Zhican Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhican Wang has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Guanghui He
Shanghai Jiao Tong University
7 shared publications - Hongxiang Fan
Imperial College London
4 shared publications - Chen Zhang
Shanghai Jiao Tong University, Shanghai, Shanghai, China
3 shared publications - Yuzhou Chen
Shanghai Jiao Tong University, Shanghai, Shanghai, China
3 shared publications - Gang Wang
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
2 shared publications - Pan Zhao
Shanghai Jiao Tong University, Shanghai, Shanghai, China
2 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (10) , 3653-3668
SD-Acc: Accelerating Stable Diffusion through Phase-Aware Sampling and Hardware Co-Optimizations
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (10) , 3653-3668
SD-Acc: Accelerating Stable Diffusion through Phase-Aware Sampling and Hardware Co-Optimizations
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
SpRDA: An Efficient Sparse Accelerator for Robotics Diffusion Model
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessSpRDA: An Efficient Sparse Accelerator for Robotics Diffusion Model
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
PipeGS: Unlocking 3DGS Pipeline Parallelism via Hierarchical Reuse and Dynamic Partitioning
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessPipeGS: Unlocking 3DGS Pipeline Parallelism via Hierarchical Reuse and Dynamic Partitioning
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (6) , 2058-2072
DESA: Dataflow Efficient Systolic Array for Acceleration of Transformers
Transformers have become prevalent in various Artificial Intelligence (AI) applications, spanning natural language processing to computer vision. Owing to their suboptimal performance on general-purpose platforms, various domain-specific accelerators that explore and utilize the model sparsity have been developed. Instead, we conduct a quantitative analysis of Transformers. (Transformers can be categorized into three types: Encoder-Only, Decoder-Only, and Encoder-Decoder. This paper focuses on Encoder-Only Transformers.) to identify key inefficiencies and adopt dataflow optimization to address them. These inefficiencies arise from 1) diverse matrix multiplication, 2) multi-phase non-linear operations and their dependencies, and 3) heavy memory requirements. We introduce a novel dataflow design to support decoupling with latency hiding, effectively reducing the dependencies and addressing the performance bottlenecks of nonlinear operations. To enable fully fused attention computation, we propose practical tiling and mapping strategies to sustain high throughput and notably decrease memory requirements from$O(N^{2}H)$ to$O(N)$ . A hybrid buffer-level reuse strategy is also introduced to enhance utilization and diminish off-chip access. Based on these optimizations, we propose a novel systolic array design, named DESA, with three innovations: 1) A reconfigurable vector processing unit (VPU) and immediate processing units (IPUs) that can be seamlessly fused within the systolic array to support various normalization, post-processing, and transposition operations with efficient latency hiding. 2) A hybrid stationary systolic array that improves the compute and memory efficiency for matrix multiplications with diverse operational intensity and characteristics. 3) A novel tile fusion processing that efficiently addresses the low utilization issue in the conventional systolic array during the data setup and offloading. Across various benchmarks, extensive experiments demonstrate that DESA archives$5.0\boldsymbol{\times\thicksim}8.3\boldsymbol{\times}$ energy saving over 3090 GPU and$25.6\boldsymbol{\times\thicksim}88.4\boldsymbol{\times}$ than Intel 6226R CPU. Compared to the SOTA designs, DESA achieves$11.6\boldsymbol{\times\thicksim}15.0\boldsymbol{\times}$ speedup and up to$2.3\times$ energy saving over the SOTA accelerators.- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (6) , 2058-2072
DESA: Dataflow Efficient Systolic Array for Acceleration of Transformers
Transformers have become prevalent in various Artificial Intelligence (AI) applications, spanning natural language processing to computer vision. Owing to their suboptimal performance on general-purpose platforms, various domain-specific accelerators that explore and utilize the model sparsity have been developed. Instead, we conduct a quantitative analysis of Transformers. (Transformers can be categorized into three types: Encoder-Only, Decoder-Only, and Encoder-Decoder. This paper focuses on Encoder-Only Transformers.) to identify key inefficiencies and adopt dataflow optimization to address them. These inefficiencies arise from 1) diverse matrix multiplication, 2) multi-phase non-linear operations and their dependencies, and 3) heavy memory requirements. We introduce a novel dataflow design to support decoupling with latency hiding, effectively reducing the dependencies and addressing the performance bottlenecks of nonlinear operations. To enable fully fused attention computation, we propose practical tiling and mapping strategies to sustain high throughput and notably decrease memory requirements from$O(N^{2}H)$ to$O(N)$ . A hybrid buffer-level reuse strategy is also introduced to enhance utilization and diminish off-chip access. Based on these optimizations, we propose a novel systolic array design, named DESA, with three innovations: 1) A reconfigurable vector processing unit (VPU) and immediate processing units (IPUs) that can be seamlessly fused within the systolic array to support various normalization, post-processing, and transposition operations with efficient latency hiding. 2) A hybrid stationary systolic array that improves the compute and memory efficiency for matrix multiplications with diverse operational intensity and characteristics. 3) A novel tile fusion processing that efficiently addresses the low utilization issue in the conventional systolic array during the data setup and offloading. Across various benchmarks, extensive experiments demonstrate that DESA archives$5.0\boldsymbol{\times\thicksim}8.3\boldsymbol{\times}$ energy saving over 3090 GPU and$25.6\boldsymbol{\times\thicksim}88.4\boldsymbol{\times}$ than Intel 6226R CPU. Compared to the SOTA designs, DESA achieves$11.6\boldsymbol{\times\thicksim}15.0\boldsymbol{\times}$ speedup and up to$2.3\times$ energy saving over the SOTA accelerators.- Open Access
