0c77d8f2c8429e53892a3a70d407c4 Description-en: NVIDIA cuBLAS Library The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . The cuBLAS library is an implementation of BLAS (Basic Linear Algebra Subprograms) on top of the NVIDIA CUDA runtime. It allows the user to access the computational resources of NVIDIA Graphics Processing Unit (GPU), but does not auto-parallelize across multiple GPUs. . This package contains the cuBLAS runtime library. Package: libcublaslt12 Description-md5: 785c52463c947123d690fd61ff5b3adb Description-en: NVIDIA cuBLASLt Library The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . The cuBLASLt library is a lightweight GEMM library with a flexible API and tensor core support for INT8 inputs and FP16 CGEMM split-complex matrix multiplication. . This package contains the cuBLASLt runtime library. Package: libcudart12 Description-md5: d81acb8bf87762012a0607e71f8eff2e Description-en: NVIDIA CUDA Runtime Library The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . This package contains the CUDA Runtime API library for high-level CUDA programming, on top of the CUDA Driver API. Package: libcufft11 Description-md5: 323d8bcdb5ce372c028cb925743b7ad1 Description-en: NVIDIA cuFFT Library The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . The FFT is a divide-and-conquer algorithm for efficiently computing discrete Fourier transforms of complex or real-valued data sets. It is one of the most important and widely used numerical algorithms in computational physics and general signal processing. The cuFFT library provides a simple interface for computing FFTs on an NVIDIA GPU, which allows users to quickly leverage the floating-point power and parallelism of the GPU in a highly optimized and tested FFT library. . This package contains the cuFFT runtime library. Package: libcufftw11 Description-md5: 12b7b2ed306369c1f0fb326c4e9feefa Description-en: NVIDIA cuFFTW Library The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . The FFT is a divide-and-conquer algorithm for efficiently computing discrete Fourier transforms of complex or real-valued data sets. It is one of the most important and widely used numerical algorithms in computational physics and general signal processing. The cuFFT library provides a simple interface for computing FFTs on an NVIDIA GPU, which allows users to quickly leverage the floating-point power and parallelism of the GPU in a highly optimized and tested FFT library. . This package contains the cuFFTW runtime library. Package: libcufile-dev Description-md5: c1cd67475ecf5c9f7b33393d15d2499f Description-en: GPUDirect Storage - development files GPUDirect Storage (GDS) enables a direct data path for direct memory access (DMA) transfers between GPU memory and storage, which avoids a bounce buffer through the CPU. . This package contains the development files: headers and libraries. Package: libcufile-rdma1 Description-md5: a788bd06834da289befc94d603814f4a Description-en: GPUDirect Storage cuFile RDMA runtime library GPUDirect Storage (GDS) enables a direct data path for direct memory access (DMA) transfers between GPU memory and storage, which avoids a bounce buffer through the CPU. . This package contains the cuFile RDMA runtime library. Package: libcufile0 Description-md5: 10a0a46c2d90b38926742cf0189ef399 Description-en: GPUDirect Storage cuFile runtime library GPUDirect Storage (GDS) enables a direct data path for direct memory access (DMA) transfers between GPU memory and storage, which avoids a bounce buffer through the CPU. . This package contains the cuFile runtime library. Package: libcuinj64-12.3 Description-md5: 9eca092b41526faa574873e622a445e3 Description-en: NVIDIA CUINJ Library (64-bit) The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . CUINJ is the CUDA internal library for profiling. . This package contains the 64-bit CUINJ runtime library. Package: libcupti-dev Description-md5: 49cdc8386d120bdf14c58bebe2b3388d Description-en: NVIDIA CUDA Profiler Tools Interface development files The CUDA Profiler Tools Interface (CUPTI) enables the creation of profiling and tracing tools that target CUDA applications. CUPTI provides a set of APIs targeted at ISVs creating profilers and other performance optimization tools. The CUPTI APIs are not intended to be used by developers in their CUDA applications. . This package contains the development files: headers and libraries. Package: libcupti-doc Description-md5: 0c6d9f272f89c82663423610515dd3eb Description-en: NVIDIA CUDA Profiler Tools Interface documentation The CUDA Profiler Tools