Nvidia and Supermicro have announced the availability of a new class of server that combines parallel Nvidia Tesla GPUs with multi-core CPUs in a single 1U rack-mount server.
This new configuration claims to deliver 12 times the performance of a traditional quad-core CPU-based 1U server.
The new servers are based on Nvidia CUDA architecture as other Tesla GPU-based solutions. These servers claim to offer unprecedented levels of integration and reliability for enterprise-class users. In addition, the GPU can be integrated directly into the remote monitoring capabilities of the server to improve system level management.
Don Clegg, vice president of marketing at Supermicro, said: Our new Tesla GPU-based SuperServer 6016T-GF Series delivers a much higher performance-per-watt and per-rack than any other 1U solution in the market today. This 2-Teraflop SuperServer meets the most demanding enterprise data center requirements for reliability and manageability.
Petrobras has recently invested in a Verari Systems’ GPU-based cluster consisting of 190 NVIDIA Tesla GPU computing processors for scientific parallel processing, with transformative results. The Brazilian energy company expects scalable increase in GPU performance to continue as they build out their datacenter to deliver more than 400 TFLOPS.
