skip to main content


Title: Virtuoso : Energy- and Latency-Aware Streamlining of Streaming Videos on SOCs
Efficient and adaptive computer vision systems have been proposed to make computer vision tasks, such as image classification and object detection, optimized for embedded or mobile devices. These solutions, quite recent in their origin, focus on optimizing the model (a deep neural network, DNN) or the system by designing an adaptive system with approximation knobs. Despite several recent efforts, we show that existing solutions suffer from two major drawbacks. First , while mobile devices or systems-on-chips (SOCs) usually come with limited resources including battery power, most systems do not consider the energy consumption of the models during inference. Second , they do not consider the interplay between the three metrics of interest in their configurations, namely, latency, accuracy, and energy. In this work, we propose an efficient and adaptive video object detection system — Virtuoso , which is jointly optimized for accuracy, energy efficiency, and latency. Underlying Virtuoso is a multi-branch execution kernel that is capable of running at different operating points in the accuracy-energy-latency axes, and a lightweight runtime scheduler to select the best fit execution branch to satisfy the user requirement. We position this work as a first step in understanding the suitability of various object detection kernels on embedded boards in the accuracy-latency-energy axes, opening the door for further development in solutions customized to embedded systems and for benchmarking such solutions. Virtuoso is able to achieve up to 286 FPS on the NVIDIA Jetson AGX Xavier board, which is up to 45 times faster than the baseline EfficientDet D3 and 15 times faster than the baseline EfficientDet D0. In addition, we also observe up to 97.2% energy reduction using Virtuoso compared to the baseline YOLO (v3) — a widely used object detector designed for mobiles. To fairly compare with Virtuoso , we benchmark 15 state-of-the-art or widely used protocols, including Faster R-CNN (FRCNN) [NeurIPS’15], YOLO v3 [CVPR’16], SSD [ECCV’16], EfficientDet [CVPR’20], SELSA [ICCV’19], MEGA [CVPR’20], REPP [IROS’20], FastAdapt [EMDL’21], and our in-house adaptive variants of FRCNN+, YOLO+, SSD+, and EfficientDet+ (our variants have enhanced efficiency for mobiles). With this comprehensive benchmark, Virtuoso has shown superiority to all the above protocols, leading the accuracy frontier at every efficiency level on NVIDIA Jetson mobile GPUs. Specifically, Virtuoso has achieved an accuracy of 63.9%, which is more than 10% higher than some of the popular object detection models, FRCNN at 51.1%, and YOLO at 49.5%.  more » « less
Award ID(s):
1919197
NSF-PAR ID:
10378937
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Date Published:
Journal Name:
ACM Transactions on Design Automation of Electronic Systems
ISSN:
1084-4309
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Mobile devices such as drones and autonomous vehicles increasingly rely on object detection (OD) through deep neural networks (DNNs) to perform critical tasks such as navigation, target-tracking and surveillance, just to name a few. Due to their high complexity, the execution of these DNNs requires excessive time and energy. Low-complexity object tracking (OT) is thus used along with OD, where the latter is periodically applied to generate "fresh" references for tracking. However, the frames processed with OD incur large delays, which does not comply with real-time applications requirements. Offloading OD to edge servers can mitigate this issue, but existing work focuses on the optimization of the offloading process in systems where the wireless channel has a very large capacity. Herein, we consider systems with constrained and erratic channel capacity, and establish parallel OT (at the mobile device) and OD (at the edge server) processes that are resilient to large OD latency. We propose Katch-Up, a novel tracking mechanism that improves the system resilience to excessive OD delay. We show that this technique greatly improves the quality of the reference available to tracking, and boosts performance up to 33%. However, while Katch-Up significantly improves performance, it also increases the computing load of the mobile device. Hence, we design SmartDet, a low-complexity controller based on deep reinforcement learning (DRL) that learns to achieve the right trade-off between resource utilization and OD performance. SmartDet takes as input highly-heterogeneous context-related information related to the current video content and the current network conditions to optimize frequency and type of OD offloading, as well as Katch-Up utilization. We extensively evaluate SmartDet on a real-world testbed composed by a JetSon Nano as mobile device and a GTX 980 Ti as edge server, connected through a Wi-Fi link, to collect several network-related traces, as well as energy measurements. We consider a state-of-the-art video dataset (ILSVRC 2015 - VID) and state-of-the-art OD models (EfficientDet 0, 2 and 4). Experimental results show that SmartDet achieves an optimal balance between tracking performance – mean Average Recall (mAR) and resource usage. With respect to a baseline with full Katch-Up usage and maximum channel usage, we still increase mAR by 4% while using 50% less of the channel and 30% power resources associated with Katch-Up. With respect to a fixed strategy using minimal resources, we increase mAR by 20% while using Katch-Up on 1/3 of the frames. 