Interface (CUPTI) enables the creation of profiling and tracing tools that target CUDA applications. CUPTI provides a set of APIs targeted at ISVs creating profilers and other performance optimization tools. The CUPTI APIs are not intended to be used by developers in their CUDA applications. . This package contains the documentation and examples. Package: libcupti12 Description-md5: 65f2f1bea81316b239224ffd680c5064 Description-en: NVIDIA CUDA Profiler Tools Interface runtime library The CUDA Profiler Tools Interface (CUPTI) enables the creation of profiling and tracing tools that target CUDA applications. CUPTI provides a set of APIs targeted at ISVs creating profilers and other performance optimization tools. The CUPTI APIs are not intended to be used by developers in their CUDA applications. . This package contains the runtime library. Package: libcurand10 Description-md5: 05f7818fdfa9c23c51a9db2407910cae Description-en: NVIDIA cuRAND Library The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . The cuRAND library 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 n-dimensional points is generated by a deterministic algorithm designed to fill an n-dimensional space evenly. . This package contains the cuRAND runtime library. Package: libcusolver11 Description-md5: a30cfc560fa3fdce643526b0177ea7ba Description-en: NVIDIA cuSOLVER Library The cuSOLVER library contains LAPACK-like functions in dense and sparse linear algebra, including linear solver, least-square solver and eigenvalue solver. . This package contains the cuSOLVER runtime library. Package: libcusolvermg11 Description-md5: 6bd7798cc05ca17920d01c4430269d51 Description-en: NVIDIA cuSOLVERmg Library The cuSOLVER library contains LAPACK-like functions in dense and sparse linear algebra, including linear solver, least-square solver and eigenvalue solver. . This package contains the cuSOLVERmg runtime library. Package: libcusparse12 Description-md5: 12835bf1c971845122d660784efe714a Description-en: NVIDIA cuSPARSE Library The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . The cuSPARSE library contains a set of basic linear algebra subroutines used for handling sparse matrices. It is implemented on top of the NVIDIA CUDA runtime and is designed to be called from C and C++. The library routines can be classified into four categories: * Level 1: operations between a vector in sparse format and a vector in dense format * Level 2: operations between a matrix in sparse format and a vector in dense format * Level 3: operations between a matrix in sparse format and a set of vectors in dense format * Conversion: operations that allow conversion between different matrix formats . This package contains the cuSPARSE runtime library. Package: libnppc12 Description-md5: 371330c0e4596d14c1ae0b854eecfa9c Description-en: NVIDIA Performance Primitives core runtime library NVIDIA NPP is a library of functions for performing CUDA accelerated processing. The initial set offunctionality in the library focuses on imaging and video 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. . This package contains the NVIDIA Performance Primitives core runtime library. Package: libnppial12 Description-md5: bedf7547f548db0fc00407b8bb5572af Description-en: NVIDIA Performance Primitives lib for Image Arithmetic and Logic NVIDIA NPP is a library of functions for performing CUDA accelerated processing. . This package contains the NVIDIA Performance Primitives runtime library for Image Arithmetic and Logic operations, which is a sub-library of nppi. Package: libnppicc12 Description-md5: 5c43692beedf3cbda68cb3add3a2f55f Description-en: NVIDIA Performance Primitives lib for Image Color Conversion NVIDIA NPP is a library of functions for performing CUDA accelerated processing. . This package contains the NVIDIA Performance Primitives runtime library for Image Color and sampling Conversion, which is a sub-library of nppi. Package: libnppidei12 Description-md5: 96ae21f243272a0c4cf855590b806f52 Description-en: NVIDIA Performance Primitives lib for Image Data Exchange and Initialization NVIDIA NPP is a library of functions for performing CUDA accelerated processing. . This package contains the NVIDIA Performance Primitives runtime library for Image Data Exchange and Initialization, which is a sub-library of nppi. Package: libnppif12 Description-md5: 25b0779ba1f9f488a81add47bc943c6a Description-en: NVIDIA Performance Primitives lib for Image Filters NVIDIA NPP is a library of functions for performing CUDA accelerated processing. . This package contains the NVIDIA Performance Primitives runtime library for Image Filters, which is a sub-library of nppi. Package: libnppig12 Description-md5: 1f9ccb01fdd747cf6305e037d1c19323 Description-en: NVIDIA Performance Primitives lib for Image Geometry transforms NVIDIA NPP is a library of functions for performing CUDA accelerated processing. . This package contains the NVIDIA Performance Primitives runtime library for Image Geometry transforms, which is a sub-library of nppi. Package: libnppim12 Description-md5: f03f24db87826ca6b27a88b05bc823c0 Description-en: NVIDIA Performance Primitives lib for Image Morphological operations NVIDIA NPP is a library of functions for performing CUDA accelerated processing. . This package contains the NVIDIA Performance Primitives runtime library for Image Morphological operations, which is a sub-library of nppi. Package: libnppist12 Description-md5: c9507fd21beb3b0609afeb40e63f4792 Description-en: NVIDIA Performance Primitives lib for Image Statistics NVIDIA NPP is a library of functions for performing CUDA accelerated processing. . This package contains the NVIDIA Performance Primitives runtime library for Image Statistics and Linear Transformation, which is a sub-library of nppi. Package: libnppisu12 Description-md5: 37b8fa6ff382e1378e1a21c6d0074f80 Description-en: NVIDIA Performance Primitives lib for Image Support NVIDIA NPP is a library of functions for performing CUDA accelerated processing. . This package contains the NVIDIA Performance Primitives runtime library for Image Support, which is a sub-library of nppi. Package: libnppitc12 Description-md5: d1f0489937a1662cf9d2bf3e68764e1f Description-en: NVIDIA Performance Primitives lib for Image Threshold and Compare NVIDIA NPP is a library of functions for performing CUDA accelerated processing. . This package contains the NVIDIA Performance Primitives runtime library for Image Threshold and Compare, which is a sub-library of nppi. Package: libnpps12 Description-md5: 24aac8a47c80e58916c189d81d7a7714 Description-en: NVIDIA Performance Primitives for signal processing runtime library NVIDIA NPP is a library of functions for performing CUDA accelerated processing. The initial set offunctionality in the library focuses on imaging and video 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. . This package contains the NVIDIA Performance Primitives runtime library for signal processing. Package: libnvblas12 Description-md5: e77f7a1f1173b44f2910c8a51eff1d1c Description-en: NVBLAS runtime library The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . The NVBLAS Library is a GPU-accelerated Library that implements BLAS (Basic Linear Algebra Subprograms). It can accelerate most BLAS Level-3 routines by dynamically routing BLAS calls to one or more NVIDIA GPUs present in the system, when the characteristics of the call make it to speedup on a GPU. Package: libnvidia-ml-dev Description-md5: 1a3cdb21304c933ce9becbb20eb9aa0f Description-en: NVIDIA Management Library (NVML) development files The NVIDIA Management Library (NVML) provides a monitoring and management API. It provides a direct access to the queries and commands exposed via nvidia-smi. . This package contains the header file and depends on the driver-provided library. Package: libnvjitlink12 Description-md5: 795531b08acffe00a6ebc632c3d8e806 Description-en: NVIDIA Compiler JIT LTO Library NVIDIA's CUDA Compiler (NVCC) may apply Just-in-Time (JIT) Link-Time-Optimization (LTO) to improve performance of CUDA kernels comprised of multiple separate compilation units. . This package contains the NVIDIA Compiler JIT LTO runtime library. Package: libnvjpeg12 Description-md5: 623ac7d33181f0192b9126244e553a5c Description-en: NVIDIA JPEG library (nvJPEG) The nvJPEG 1.0 library provides 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. Package: libnvrtc-builtins12.3 Description-md5: a446d5189a000ea8dd760125227b0954 Description-en: CUDA Runtime Compilation (NVIDIA NVRTC Builtins Library) CUDA Runtime Compilation library (nvrtc) provides an API to compile CUDA-C++ device source code at runtime. . The resulting compiled PTX can be launched on a GPU using the CUDA Driver API. . This package contains the NVRTC Builtins library. Package: libnvrtc12 Description-md5: b1b9b1f5f271a283664f94ae0f1e94b4 Description-en: CUDA Runtime Compilation (NVIDIA NVRTC Library) CUDA Runtime Compilation library (nvrtc) provides an API to compile CUDA-C++ device source code at runtime. . The resulting compiled PTX can be launched on a GPU using the CUDA Driver API. . This package contains the NVRTC