Fast Performance Estimation and Design Space Exploration of SSD Using AI Techniques

Abstract

SSD has become an indispensable element in today’s computer systems, and their architecture is constantly evolving with new host interfaces for higher performance and larger storage capacities thanks to incessant flash technology development. As the complexity of SSD architecture increases, it is necessary to use a systematic methodology for architecture design. In this paper, we propose a novel methodology to explore the design space of an SSD based on a genetic algorithm at the early design stage. The key technical challenge in the design space exploration (DSE) is fast and accurate performance estimation or fitness evaluation in the genetic algorithm. To tackle this challenge, we propose two performance estimation methods. One is based on the scheduling of the task graph abstracted from the firmware and the other one is based on a neural network (NN) regression model. While the NN-based method is faster, the accuracy of the NN-based method depends on the training data set that consists of hardware configurations and performance. The scheduling-based performance estimator is used to generate the training data set fast. The viability of the proposed methodology is confirmed by comparison with a state-of-the-art SSD simulator in terms of accuracy and speed for design space exploration.