Astrophysical Supercomputing with “ Green ” GPU

نویسنده

  • M. M. Resch
چکیده

its tenth year and this is a good reason to look back a little bit. When the three national centers decided to launch Inside in 2002 this was a first step to bring together the activities of the centers and make them visible to a broader audience. Since then German supercomputing has undergone a number of major developments and has made great leaps forward. As a first step a national super-computing strategy was developed. Following from this, the Gauss Center for Supercomputing (GCS) as the coordinating body for the three national centers was established. The Gauss Alliance followed to bring together the regional and topical German centers. For the national centers a project " PetaGCS " was started providing 400 Mio Euro for hardware and operational costs to guarantee Germany a leading position in supercomputing in Europe and worldwide. For the mid-range centers a special line of funding was opened which provided 100 Mio Euro for the renewal of systems. All this funding for hardware was supported by strategies for the development of new algorithms and software. The Federal Ministry for Education and Science (BMBF) started a special HPC software funding line. Through this initiative Germany has seen two calls for proposals in HPC software over the last 3 years. While BMBF was focusing its funding on application driven projects the German Research Foundation (DFG) initiated a special program for the funding of basic technologies targeting highly scalable software for supercomputing. The projects funded in this initiative will start later this year. In this issue you will find reports and articles about some of the achievements of these combined hardware and software initiatives. HLRS at Stuttgart inaugurated its first Petascale system. LRZ at Garching is about to launch its 3 Petaflops system with an inauguration in July of this year. A number of application reports show the usage of GCS-systems. Project reports highlight the German research activities in software development. Obviously German supercomputing has made big steps forward over the last year. However, we do not only look back on our successes. The next steps for supercomputing in Germany are in the pipeline already. GCS will start the next round of hardware upgrades soon with the Juelich Supercomputing Center installing a new BlueGene system late this year. LRZ and HLRS will follow in 2013 and 2014. Discussions about the continuation of GCS beyond 2017 have already started. The funding for …

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

GPU Scaling: From Personal Supercomputing to the Cloud

Current state-of-the-art GPU-based systems offer unprecedented performance advantages through accelerating the most compute-intensive portions of applications by an order of magnitude. GPU computing presents a viable solution for the ever-increasing complexities in applications and the growing demands for immense computational resources. In this paper the authors investigate different platforms...

متن کامل

Astrophysical Supercomputing with GPUs: Critical Decisionsfor Early Adopters*

General-purpose computing on graphics processing units (GPGPU) is dramatically changing the landscape of high performance computing in astronomy. In this paper, we identify and investigate several key decision areas, with a goal of simplifying the early adoption of GPGPU in astronomy. We consider the merits of OpenCL as an open standard in order to reduce risks associated with coding in a nativ...

متن کامل

Computación y Sistemas, Vol. 18, No. 4, 2014

We present a set of algorithms for simulating and visualizing real-time crowds in GPU (Graphics Processing Units) clusters. First we present crowd simulation and rendering techniques that take advantage of single GPU machines. Then, using as an example a wandering crowd behavior simulation algorithm, we explain how this kind of algorithms can be extended for their use in GPU cluster environment...

متن کامل

Astrophysical Particle Simulations on Heterogeneous CPU-GPU Systems

A heterogeneous CPU-GPU node is getting popular in HPC clusters. We need to rethink algorithms and optimization techniques for such system depending on the relative performance of CPU vs. GPU. In this paper, we report a performance optimized particle simulation code ”OTOO”, that is based on the octree method, for heterogenous systems. Main applications of OTOO are astrophysical simulations such...

متن کامل

Validation of the GPU-Accelerated CFD Solver ELBE for Free Surface Flow Problems in Civil and Environmental Engineering

This contribution is dedicated to demonstrating the high potential and manifold applications of state-of-the-art computational fluid dynamics (CFD) tools for free-surface flows in civil and environmental engineering. All simulations were performed with the academic research code ELBE (efficient lattice boltzmann environment, http://www.tuhh.de/elbe). The ELBE code follows the supercomputing-on-...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012