Tianyang Yu

Tianyang Yu

Auto-generated profile, based on publicly available information

Tianyang Yu

College of Integrated Circuits and the Key Laboratory of Aerospace Integrated Circuits and Microsystem, Ministry of Industry and Information Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China

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
9 January 2024 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
BWBi Wu
Bi Wu
TYTianyang Yu
Tianyang Yu
KCKe Chen
Ke Chen
WLWeiqiang Liu
Weiqiang Liu
With the rapid development of the Internet of Things (IoT), it has become a common concern of academia and industry to provide real-time high performance services for edge-side applications and to bestow intelligence on massive edge-side devices. Due to the limitations of storage space, volume and power consumption of edge side devices, it is difficult for existing convolutional neural networks with large number of parameters and large amount of computation to match them. Network pruning can effectively alleviate the excessive parameters and computation issues in CNNs. However, fine-grained pruning is not hardware friendly, while other structured pruning schemes will result in a much higher loss of accuracy under the same compression ratio. In this paper, an model compression strategy is given including the proposed efficient fine-grained pruning scheme, a dynamic pruning & training method, and a weight importance judgment method. Depending on this strategy, sparse VGG16 (ResNet50) model can be obtained by training from scratch, and achieves a total of 16 $\times$ compression ratio with 1/32 indexing overhead. Further, a light-weight, high-performance sparse CNN accelerator with modified systolic array is proposed. Implementing VGG16 and ResNet50 on the proposed accelerator, the experimental results show that compared with the most advanced design, the proposed accelerator can achieve 8.13 Frames Per Second (FPS) with 2.17 $\times$ better power efficiency and at most 4.14 $\times$ better calculation density.

29 November 2023 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
TYTianyang Yu
Tianyang Yu
BWBi Wu
Bi Wu
KCKe Chen
Ke Chen
GZGong Zhang
Gong Zhang
WLWeiqiang Liu
Weiqiang Liu
Brain-inspired hyperdimensional computing (HDC) is a new computational paradigm that encodes input sample into a hypervector (generally with dimensions of $2K-10K$ ), and performs simple arithmetic and logic operations in the hyperdimensional space to complete perceptual tasks like human brain. Due to its simplicity, interpretability, and robustness, HDC has gradually become a competitor and substitute for deep neural network (DNN) in many tasks. However, there exists an accuracy gap between existing heuristic HDC algorithms and DNN in computer vision tasks, as existing encoding methods have difficulty in filtering out large amount of background and noise in the images, and effectively extracting the spatial structure features of images. In addition, the existing hardware for HDC deployment mainly focuses on in-memory computing (IMC), application specific integrated circuit (ASIC), or high-capacity field programmable gate array (high-capacity FPGA), which cannot meet the flexibility, small area, and low power requirements of edge-side applications. In this paper, a fully learnable HDC framework with learnable preprocessing, encoding and querying, is proposed to boost the accuracy in computer vision tasks, as well as an ultra-tiny accelerator based on edge-side FPGA which matches the proposed framework. Experiments show that on multiple commonly-used image datasets, the proposed HDC framework has an average computation reduction of 80% compared to other most advanced strategies, while achieves a 1.2% accuracy increase. Evaluation on edge-side FPGA shows that compared to other FPGA based state-of-the-art designs, the proposed accelerator saves more than $10\boldsymbol{\times}$ hardware resource and power consumption.

17 April 2024 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
TYTianyang Yu
Tianyang Yu
BWBi Wu
Bi Wu
KCKe Chen
Ke Chen
CYChenggang Yan
Chenggang Yan
WLWeiqiang Liu
Weiqiang Liu
Leveraging approximate multipliers in approximate neural networks (ApproxNNs) can effectively reduce hardware area and power consumption, making them suitable for edge-side applications. However, the propagation of layer-by-layer errors limits the application of approximate multipliers to large-scale ApproxNNs and complex tasks. Currently, retraining techniques that consider approximate multiplication errors are commonly used to compensate for the accuracy loss. However, due to the irregularity of the errors introduced by approximate multiplier, it is difficult for the existing generic acceleration hardware (e.g., GPU) to efficiently simulate its function and accelerate retraining, which thereby leads to a huge retraining overhead in ApproxNNs’ application. In this article, we propose an ApproxNN framework that introduces errors with regular and controlled positions for high-efficiency retraining of large-scale ApproxNNs. An approximate multiplier design that matches this framework is also presented to verify the effectiveness of the proposed ApproxNN framework. Experiment results demonstrate that the proposed ApproxNN framework is able to achieve up to $46\times $ speedup in retraining, and the proposed approximate multiplier reduces area/power-delay product (PDP) by 31%/63% compared to the exact multiplier. Compared with the floating-point neural network (NN) model, an accuracy decrease of only 1.13% is achieved when applied to ResNet50 on ImageNet dataset with only 15-epochs retraining, which surpasses other state-of-the-art designs.

