GPGPU stands for General-Purpose computation on Graphics Processing Units, also known as GPU Computing.

Graphics Processing Units (GPUs) are high-performance many-core processors capable of very high computation and data throughput. Once specially designed for computer graphics and difficult to program, todays GPUs are general-purpose parallel processors with support for accessible programming interfaces and industry-standard languages such as C. Developers who port their applications to GPUs often achieve speedups of orders of magnitude vs. optimized CPU implementations. The goal of GPGPU.org is to catalog the current and historical use of GPUs for general-purpose computation, and to provide a central resource for GPGPU software developers. The term GPGPU was coined and GPGPU.org was founded by Mark Harris in 2002 when he recognized an early trend of using GPUs for non-graphics applications. GPGPU.org has grown from an obscure site visited by few into a popular destination for developers and researchers.

A 2 day CUDA workshop will be held in Berlin from July 2-3, for developers who want to learn how to program and utilize the Graphics Processing Unit (GPU) using NVIDIAs CUDA programming framework. No prior knowledge of parallel computing concepts is necessary, but some basic C/C++ knowledge will be required.

On May 30th 2012, the CUDA research center at TU Darmstadt and Fraunhofer IGD hosted the introductory workshop on OpenACC and CUDA C/C++. Participation on this workshop was possible without prior knowledge of computing on graphics processing units (GPUs) or parallelization using OpenACC. The aim of this workshop was getting a broad overview of the few topics in several lectures that were held. Topics which were covered during this workshop were: Nvidia Tesla Overview General Overview of GPU Programming with CUDA C/C++ General overview of GPU Acceleration with OpenACC Directives During the workshop, participants were able to visit the hardware exhibition hosted by CADnetwork GmbH, where new NVIDIA hardware architectures could be seen.

The CUDA research center at TU Darmstadt and Fraunhofer IGD will host an introductory workshop on OpenACC and CUDA C/C++ on May 30th 2012. The workshop is intended for a broad audience - no prior knowledge of computing on GPUs (graphics processing units) or parallelization using OpenACC is required. Participants will get a broad overview of the topic in several lecture and have the opportunity to interact with the speakers during the coffee break and over lunch.

Participation in the workshop including coffee break and lunch is free. We strongly request advance registration until Friday May 25th, 2012 in order to plan accordingly. Catering may not be available for later registrations.