library. Package: libnvtoolsext1 Description-md5: 301861470547d1207ee0ad56dfa1ef90 Description-en: NVIDIA Tools Extension Library The NVIDIA Tools Extension SDK (NVTX) is a C-based API for marking events and ranges in your applications. Applications which integrate NVTX can use Nsight to capture and visualize these events and ranges. . This package contains the NVIDIA Tools Extension runtime library. Package: libnvvm4 Description-md5: 1efd5ade308f30b7de84c0430187211c Description-en: NVIDIA NVVM Library NVIDIA's CUDA Compiler (NVCC) is based on the widely used LLVM open source compiler infrastructure. . The NVVM library is used by NVCC to compile CUDA binary code to run on NVIDIA GPUs. . This package contains the NVIDIA NVVM runtime library. Package: libparmetis-dev Description-md5: 839c770f477cb92f6af09275d807c484 Description-en: Parallel Graph Partitioning and Sparse Matrix Ordering Libs: Devel ParMetis computes minimal-cut partitions of graphs and meshes in parallel, and orders variables for minimal fill when using direct solvers for sparse matrices. It does all this in parallel, and also can efficiently re-partition a graph or mesh whose connectivity has changed. . This package contains files needed to develop programs using ParMetis. Package: libparmetis4.0 Description-md5: 17a6686f47a3b63f4328881bffab697b Description-en: Parallel Graph Partitioning and Sparse Matrix Ordering Shared Libs ParMetis computes minimal-cut partitions of graphs and meshes in parallel, and orders variables for minimal fill when using direct solvers for sparse matrices. It does all this in parallel, and also can efficiently re-partition a graph or mesh whose connectivity has changed. . This package contains the ParMetis shared libraries. Package: libsocl-contrib-1.4-1t64 Description-md5: 4a69ce3f02f2cf01466ed8b9a22d8758 Description-en: Task scheduler for heterogeneous multicore machines StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains an OpenCL-compatible library interface to StarPU. This "contrib" version is built against CUDA. Package: libstarpu-contrib-1.4-6 Description-md5: f0ca811d02d6bbb6c830781bf9811bff Description-en: Task scheduler for heterogeneous multicore machines StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains the main StarPU library This "contrib" version is built against CUDA. Package: libstarpu-contrib-dev Description-md5: e7f42763fbe9c087a6defa203190f56e Description-en: Task scheduler for heterogeneous multicore machines - dev StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains development headers and libraries. This "contrib" version is built against CUDA. Package: libstarpu-contrib-openmp-llvm-1.4-1t64 Description-md5: 0c4cf9967f5b66c184481dbb23c8faa6 Description-en: Task scheduler for heterogeneous multicore machines StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains the runtime support for LLVM OpenMP. This "contrib" version is built against CUDA. Package: libstarpu-contribfft-1.4-1t64 Description-md5: 1079179920c93a735ab89566a3855d36 Description-en: Task scheduler for heterogeneous multicore machines StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains a hybrid CPU+GPU FFT library. This "contrib" version is built against CUDA. Package: libstarpu-contribmpi-1.4-3t64 Description-md5: 4d3ce5602db3c9fbd91b7e19dcc14e2a Description-en: Task scheduler for heterogeneous multicore machines StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains MPI extensions for StarPU. This "contrib" version is built against CUDA. Package: libstarpu-contribrm-1.4-1t64 Description-md5: 3008682b6502a417f1d5f1b0170499a0 Description-en: Task scheduler for heterogeneous multicore machines StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains the resource management library. This "contrib" version is built against CUDA. Package: nsight-compute Description-md5: ae73c3bbcf7dbd4b9a83f57a09c0d8b3 Description-en: NVIDIA Nsight Compute NVIDIA Nsight Compute is an interactive kernel profiler for CUDA applications. It provides detailed performance metrics and API debugging via a user interface and command line tool. In addition, its baseline feature allows users to compare results within the tool. Nsight Compute provides a customizable and data-driven user interface and metric collection and can be extended with analysis scripts for post-processing results. Package: nsight-compute-target Description-md5: 63cc5f774d2e4cd2d5746e323baf9499 Description-en: NVIDIA Nsight Compute (target specific libraries) NVIDIA Nsight Compute is an interactive kernel profiler for CUDA applications. It