This work focuses on the time-predictable execution of Deep Neural Networks (DNNs) accelerated on FPGA System-on-Chips (SoCs). The modern DPU accelerator by Xilinx is considered. An extensive profiling campaign targeting the Zynq Ultrascale+ platform has been performed to study the execution behavior of the DPU when accelerating a set of state-of-the-art DNNs for Advanced Driver Assistance Systems (ADAS). Based on the profiling, an execution model is proposed and then used to derive a response-time analysis. A custom FPGA module named DICTAT is also proposed to improve the predictability of the acceleration of DNNs and tighten the analytical bounds. A rich set of experimental results based on both analytical bounds and measurements from the target platform is finally presented to assess the effectiveness and the performance of the proposed approach on ADAS applications.

Time-Predictable Acceleration of Deep Neural Networks on FPGA-based SoC

**Session chair:** Daniel Casini
- 25 min: [**Time-Predictable Acceleration of Deep Neural Networks on FPGA SoC Platforms**](https://conferences.computer.org/rtsspub/pdfs/RTSS2021-23beZleJJDdiozCiQ9rzXD/280200a441/280200a441.pdf), *Francesco Restuccia and Alessandro Biondi*
- 25 min: [**LaLaRAND: Flexible Layer-by-Layer CPU/GPU Scheduling for Real-Time DNN Task**](https://conferences.computer.org/rtsspub/pdfs/RTSS2021-23beZleJJDdiozCiQ9rzXD/280200a329/280200a329.pdf), *Woosung Kang, Kilho Lee, Jinkyu Lee, Insik Shin and Hoon Sung Chwa*
- 25 min: [**Data-Driven Structured Thermal Modeling for COTS Multi-Core Processors**](https://conferences.computer.org/rtsspub/pdfs/RTSS2021-23beZleJJDdiozCiQ9rzXD/280200a201/280200a201.pdf), *Seyedmehdi Hosseinimotlagh, Daniel Enright, Christian Shelton and Hyoseung Kim*
- 25 min: [**A Multi-Level DPM Approach for Real-Time DAG Tasks in Heterogeneous Processors**](https://conferences.computer.org/rtsspub/pdfs/RTSS2021-23beZleJJDdiozCiQ9rzXD/280200a014/280200a014.pdf), *Federico Reghenzani, Ashikahmed Bhuiyan, William Fornaciari and Zhishan Guo*



3.11 - DNNs, Energy- and Thermal-Aware Design

technical paper

 **RTSS 2021** has successfully concluded. Hope you have enjoyed it, and look forward to seeing you next year in person.
    Announcement for the Awards:
 * Best Paper Award goes to: Monte Carlo Response-Time Analysis, Sergey Bozhko, Georg von der Brüggen, and Björn Brandenburg
 * Best Student Paper Award goes to: Automatic Energy-Hotspot Detection and Elimination in Real-Time Deeply Embedded Systems, Mohsen Shekarisaz, Lothar Thiele, and Mehdi Kargahi.
 * Best Solution Award for Industry Session goes to: Toward Real-Time Guaranteed Scheduling for Autonomous Driving Systems. Jinghao Sun, Tianyi Wang, Kailu Duan, Bin Lu, Jiankang Ren, Zhishan Guo, and Guozhen Tan.



IEEE RTSS 2021

The IEEE Real-Time Systems Symposium (RTSS) is the premier conference in the field of real-time systems, and is a venue for researchers and practitioners to showcase innovations covering all aspects of real-time systems, including theory, design, analysis, implementation, evaluation, and experience. 

Alessandro Biondi

1

Presentations

Time-Predictable Acceleration of Deep Neural Networks on FPGA-based SoC

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES