Search Results for "distributed shared memory" - Page 5

A data parallel scientific programming model. Compiles efficiently to different platforms like distributed memory (MPI), shared memory multi-processor (pthreads), Cell BE processor, Nvidia Cuda, SIMD vectorization (SSE, Altivec), and sequential C++ code.

STLshm provides an C++ STL Allocator implementation for creating and using STL containers (and any other allocator aware types) in shared memory regions. It supports multiple shared region implementations.

QuickMP (Quick Multi-Processing) is a simple cross-platform C++ API for generating parallel for loops in shared-memory programs, similar to OpenMP. It provides automatic scalable performance based on the number of available processors.

Blackboard implements a lightweight, portable tuple space suitable for multi-agent system and distributed component design. Supports implicit invocation via content-filtered asynchronous events, blocking call semantics, and shared memory messaging.

libdocsis is a shared library suitable for working with DOCSIS option files. The library provides an API to encode/decode/verify DOCSIS option files from a variety of sources including file streams, character buffers, and in-memory mapped locations.

coThreads (formerly known as STMlib), is a concurrent programming library for OCaml. It features both high and low level constructors, for both shared-memory and message-passing style concurrency. The library is equipped with a set of source-level and ob

an integration framework for UML and MOF case tools based on Jini and SOAP. It exchanges models from ArgoUML, Poseidon, Rose, etc. as XMI (UML stored in XML), checks them and generates code. New services simply plug in and can be shared world-wide.

JVMCluster Features: - clusterable Java Virtual Machine (based on PVM) - uses CPPVM as adapter layer to PVM - object persistent layer integrated into JVM - memory management unit is based on integrated relational database - JDBC/ODBC api to acces

(1) smart pointer class (memory management via reference counting), (2) Lockable class (for controlling shared object mutability), (3) lockable, reference-counted array and string classes, (4) stream-based serialization classes

The Tiny Grasshopper Cache Store provides a memory based, least recently used (LRU), thread-safe caching mechanism that can openly cache any Java Object. The cache store is easy to use and doesn't require any setup.

RELICS is based on the concept that a diverse collection of independent users are likely to make certain types of decisions and predictions better than any one individual or panel of experts. The RELICS platform is the keystone software application that connects and harmonizes all operations of the intelligence process using both human intelligence and biologically inspired learning algorithms to perform intelligence tasks. RELICS users are connected on a peer-to-peer network forming a...