Advancing Compilation of DNNs for FPGAs Using Operation Set Architectures

摘要

The slow-down of technology scaling combined with the exponential growth of modern machine learning and artificial intelligence models has created a demand for specialized accelerators, such as GPUs, ASICs, and field-programmable gate arrays (FPGAs). FPGAs can be reconfigured and have the potential to outperform other accelerators, while also being more energy-efficient, but are cumbersome to use with today's fractured landscape of tool flows. We propose the concept of an operation set architecture to overcome the current incompatibilities and hurdles in using DNN-to-FPGA compilers by combining existing specialized frameworks into one organic compiler that also allows the efficient and automatic re-use of existing community tools. Furthermore, we demonstrate that mixing different existing frameworks can increase the efficiency by more than an order of magnitude.