Search Results for "opencl test"

mtsieve is a framework wrapped around primesieve to distribute prime numbers to worker classes to do work with those prime numbers. The "mt" means that it is multi-threaded. The "sieve" means that the framework is typically used to eliminate candidate terms with small from a set of numbers. The numbers remaining after using mtsieve can then be used by programs such as llr and pfgw to test those numbers for primality. Another usage could be to use those prime numbers to test each...

... themselves with teams. It has a number of webpages that can be used to show current progress and statistics. It also has the ability to send e-mail when a new prime is found. Although PRPNet works well for home users with multiple cores or multiple machines, it does scale well up to a few hundred users. PrimeGrid runs most of its smaller projects on PRPNet.. PRPNet also has the ability to test for Wieferich and Wall-Sun-Sun primes. The client can run an OpenCL application for maximum throughput.

Copenhagen Computed Tomography Toolbox is a collection of applications and libraries for flexible and efficient CT reconstruction. The toolbox apps generally take a set of projections (X-ray intensity measurements) and filter and back project them in order to recreate the image or volume that the projections represent. The project includes both mostly informative CPU implementations and highly efficient GPU implementations. Regular releases are hosted at the Python Package Index.

Develop scripts to perform simple forensic functions like image, overwrite, hash, and search. The core of the script is Python Cuda/OpenCL. Initially the goal is to test the performance of the concept. If performance shows value the next step would be to develop scripts to perform each function.

A GPU memory test utility for NVIDIA and AMD GPUs using well established patterns from memtest86/memtest86+ as well as additional stress tests. The tests are designed to find hardware and soft errors. The code is written in CUDA and OpenCL.

This is a research project to test GPU (OpenCL) usability for image compression. Jpeg format is chosen because it is relatively simple and I am familiar with it. 2013-01-22: For now only pixel conversion and DCT transform is done with OpenCL, entropy coding is done with CPU in one thread. Unfortunately this implementation is no match for even one threaded SSE2 jpeg encoder, too much data goes through PCIe. Look at "Debunking the 100X GPU vs. CPU Myth: An Evaluation of Throughput Computing...