Workshop Program

All times are in US Eastern time (UTC-4).

10:00 AM - 10:10 AM Opening Remarks
10:10 AM - 11:10 AM [Keynote] Building Performant and Portable Heterogenous Code using GPU Compute Accelerators
Derek Bouius, AMD [Link]
11:10 AM - 11:30 AM Break
Session 1 Session Chair: Daniel Wong
11:30 AM - 11:50 AM [Paper] Near LLC Versus Near Main Memory Processing
Hossein Bitalebi, Vahid Geraeinejad, Masoumeh Ebrahimi (KTH Royal Institute of Technology)
11:50 AM - 12:10 PM [Paper] Accelerating Data Transfer between Host and Device using Idle GPU
Yuya Tatsugi, Akira Nukada (University of Tsukuba)
12:10 PM - 12:30 PM [Invited Talk] Towards True Coherent Shared Memory for Next-generation Multi-GPU Systems
José L. Abellán (Universidad Católica de Murcia)
12:30 PM - 12:50 PM [Invited Talk] Re-design GPU NoC and LLC System
Xia Zhao (Academy of Military Sciences)
12:50 PM - 01:10 PM Break
Session 2 Session Chair: Hoda NaghibiJouybari
01:10 PM - 01:30 PM [Paper] Systematically Extending a High-Level CodeGenerator with Support for Tensor Cores
Lukas Siefke, Bastian Köpcke (University of Münster), Michel Steuwer (University of Edinburgh), Sergei Gorlatch (University of Muenster)
01:30 PM - 01:50 PM [Paper] Compiler-Assisted Scheduling for Multi-Instance GPUs
Chris Porter (Georgia Institute of Technology), Chao Chen (Amazon Web Service), Santosh Pande (Georgia Institute of Technology)
01:50 PM - 02:05 PM [Work-in-Progress Presentation] PTXVM: Translating PTX to C
Sreepathi Pai, Benjamin Carleton, Benjamin Valpey, Amr Elhelw (University of Rochester)
02:05 PM - 02:20 PM [Work-in-Progress Presentation] Understanding Wafer-Scale GPU Performance using an Architectural Simulator
Chris Thames, Yifan Sun (William & Mary)
02:20 PM - 02:35 PM [Work-in-Progress Presentation] ScaleServe: A Scalable Multi-GPU Machine Learning Inference System and Benchmarking Suite
Ali Jahanshahi, Marcus Chow, Daniel Wong (UC Riverside)
02:35 PM - 02:40 PM Closing Remarks

Important Dates

  • Papers due: January 25, 2022 February 8, 2022
  • Notification: March 15, 2022
  • Final paper due: April 2, 2022

Submission Guidelines

Full paper submissions must be in PDF format for US letter-size paper. They must not exceed 6 pages (all inclusive) in standard ACM two-column conference format (review mode, with page numbers and both 9 or 10pt can be used). GPGPU also accepts extended abstracts (2 pages including references). Authors can select if they want to reveal their identity in the submission. Templates for ACM format are available for Microsoft Word and LaTeX at:

At least one author must present at the workshop conference. Travel func may be applied through SIGPLAN Professional Activities Committee (PAC). Details are available here

Submission Site: GPGPU 2022

Workshop Organizers

Yifan Sun Daniel Wong Hoda NaghibiJouybari Hongyuan Liu
Co-chair Co-chair Co-chair Publication/Web Chair
William & Mary UC Riverside Binghamton University William & Mary
Please contact the organizers if you have any questions.

Program Committee

  • Tor M. Aamodt (University of British Columbia)
  • José L. Abellán (Universidad Católica de Murcia)
  • Nael Abu-Ghazaleh (University of California, Riverside)
  • Trinayan Baruah (AMD)
  • Zhongliang Chen (AMD)
  • Shi Dong (Cerebras)
  • Xiang Gong (Qualcomm)
  • Hyeran Jeon (University of California, Merced)
  • Adwait Jog (William & Mary)
  • David Kaeli (Northeastern University)
  • Onur Kariyan (AMD)
  • Gunjae Koo (Korea University)
  • Jiajia Li (William & Mary)
  • Ashutosh Pattnaik (ARM)
  • Seunghee Shin (Binghamton University)
  • Jieming Yin (Lehigh University)
  • Jishen Zhao (University of California, San Diego)
  • Huiyang Zhou (North Carolina State University)

History and Impact

David Kaeli (Northeastern) and John Cavazos (Delaware) started this GPGPU workshop series, which was first held in 2007 at Northeastern University. In 2008, the workshop was held with ASPLOS 2008. This trend continued and this GPGPU workshop was held with ASPLOS for the next 6 years. From 2015 to 2018, the GPGPU workshop was co-located with PPoPP. In 2019 and 2020, the GPGPU workshop is co-hosted by Adwait Jog (William & Mary), Onur Kayiran (AMD), and Ashutosh Pattnaik (ARM). The average citation count (as per Google Scholar), for a GPGPU workshop paper is currently 37.5, where there have been 8 influential papers with 100+ citations.

Previous versions of the GPGPU workshop: