Litcius/Paper detail

HW-ADAM: FPGA-Based Accelerator for Adaptive Moment Estimation

Weiyi Zhang, Liting Niu, Debing Zhang, Guangqi Wang, Fasih Ud Din Farrukh, Chun Zhang

2023Electronics16 citationsDOIOpen Access PDF

Abstract

The selection of the optimizer is critical for convergence in the field of on-chip training. As one second moment optimizer, adaptive moment estimation (ADAM) shows a significant advantage compared with non-moment optimizers such as stochastic gradient descent (SGD) and first-moment optimizers such as Momentum. However, ADAM is hard to implement on hardware due to the computationally intensive operations, including square, root extraction, and division. This work proposed Hardware-ADAM (HW-ADAM), an efficient fixed-point accelerator for ADAM highlighting hardware-oriented mathematical optimizations. HW-ADAM has two designs: Efficient-ADAM (E-ADAM) unit reduced the hardware resource consumption by around 90% compared with the related work. E-ADAM achieved a throughput of 2.89 MUOP/s (Million Updating Operation per Second), which is 2.8× of the original ADAM. Fast-ADAM (F-ADAM) unit reduced 91.5% flip-flops, 65.7% look-up tables, and 50% DSPs compared with the related work. The F-ADAM unit achieved a throughput of 16.7 MUOP/s, which is 16.4× of the original ADAM.

Topics & Concepts

Computer scienceField-programmable gate arrayMoment (physics)ThroughputConvergence (economics)Computer hardwareTelecommunicationsPhysicsClassical mechanicsEconomicsEconomic growthWirelessNumerical Methods and AlgorithmsError Correcting Code TechniquesAdvanced Neural Network Applications
HW-ADAM: FPGA-Based Accelerator for Adaptive Moment Estimation | Litcius