Today was an exciting day for HP and NVIDIA with the announcement of the new Tesla M2090 GPU and its upcoming availability in multiple HP ProLiant servers.
The high performance computing (HPC) segment has an endless thirst for performance and this has made the use of GPUs a disruptive force. For researchers, scientists and engineers, enhanced performance allows for faster innovation that will result in the kinds of discoveries that can change the world.
HP and NVIDIA have collaborated for over a decade on GPU enabled Hybrid systems development. Back in 2007, HP and NVIDIA demonstrated the 1st GPU enabled system; today we support 14 GPU-enabled systems.
The result of HP and NVIDIA’s collaboration is evident by the world’s most noted supercomputers, such as Tsubame 2.0 at the Tokyo Institute of Technology. This system uses 1,408 HP ProLiant SL390s G7 servers and was named by the Green 500 site as the “World’s Greenest Production Supercomputer.” It’s also the 4th fastest in the world according to the November 2010 Top 500 list.
Tsubame 2.0 is an incredible achievement in performance per watt, especially if you compare it to Jaguar, which is listed as the #2 system on the Top 500 list. Both have similar peak petaflop performance, but Tsubame 2.0 does it with 92 percent fewer servers and consumes only 1/7th the power. Take that into consideration and it’s easy to see why GPUs have made such an impact in HPC.
Late last year HP introduced the HP ProLiant SL390s G7 server – two of our half-width HP ProLiant SL390s G7 servers deliver 16 GPUs and 4 CPUs in 4U – that’s the highest GPU-to-CPU ratio on the market. For HPC users, that means it packs a big punch in a comparatively small footprint – a critical need in just about every datacenter on the planet.
HP congratulates NVIDIA on the new M2090. We remain proud to work with a strategic and innovative partner and look forward to continued collaboration that will allow us to change the world. Long live disruptive technologies.