NVIDIA Unveils Tesla Preconfigured Clusters
2009-05-06
Preconfigured clusters are ready to use off the shelf machines that can be customized NVIDIA has launched its new ready-to-deploy Tesla GPU Preconfigured Cluster. The Tesla Cluster allows IT managers and researchers to efficiently add GPU computing capabilities to their existing data centers. NVIDIA says that the Tesla Cluster offers up to 30 times the performance of CPU-only solutions for the data center and that the Tesla Cluster consumes significantly less power at a lower cost. The GPU maker points to French bank BNP Paribas' Corporate and Investment Banking Division which recently replaced 500 CPU cores that consumed 25 kW of power with smaller CPU clusters and a pair of Tesla S1070 1U systems that consume only 2 kW (while at the same time offering better performance). NVIDIA's Tesla general manager Andy Keane said, "There are 15 to 20 million engineers, scientists and researchers around the world struggling for time on supercomputers, which has led to a huge pent-up demand for computation. With the launch of the Tesla Preconfigured Cluster, every one of them can easily deploy a GPU-powered supercomputing cluster that dramatically reduces their power consumption while still advancing the pace of their work." The Preconfigured Tesla clusters are made from x86 CPU servers coupled with Tesla S1070 1U GPU systems starting at 16 teraflops. Each of the S1070 clusters has four Tesla 10-series GPUs. The Tesla Preconfigured Clusters are available via NVIDIA partners now including MAX, Appro, CADNetwork, Colfax, Cray, Depo, FluiDyna, HPC Technologies, Inspur, JRTI, Megware, Microway, NetWeb, PCPC, Penguin, Silicon Mechanics, Sprinx, T-Platforms, Viglen and Xenon. Axel Kohlmeyer, associate director at the Center for Molecular Modeling at the University of Pennsylvania said, "Time on a supercomputer can be extremely difficult to get, especially since some of our computations run for weeks to months. Also, buying a supercomputer is expensive for every university research group. Since we got access to a Tesla GPU enabled cluster, we can run our molecular dynamics algorithms up to 100X faster and more importantly run bigger and more complex simulations and do research that was impossible to do before - this is game changing for us." NVIDIA launched its Tesla Supercomputer in November 2008.