This week at the OpenPOWER Summit in San Jose, the OpenPOWER Foundation showed off real hardware for the first time with 13 systems including a a prototype HPC server from IBM and new microprocessor customized for China. Built collaboratively by OpenPOWER members, the new solutions exploit the POWER architecture to provide more choice, customization and performance to customers, including hyperscale data centers.
In this episode, the Radio Free HPC team wraps up the GPU Technology Conference. The theme of the show this year was Deep Learning, a topic that is heating up the market for GPUs with challenges like image recognition and self-driving cars. As a sister conference, the OpenPOWER Summit this week in San Jose showcased the first OpenPower hardware, including a prototype HPC server from IBM that will pave the way to the two IBM/Nvidia/Mellanox Coral supercomputers expected in 2017.
“The significance of the Coral announcement goes far beyond the specialism of high-performance computing (HPC) into enterprise computing, where the technologies being developed for HPC could transform this much wider and financially more important sector of the economy, according to the members of the winning partnership of IBM, Nvidia, and Mellanox. ‘There are game-changing elements to what we are doing,’ Ken King, general manger of OpenPower Alliances at IBM, told Scientific Computing World.”
“According to Big Blue, the new scale-out Power servers culminate a $2.4 billion investment and are built from the ground up to harness Big Data with the new IBM Power8 processor. During the launch event, IBM unveiled a rack full of 2U Power8 servers with up to 100 Terabytes of in-memory analytics capacity.”