We propose a DSE flow based on active learning, namely ARS-Flow. It is featured with Pareto-region-oriented stochastic resampling method (PRSRS) and ...

Abstract— Surrogate model-based design space exploration. (DSE) is the mainstream method to search for optimal mi- croarchitecture designs.

Mar 28, 2024 · Second, ARAPrototyper provides a clean interface to quickly integrate users' own accelerators written in high-level synthesis (HLS) code. The ...

Fast and accurate wire timing estimation based on graph learning ... ARS-Flow: A Design Space Exploration Flow for Accelerator-rich System based on Active ...

Such architectures present many new challenges and opportunities, such as accelerator synthesis, scheduling, sharing, virtualization, memory hierarchy ...

ARS-Flow: A Design Space Exploration Flow for Accelerator-rich System based on Active Learning. Conference Paper. Jan 2024. Shuaibo Huang ...

Jan 26, 2021 · ABSTRACT. Modern SoC systems consist of general-purpose processor cores augmented with large numbers of specialized accelerators. Building.

This setup enables numerous opportunities for design space exploration of accelerator rich systems. For one, users have the ability to track memory ...

RTL co-simulation, pre-RTL modeling, and prototyping provide a more cost-effective alternative for system-level design space exploration of accelerator-rich ...

ARS-Flow: A Design Space Exploration Flow for Accelerator-rich System based on Active Learning. Authors. Shuaibo Huang · Yuyang Ye · Hao Yan · Longxing Shi ...