provides detailed performance metrics and API debugging via a user interface and command line tool. In addition, its baseline feature allows users to compare results within the tool. Nsight Compute provides a customizable and data-driven user interface and metric collection and can be extended with analysis scripts for post-processing results. . This package contains the target specific libraries. Package: nsight-systems Description-md5: 07ace54e5beaed541842de61e76de614 Description-en: NVIDIA Nsight Systems NVIDIA Nsight Systems is a system-wide performance analysis tool designed to visualize an application’s algorithms, help you identify the largest opportunities to optimize, and tune to scale efficiently across any quantity or size of CPUs and GPUs; from large server to smallest SoCs. Package: nsight-systems-target Description-md5: 314a9e91087893dedfe9c4aa99b10e74 Description-en: NVIDIA Nsight Systems (target specific libraries) NVIDIA Nsight Systems is a system-wide performance analysis tool designed to visualize an application’s algorithms, help you identify the largest opportunities to optimize, and tune to scale efficiently across any quantity or size of CPUs and GPUs; from large server to smallest SoCs. . This package contains the target specific libraries. Package: nvidia-cuda-dev Description-md5: 23a17262479fe7daf1cae67727e949c7 Description-en: NVIDIA CUDA development files The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . This package contains the development files: headers and libraries. Package: nvidia-cuda-gdb Description-md5: 03d8613224997399b5d081ffb05a91f3 Description-en: NVIDIA CUDA Debugger (GDB) The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . This package contains the cuda-gdb debugger. Package: nvidia-cuda-toolkit Description-md5: 4df65757189fdcbdcc50ffa97fccca02 Description-en: NVIDIA CUDA development toolkit The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . This package contains the nvcc compiler and other tools needed for building CUDA applications. . Running CUDA applications requires a supported NVIDIA GPU and the NVIDIA driver kernel module. Package: nvidia-cuda-toolkit-doc Description-md5: 37628d7854344886d340076661277f47 Description-en: NVIDIA CUDA and OpenCL documentation The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . OpenCL (Open Computing Language) is a multi-vendor open standard for general-purpose parallel programming of heterogeneous systems that include CPUs, GPUs and other processors. . Note that CUDA documentation is no longer bundled with CUDA toolkit releases. Visit https://docs.nvidia.com/cuda for the latest documentation on CUDA. Package: nvidia-cuda-toolkit-gcc Description-md5: 7ce75ce1d326c959ae1d41d38407d4e7 Description-en: NVIDIA CUDA development toolkit (GCC compatibility) The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . This package provides the /usr/bin/cuda-gcc, /usr/bin/cuda-g++ symlinks to simplify building packages that need to be built with a CUDA-compatible compiler. . This package ensures a deterministic nvcc/gcc combination is used by default and is therefore recommended to be used as build dependency for all source packages needing nvcc for building. Package: nvidia-fs-dkms Description-md5: 72d9e86231846b86e7ec42b9fab514c0 Description-en: NVIDIA file-system - nvidia-fs.ko kernel driver GPUDirect Storage (GDS) enables a direct data path for direct memory access (DMA) transfers between GPU memory and storage, which avoids a bounce buffer through the CPU. . This package builds the nvidia-fs.ko kernel driver. Package: nvidia-opencl-dev Description-md5: 5404c4fac54bb1c7a833b77f92a02e84 Description-en: NVIDIA OpenCL development files OpenCL (Open Computing Language) is a multi-vendor open standard for general-purpose parallel programming of heterogeneous systems that include CPUs, GPUs and other processors. . This metapackage provides the development files: headers and libraries. Package: nvidia-profiler Description-md5: 83d361c54427ed94d5493552d5ade11b Description-en: NVIDIA Profiler for CUDA and OpenCL The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . OpenCL (Open Computing Language) is a multi-vendor open standard for general-purpose parallel programming of heterogeneous systems that include CPUs, GPUs and other processors. . This package contains the nvprof profiler. Package: nvidia-visual-profiler Description-md5: c762f649b112cccddd5b9e96863b94c7 Description-en: NVIDIA Visual Profiler for CUDA and OpenCL The NVIDIA Visual Profiler is a cross-platform performance profiling tool