Search Results for "distributed shared memory" - Page 2

Apache MXNet is an open source deep learning framework designed for efficient and flexible research prototyping and production. It contains a dynamic dependency scheduler that automatically parallelizes both symbolic and imperative operations. On top of this is a graph optimization layer, overall making MXNet highly efficient yet still portable, lightweight and scalable.

...Build resilient projects, better coordination, and positive-sum outcomes. Growing networks with aligned incentives toward the wellbeing of each participant and the system as a whole. Through distributed funding and organizations, we build together toward our shared goals.

...It achieves this by providing simple and extensible interfaces and abstractions for model components, and by using PyTorch’s capabilities of exporting models for inference via the optimized Caffe2 execution engine. We use PyText at Facebook to iterate quickly on new modeling ideas and then seamlessly ship them at scale. Distributed-training support built on the new C10d backend in PyTorch 1.0. Mixed precision training support through APEX (trains faster with less GPU memory on NVIDIA Tensor Cores). Extensible components that allows easy creation of new models and tasks.

...By eliminating infrastructure complexity, going from prototype to production has never been simpler. When we set out to build Wally, we had several high-level goals in mind. Create a dependable and resilient distributed computing framework. Take care of the complexities of distributed computing "plumbing," allowing developers to focus on their business logic. Provide high-performance & low-latency data processing. Be portable and deploy easily (i.e., run on-prem or any cloud). Manage in-memory state for the application. Allow applications to scale as needed, even when they are live and up-and-running. ...

How can we easily develop applications for multicore or multicomputer architectures? We frequently use middlewares for that problem, but they are often complex and less productive. This way, at DECOM-UFOP, we have a middleware, named JavaCa&La or just JCL, to build portable and scalable solutions over many high performance computer architectures. Our middleware APIs is simple, intuitive and designed for young and senior programmers who don’t have high performance programming skills. Using...

As of now, you can get Ehcache only from ehcache.org or Maven central. A simple, fast, thread safe, standards based cache for Java, and provides memory and disk stores and distributed operation for clusters. ehcache is widely used in such open source projects as Hibernate and Spring. Terracotta offers enterprise edition

Java implementation of a Tuplespace. Moved to https://github.com/mike-k-houghton/tuplespace A Tuple is an ordered list of items. A Tuple Space is a form of associative memory where entries, tuples, are stored in the space and are retrieved using search criteria that are based on the intrinsic properties of the tuples. The two key operations are put get And that is it! There are refinements on these operations including, for example, timeouts where the tuple will only exist...

TechMVC is a very powerful and highly optimized MVC2 based web application framework, which enables developers to build high performance Website. Current Version: 3.1.1 Features Upgraded: =============== 1. Meta Character set support enabled. Can be specified from Config.php($var->defaultCharacterSet). Default: utf-8 2. Following functions added: a. TechMVC::LoadLibrary($path, $shared = false) -> Include library to TechMVC runtime. b. In Config.php varriable...

Channel is a C++ framework for distributed message passing and event dispatching, configurable with its components (msg ids,routing algorithms...) as template parameters. As a namespace shared by peer threads, channel supports scope control and filtering

Library that offers users an easy to use interface to synchronize shared data access following the software transactional memory principle.

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.