Accelerated Machine Learning on Intel® FPGAs Using oneAPI
In this demonstration, InAccel* presented how their machine-learning applications run up to 40x faster using oneAPI. As a use case, logistic regression training is shown to run 42x faster on an Intel® Arria® 10 FPGA using the oneAPI interface. The reference code for the model was ported to DPC++ and the results were compared. The implementation was done on Intel FPGA using the oneAPI development flow.