Search Results for "mpi"

...It provides a suite of mechanisms that are commonly required by many classes of batch & elastic workload including machine learning/deep learning, bioinformatics/genomics, and other "big data" applications. These types of applications typically run on generalized domain frameworks like TensorFlow, Spark, Ray, PyTorch, MPI, etc, which Volcano integrates with. Volcano builds upon a decade and a half of experience running a wide variety of high-performance workloads at scale using several systems and platforms, combined with best-of-breed ideas and practices from the open-source community. Until June 2021, Volcano has been widely used around the world at a variety of industries such as Internet/Cloud/Finance/ Manufacturing/Medical. ...

...Its custom-built operating system (OS) bypass hardware interface enhances the performance of inter-instance communications, which is critical to scaling these applications. With EFA, High Performance Computing (HPC) applications using the Message Passing Interface (MPI) and Machine Learning (ML) applications using NVIDIA Collective Communications Library (NCCL) can scale to thousands of CPUs or GPUs. As a result, you get the application performance of on-premises HPC clusters with the on-demand elasticity and flexibility of the AWS cloud.

Classdesc is a system for adding reflection to C++, ie the ability to query an object's structure at runtime.

DAE Tools is a cross-platform equation-based object-oriented modelling, simulation and optimisation software. It is not a modelling language nor a collection of numerical libraries but rather a higher level structure – an architectural design of interdependent software components providing an API for: - Model development/specification - Activities on developed models, such as simulation, optimisation, sensitivity analysis and parameter estimation - Processing of the results, such as...

ECF is a framework intended for application of any type of evolutionary computation (GA/GP, DE, Clonalg, ES, PSO, ABC, GAn, local search...). It offers simplicity for the end-user (parameterless usage, tutorial) and customization for experienced EC practicioners.

...Margetts, Three-dimensional cellular automata modelling of cleavage propagation across crystal boundaries in polycrystalline microstructures, Proc. Roy. Soc. A 471:20150039, DOI: http://dx.doi.org/10.1098/rspa.2015.0039. CASUP can be linked with FE (e.g. MPI FE library ParaFEM, http://parafem.org.uk) for a multi-scale multi-physics CA-FE framework. CASUP extensively uses Fortran 2008 and 2018 coarrays, as well as MPI, OpenMP and do concurrent. CASUP can be used with Cray, Intel and GCC/OpenCoarrays compilers. Scaling beyond 100,000 cores on Cray XC30 was demonstrated.

pFUnit is now hosted and developed on GitHub. And will be completely removed from sourceforge on January 01, 2020 Please use: https://github.com/Goddard-Fortran-Ecosystem/pFUnit GitHub has been the primary host for some time now, but with the release of pFUnit 4.0 earlier in 2019, the sourceforge site is very out of date.

...The Tiramisu compiler is based on the polyhedral model thus it can express a large set of loop optimizations and data layout transformations. Currently, it targets (1) multicore X86 CPUs, (2) Nvidia GPUs, (3) Xilinx FPGAs (Vivado HLS) and (4) distributed machines (using MPI). It is designed to enable easy integration of code generators for new architectures.

NOMAD is a C++ code that implements the MADS algorithm (Mesh Adaptive Direct Search) for difficult blackbox optimization problems. Such problems occur when the functions to optimize are costly computer simulations with no derivatives.

mpiP is a lightweight profiling library for MPI applications.

DMTA (Distributed Multithreaded Apriori) is a parallel implementation of Apriori algorithm, which exploits the parallelism at the level of threads and processes, seeking to perform load balancing among the cores. Was implemented in C++ language, using the parallelization libraries OpenMP and MPI. The algorithm was generated as a result of a project developed by André Camilo Bolina, under the guidance of teachers Marluce Rodrigues Pereira, Ahmed Ali Abdalla Esmin and Denilson Alves Pereira, in Department of Computer Science at Federal University of Lavras. The results of this project were published in the Revista de Sistemas de Informação da FSMA and is available in http://www.fsma.edu.br/si/edicao11/FSMA_SI_2013_1_Principal_1.html

A Message-Passing Interface (MPI) library, allowing a Java application to efficiently run on a distributed, parallel, and high performance architecture. Developed within HPJava project (www.hpjava.org), and maintained by LarKC project (www.larkc.eu)

SYSTEM FOR DESIGNING AND SIMULATE CONCURRENT AND DISTRIBUTED PROGRAMS IN CLUSTER ARCHITECTURE Provides graphical interface for configuring relationships between cooperating, abstract processes and simulate it in real cluster environment, using MPI.

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.

MorphMPI simulates an ABI for MPI. Applications compiled using MorphMPI can easily be relinked to use any MPI implementation on a compatible OS-cpu combination.

PyLife is an implementation of the game of life algorithm featuring parallel programming. It uses MPI and python to achieve a consistent software architecture and reliably performance.

This Project implements the mergesort algorithm in a MPICH2 (parallel programming -) environment.

The Collaborative Testing System (CTS) tests parallel software using various implementations of MPI. It works on multiple platforms and supports batch systems including LSF, LCRM and workstations without a batch system. It includes a numerical diff tool.

MPI for MOO is a MPI implementation done in the MOO programing language, for use with the Lambda MOO data base core, and Lambda MOO server.

The project is a “data-parallel” C++ library to teach parallel programming concepts. We intend to make this library portable, small, and easy to extend to work with real parallel message passing systems such as MPI and PVM. Darrell Raymond Ulm

GatewayMU* is the result of a combination of what several of my friends and myself desire of a MUCK/MUD/MUSH/MU* client, a fully customizable integrated development environment with MUF and MPI support by default, and many wizards.

The Arbitrarily-Decomposed MPI FFT library is a C subroutine library for the computation of the multidimensional Fast Fourier Transform (FFT) of a distributed grid using the Message-Passing Interface (MPI).