    more » « less
  2. The energy and latency demands of critical workload execution, such as object detection, in embedded systems vary based on the physical system state and other external factors. Many recent mobile and autonomous System-on-Chips (SoC) embed a diverse range of accelerators with unique power and performance characteristics. The execution flow of the critical workloads can be adjusted to span into multiple accelerators so that the trade-off between performance and energy fits to the dynamically changing physical factors. In this study, we propose running neural network (NN) inference on multiple accelerators of an SoC. Our goal is to enable an energy-performance trade-off with an by distributing layers in a NN between a performance- and a power-efficient accelerator. We first provide an empirical modeling methodology to characterize execution and inter-layer transition times. We then find an optimal layers-to-accelerator mapping by representing the trade-off as a linear programming optimization constraint. We evaluate our approach on the NVIDIA Xavier AGX SoC with commonly used NN models. We use the Z3 SMT solver to find schedules for different energy consumption targets, with up to 98% prediction accuracy. 
    more » « less
  3. Model-serving systems expose machine learning (ML) models to applications programmatically via a high-level API. Cloud plat- forms use these systems to mask the complexities of optimally managing resources and servicing inference requests across multi- ple applications. Model serving at the edge is now also becoming increasingly important to support inference workloads with tight latency requirements. However, edge model serving differs substan- tially from cloud model serving in its latency, energy, and accuracy constraints: these systems must support multiple applications with widely different latency and accuracy requirements on embedded edge accelerators with limited computational and energy resources. To address the problem, this paper presents Dělen,1 a flexible and adaptive model-serving system for multi-tenant edge AI. Dělen exposes a high-level API that enables individual edge applications to specify a bound at runtime on the latency, accuracy, or energy of their inference requests. We efficiently implement Dělen using conditional execution in multi-exit deep neural networks (DNNs), which enables granular control over inference requests, and evalu- ate it on a resource-constrained Jetson Nano edge accelerator. We evaluate Dělen flexibility by implementing state-of-the-art adapta- tion policies using Dělen’s API, and evaluate its adaptability under different workload dynamics and goals when running single and multiple applications. 
    more » « less
  4. Recently, point cloud (PC) has gained popularity in modeling various 3D objects (including both synthetic and real-life) and has been extensively utilized in a wide range of applications such as AR/VR, 3D reconstruction, and autonomous driving. For such applications, it is critical to analyze/understand the surrounding scenes properly. To achieve this, deep learning based methods (e.g., convolutional neural networks (CNNs)) have been widely employed for higher accuracy. Unlike the deep learning on conventional 2D images/videos, where the feature computation (matrix multiplication) is the major bottleneck, in point cloud-based CNNs, the sample and neighbor search stages are the primary bottlenecks, and collectively contribute to 54% (up to 80%) of the overall execution latency on a typical edge device. While prior efforts have attempted to solve this issue by designing custom ASICs or pipelining the neighbor search with other stages, to our knowledge, none of them has tried to “structurize” the unstructured PC data for improving computational efficiency. In this paper, we first explore the opportunities of structurizing PC data using Morton code (which is originally designed to map data from a high dimensional space to one dimension, while preserving spatial locality) and observe that there is a huge scope to “skip” the sample and neighbor search computation by operating on the “structurized” PC data. Based on this, we propose two approximation techniques for the sampling and neighbor search stages. We implemented our proposals on an NVIDIA Jetson AGX Xavier edge GPU board. The evaluation results collected on six different workloads show that our design can accelerate the sample and neighbor search stages by 3.68× (up to 5.21×) with minimal impact on inference accuracy. This acceleration in turn results in 1.55× speedup in the end-to-end execution latency and saves 33% of energy expenditure. 
    more » « less
  5. The continuous increase in demanding for availability and ultra-reliability of low-latency and broadband wireless connections is instigating further research in the standardization of next-generation mobile systems. 6G networks, among other benefits, should offer global ubiquitous mobility thanks to the utilization of the Space segment as an intelligent yet autonomous ecosystem. In this framework, multi-layered networks will take charge of providing connectivity by implementing Cloud-Radio Access Network (C-RAN) functionalities on heterogeneous nodes distributed over aerial and orbital segments. Unmanned Aerial Vehicles (UAVs), High-Altitude Plat-forms (HAPs), and small satellites compose the Space ecosystem encompassing the 3D networks. Recently, a lot of interest has been raised about splitting operations to distribute baseband processing functionalities among such nodes to balance the computational load and reduce the power consumption. This work focuses on the hardware development of C-RAN physical (PHY-) layer operations to derive their computational and energy demand. More in detail, the 5G Downlink Shared Channel (DLSCH) and the Physical Downlink Shared Channel (PDSCH) are first simulated in MATLAB environment to evaluate the variation of computational load depending on the selected splitting options and number of antennas available at transmitter (TX) and receiver (RX) side. Then, the PHY-layer processing chain is software-implemented and the various splitting options are tested on low-cost processors, such as Raspberry Pi (RP) 3B+ and 4B. By overclocking the RPs, we compute the execution time and we derive the instruction count (IC) per program for each considered splitting option so to achieve the mega instructions per second (MIPS) for the expected processing time. Finally, by comparing the performance achieved by the employed RPs with that of Nvidia Jetson Nano (JN) processor used as benchmark, we shall discuss about size, weight, power and cost (SWaP-C)... 
    more » « less