Search Results for "compute"

Ubicloud is an open-source cloud platform that aims to provide a decentralized alternative to traditional hyperscale cloud providers. It focuses on building a federated network of providers where individuals and organizations can contribute infrastructure and offer compute, storage, and networking resources. Ubicloud emphasizes transparency and openness: APIs, orchestration, and management layers are open, enabling users to audit and customize their infrastructure instead of relying on proprietary platforms. The system is designed to run workloads in a multi-tenant fashion, providing container and VM orchestration, security isolation, and billing mechanisms. ...

...It bridges the gap between computation frameworks and storage systems, bringing data from the storage tier closer to the data driven applications. This enables applications to connect to numerous storage systems through a common interface. It makes data local, more accessible and as elastic as compute.

UNICORE is a software suite for building federated systems, providing secure and seamless access to heterogeneous resource such as compute clusters and file systems. UNICORE deals with authentication, user mapping and authorization, and provides a comprehensive set of RESTful APIs for HPC access and workflows. Contributors: visit https://github.com/UNICORE-EU

dispy is a generic and comprehensive, yet easy to use framework for creating and using compute clusters to execute computations in parallel across multiple processors in a single machine (SMP), among many machines in a cluster, grid or cloud. dispy is well suited for data parallel (SIMD) paradigm where a computation (Python function or standalone program) is evaluated with different (large) datasets independently. dispy supports public / private / hybrid cloud computing, fog / edge computing.

This roll provides rpm packages to mount the lustre filesystem on the frontends and compute nodes of a rocks cluster. Please contact me if you need this roll for another kernel and/or lustre version.

ThunderstormDistributor is a queuing system that distributes jobs and computational workload across dynamic clusters in the cloud. It manages the assignment of jobs to maximize CPU and memory usage and prevent oversubscription of compute nodes. It also performs advanced statistics collection on individual compute nodes and jobs to graph the distribution of disk, network, CPU, and memory usage over time, which facilitates the advanced optimization and tuning of computational workflows.

RainforestCluster is an Amazon EC2 python program that manages and load-balances dynamic clusters to allow for maximum workflow flexibility and speed at minimal cost. It enables one to quickly and cheaply create dynamic compute clusters in the cloud, which can then run computational pipelines generically. It is also able to optimize the use of spot instances - idle computers in Amazon's cloud that are available at drastically reduced cost (5x-10x cheaper) - but can be terminated at any moment if capacity drops or the bid price rises. It also provides pre-installed features such as GlusterFS distributed filesystems, ThunderstormDistributor queuing system, RAID 0 /scratch, password-less ssh, and automatic cluster management, for ease of use and maximum processing speed for computational tools. ...

Mpaxs provides a simple abstraction for executing Callables and Runnables either locally within the same Virtual Machine, on the same host via RMI, or on remote machines, also via RMI. It supports launching of new compute hosts via an extensible API, currently featuring local compute host launching and grid compute host launching using the DRMAA API.

SCR caches checkpoint data in storage on the compute nodes of a Linux cluster to provide a fast, scalable checkpoint / restart capability for MPI codes.

SJM is a tool for managing jobs running on a compute cluster with a job scheduler such as Sun Grid Engine or Platform LSF. Use it to manage dependencies between jobs, monitor job completion status, restart failed jobs without rerunning jobs that finished successfully, and more!

ReScaGrid stands for REsource SCAvenging Grid. This project executes Javascript on compute engines and returns results back to a central task broker. It is designed to scavenge unused compute resources (e.g. user desktops) for bacth computation.

Spotckpt is a simulator for the following study; "Reducing Costs of Spot Instances via Checkpointing in the Amazon Elastic Compute Cloud"

OpenCL implementation for utilization of compute resources over a network.

PPIV is a parallel software application used in Particle Image Velocimetry (PIV) analysis. The software will compute the vector field for one image pair or multiple image pairs. PPIV can run on a single desktop machine or in a cluster environment.

"Distributed breve" (distbreve) is an open-source software package to make the process of implementing asynchronous, parallelizable steve code running under the breve simulation environment easily distributable amongst as many compute nodes as possible.

Designed to allow quick setup of powerful NOW-based clusters to run compute-intensive applications. Applications do not have to be designed specially for these clusters to benefit.