DiGamma: Domain-aware Genetic Algorithm for HW-Mapping Co-optimization for DNN Accelerators
This work addresses the co-optimization challenge for DNN accelerator design, which is incremental as it builds on existing independent optimization methods.
The paper tackled the problem of co-optimizing hardware resource configuration and mapping strategy for DNN accelerators, which is challenging due to a large search space, and achieved a geomean speedup of 3.0x in edge settings and 10.0x in cloud settings compared to baseline algorithms.
The design of DNN accelerators includes two key parts: HW resource configuration and mapping strategy. Intensive research has been conducted to optimize each of them independently. Unfortunately, optimizing for both together is extremely challenging due to the extremely large cross-coupled search space. To address this, in this paper, we propose a HW-Mapping co-optimization framework, an efficient encoding of the immense design space constructed by HW and Mapping, and a domain-aware genetic algorithm, named DiGamma, with specialized operators for improving search efficiency. We evaluate DiGamma with seven popular DNNs models with different properties. Our evaluations show DiGamma can achieve (geomean) 3.0x and 10.0x speedup, comparing to the best-performing baseline optimization algorithms, in edge and cloud settings.