QADAM: Quantization-Aware DNN Accelerator Modeling for Pareto-Optimality
This work addresses the need for efficient design space exploration in custom DNN accelerators for the machine learning and systems communities, though it is incremental as it builds on existing quantization and accelerator modeling approaches.
The authors tackled the problem of designing energy-efficient deep neural network accelerators by developing QADAM, a quantization-aware modeling framework that incorporates varied bit precision and processing element types, resulting in performance per area and energy improvements of up to 5.7x compared to INT16-based designs.
As the machine learning and systems communities strive to achieve higher energy-efficiency through custom deep neural network (DNN) accelerators, varied bit precision or quantization levels, there is a need for design space exploration frameworks that incorporate quantization-aware processing elements (PE) into the accelerator design space while having accurate and fast power, performance, and area models. In this work, we present QADAM, a highly parameterized quantization-aware power, performance, and area modeling framework for DNN accelerators. Our framework can facilitate future research on design space exploration and Pareto-efficiency of DNN accelerators for various design choices such as bit precision, PE type, scratchpad sizes of PEs, global buffer size, number of total PEs, and DNN configurations. Our results show that different bit precisions and PE types lead to significant differences in terms of performance per area and energy. Specifically, our framework identifies a wide range of design points where performance per area and energy varies more than 5x and 35x, respectively. We also show that the proposed lightweight processing elements (LightPEs) consistently achieve Pareto-optimal results in terms of accuracy and hardware-efficiency. With the proposed framework, we show that LightPEs achieve on par accuracy results and up to 5.7x more performance per area and energy improvement when compared to the best INT16 based design.