Real-Time Scheduling upon a Host-Centric Acceleration Architecture with Data Offloading

Sun, Jun; Li, Jing; Guo, Zhishan; Zou, An; Zhang, Xuan; Agrawal, Kunal; Baruah, Sanjoy

doi:10.1109/rtas48715.2020.00-17

Cited by 8 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So far, most researchers have focused on improving the accuracy of perception and prediction methods and models. In contrast, there have been fewer studies on identifying the relationship and trade-off between runtime-accuracy and the end-to-end delay of autonomous driving operation [ 10 , 11 ]. Since autonomous driving operation consists of several different stages of process, as illustrated in Figure 1 , it is very important to complete the flow of these processes within some time constraints.…”

Section: Introductionmentioning

confidence: 99%

Environmental-Driven Approach towards Level 5 Self-Driving

Hurair,

Ju,

Han

2024

Sensors

View full text Add to dashboard Cite

As technology advances in almost all areas of life, many companies and researchers are working to develop fully autonomous vehicles. Such level 5 autonomous driving, unlike levels 0 to 4, is a driverless vehicle stage and so the leap from level 4 to level 5 autonomous driving requires much more research and experimentation. For autonomous vehicles to safely drive in complex environments, autonomous cars should ensure end-to-end delay deadlines of sensor systems and car-controlling algorithms including machine learning modules, which are known to be very computationally intensive. To address this issue, we propose a new framework, i.e., an environment-driven approach for autonomous cars. Specifically, we identify environmental factors that we cannot control at all, and controllable internal factors such as sensing frequency, image resolution, prediction rate, car speed, and so on. Then, we design an admission control module that allows us to control internal factors such as image resolution and detection period to determine whether given parameters are acceptable or not for supporting end-to-end deadlines in the current environmental scenario while maintaining the accuracy of autonomous driving. The proposed framework has been verified with an RC car and a simulator.

show abstract

Section: Introductionmentioning

confidence: 99%

Environmental-Driven Approach towards Level 5 Self-Driving

Hurair,

Ju,

Han

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…The demand to achieve high accuracy for increasingly computational tasks leads to ever-growing model sizes of modern DNNs [8], [9]. Processing such huge DNNs [5], [6], [7], [8], [9] in systems with conventional Von Neumann architectures [10], [11], [12] incurs enormous energy consumption and significant execution latency due to the vast data movement between the separate memory and computing elements. To tackle this challenge, processingin-memory (PIM) is introduced as a promising paradigm by co-locating compute and memory.…”

Section: Introductionmentioning

confidence: 99%

Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals

Cao,

Zhao,

Boloor

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Processing-in-memory (PIM) architectures have demonstrated great potential in accelerating numerous deep learning tasks. Particularly, resistive random-access memory (RRAM) devices provide a promising hardware substrate to build PIM accelerators due to their abilities to realize efficient in-situ vector-matrix multiplications (VMMs). However, existing PIM accelerators suffer from frequent and energy-intensive analog-to-digital (A/D) conversions, severely limiting their performance. This paper presents a new PIM architecture to efficiently accelerate deep learning tasks by minimizing the required A/D conversions with analog accumulation and neural approximated peripheral circuits. We first characterize the different dataflows employed by existing PIM accelerators, based on which a new dataflow is proposed to remarkably reduce the required A/D conversions for VMMs by extending shift and add (S+A) operations into the analog domain before the final quantizations. We then leverage a neural approximation method to design both analog accumulation circuits (S+A) and quantization circuits (ADCs) with RRAM crossbar arrays in a highly-efficient manner. Finally, we apply them to build a RRAMbased PIM accelerator (i.e., Neural-PIM) upon the proposed analog dataflow and evaluate its system-level performance. Evaluations on different benchmarks demonstrate that Neural-PIM can improve energy efficiency by 5.36× (1.73×) and speed up throughput by 3.43× (1.59×) without losing accuracy, compared to the state-of-the-art RRAM-based PIM accelerators, i.e., ISAAC [1] (CASCADE [2]).

show abstract

Energy Efficient Real-Time Scheduling on Heterogeneous Architectures with Self-Suspension

Xu,

Zhang,

et al. 2023

2023 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)

View full text Add to dashboard Cite

Real-Time Scheduling upon a Host-Centric Acceleration Architecture with Data Offloading

Cited by 8 publications

References 36 publications

Environmental-Driven Approach towards Level 5 Self-Driving

Environmental-Driven Approach towards Level 5 Self-Driving

Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals

Energy Efficient Real-Time Scheduling on Heterogeneous Architectures with Self-Suspension

Contact Info

Product

Resources

About