We're proud to continue and improve on two benchmarking and code acceleration programs for GPUs.

• 
  SimCluster - Try 10 TFLOPS Before You Buy 
  Our 4 node SimCluster is available for benchmarking. It includes 4 NumberSmasher® 1U GPU nodes, each with 2 Tesla M2090 GPUs, 2 Xeon X5675 CPUs, 48GB DDR3 memory, and InfiniBand. AMBER and NAMD are preinstalled, but we also offer customers the opportunity to benchmark custom CUDA code. For customers requiring a rapid deployment, the benchmark configuration can ship within 48 hours.
  
  For SimCluster hardware information: SimCluster Datasheet
  Register to test on the SimCluster here
• 2X in 4 Weeks, Guaranteed! 
  Achieve 2X in 4 Weeks using PGI directives-based compilers. No prior GPU-programming experience required. Start the directives-based implementation on your existing machine(s). When ready to deploy, Microway is providing benchmark time on our SimCluster to measure results with the latest hardware.
  
  Register here to run your implementation on our SimCluster
  Read the guarantee FAQ for 2X in 4 Weeks from NVIDIA and PGI
• Recruiting Tesla Speed-up Case-Studies 
  If you've experienced a positive speed-up with our Tesla solutions, we'd love to hear your story. Whether you've employed our WhisperStation- Tesla PSC, SimCluster, a NumberSmasher 1U GPU Node, or OctoPuter, we'd like to hear about and hopefully share your experience with others.
  
  Submit your benchmarking success story, and we'll provide you with a free Tesla Thumbdrive and a special discount on up to four Tesla GPUs.
  

Abstract: With the 2x in 4 Weeks promotion, NVIDIA and PGI intend to demonstrate that almost anyone can succeed. The new OpenACC directives standard allows the compiler to accelerate code without a complete rewrite or digging into CUDA. Your application can be running twice as fast (or more) with less than a month of work. And if you register with Microway, you can have easy access to our 8 GPU Tesla SimCluster to recompile your application for GPUs and see the speedup! This post will walk you through the process.

Want insight into the latest platforms we'll debut with the Xeon E5 CPUs? The inside information on our production and integration work that takes place here in the US? Watch our interview with Techinsight.tv. It includes information on our future WhisperStation and the evolution of our NumberSmasher Twin² platform.

Microway's Tech Team recommends two notable HPC resources and articles:

• Linux Journal: The Lustre Distributed Filesystem
  

  Excerpt: There comes a time in a network or storage administrator's career when a large collection of storage volumes needs to be pooled together and distributed within a clustered or multiple client network, while maintaining high performance with little to no bottlenecks when accessing the same files. That is where Lustre comes into the picture. The Lustre filesystem is a high-performance distributed filesystem intended for larger network and high-availability environments.

  
  For more information, see http://www.linuxjournal.com/content/lustre-distributed-filesystem
• Admin Magazine: Parallel Programming with OpenCL
  

  Excerpt: Just a few years ago, video cards were designed solely for accelerating special applications. To perform such precise, generic calculations, programmers had to dig deep into their box of tricks and take a roundabout route to achieve their aims. For example, a scientist who wanted to add two large matrices could interpret them as textures with OpenGL, position them one in front of the other, and make the front half transparent. The rendered result is a texture that can then be interpreted as the resulting matrix. Although this might sound like a fairly simple addition, you will soon hit limits if you start to multiply or introduce loops, jumps, or conditions...

  OpenCL now provides a cross-platform standard for creating heterogeneous, parallel programs for CPUs, GPUs, and other processors. The presence of the OpenCL standard makes it possible to perform generic calculations on the GPU independently of the platform and manufacturer.

  For more information, see http://hpc.admin-magazine.com/Articles/Parallel-Programming-with-OpenCL

• Navion QuadPuter® 2U GPU Server with 2 Tesla GPUs
  Microway's new QuadPuter GPU Server provides 4 CPUs + 2 GPUs in a single Opteron server. Expect up to 64 x86 cores from the new AMD Opteron 6200 series CPUs and 2 Tesla GPUs with 2.66 TFLOPS of total floating point performance. This platform is ideal for a user who wants as many CPU and GPU cores as possible in a single system.
  
  For more information visit our QuadPuter Landing Page
• Microway SimpleCL™ Beta
  Microway's SimpleCL development and benchmarking tool for OpenCL is now available for beta testing. SimpleCL makes it easy to develop and test OpenCL compute kernels on a variety of CPUs and GPUs without having to use the cumbersome low-level APIs.
  
  Sign up for an account on https://gpgpu.microway.com and follow the instructions on the site to download your copy today.

Microway is growing, and we're looking to hire for two positions. Click through to the full listings for more information:

Sales Engineer - Help HPC work better for scientists and researchers worldwide!  Well spoken techie will advise our clients on design and implementation of GPU and cluster solutions for their specific needs.

Integration/Tech Support - Integrate, test, and assist supporting the latest HPC clusters and WhisperStations  - work with bleeding edge technologies!  Our systems incorporate Intel and AMD processors, NVIDIA GPUs, storage, InfiniBand, graphics and Linux software. Knowledge of server hardware, parallel processing, parallel programming (use of MPI, OpenMP) and computer architecture is highly desirable.