Microway April/May, 2010 News Brief
BioIT Award and Tesla Fermi Technical Info
Tesla Fermi C2050 Now Shipping, Benchmarks Now Available
Tesla Fermi C2050 drastically outperforms traditional CPUs and Tesla C1060 GPUs - See the results here
Performance comparisons include Linpack, AMBER, OpenEye ROCS Virtual Drug Screening, n-body, ray tracing, LAPACK, single and double-precision BLAS, FFT, Sparse Matrix-Vector Multiplication, and Radix Sort.
Tesla C2050 GPU specifications include:
- 448 CUDA cores provide 515 GFLOPS double- and 1.03 TFLOPS single-precision floating point performance
- 3GB GDDR5 memory with optional ECC provides memory bandwidth of 141 GB/sec
Cost-effective solutions for the above applications with Tesla C1060 will continue to be available.
Microway BioStack™ Earns Best of Show Finalist at BioIT World Conference
delivers a hybrid computational environment for life sciences applications. At the conference the BioStack ran VMD simulating a customer supplied molecule. The judges declared the BioStack™ a Best of Show Finalist.
- Total of 1.4TFLOPs double precision CPU and 6TFLOPs double precision GPU performance (12+ TFLOPs single)
- Navion 4-way Opteron SMP Master Node with Storage: 48 CPU cores and 6TB
- Six GPU Compute Nodes: each with 2 Tesla™ Fermi C2050 448 core GPUs and 24 AMD Opteron CPU cores
- Microway 24 port DDR FasTree™ InfiniBand switch
- Compact 9U Cabinet for excellent scalability
Microway also displayed a WhisperStation-LS
with 2 Tesla Fermi C2050 GPUs and dual 6-Core Xeons. The WhisperStation-LS was shown running a Radiological Path Length Tool for Proton Treatment Planning
courtesy of the Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School and Harvard University, School of Engineering and Applied Sciences (SEAS).
New Microway White Paper: GPGPU Architecture Comparison of NVIDIA and ATI GPUs
For customers directly comparing GPUGPU architectures, there have been few detailed technical resources. This white paper shows the two main competing GPGPU architectures, their derivative products, and presents Microway solutions optimized for all GPU:CPU ratios and implementations.
CUDA Coding Resource: Programming Massively Parallel Processors Textbook
For those learning GPGPU programming this book by David Kirk and Wen-mei Hwu is the definitive resource.
"Programming Massively Parallel Processors: A Hands-on Approach shows both student and professional alike the basic concepts of parallel programming and GPU architecture. Various techniques for constructing parallel programs are explored in detail. Case studies demonstrate the development process, which begins with computational thinking and ends with effective and efficient parallel programs."-Elsevier Publishing.
Accelerate your research!
Take advantage of our expertise: we can recommend the most effective compute solutions, help you plan a painless installation, and deliver fully-tested/fully-integrated clusters, servers and workstations.
Eliot Eshelman at 508-732-5534
Brett Newman at 508-732-5542
GSA Schedule GS-35F-0431N