Please note that JavaScript and style sheet are used in this website,
Due to unadaptability of the style sheet with the browser used in your computer, pages may not look as original.
Even in such a case, however, the contents can be used safely.
NEC hybrid supercomputers combine traditional x86 processors with accelerators. Offloading computationally–intensive activities from the CPU to the GPU is of growing interest in the HPC arena. This hybrid supercomputer is one GPU solution offering among a series of GPU based compute servers. It integrates a large number of NVIDIA graphic processing units which converts the HPC system into a highly productive and cost-effective hybrid supercomputer.
This hybrid supercomputer is optimized for the right balance between GPUs and the latest Intel Xeon and AMDR OpteronR processor generation. One fully equipped rack delivers up to 20 Teraflops Peak performance of double precision. The Tesla20-series GPU-card is the next generation NVIDIA CUDATM GPU architecture codenamed “Fermi”. It will support many “must have” features for technical and enterprise computing. These include ECC memory for uncompromised accuracy and scalability, L1 and L2 caches, support for C++, 2x the memory bandwidth and 8x the double precision performance compared Tesla 10-series GPU computing products.
NEC offers to you a complete turn-key solution with additional support such as code porting, CUDA Training and CUDA Optimization.