- 20 January 2025
- Published by Association for Computing Machinery (ACM)
- p. 988-994
Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis
Recent advances in code generation have illuminated the potential of employing large language models (LLMs) for general-purpose programming languages such as Python and C++, opening new opportunities for automating software development and enhancing programmer productivity. The potential of LLMs in software programming has sparked significant interest in exploring automated hardware generation and automation. Although preliminary endeavors have been made to adopt LLMs in generating hardware description languages (HDLs) such as Verilog and SystemVerilog, several challenges persist in this direction. First, the volume of available HDL training data is substantially smaller compared to that for software programming languages. Second, the pre-trained LLMs, mainly tailored for software code, tend to produce HDL designs that are more error-prone. Third, the generation of HDL requires a significantly higher number of tokens compared to software programming, leading to inefficiencies in cost and energy consumption. To tackle these challenges, this paper explores leveraging LLMs to generate High-Level Synthesis (HLS)-based hardware design. Although code generation for domain-specific programming languages is not new in the literature, we aim to provide experimental results, insights, benchmarks, and evaluation infrastructure to investigate the suitability of HLS over low-level HDLs for LLM-assisted hardware design generation. To achieve this, we first finetune pretrained models for HLS-based hardware generation, using a collected dataset with text prompts and corresponding reference HLS designs. An LLM-assisted framework is then proposed to automate end-to-end hardware code generation, which also investigates the impact of chain-of-thought and feedback loops promoting techniques on HLS- design generation. Comprehensive experiments demonstrate the effectiveness of our methods.
- 20 January 2025
- Published by Association for Computing Machinery (ACM)
- p. 988-994
Open AccessExploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis
Recent advances in code generation have illuminated the potential of employing large language models (LLMs) for general-purpose programming languages such as Python and C++, opening new opportunities for automating software development and enhancing programmer productivity. The potential of LLMs in software programming has sparked significant interest in exploring automated hardware generation and automation. Although preliminary endeavors have been made to adopt LLMs in generating hardware description languages (HDLs) such as Verilog and SystemVerilog, several challenges persist in this direction. First, the volume of available HDL training data is substantially smaller compared to that for software programming languages. Second, the pre-trained LLMs, mainly tailored for software code, tend to produce HDL designs that are more error-prone. Third, the generation of HDL requires a significantly higher number of tokens compared to software programming, leading to inefficiencies in cost and energy consumption. To tackle these challenges, this paper explores leveraging LLMs to generate High-Level Synthesis (HLS)-based hardware design. Although code generation for domain-specific programming languages is not new in the literature, we aim to provide experimental results, insights, benchmarks, and evaluation infrastructure to investigate the suitability of HLS over low-level HDLs for LLM-assisted hardware design generation. To achieve this, we first finetune pretrained models for HLS-based hardware generation, using a collected dataset with text prompts and corresponding reference HLS designs. An LLM-assisted framework is then proposed to automate end-to-end hardware code generation, which also investigates the impact of chain-of-thought and feedback loops promoting techniques on HLS- design generation. Comprehensive experiments demonstrate the effectiveness of our methods.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44 (2) , 723-736
COSA Plus: Enhanced Co-Operative Systolic Arrays for Attention Mechanism in Transformers
The attention mechanism is becoming a vital building block across various modern neural networks, e.g., Transformers. However, it encounters low efficiency when deployed on the general-purpose GPU/CPU platform, which motivates the dedicated accelerator design. Existing accelerators are commonly devised by exploring the potential sparsity in attention mechanism using a hardware-software codesign scheme, which suffers from complicated training, fine-tuning processes, and possible accuracy degradation. More importantly, the sparse pattern only focuses on certain datasets with less generality, and the fine-grained sparse pattern could also bring hardware inefficiency. Instead, we try to solve these issues from another perspective: by systematically analysing the inherent dataflow characteristics of the attention mechanism, we propose the co-operative systolic arrays (COSAs) with an optimized dataflow to support the general purpose attention mechanism and pursue higher computational efficiency. COSA system exploits the high parallelism from the inherent model and leverages run-time configurable hybrid dataflows, i.e., weight and output stationary (OS) for a systolic array (SA) to support the varying matrix multiplication in the attention mechanism. Regarding the cascaded matrix multiplications, COSA proposes levels of fusion methodologies to reduce the off-chip access and enhance processing element (PE) utilization, such as directly using the result of OS as the weight of weight stationary SA by deep fusion. Additionally, the COSA system also provides the solution to hide the latency and radically save the buffer size related to the softmax. Experiment results show that, across various benchmarks, COSA can achieve$2.29-2.60\times $ throughput improvement over the traditional SA of the same MAC number, with up to 94.7% PE utilization rate and$8.2\times $ less off-chip memory access. Compared with the general-purpose platforms,$7.6-12.4\times $ energy efficiency over NVIDIA GeForce 3090 GPU and$35.2-80.9\times $ energy efficiency over Intel 6226R server CPU.- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44 (2) , 723-736
