The new POWER9 systems are built specifically for compute-intensive artificial intelligence (AI) workloads. According to the company, they are capable of improving the training times of deep learning frameworks by nearly 4x, allowing enterprises to build more accurate AI applications - ranging from deep learning in scientific research, real-time fraud detection, and credit risk analysis - and to build them faster.
The new POWER9-based AC922 Power Systems embed PCI-Express 4.0, next-generation NVIDIA NVLink high-speed interconnect, and the OpenCAPI open interface architecture - which combined, says the company, can accelerate data movement calculated at 9.5x faster than PCI-E 3.0 based x86 systems. The system was designed to drive demonstrable performance improvements across popular AI frameworks such as Chainer, TensorFlowm, and Caffe, as well as accelerated databases such as Kinetica.
According to the company, POWER9 is "at the heart" of the soon-to-be most powerful data-intensive supercomputers in the world - the U.S. Department of Energy's " Summit" and " Sierra" supercomputers, and has been tapped by Google.
"We've built a game-changing powerhouse for AI and cognitive workloads," says Bob Picciano, SVP of IBM Cognitive Systems. "In addition to arming the world's most powerful supercomputers, IBM POWER9 Systems is designed to enable enterprises around the world to scale unprecedented insights, driving scientific discovery enabling transformational business outcomes across every industry."