Wednesday, November 09, 2011
Sandia Installs HPC Cluster with AMD Fusion Chips
Penguin Computing, experts in high performance computing (HPC) solutions, today announced that the company has successfully installed the world's first HPC cluster powered by AMD Accelerated Processing Units (APUs) at Sandia National Labs in Albuquerque, New Mexico. The system comprises 104 servers that are interconnected through a QDR InfiniBand fabric.
99% BAD HARDWARE WEEK: AMD has plans in the works for an "HPC APU that would utilize even a larger GPU and fewer x86 core" than the current desktop chips. He thinks the company can build HPC APUs that run about 150 watts and would be powerful enough to power an exaflop computer that consumes no more than 20 MW. 128 000 chips for Exaflops? 8 TFLOPS GPU per chip. Hmm. It is now able for 1 TFlops. In 2018 might crunch 8 TFlops. Thus, we solved the secret of Exaflops supercomputer design.
99% BAD HARDWARE WEEK: AMD has plans in the works for an "HPC APU that would utilize even a larger GPU and fewer x86 core" than the current desktop chips. He thinks the company can build HPC APUs that run about 150 watts and would be powerful enough to power an exaflop computer that consumes no more than 20 MW. 128 000 chips for Exaflops? 8 TFLOPS GPU per chip. Hmm. It is now able for 1 TFlops. In 2018 might crunch 8 TFlops. Thus, we solved the secret of Exaflops supercomputer design.
THIS LINK posted by Joseph Bell : 1:54 PM
