Thursday, November 3, 2022

4th Workshop on Accelerator Computer Aided Design

(ACCAD 2022)

Co-located with ICCAD 2022

San Diego, CA

October 30 - November 3, 2022

Organizers:

Abe Elfadel, Khalifa University, Abu Dhabi, UAE

Subhasish Mitra, Stanford University, Palo Alto, CA, USA

The ACCAD workshop provides a forum to present and discuss the current trends in computer-aided design in support of domain-specific accelerator chips, especially for artificial intelligence and machine learning applications. The workshop will be concerned with the VLSI methodology flow from high-level synthesis to physical verification and performance prediction, particularly in the way it gets impacted with the emerging design paradigms of domain-specific instruction sets, approximate computing, in-memory computing, and stochastic computing. Of particular interest to the workshop are the transformations that VLSI CAD has to undergo to adapt to the post-CMOS technologies when they are considered in the context of accelerator design. The workshop will include, but will not be limited to, the following topics:

  • High-level synthesis of machine-learning accelerators.

  • Design space exploration of domain-specific accelerators.

  • Tools and methodologies for in-memory computing.

  • Tools and methodologies for approximate computing.

  • CAD for emerging accelerator technologies: ReRAM, MRAM, Photonics, etc.

  • Tools and methodologies for the post-CNN era.

  • Tools and methodologies for the testing and verification of accelerator chips.

Each year, the workshop will be devoted to four focus areas of accelerator CAD. Renowned speakers are invited to speak on each of the four areas. This edition of the workshop will feature both invited speakers and submitted presentations. Potential presenters should submit a two-page abstract describing the contents of their presentations. Abstracts will be reviewed and selected ones will be scheduled for oral presentations. Other selected abstracts may be featured in a poster session.

The four focus areas selected for this year are the following:

  1. ML Compilers and their Quality of Results

  2. AI Accelerator Virtualization for Cloud Computing

  3. Acceleration on the Edge: ASIC or MCU?

  4. AI Accelerators as a Cloud Service.

Invited speakers include:

  1. Dr. Albert Cohen, Google (confirmed)

  2. Prof. Anand Raghunathan , Purdue

  3. Prof. David Atienza, EPFL (confirmed)

  4. Prof. Hussam Amrouch, Stuttgart (confirmed)

  5. Dr. Rasit O. Topaloglu, IBM (confirmed)

  6. Prof. Cong "Callie" Hao, Georgia Tech (confirmed)

  7. Prof. Yun Eric Liang, Peking (confirmed)

  8. Dr. Lilas Alrahis, NYU Abu Dhabi (confirmed)

  9. Dr. Weier Wan, Stanford (confirmed)

  10. Prof. Tomas Teijeiro, Basque Country (confirmed)

  11. Ms. Unal Pale, EPFL (confirmed)

  12. Dr. Jinwook Jung, IBM Research (confirmed)

Past Workshops:

  1. ACCAD 2020

  2. ACCAD 2021

The workshop will be a hybrid event co-located with ICCAD 2022, Oct 30 - Nov 3, 2022

Contact: Abe Elfadel, Khalifa University, Abu Dhabi, UAE, Email: ibrahim.elfadel AT ku.ac.ae

Hybrid Workshop

The worksop is co-located with ICCAD 2022, Oct 30 - Nov 3, 2022.

Registration is through the ICCAD 2022 Registration web page at

https://iccad.com/registration/

The workshop will use the same conference platform as ICCAD 2022:


IFIP Working Group 10.5