May 11, 2011
May 11 -- RenderStream is pleased to announce its AMD Radeon based 21.6 teraflop servers and workstations for OpenCL / OpenGL / Brooks based applications and product development.
OpenCL is rapidly a maturing programming language that, with its continued development, begins to rival CUDA, enabling high performance computing with AMD GPUs. GPGPU high-performance computing using AMD GPUs show great potential for information security, medical imaging, computer graphics and rendering, server side rendering, finite-difference-time-domain (FDTD), electro-magnetics, physics, bioscience and EDA. These systems need to be seriously considered in any development plans for GPGPU acceleration.
If your application uses OpenCL / OpenGL / Brooks then consider RenderStream's AMD Radeon HD 6970 based VDACTr8 or our HD 6990 based VDAC4x2. The 1,536 stream processors and eight GPUs per system provide access to 12,288 cores and 21.6 teraflops of aggregate compute power (operating at an over-clocked peak performance).
As an example from information security, using the integer-based oclHashCat, RenderStream's customers are seeing near linear scaling in computational power which simply trounces the 4,096 cores and 12.6 teraflops of our GTX 580 based VDACTr8. In this example the HD 6970 and HD 6990 based VDACTr8 evaluated over 45 billion solutions per second versus 18 billion for the GTX 580 based systems, depending on the implementation. For more information, visit http://www.tmto.org.
Please note GPGPU is still in its infancy. How a GPU performs is impacted by not only the architecture of the hardware and the GPU, but also the drivers and the software tools available to utilize the GPU. Looking at the chart below we see that 4 HD 6990 cards were more than twice as fast as 8 GTX 580 cards in this application. That being said, the difference in speed may be that critical software tools are missing, that when fixed, would make the 580 the king again.
NVIDIA and AMD both provide great performing HPC solutions. It just comes down to your ability to implement an optimal solution. So keep this in mind and make careful, well-researched choices. RenderStream is dedicated to promoting GPU-accelerated HPC, visualization, medical imaging, bioinformatics, GIS, server side rendering and computer graphics industries. The company does this by offering general purpose GPU systems that can be used prior to implementation of its HPC GPU based products that use Tesla and FireStream.
Availability and Pricing
RenderStream offers four and eight NVIDIA/AMD based GPGPU VDAC systems for development and production. Prices start at $5,995 USD for a system with 1,792 CUDA cores, on up to tens of thousands for production systems with the ultimate performance and stability. For the company's popular development systems, prices fall in the $12,000 to $18,000 range for an eight GPU system. RenderStream sells and supports its products worldwide. For more information or to request a quote, contact RenderStream at 512-850-4098 or email email@example.com.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?