Abstract
Parameterizable ML accelerators are the product of recent breakthroughs in machine learning (ML). To fully enable the design space exploration, we propose a physical-design-driven, learning-based prediction framework for hardware-accelerated deep neural network (DNN) and non-DNN ML algorithms. It employs a unified methodology, coupling backend power, performance and area (PPA) analysis with frontend performance simulation, thus achieving realistic estimation of both backend PPA and system metrics (runtime and energy). Experimental studies show that the approach provides excellent predictions for both ASIC (in a 12nm commercial process) and FPGA implementations on the VTA and VeriGOOD-ML platforms.
Original language | English (US) |
---|---|
Title of host publication | MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD |
Publisher | Association for Computing Machinery, Inc |
Pages | 119-126 |
Number of pages | 8 |
ISBN (Electronic) | 9781450394864 |
DOIs | |
State | Published - Sep 12 2022 |
Event | 4th ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2022 - Snowbird, United States Duration: Sep 12 2022 → Sep 13 2022 |
Publication series
Name | MLCAD 2022 - Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD |
---|
Conference
Conference | 4th ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2022 |
---|---|
Country/Territory | United States |
City | Snowbird |
Period | 9/12/22 → 9/13/22 |
Bibliographical note
Funding Information:This material is based on research sponsored in part by Air Force Research Laboratory (AFRL) and Defense Advanced Research Projects Agency (DARPA) under agreement number FA8650-20-2-7009. Andrew B. Kahng is also supported in part by NSF CCF-2112665. The U. S. government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of AFRL, DARPA, or the U. S. government.
Publisher Copyright:
© 2022 Owner/Author.
Keywords
- design space exploration
- ML accelerator
- PPA prediction