Runbin Shi

Mr. Runbin Shi

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 March 2021 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
TJTong Jian
Tong Jian
YGYifan Gong
Yifan Gong
ZZZheng Zhan
Zheng Zhan
RSRunbin Shi
Runbin Shi
NSNasim Soltani
Nasim Soltani
SIStratis Ioannidis
Stratis Ioannidis
Deep learning methods have been very successful at radio frequency fingerprinting tasks, predicting the identity of transmitting devices with high accuracy. We study radio frequency fingerprinting deployments at resource-constrained edge devices. We use structured pruning to jointly train and sparsify neural networks tailored to edge hardware implementations. We compress convolutional layers by a $27.2\times$ factor while incurring a negligible prediction accuracy decrease (less than 1 percent). We demonstrate the efficacy of our approach over multiple edge hardware platforms, including a Samsung Gallaxy S10 phone and a Xilinx-ZCU104 FPGA. Our method yields significant inference speedups, $11.5\times$ on the FPGA and $3\times$ on the smartphone, as well as high efficiency: the FPGA processing time is $17\times$ smaller than in a V100 GPU. To the best of our knowledge, we are the first to explore the possibility of compressing networks for radio frequency fingerprinting; as such, our experiments can be seen as a means of characterizing the informational capacity associated with this specific learning task.

3 August 2020 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
TGTong Geng
Tong Geng
ALAng Li
Ang Li
TWTianqi Wang
Tianqi Wang
CWChunshu Wu
Chunshu Wu
YLYanfei Li
Yanfei Li
MHMartin Herbordt
Martin Herbordt
Binarized Neural Networks (BNN), which significantly reduce computational complexity and memory demand, have shown potential in cost- and power-restricted domains, such as IoT and smart edge-devices, where reaching certain accuracy bars is sufficient and real-time is highly desired. In this article, we demonstrate that the highly-condensed BNN model can be shrunk significantly by dynamically pruning irregular redundant edges. Based on two new observations on BNN-specific properties, an out-of-order (OoO) architecture, O3BNN-R, which can curtail edge evaluation in cases where the binary output of a neuron can be determined early at runtime during inference, is proposed. Similar to instruction level parallelism (ILP), fine-grained, irregular, and runtime pruning opportunities are traditionally presumed to be difficult to exploit. To further enhance the pruning opportunities, we conduct an algorithm/architecture co-design approach where we augment the loss function during the training stage with specialized regularization terms favoring edge pruning. We evaluate our design on an embedded FPGA using networks that include VGG-16, AlexNet for ImageNet, and a VGG-like network for Cifar-10. Results show that O3BNN-R without regularization can prune, on average, 30 percent of the operations, without any accuracy loss, bringing 2.2× inference-speedup, and on average 34× energy-efficiency improvement over state-of-the-art BNN implementations on FPGA/GPU/CPU. With regularization at training, the performance is further improved, on average, by 15 percent.

11 November 2023
Verified
Conference Paper
Open access
WJWenqi Jiang
Wenqi Jiang
SLSHIGANG LI
SHIGANG LI
YZYu Zhu
Yu Zhu
JLJohannes De Fine Licht
Johannes De Fine Licht
ZHZhenhao He
Zhenhao He
GAGustavo Alonso
Gustavo Alonso
Vector search has emerged as the foundation for large-scale information retrieval and machine learning systems, with search engines like Google and Bing processing tens of thousands of queries per second on petabyte-scale document datasets by evaluating vector similarities between encoded query texts and web documents. As performance demands for vector search systems surge, accelerated hardware offers a promising solution in the post-Moore's Law era. We introduce FANNS, an end-to-end and scalable vector search framework on FPGAs. Given a user-provided recall requirement on a dataset and a hardware resource budget, FANNS automatically co-designs hardware and algorithm, subsequently generating the corresponding accelerator. The framework also supports scale-out by incorporating a hardware TCP/IP stack in the accelerator. FANNS attains up to 23.0× and 37.2× speedup compared to FPGA and CPU baselines, respectively, and demonstrates superior scalability to GPUs, achieving 5.5× and 7.6× speedup in median and 95th percentile (P95) latency within an eight-accelerator configuration. The remarkable performance of FANNS lays a robust groundwork for future FPGA integration in data centers and AI supercomputers.

2 June 2019
Verified
Conference Paper
Open access
RSRunbin Shi
Runbin Shi
JLJunjie Liu
Junjie Liu
Hayden K.-H. SoHayden K.-H. So
Hayden K.-H. So
SWShuo Wang
Shuo Wang
YLYun Liang
Yun Liang

6 March 2019 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
RSRunbin Shi
Runbin Shi
JWJustin S.J. Wong
Justin S.J. Wong
Hayden K.-H. SoHayden K.-H. So
Hayden K.-H. So
Parallel hardware designed for image processing promotes vision-guided intelligent applications. With the advantages of high-throughput and low-latency, streaming architecture on FPGA is especially attractive to real-time image processing. Notably, many real-world applications, such as region of interest (ROI) detection, demand the ability to process images continuously at different sizes and resolutions in hardware without interruptions. FPGA is especially suitable for implementation of such flexible streaming architecture, but most existing solutions require run-time reconfiguration, and hence cannot achieve seamless image size-switching. In this paper, we propose a dynamically-programmable buffer architecture (D-SWIM) based on the Stream-Windowing Interleaved Memory (SWIM) architecture to realize image processing on FPGA for image streams at arbitrary sizes defined at run time. D-SWIM redefines the way that on-chip memory is organized and controlled, and the hardware adapts to arbitrary image size with sub-100 ns delay that ensures minimum interruptions to the image processing at a high frame rate. Compared to the prior SWIM buffer for high-throughput scenarios, D-SWIM achieved dynamic programmability with only a slight overhead on logic resource usage, but saved up to 56 % of the BRAM resource. The D-SWIM buffer achieves a max operating frequency of 329.5 MHz and reduction in power consumption by 45.7 % comparing with the SWIM scheme. Real-world image processing applications, such as 2D-Convolution and the Harris Corner Detector, have also been used to evaluate D-SWIM’s performance, where a pixel throughput of 4.5 Giga Pixel/s and 4.2 Giga Pixel/s were achieved respectively in each case. Compared to the implementation with prior streaming frameworks, the D-SWIM-based design not only realizes seamless image size-switching, but also improves hardware efficiency up to 30 × .

10 March 2021 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
HLHe Li
He Li
AAAmeer Abdelhadi
Ameer Abdelhadi
RSRunbin Shi
Runbin Shi
JZJiliang Zhang
Jiliang Zhang
QLQiang Liu
Qiang Liu
The lately attack on the Qualcomm’s Snapdragon chip reminds us security risks related to digital arithmetic circuits. Most system designers neglect the employed computer arithmetic algorithms or their implementation details. Arithmetic circuits are therefore usually used as “black box” units that are instantiated by third-party intellectual-property core or electronic design-automation tool vendors. In this brief, we propose the first most-significant digit-first arithmetic-based hardware Trojan attack by addressing the questions of where to insert and with what . First, we demonstrate how functional camouflage is achieved. Certain arithmetic modules can be quietly replaced with functionally equivalent ones, which we term functionally camouflaged Trojans. Next, we introduce a topologically camouflaged Trojan by employing graph-centrality analysis on rare behaviours in the circuit. The proposed approach is applicable to any digital computing scenarios. Experimental results on a financial computing system demonstrate that completely inaccurate numeric results are yielded, along with an up-to 91.6% numerical error tested.