Displaying 1 to 8 from 8 results

fbg - FBGraphics (FBG) is a simple C 24 bpp graphics library for the Linux framebuffer with parallelism support

  •    C

FBGraphics (FBG) is a simple C 24 bpp graphics library for the Linux framebuffer with parallelism support. The library is relatively generic, most functions (including parallel ones) only manipulate buffers, it should be easy to extract some parts and adapt it to other means, you may want to check fbg_setup fbg_draw fbg_flipand fbg_close for that.

drwmutex - Distributed RWMutex in Go

  •    Go

The default Go implementation of sync.RWMutex does not scale well to multiple cores, as all readers contend on the same memory location when they all try to atomically increment it. This repository provides an n-way RWMutex, also known as a "big reader" lock, which gives each CPU core its own RWMutex. Readers take only a read lock local to their core, whereas writers must take all locks in order. Note that the current implementation only supports x86 processors on Linux; other combinations will revert (automatically) to the old sync.RWMutex behaviour. To support other architectures and OSes, the appropriate cpu_GOARCH.go and cpus_GOOS.go files need to be written. If you have a different setup available, and have the time to write one of these, I'll happily accept patches.

pthread_pool - A simple implementation of thread pooling for C/C++ using POSIX threads

  •    C

A simple implementation of thread pooling for C/C++ using POSIX threads. Each pool has a designated worker function, and expects to be given a number of work items. Any thread in the pool can take a work item, and will pass the work item to the pool's worker function. The work items are void *, and are passed to the worker function exactly as they are given to pool_enqueue. The return values of the worker functions are ignored.




pararr.js - Parallel computing for Node

  •    Javascript

Modern multicore systems can process lots of data in parallel but writing parallel code can be tricky. Pararr.js provides an easy-to-use API for parallel computing in Node and parallel implementations of standard array functions like map or filter that utilize all available cores in the system when calculating their result. ##Considerations Pararr creates a V8 instance for each CPU core which has an effect memory consumption and startup time. When a calculation is dispatched to a worker the function and its data is copied and sent to the corresponding instance which causes an shorter or longer delay depending mainly on the data volume. Generally speaking we can benefit from parallelization in this form when data volumes are small and CPU cycles is a bottleneck.

corebench - corebench - run your benchmarks against high performance computing servers with many CPU cores

  •    Go

Benchmark utility that's intended to exercise benchmarks and how they scale with a large number of cores. First Provider: DigitalOcean up to 48 cores currently.

pthreadpool - pthread-based thread pool for C/C++

  •    C

pthreadpool is a pthread-based thread pool implementation. It is intended to provide functionality of #pragma omp parallel for for POSIX systems where OpenMP is not available.

veros - The versatile ocean simulator, in pure Python, powered by JAX.

  •    Python

Veros is the versatile ocean simulator -- it aims to be a powerful tool that makes high-performance ocean modeling approachable and fun. Because Veros is a pure Python module, the days of struggling with complicated model setup workflows, ancient programming environments, and obscure legacy code are finally over. Veros supports a NumPy backend for small-scale problems and a high-performance JAX backend with CPU and GPU support. It is fully parallelized via MPI and supports distributed execution.







We have large collection of open source products. Follow the tags from Tag Cloud >>


Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.