NVIDIA Corp.’s Tesla C1060 GPU Computing processors are now available in the new Cray CX1 line of supercomputers. With the ability to fit into a standard office setting, the CX1 brings high-productivity computing solutions to a broad array of markets.
Each Tesla processor has hundreds of processor cores that deliver nearly 1 TFLOP of peak computing performance. When configured with four Tesla devices, the CX1 provides up to 4 TFLOPS of computing power at the user’s desk side.
Using GPUs, researchers have reported up to a 100x speed increase in applications such as molecular dynamics, quantum chemistry, finite element analysis, particle simulation, and electronic design automation. The highly parallel architecture of the GPU has been made accessible for these industries through the NVIDIA CUDA architecture.
With NVIDIA’s C-compiler and software development kit (SDK) for developing parallel computing applications on GPUs, developers can exploit the GPU’s parallel computing architecture and automatically distribute computing work across tens of thousands of threads and hundreds of processor cores, NVIDIA said.