that delivers developers vital feedback for optimizing CUDA C/C++ and OpenCL applications. Package: ogma Description-md5: dbb56c114e8be77e8d1ddc914dda97ea Description-en: Helper tool to interoperate between Copilot and other languages Ogma is a tool to facilitate the integration of safe runtime monitors into other systems. Ogma extends , a high-level runtime verification framework that generates hard real-time C99 code. . Some use cases supported by Ogma include: . - Translating requirements defined in structured natural language into monitors in Copilot. . - Generating the glue code necessary to work with C structs in Copilot. . - Generating applications that use Copilot for monitoring data received from the message bus. . - Generating message handlers for NASA Core Flight System applications to make external data in structs available to a Copilot monitor. . - Generating applications that use Copilot for monitoring data received from different topics. . - Generating components that use Copilot for monitoring. . - Generating monitors from state diagrams specified using a graphical notation. Package: parmetis-doc Description-md5: 55cc39b179c0b5b2dedead6fc6a8c34f Description-en: Parallel Graph Partitioning and Sparse Matrix Ordering Lib - Docs ParMetis computes minimal-cut partitions of graphs and meshes in parallel, and orders variables for minimal fill when using direct solvers for sparse matrices. It does all this in parallel, and also can efficiently re-partition a graph or mesh whose connectivity has changed. . This package contains the documentation and example files. Package: parmetis-test Description-md5: b9b53f52a3b7e53d03b5260911e600a9 Description-en: Parallel Graph Partitioning and Sparse Matrix Ordering Tests ParMetis computes minimal-cut partitions of graphs and meshes in parallel, and orders variables for minimal fill when using direct solvers for sparse matrices. It does all this in parallel, and also can efficiently re-partition a graph or mesh whose connectivity has changed. . This package contains programs which test the ParMetis libraries using files in the parmetis-doc package's examples directory. Package: sift Description-md5: 7788bf12148938f8dc8e4675657ce605 Description-en: predicts if a substitution in a protein has a phenotypic effect SIFT is a sequence homology-based tool that sorts intolerant from tolerant amino acid substitutions and predicts whether an amino acid substitution in a protein will have a phenotypic effect. SIFT is based on the premise that protein evolution is correlated with protein function. Positions important for function should be conserved in an alignment of the protein family, whereas unimportant positions should appear diverse in an alignment. Package: starpu-contrib-examples Description-md5: 11b8c6811b08d3b761c4e2f5fd0e0890 Description-en: Task scheduler for heterogeneous multicore machines - exs StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains application examples. This "contrib" version is built against CUDA. Package: starpu-contrib-tools Description-md5: 21e204c0915cd3972a9cf41ad059d147 Description-en: Task scheduler for heterogeneous multicore machines - tools StarPU is a runtime system that offers support for heterogeneous multicore machines. While many efforts are devoted to design efficient computation kernels for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's SPUs), StarPU not only takes care of offloading such kernels (and implementing data coherency across the machine), but it also makes sure the kernels are executed as efficiently as possible. . This package contains StarPU tools. This "contrib" version is built against CUDA. Package: libhwloc-contrib-plugins Description-md5: 2b02fbf995ab5fe6645ca4e4ad3e8d3f Description-en: Hierarchical view of the machine - contrib plugins libhwloc provides a portable abstraction (across OS, versions, architectures, ...) of the hierarchical topology of modern architectures. It primarily aims at helping high-performance computing applications with gathering information about the hardware so as to exploit it accordingly and efficiently. . libhwloc provides a hierarchical view of the machine, NUMA memory nodes, sockets, shared caches, cores and simultaneous multithreading. It also gathers various attributes such as cache and memory information. . libhwloc supports old kernels not having sysfs topology information, with knowledge of cpusets, offline cpus, and Kerrighed support . This package contains plugins to add discovery support for non-free items. This includes - CUDA support.