CPSLab Cyber-Physical Systems Lab, Boston University

Publications Memory & Shared-Resource Management

Coherence-Aided Memory Bandwidth Regulation

Ivan Izhbirdeev, Denis Hoornaert, Weifan Chen, Alexander Zuepke, Youssef Hammad, Marco Caccamo, Renato Mancuso

45th IEEE Real-Time Systems Symposium (RTSS 2024), December 2024, York, UK

Best Paper Award

Read the PDF Code and artifacts Cite

Fig. 3: Integration of MemCoRe into the SoC’s cache coherency architecture. The blue arrow indicates the snoop direction. The red arrows indicate the directions of the enacting signals. The red components are from CoreSight.

Abstract

With the increasing adoption of PS-PL (Processor System-Programmable Logic) platforms, also known as CPU+FPGA systems, there arises a need for efficient resource management strategies. This work explores memory bandwidth regulation in such systems, leveraging the capabilities of tightly coupled FPGAs to offer elegant, low-overhead solutions with highly flexible regulation policies. We introduce MemCoRe, a novel approach that exploits the FPGA’s interaction with cache coherence interfaces and cross-trigger signals to achieve fine-grained spatiotemporal awareness of processor activity and software-free control. By comparing MemCoRe with state-of-the-art software-based approaches, namely MemGuard and MemPol, we demonstrate significant improvements in regulation precision and overhead reduction. Key contributions include nanosecond-scale memory bandwidth regulation, off-core memory bandwidth accounting, address-aware regulation, low-overhead token-bucket regulation, and asymmetric on-off core throttling. Our evaluation on a Xilinx Zynq UltraScale+ ZCU102 CPU+FPGA platform showcases MemCoRe’s capability to regulate memory bandwidth with nanosecond-scale precision. Overall, MemCoRe presents a promising avenue for efficient memory bandwidth regulation in PS-PL platforms, with strong applicability to real-time systems.

Code and hardware artifacts

Cite this paper

@inproceedings{memcore24,
  title     = {{Coherence-Aided Memory Bandwidth Regulation}},
  author    = {Izhbirdeev, Ivan and Hoornaert, Denis and Chen, Weifan and Zuepke, Alexander and Hammad, Youssef and Caccamo, Marco and Mancuso, Renato},
  booktitle = {45th IEEE Real-Time Systems Symposium (RTSS 2024)},
  year      = 2024,
  month     = dec,
  address   = {York, UK},
  url       = {https://cs-people.bu.edu/rmancuso/files/papers/MemCoRe_RTSS24.pdf},
  note      = {Best Paper Award}
}

Download .bib