HiPEAC Best Paper Award for MetaSys

Congratulations to SAFARI Research Group members Nandita Vijaykumar, Ataberk Olgun, Konstantinos Kanellopoulos, F. Nisa Bostanci, Hasan Hassan, Mehrshad Lotfi, Phillip B. Gibbons, and Onur Mutlu, for their Best Paper Award at the HiPEAC 2023 conference for their ACM TACO paper “MetaSys: A Practical Open-source Metadata Management System to Implement and Evaluate Cross-layer Optimizations”. The paper was awarded one of the three Best Paper Awards among all papers published at HiPEAC 2023, by a selection committee from Huawei and HiPEAC.  Ataberk Olgun presented the paper at the HiPEAC 2023 conference and accepted the award.

The MetaSys source code is completely and freely available at https://github.com/CMU- SAFARI/MetaSys.  You can find the links to the paper and the presentations below.

This paper introduces the first open-source FPGA-based in- frastructure, MetaSys, with a prototype in a RISC-V system, to enable the rapid implementation and evaluation of a wide range of cross-layer techniques in real hardware. Hardware-software cooperative techniques are powerful approaches to improving the performance, quality of service, and security of general-purpose processors. They are however typically challenging to rapidly implement and evaluate in real hardware as they require full-stack changes to the hardware, system software, and instruction-set architecture (ISA).

MetaSys implements a rich hardware-software interface and lightweight metadata support that can be used as a common basis to rapidly implement and evaluate new cross-layer techniques. We demonstrate MetaSys’s versatility and ease-of-use by implementing and evaluating three cross-layer techniques for: (i) prefetching in graph analytics; (ii) bounds checking in memory unsafe languages, and (iii) return address protection in stack frames; each technique requiring only ~100 lines of Chisel code over MetaSys.

Using MetaSys, we perform the first detailed experimental study to quantify the performance overheads of using a single metadata management system to enable multiple cross-layer optimizations in CPUs. We identify the key sources of bottlenecks and system inefficiency of a general metadata management system. We design MetaSys to minimize these inefficiencies and provide increased versatility compared to previously-proposed metadata systems. Using three use cases and a detailed characterization, we demonstrate that a common metadata management system can be used to efficiently support diverse cross-layer tech- niques in CPUs.

“MetaSys: A Practical Open-source Metadata Management System to Implement and Evaluate Cross-layer Optimizations”ACM Transactions on Architecture and Code Optimization (TACO), June 2022.
[arXiv version]
Presented at the 18th HiPEAC Conference, Toulouse, France, January 2023.
Slides (pptx) (pdf)]
[Preliminary Talk Video (14 minutes)]
[SAFARI Live Seminar Video (1 hour 26 minutes)]
[MetaSys Source Code]
Best paper award at HiPEAC 2023.

Posted in Awards, Code, Conference, Lectures, Papers, Talks.