FPGAs accelerate conversational AI and Natural Language Processing applications
An FPGA can be a very attractive platform for many Machine Learning (ML) inference applications. In this presentation, using the example of automatic speech recognition (ASR), we will explore how FPGAs can be used to accelerate conversational AI and Natural Language Processing applications. We’ll review the key components in the Achronix FPGAs architecture, such as a 2D Network on Chip (NoC), high-speed external memory, and optimized Machine Learning Processor (MLP), and how our symmetrical architecture can make scaling solutions in the FPGA transparent and short time to deploy. Using standard benchmarks, we demonstrate an ASR appliance that can reduce costs by as much as 90% compared with alternative approaches.