KappaCUDA 1.5.0

This version is compiled with the CUDA ToolKit 3.1 but does not yet support (writable) surfaces or changing the limits for kernel printf (cuCtxSetLimit).<br /><br />Kappa can show an easy ten times speed increase on GF100 GPUs (compared to CUDA driver or runtime 3.1 API programs)<br /><br />Details are available here for the list of changes made to the Kappa library. The Perl, Python, and other language bindings are now packaged in the Kappa installer (all language bindings remain under the MIT License). This version is ABI backward compatible with previous versions (in other words, the ikappa program from version 1.1 can run using the 1.2 shared libraries). Keyword commands (CSV, Perl, and Python) are not backward compatible and will need to be recompiled for the new version 1.2. <br /><br />The primary goal of Kappa is to allow for the creation of sophisticated, powerful, and complex processing that retain simple and easy-to-use interfaces. Kappa provides for creating processes with dynamic sizing, scheduling, and interactive execution for C and CUDA kernels to process data efficiently using the available resources.<br />Kappa provides a library for creating processes to use combinations of CPUs and a GPU for tasks. Within a single host program process, a Kappa process can be created for each CUDA GPU*using all GPUs. Each Kappa process can use all of the multiprocessors of each GPU, share all of the CPUs of the host system, have its own separate namespace, and have its own separate CUDA context.<br /><br /> * The Kappa library provides: access to the GPU and instantiated kernel properties at runtime<br /> * nvcc and CUDA JIT compilation loading<br /> * fully concurrent C++, C++ OpenMP, and CUDA kernel execution<br /> * dynamic sizing of data and kernel invocation<br /> * dynamic scheduling and cancellation of the execution of related steps<br /> * process level functional blocks (named or anonymous subroutines and named functions) built from dynamically scheduled execution of mixtures of C++ and CUDA kernels<br /> * subject domain extensibility<br /> * for performance, execution is scheduled*not interpreted<br /><br /> * The Kappa library was designed to especially ease use by providing, for example: interactive or batch capability for rapid development or testing,<br /> * resource management (constructor, destructor, and automatic data copy),<br /> * fail-safe default behavior,<br /> * thread-safe locking,<br /> * and exception handling.

Requirements:	No special requirements
Platforms:	*nix, Linux
Keyword:	Bindings,  C2b2b,  Creating,  Dynamic,  Execution,  Interactive,  Kappa,  Kernel,  Language,  Library,  Named,  Process,  Processes,  Program,  Python,  Scheduling,  Sizing,  Version
Users rating:	0/10