NEW NVIDIA®
GPU PSC & Servers
Servers • Storage • Solutions
Boston’s Venom series of NVIDIA®
massive levels of computational processing power made available by NVIDIA®
GPU compute platforms provide GPU compute processors
Tesla
TM
20-series (Fermi) computing processors
Boston Venom T4100 PSC (Personal Super Computer)
As the latest addition to Boston’s highly succesful Venom series of GPU compute platforms the Venom T4100 PSC provides staggering levels of computational performance to tackle large scale problems far faster than a small server cluster.
Based on NVIDIA’s® latest Tesla
TM
20-series GPU architecture (codename
Fermi) the Boston Venom T4100 PSC has been designed to push the performance envelope further with over 100% more GPU compute performance in comparison to previous G80 based Tesla
TM
Key features:
� 4x NVIDIA®
� 2x Intel® solutions. Fermi C2050 GPU compute processors Xeon® X5650 Six Core 2.66 GHz, 6.40 GT/s processors
� 12GB Supermicro Validated DDR3-1333 Reg ECC memory � Redundant 1400W Gold Level (93%) high-efficiency Power Supply
Ask about NVIDIA’s® next generation Tesla™
Next generation high performance CUDA™ cores
� Optimized performance & accuracy with up to 8X faster double precision
� Versatile accelerators for a wide variety of applications
20-series (Fermi)
NVIDIA® Parallel DataCache technology
� First GPU architecture to support a true cache hierarchy in combination with on-chip shared memory
� Improves bandwidth & reduces latency through L1 cache’s configurable shared memory
� Fast, coherent data sharing across the GPU through unified L2 cache
A small selection of industries taking advantage of this excting new technology:
Grid computing
High performance & Compute clusters
Segmentation Raytracing
Scientic computing
video encoding & processing Chemistry
Bioinformatics Hardware accelerated
Load balancing clusters Oil & gas
Molecular Dynamics Video Processing
Analogue signal processing Geosciences
Bio & Life sciences Audio signal processing
Weather forecasting & climate research
Medical imaging Computational
Mathematical & Financial computing
Amongst many more…
©2010 Boston Limited. Specification subject to change without notice. All brands, names and trademarks remain the property of their respective owners. Errors & Omissions Excepted.
For more information contact Boston Tel: +44(0)1727 876 100 Email:
sales@boston.co.uk www.boston.co.uk
NVIDIA® GigaThread™ engine
� Increased efficiency with concurrent kernel execution
� Dedicated, bi-directional data transfer engines Intelligently manage tens of thousands of threads
ECC support
� First GPU architecture to support ECC � Detects & corrects errors before system is affected
� Protects register files, shared memories, L1 and L2 cache, and DRAM
Boston Venom T1100 1U GPU compute node
Having had great success within the scientific and HPC community with our Venom series of GPU compute nodes Boston have rewritten the rule books once again with the launch of our latest Venom T1100 GPU compute node.
With the latest generation of high performance Tesla
TM
20-series GPU
compute cores all packaged within a tiny 1U enclosure Boston’s Venom T1100 GPU compute node provides unrivalled processing power and power efficiency.
Key features:
� 2x NVIDIA®
� 2x Intel® Fermi M2050 GPU compute processors Xeon® X5650 Six Core 2.66 GHz, 6.40 GT/s processors
� 12GB Supermicro Validated DDR3-1333 Reg ECC memory � 1400W high-efficiency Gold Level (93%) Power Supply with PMbus
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60