Xilinx and Numenta claim dramatic speed-up of neural nets versus Nvidia GPUs

The measure of success is throughput that trained neural networks are able to perform. XilinxThe benchmark performance carried out by Xilinx and Numenta was done on two common benchmark tests of machine learning algorithms. The implementations of sparsity in the Xilinx chips, said Ahmad, means "we can design the circuitry to be custom-built for sparse networks." "People always talk about TOPS, TOPS, TOPS," said Peng. Although the AIE is a key ingredient, the Xilinx chips can do well at accelerating other tasks, not just the linear algebra, what the company calls "whole-application acceleration."