COSA Plus: Enhanced Co-Operative Systolic Arrays for Attention Mechanism in Transformers
The attention mechanism is becoming a vital building block across various modern neural networks, e.g., Transformers. However, it encounters low efficiency when deployed on the general-purpose GPU/CPU platform, which motivates the dedicated accelerator design. Existing accelerators are commonly devised by exploring the potential sparsity in attention mechanism using a hardware-software codesign scheme, which suffers from complicated training, fine-tuning processes, and possible accuracy degradation. More importantly, the sparse pattern only focuses on certain datasets with less generality, and the fine-grained sparse pattern could also bring hardware inefficiency. Instead, we try to solve these issues from another perspective: by systematically analysing the inherent dataflow characteristics of the attention mechanism, we propose the co-operative systolic arrays (COSAs) with an optimized dataflow to support the general purpose attention mechanism and pursue higher computational efficiency. COSA system exploits the high parallelism from the inherent model and leverages run-time configurable hybrid dataflows, i.e., weight and output stationary (OS) for a systolic array (SA) to support the varying matrix multiplication in the attention mechanism. Regarding the cascaded matrix multiplications, COSA proposes levels of fusion methodologies to reduce the off-chip access and enhance processing element (PE) utilization, such as directly using the result of OS as the weight of weight stationary SA by deep fusion. Additionally, the COSA system also provides the solution to hide the latency and radically save the buffer size related to the softmax. Experiment results show that, across various benchmarks, COSA can achieve$2.29-2.60\times $ throughput improvement over the traditional SA of the same MAC number, with up to 94.7% PE utilization rate and$8.2\times $ less off-chip memory access. Compared with the general-purpose platforms,$7.6-12.4\times $ energy efficiency over NVIDIA GeForce 3090 GPU and$35.2-80.9\times $ energy efficiency over Intel 6226R server CPU.- Open Access
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
DEFA: Efficient Deformable Attention Acceleration via Pruning-Assisted Grid-Sampling and Multi-Scale Parallel Processing
Multi-scale deformable attention (MSDeformAttn) has emerged as a key mechanism in various vision tasks, demonstrating explicit superiority attributed to multi-scale grid-sampling. However, this newly introduced operator incurs irregular data access and enormous memory requirement, leading to severe PE under-utilization. Meanwhile, existing approaches for attention acceleration cannot be directly applied to MSDeformAttn due to lack of support for this distinct procedure. Therefore, we propose a dedicated algorithm-architecture co-design dubbed DEFA, the first-of-its-kind method for MSDeformAttn acceleration. At the algorithm level, DEFA adopts frequency-weighted pruning and probability-aware pruning for feature maps and sampling points respectively, alleviating the memory footprint by over 80%. At the architecture level, it explores the multi-scale parallelism to boost the throughput significantly and further reduces the memory access via fine-grained layer fusion and feature map reusing. Extensively evaluated on representative benchmarks, DEFA achieves 10.1-31.9X speedup and 20.3-37.7X energy efficiency boost compared to powerful GPU platforms. It also rivals the related accelerators by 2.2-3.7X energy efficiency improvement while providing pioneering support of MSDeformAttn.
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessDEFA: Efficient Deformable Attention Acceleration via Pruning-Assisted Grid-Sampling and Multi-Scale Parallel Processing
Multi-scale deformable attention (MSDeformAttn) has emerged as a key mechanism in various vision tasks, demonstrating explicit superiority attributed to multi-scale grid-sampling. However, this newly introduced operator incurs irregular data access and enormous memory requirement, leading to severe PE under-utilization. Meanwhile, existing approaches for attention acceleration cannot be directly applied to MSDeformAttn due to lack of support for this distinct procedure. Therefore, we propose a dedicated algorithm-architecture co-design dubbed DEFA, the first-of-its-kind method for MSDeformAttn acceleration. At the algorithm level, DEFA adopts frequency-weighted pruning and probability-aware pruning for feature maps and sampling points respectively, alleviating the memory footprint by over 80%. At the architecture level, it explores the multi-scale parallelism to boost the throughput significantly and further reduces the memory access via fine-grained layer fusion and feature map reusing. Extensively evaluated on representative benchmarks, DEFA achieves 10.1-31.9X speedup and 20.3-37.7X energy efficiency boost compared to powerful GPU platforms. It also rivals the related accelerators by 2.2-3.7X energy efficiency improvement while providing pioneering support of MSDeformAttn.