Design Space Exploration of Heterogeneous-Accelerator SoCs with Hyperparameter Optimization - Archive ouverte HAL Access content directly
Conference Papers Year :

Design Space Exploration of Heterogeneous-Accelerator SoCs with Hyperparameter Optimization

(1) , (1)
1

Abstract

Modern SoC systems consist of general-purpose processor cores augmented with large numbers of specialized accelerators. Building such systems requires a design flow allowing the design space to be explored at the system level with an appropriate strategy. In this paper, we describe a methodology allowing to explore the design space of power-performance heterogeneous SoCs by combining an architecture simulator (gem5-Aladdin) and a hyperparameter optimization method (Hyperopt). This methodology allows different types of parallelism with loop unrolling strategies and memory coherency interfaces to be swept. The flow has been applied to a convolutional neural network algorithm. We show that the most energy efficient architecture achieves a 2x to 4x improvement in energy-delay-product compared to an architecture without parallelism. Furthermore, the obtained solution is more efficient than commonly implemented architectures (Systolic, 2D-mapping, and Tiling). We also applied the methodology to find the optimal architecture including its coherency interface for a complex SoC made up of six accelerated-workloads.We show that a hybrid interface appears to be the most efficient; it reaches 22% and 12% improvement in energy-delay-product compared to just only using non-coherent and only LLC-coherent models, respectively.
Fichier principal
Vignette du fichier
cong_aspdac2021.pdf (860.74 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03119732 , version 1 (26-01-2021)

Identifiers

  • HAL Id : hal-03119732 , version 1

Cite

Thanh Cong, François Charot. Design Space Exploration of Heterogeneous-Accelerator SoCs with Hyperparameter Optimization. ASP-DAC 2021 - 26th Asia and South Pacific Design Automation Conference, Jan 2021, Virtual Conference, Japan. pp.1-6. ⟨hal-03119732⟩
48 View
409 Download

Share

Gmail Facebook Twitter LinkedIn More