The new POWER9 systems are capable of improving the training times of deep learning frameworks by nearly four times, allowing enterprises to build more accurate AI applications at a faster rate, IBM said in a statement on 8 June.
"IT infrastructure needs to be re-designed for the AI era, which lets companies analyse data in milliseconds and make decisions driven by data," said Viswanath Ramaswamy, director of systems (India/South Asia) at IBM India.
"AI workloads demand new hardware and software paradigms and the infrastructure to deliver data-driven workloads. The P9 architecture aims to transform computing across every industry and profession, turning client data into faster insights where inferences can be drawn quicker and faster to market," Ramaswamy added.
The new POWER9-based "AC922 Power Systems" can significantly accelerate data movement, IBM said.
The system was designed to drive demonstrable performance improvements across popular AI frameworks such as Chainer, TensorFlow and Caffe, as well as accelerated databases such as Kinetica.
As a result, data scientists can build applications faster, ranging from deep learning insights in scientific research, real-time fraud detection and credit risk analysis, the statement added.