12 August 2024 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
TYTianyang Yu
Tianyang Yu
BWBi Wu
Bi Wu
KCKe Chen
Ke Chen
GZGong Zhang
Gong Zhang
WLWeiqiang Liu
Weiqiang Liu
As a new computing paradigm, hyperdimensional computing (HDC) has gradually manifested its advantages in edge-side intelligent applications by virtue of its interpretability, hardware-friendliness and robustness. The core of HDC is to encode input samples into a hypervector, and then use it to query the class hypervector space. Compared with the conventional architecture that uses CMOS-based circuits to complete the computation in the query operation, the hyperdimensional associative memory (HAM) enables the query operation to be completed in memory, which significantly reduces the query delay and energy consumption. However, the existing HDC algorithms require the HAM to achieve high precision query in inference, which leads to the complex structure of the HAM, and thus makes the area and energy consumption of the HAM unable to be further reduced. In this paper, a novel efficient HAM architecture based on approximate query method is proposed, to simplify the existing architecture. Meanwhile, a training method of HDC which matches the proposed HAM architecture is proposed to compensate for the decrease in accuracy caused by approximate query. Experimental results show that the proposed HAM framework can save more than 60% of area and energy consumption, and achieve accuracy comparable to existing state-of-the-art methods by using the proposed training method.

14 May 2024 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
HZHaonan Zhu
Haonan Zhu
BWBi Wu
Bi Wu
TYTianyang Yu
Tianyang Yu
KCKe Chen
Ke Chen
CYChenggang Yan
Chenggang Yan
WLWeiqiang Liu
Weiqiang Liu
Due to the physical separation of data processing and storage, the conventional Von Neumann architecture exists excessive data migration overhead to curtail the progress of data-intensive applications. In this way, the Computing-in-Memory (CiM) architecture is proposed. Due to the boolean property of the memory cell, the current CiM mainly focuses on single-bit logic design. For the multi-bit arithmetic design, a prevalent patchwork approach is employed using single-bit logic, leaving the design with insufficient parallelism. This paper proposes a high-performance in-memory multi-bit addition (M-Add) and multiplication (M-Mul) scheme based on unipolar switching SOT-MRAM. For the M-Add scheme, transmission logic-based circuit design is proposed to realize single-step inter-column XOR operations, which is logically fits perfectly the g operator of parallel prefix algorithm. Further, the oBK algorithm is presented to maximize the g operator occupancy. For the M-Mul scheme, mapping the Booth decoder to the control signal of the proposed modified flip-flop queue, only two steps are required to realize the decoding of three encoded signals in parallel. The simulation results indicate the proposed design reduces the latency of N-bit Add (N-bit Mul) by an average of 82.6% (31.5%) compared to state-of-the-art CiM designs. Further, a CNN application based on proposed operations achieves 1.23 TOPS/w on the CIFAR-10 dataset, with an average of 47.57% increase over other CiM designs.

1 July 2024 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
TYTianyang Yu
Tianyang Yu
BWBi Wu
Bi Wu
KCKe Chen
Ke Chen
GZGong Zhang
Gong Zhang
WLWeiqiang Liu
Weiqiang Liu
With low complexity and robustness, hyperdimensional computing (HDC) has become a promising paradigm for edge-side applications. HDC employs hypervectors (generally with 2–10 K dimensions) to represent input samples, and performs logical operations in hyperdimensional space to complete perceptual tasks. Compared to deep neural network (DNN), HDC is more suitable for lightweight edge-side applications (i.e., speech, activity recognition), due to its low complexity and less computational scheduling. However, existing HDC’s querying process relies on trained class hypervectors, resulting in on-chip storage and transmission overhead which limits the application of ASIC-based or FPGA-based HDC accelerators in embedded systems. In this article, a logic-aggregation-based query method called LAHDC is proposed to eliminate such overhead. In addition, an ultratiny HDC accelerator design matching LAHDC is also proposed, as well as an automated tool to search for optimal structure and generate hardware design code. Experimental results show that, compared to existing ASIC-based HDC accelerators, the proposed design reduce the area/energy by more than 95%/80%.