Source: nvidia-cuda-toolkit Section: non-free/libs Priority: optional Maintainer: Debian NVIDIA Maintainers Uploaders: Andreas Beckmann , Graham Inggs , Zhou Mo , Build-Depends: debhelper-compat (= 12), quilt, libncurses5, libexpat1 [ppc64el], hardlink [amd64], # for nvidia-openjdk-8-jre libasound2 [amd64], libgl1 [amd64], libgtk2.0-0 [amd64], libxslt1.1 [amd64], libxtst6 [amd64], libxxf86vm1 [amd64], Rules-Requires-Root: no Standards-Version: 4.3.0 Homepage: https://developer.nvidia.com/cuda-zone Vcs-Browser: https://salsa.debian.org/nvidia-team/nvidia-cuda-toolkit Vcs-Git: https://salsa.debian.org/nvidia-team/nvidia-cuda-toolkit.git XS-Autobuild: yes Package: nvidia-cuda-toolkit Section: non-free/devel Architecture: amd64 ppc64el Depends: nvidia-profiler (= ${binary:Version}), nvidia-cuda-dev (= ${binary:Version}), nvidia-opencl-dev (= ${binary:Version}) | opencl-dev, gcc-7 | clang-5.0 | clang-4.0 | clang-3.9 | clang-3.8 | clang (<< 1:6~) | gcc-6 | gcc-5 | gcc-4.9 | gcc-4.8, g++-7 | clang-5.0 | clang-4.0 | clang-3.9 | clang-3.8 | clang (<< 1:6~) | g++-6 | g++-5 | g++-4.9 | g++-4.8, ${shlibs:Depends}, ${misc:Depends}, Recommends: nvidia-cuda-doc (= ${source:Version}), nvidia-cuda-gdb (= ${binary:Version}), nvidia-visual-profiler (= ${binary:Version}) [${cuda:arch:has-java}], Suggests: libcupti-dev, nvidia-driver (>= ${nvidia:MinVersion}) [${cuda:arch:has-driver}], Conflicts: # packages from the repository packages provided by NVIDIA cuda-repo-ubuntu1404, cuda-repo-ubuntu1404-7-5-local, cuda-repo-ubuntu1410, cuda-repo-ubuntu1504, cuda-repo-ubuntu1504-7-5-local, cuda-license-7-5, Description: 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-doc Section: non-free/doc Architecture: all Depends: libjs-html5shiv, libjs-jquery, ${misc:Depends} Description: 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. . This package contains the developer documentation. Package: nvidia-cuda-gdb Section: non-free/devel Architecture: amd64 ppc64el Depends: ${shlibs:Depends}, ${misc:Depends} Recommends: nvidia-cuda-doc (= ${source:Version}) Description: NVIDIA CUDA Debugger (GDB) The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation. . This package contains the cuda-gdb debugger. Package: nvidia-profiler Section: non-free/devel Architecture: amd64 ppc64el Depends: libaccinj64-${cuda:SoVersion}, libcuinj64-${cuda:SoVersion}, ${shlibs:Depends}, ${misc:Depends} Suggests: nvidia-cuda-toolkit, Description: 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-openjdk-8-jre Section: non-free/java Architecture: amd64 Depends: ${shlibs:Depends}, ${misc:Depends} Description: NVIDIA provided OpenJDK Java runtime, using Hotspot JIT Full Java runtime environment - needed for executing Java GUI and Webstart programs, using Hotspot JIT. . This package provides the openjdk-8 binaries shipped with the NVIDIA CUDA Toolkit, this obsolete version is needed for nvidia-visual-profiler and nvidia-nsight. Package: nvidia-visual-profiler Section: non-free/devel Architecture: amd64 Depends: nvidia-openjdk-8-jre, libgtk2.0-0, nvidia-profiler (= ${binary:Version}), ${perl:Depends}, ${shlibs:Depends}, ${misc:Depends} Recommends: nvidia-cuda-doc (= ${source:Version}), Homepage: https://developer.nvidia.com/nvidia-visual-profiler Description: 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: nvidia-nsight Section: non-free/devel Architecture: amd64 Depends: nvidia-openjdk-8-jre, libgtk2.0-0, ${shlibs:Depends}, ${misc:Depends} Recommends: nvidia-cuda-doc (= ${source:Version}), Homepage: https://developer.nvidia.com/cuda/nsight-eclipse-edition Description: NVIDIA Nsight Eclipse Edition NVIDIA Nsight Eclipse Edition is a full-featured IDE powered by the Eclipse platform that provides an all-in-one integrated environment to edit, build, debug and profile CUDA-C applications. Nsight Eclipse Edition supports a rich set of commercial and free plugins. Package: nvidia-cuda-dev Section: non-free/libdevel Architecture: amd64 ppc64el Depends: libaccinj64-${cuda:SoVersion} (= ${binary:Version}), libcudart${cuda:SoVersion} (= ${binary:Version}), libcuinj64-${cuda:SoVersion} (= ${binary:Version}), libnvrtc${cuda:SoVersion} (= ${binary:Version}), libnvtoolsext1 (= ${binary:Version}), libnvvm3 (= ${binary:Version}), libcublas${cuda:SoVersion} (= ${binary:Version}), libnvblas${cuda:SoVersion} (= ${binary:Version}), libcufft${cuda:SoVersion} (= ${binary:Version}), libcufftw${cuda:SoVersion} (= ${binary:Version}), libcurand${cuda:SoVersion} (= ${binary:Version}), libcusolver${cuda:SoVersion} (= ${binary:Version}), libcusparse${cuda:SoVersion} (= ${binary:Version}), libnppc${cuda:SoVersion} (= ${binary:Version}), libnppial${cuda:SoVersion} (= ${binary:Version}), libnppicc${cuda:SoVersion} (= ${binary:Version}), libnppicom${cuda:SoVersion} (= ${binary:Version}), libnppidei${cuda:SoVersion} (= ${binary:Version}), libnppif${cuda:SoVersion} (= ${binary:Version}), libnppig${cuda:SoVersion} (= ${binary:Version}), libnppim${cuda:SoVersion} (= ${binary:Version}), libnppist${cuda:SoVersion} (= ${binary:Version}), libnppisu${cuda:SoVersion} (= ${binary:Version}), libnppitc${cuda:SoVersion} (= ${binary:Version}), libnpps${cuda:SoVersion} (= ${binary:Version}), libnvgraph${cuda:SoVersion} (= ${binary:Version}), libnvidia-ml1 (>= ${nvidia:MinVersion}) [${cuda:arch:has-driver}], libthrust-dev, ${misc:Depends} Recommends: ${package:libcuda1}, libgl1-mesa-dev | libgl-dev, libvdpau-dev, libnvcuvid1, Breaks: libcuda1 (<< ${nvidia:MinVersion}), Description: 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-opencl-dev Section: non-free/libdevel Architecture: amd64 ppc64el Multi-Arch: same Depends: ocl-icd-opencl-dev, ${misc:Depends} Recommends: nvidia-opencl-icd, Breaks: nvidia-libopencl1 (>> 0), Description: 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: libcudart9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Recommends: ${package:libcuda1} Provides: no-libcuda1 [${cuda:arch:has-no-driver}], Description: 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: libaccinj64-9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libcuinj64-9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnvrtc9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Homepage: https://docs.nvidia.com/gameworks/content/gameworkslibrary/nvtx/nvidia_tools_extension_library_nvtx.htm Description: 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: libnvvm3 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Homepage: https://developer.nvidia.com/cuda-llvm-compiler Description: 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: libcupti9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Homepage: https://developer.nvidia.com/cuda-profiling-tools-interface Description: NVIDIA CUDA Profiler Tools Interface runtime library The CUDA Profiler Tools Interface (CUPTI) enables the creation of profiling and tracing tools that target CUDA applications. CUPTI provides a set of APIs targeted at ISVs creating profilers and other performance optimization tools. The CUPTI APIs are not intended to be used by developers in their CUDA applications. . This package contains the runtime library. Package: libcupti-dev Section: non-free/libdevel Architecture: amd64 ppc64el Multi-Arch: same Depends: libcupti${cuda:SoVersion} (= ${binary:Version}), ${misc:Depends} Recommends: libcupti-doc Homepage: https://developer.nvidia.com/cuda-profiling-tools-interface Description: 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 Section: non-free/doc Architecture: all Depends: ${misc:Depends} Homepage: https://developer.nvidia.com/cuda-profiling-tools-interface Description: 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: libcublas9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnvblas9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libcufft9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libcufftw9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libcurand9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libcusolver9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libcusparse9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnppc9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Conflicts: nvidia-libopencl1, Breaks: nvidia-opencl-dev (<< 9.1.85-6), Homepage: https://developer.nvidia.com/npp Description: 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: libnppial9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnppicc9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnppicom9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: NVIDIA Performance Primitives lib for Image Compression NVIDIA NPP is a library of functions for performing CUDA accelerated processing. . This package contains the NVIDIA Performance Primitives runtime library for Image Compression, which is a sub-library of nppi. Package: libnppidei9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnppif9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnppig9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnppim9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnppist9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnppisu9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnppitc9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: 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: libnpps9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Homepage: https://developer.nvidia.com/npp Description: 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: libnvgraph9.2 Architecture: amd64 ppc64el Multi-Arch: same Pre-Depends: ${misc:Pre-Depends} Depends: ${shlibs:Depends}, ${misc:Depends} Description: NVIDIA Graph Analytics library (nvGRAPH) The NVIDIA Graph Analytics library (nvGRAPH) comprises of parallel algorithms for high performance analytics on graphs with up to 2 billion edges. nvGRAPH makes it possible to build interactive and high throughput graph analytics applications. . nvGRAPH supports three widely-used algorithms: * [Page Rank] is most famously used in search engines, and also used in social network analysis, recommendation systems, and for novel uses in natural science when studying the relationship between proteins and in ecological networks. * [Single Source Shortest Path] is used to identify the fastest path from A to B through a road network, and can also be used for a optimizing a wide range of other logistics problems. * [Single Source Widest Path] is used in domains like IP traffic routing and traffic-sensitive path planning. . In addition, the nvGRAPH semi-ring SPMV operations can be used to build a wide range of innovative graph traversal algorithms. . nvGRAPH accelerates analysis of large graphs by making efficient use of the massive parallelism available in NVIDIA Tesla GPUs. The size of a graph in memory is dominated by the number of edges. An M40 with 24 GB can support a graph of up to 2 billion edges. Package: libthrust-dev Section: non-free/libdevel Architecture: all Multi-Arch: foreign Depends: ${misc:Depends} Suggests: nvidia-cuda-toolkit Description: Thrust - Parallel Algorithms Library Thrust is a parallel algorithms library which resembles the C++ Standard Template Library (STL). Thrust's high-level interface greatly enhances programmer productivity while enabling performance portability between GPUs and multicore CPUs. Interoperability with established technologies (such as CUDA, TBB, and OpenMP) facilitates integration with existing software.