While computer systems have advanced rapidly for decades, their improvement is beginning to slow. This product aims to invest in future computer systems innovations, by improving the underlying infrastructure of gem5, a widely-used tool for simulating computer systems. The project will upgrade gem5 by improving its underlying components, simplifying its interface, improving its documentation and user services, and training more junior researchers on its use.
Computer systems innovation is traditionally driven by cycle-level software simulations, where novel techniques are modeled to test for potential improvements. And with computer systems becoming increasingly large and complex, and scaling their performance growing more and more difficult, these simulations are crucial for progress.
This project will be a concerted effort to increase the impact and improve the underlying infrastructure of one of the most popular and widely used cycle-level computer architecture simulation systems, gem5. While gem5 is foundational to computer architecture research, having been cited more than 3,000 times in the last decade, it needs dedicated improvements. Volunteer students and researchers currently maintain the 15-year-old software, spending significant effort on ad hoc maintenance instead of research.
This project both improves the core capabilities of gem5 and reduces barriers to entry for researchers new to the infrastructure. A full-time programmer will support improvements to code testing coverage and the robustness of hardware device models, as well as new models for emerging devices required for evaluating important applications like machine learning, augmented and virtual reality, high performance computing, and system security. To make gem5 easier to use and more accessible for a broader range of users, the project will run gem5 summer schools, expand gem5 documentation, and simplify the infrastructure’s interface.
This project will create a sustainable path for the future of the gem5 infrastructure, ensuring that the computer systems community can continue producing groundbreaking research.
The gem5 Simulator: Version 20.0+. Jason Lowe-Power, Abdul Mutaal Ahmad, Ayaz Akram, Mohammad Alian, Rico Amslinger, Matteo Andreozzi, Adrià Armejach, Nils Asmussen, Brad Beckmann, Srikant Bharadwaj, Gabe Black, Gedare Bloom, Bobby R. Bruce, Daniel Rodrigues Carvalho, Jeronimo Castrillon, Lizhong Chen, Nicolas Derumigny, Stephan Diestelhorst, Wendy Elsasser, Carlos Escuin, Marjan Fariborz, Amin Farmahini-Farahani, Pouya Fotouhi, Ryan Gambord, Jayneel Gandhi, Dibakar Gope, Thomas Grass, Anthony Gutierrez, Bagus Hanindhito, Andreas Hansson, Swapnil Haria, Austin Harris, Timothy Hayes, Adrian Herrera, Matthew Horsnell, Syed Ali Raza Jafri, Radhika Jagtap, Hanhwi Jang, Reiley Jeyapaul, Timothy M. Jones, Matthias Jung, Subash Kannoth, Hamidreza Khaleghzadeh, Yuetsu Kodama, Tushar Krishna, Tommaso Marinelli, Christian Menard, Andrea Mondelli, Miquel Moreto, Tiago Mück, Omar Naji, Krishnendra Nathella, Hoa Nguyen, Nikos Nikoleris, Lena E. Olson, Marc Orr, Binh Pham, Pablo Prieto, Trivikram Reddy, Alec Roelke, Mahyar Samani, Andreas Sandberg, Javier Setoain, Boris Shingarov, Matthew D. Sinclair, Tuan Ta, Rahul Thakur, Giacomo Travaglini, Michael Upton, Nilay Vaish, Ilias Vougioukas, William Wang, Zhengrong Wang, Norbert Wehn, Christian Weis, David A. Wood, Hongil Yoon, Éder F. Zulian. ArXiv Preprint ArXiv:2007.03152, 2021. [2007.03152] The gem5 Simulator: Version 20.0+ (arxiv.org)
The gem5 Simulator. Nathan Binkert, Bradford Beckmann, Gabriel Black, Steven K. Reinhardt, Ali Saidi, Arkaprava Basu, Joel Hestness, Derek R. Hower, Tushar Krishna, Somayeh Sardashti, Rathijit Sen, Korey Sewell, Muhammad Shoaib, Nilay Vaish, Mark D. Hill, and David A. Wood. May 2011, ACM SIGARCH Computer Architecture News. The gem5 simulator | ACM SIGARCH Computer Architecture News
For a list of papers citing gem5, please visit https://scholar.google.com/scholar?cluster=5769943816602695435.
Systems Research
National Science Foundation