Hao Zheng

Hao Zheng

Auto-generated profile, based on publicly available information

Hao Zheng

University of Central Florida, Orlando, FL, USA

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
19 June 2020 in IEEE Micro
Verified
Journal Article
Closed access
KWKe Wang
Ke Wang
HZHao Zheng
Hao Zheng
ALAhmed Louri
Ahmed Louri
Network-on-chips (NoCs) are playing a critical role in modern multicore architecture, and NoC security has become a major concern. Maliciously implanted Hardware Trojans (HTs) inject faults into on-chip communications that saturate the network, resulting in the leakage of sensitive data via side channels and significant performance degradation. While existing techniques protect NoCs by detecting and isolating HT-infected components, they inevitably incur occasional inaccurate detection with considerable network latency and power overheads. We propose TSA-NoC, a learning-based design framework for secure and efficient on-chip communication. The proposed TSA-NoC uses an artificial neural network (ANN) for runtime HT-detection with higher accuracy. Furthermore, we propose a deep reinforcement learning (DRL)-based adaptive routing design for HT mitigation with the aim of minimizing network latency and maximizing energy-efficiency. Simulation results show that TSA-NoC achieves up to 97% HT-detection accuracy, 70% improved energy-efficiency, and 29% reduced network latency as compared to state-of-the-art HT-mitigation techniques.

6 May 2022 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
YLYuan Li
Yuan Li
KWKe Wang
Ke Wang
HZHao Zheng
Hao Zheng
ALAhmed Louri
Ahmed Louri
AKAvinash Karanth
Avinash Karanth
The complexity and size of recent deep neural network (DNN) models have increased significantly in pursuit of high inference accuracy. Chiplet-based accelerator is considered a viable scaling approach to provide substantial computation capability and on-chip memory for efficient process of such DNN models. However, communication using metallic interconnects in prior chiplet-based accelerators poses a major challenge to system performance, energy efficiency, and scalability. Photonic interconnects can adequately support communication across chiplets due to features such as distance-independent latency, high bandwidth density, and high energy efficiency. Furthermore, the salient ease of broadcast property makes photonic interconnects suitable for DNN inference which often incurs prevalent broadcast communication. In this paper, we propose a scalable chiplet-based DNN accelerator with photonic interconnects named ASCEND. ASCEND introduces (1) a novel photonic network that supports seamless intra- and inter- chiplet broadcast communication, and flexible mapping of diverse convolution layers, and (2) a tailored dataflow that exploits the ease of broadcast property and maximizes parallelism by simultaneously processing computations with shared input data. Simulation results using multiple DNN models show that ASCEND achieves 71% and 67% reduction in execution time and energy consumption, respectively, as compared to other state-of-the-art chiplet-based DNN accelerators with metallic or photonic interconnects.

18 June 2020 in IEEE Transactions on Emerging Topics in Computing
Verified
Journal Article
Closed access
HZHao Zheng
Hao Zheng
ALAhmed Louri
Ahmed Louri
In this paper, we uniquely combine power-gating and DVFS with the aim of maximizing the NoC power savings and improving performance. The proposed NoC design, called Agile, consists of several architectural designs and a reinforcement learning (RL) based control policy to mitigate the negative effects induced by the combined power-gating and DVFS. Specifically, a simple bypass switch is deployed to maintain network connectivity, avoiding frequently waking up the powered-off router. An optimized pipeline can simplify pipeline stages of the bypass switch to reduce network latency. Reversible link channel buffers can be dynamically allocated to where they are needed to improve throughput. In addition, the RL control policy predicts NoC traffic and decides optimal power-gating decisions, voltage/frequency levels and NoC architecture configurations at runtime. Furthermore, we explore the use of an artificial neural network (ANN) to efficiently reduce the area overhead of implementing RL. We evaluate our design using the PARSEC benchmarks suite. The full system simulation results show that the proposed design improves the overall power savings by up to 58% while improving the performance up to 11% as compared to state-of-the-art designs.

15 December 2017 in IEEE Computer Architecture Letters
Verified
Journal Article
Closed access
HZHao Zheng
Hao Zheng
ALAhmed Louri
Ahmed Louri
With the technology scaling into nanometer regime, static power is becoming the dominant factor in the overall power consumption of Network-on-Chips (NoCs). Static power can be reduced by powering off routers during consecutive idle time through power-gating techniques. However, power-gating techniques suffer from a large wake-up latency to wake up the powered-off routers. Recent research aims to hide the wake-up latency through early wake-up techniques. However, these techniques do not exploit the full advantage of power-gating due to the early wake-up. Consequently, they do not achieve significant power savings. In this paper, we propose an architecture called Easy Pass (EZ-Pass) router that remedies the large latency overheads while providing significant static power savings. The proposed architecture utilizes idle resources in the network interface to transmit packets without waking the router up. Additionally, the technique hides the wake-up latency by continuing to provide packet transmission during the wake-up phase. We use full system simulation to evaluate our EZ-Pass router on a 64-core NoC with a mesh topology using PARSEC benchmark suites. Our results show that the proposed router reduces static power by up to 31% and overall network latency by up to 32% as compared to early-wakeup optimized power-gating techniques.

17 June 2023
Verified
Conference Paper
Open access
JLJiajun Li
Jiajun Li
YZYuxuan Zhang
Yuxuan Zhang
HZHao Zheng
Hao Zheng
KWKe Wang
Ke Wang
Partial Differential Equations (PDEs) are widely employed to describe natural phenomena in many science and engineering fields. Many PDEs do not have analytical solutions, hence, numerical methods have become prevalent for approximating PDE solutions. The most widely used numerical method is the Finite Difference Method (FDM), which requires fine grids and high-precision numerical iterations that are both compute- and memory-intensive. PDE-solving accelerators have been proposed in the literature, however, they usually focus on specific types of PDEs with rigid grid sizes which limits their broader applicability. Besides, they rarely provided insight into the optimizations of parallel computing and data accesses for solving PDEs, which hinders further improvements in performance and energy efficiency. This paper presents FDMAX, an elastic accelerator to efficiently support FDM for different types of PDEs with any grid size. FDMAX employs a customized Processing Element (PE) array architecture that maximizes data reuse with minimized interconnection overhead. The PE array can be reconfigured to break into a set of subarrays to adapt to different grid sizes for optimal efficiency. Moreover, the PE array exploits computation and data reuse for increased performance and energy efficiency, and is reconfigurable to support a wide range of PDEs such as elliptic, parabolic, and hyperbolic equations. Evaluated on four well-known PDEs, our simulation results show that FDMAX achieves on average 1189× speedup with 1123× energy reduction over Intel Xeon CPU, and 4.9× speedup with 6.3× energy reduction over NVIDIA RTX3090 GPU, and 2.9× speedup over Alrescha, the state-of-the-art PDE-solving accelerator.

10 December 2021 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
JLJiajun Li
Jiajun Li
HZHao Zheng
Hao Zheng
KWKe Wang
Ke Wang
ALAhmed Louri
Ahmed Louri
Convolutional Neural Networks (GCNs) have emerged as promising tools for graph-based machine learning applications. Given that GCNs are both compute- and memory-intensive, this constitutes a major challenge for the underlying hardware to efficiently process large-scale GCNs. In this article, we introduce SGCNAX, a scalable GCN accelerator architecture for the high-performance and energy-efficient acceleration of GCNs. Unlike prior GCN accelerators that either employ limited loop optimization techniques, or determine the design variables based on random sampling, we systematically explore the loop optimization techniques for GCN acceleration and propose a flexible GCN dataflow that adapts to different GCN configurations to achieve optimal efficiency. We further propose two hardware-based techniques to address the workload imbalance problem caused by the unbalanced distribution of zeros in GCNs. Specifically, SGCNAX exploits an outer-product-based computation architecture that mitigates the intra-PE (Processing Elements) workload imbalance, and employs a group-and-shuffle approach to mitigate the inter-PE workload imbalance. Simulation results show that SGCNAX performs 9.2×, 1.6× and 1.2× better, and reduces DRAM accesses by a factor of 9.7×, 2.9× and 1.2× compared to HyGCN, AWB-GCN, and GCNAX, respectively.