Zeke Wang

Zeke Wang

Auto-generated profile, based on publicly available information

Zeke Wang

Zhejiang University, Hangzhou, China

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
28 April 2021 in IEEE Transactions on Computers
Verified
Journal Article
Closed access
HHHongjing Huang
Hongjing Huang
ZWZeke Wang
Zeke Wang
JZJie Zhang
Jie Zhang
ZHZhenhao He
Zhenhao He
CWChao Wu
Chao Wu
GAGustavo Alonso
Gustavo Alonso
FPGAs are starting to incorporate High Bandwidth Memory (HBM) to both reduce the memory bandwidth bottleneck encountered in some applications and to provide more capacity to store application state. However, the overall performance characteristics of HBMs are still not well understood, especially in the context of FPGAs, making it difficult to optimize designs relying on HBM. In this article, we bridge the gap between nominal specifications and actual performance by characterizing HBM on a state-of-the-art FPGA, i.e., a Xilinx Alveo U280 featuring a two-stack HBM subsystem. To this end, we have developed Shuhai, a benchmarking tool that throws light on all the subtle details of the performance and usage of HBMs on an FPGA. FPGA-based benchmarking should also provide a more accurate picture of HBM than measuring performance on CPUs/GPUs, since CPUs/GPUs are noisier systems due to their complex control logic and cache hierarchy. Since the memory itself is complex, leveraging custom hardware logic to benchmark it directly from an FPGA provides more details as well as more accurate and deterministic measurements. We observe that 1) HBM is able to provide up to 425 GB/s memory bandwidth, and 2) how HBM is used has a significant impact on the achievable throughput, which in turn demonstrates the importance of unveiling the performance characteristics of HBM so as to use HBM in the right manner. To demonstrate the generality of Shuhai, we also show results for other types of memory, e.g., DDR4, and DDR3, and quantitatively compare the performance characteristics of HBM with those of DDR4 and DDR3.

9 June 2023 in IACR Transactions on Cryptographic Hardware and Embedded Systems
Verified
Journal Article
Open access
PDF file
TLTao Lu
Tao Lu
CWChengkun Wei
Chengkun Wei
RYRuijing Yu
Ruijing Yu
CCChaochao Chen
Chaochao Chen
WFWenjing Fang
Wenjing Fang
WCWenzhi Chen
Wenzhi Chen
Zero-knowledge proof is a critical cryptographic primitive. Its most practical type, called zero-knowledge Succinct Non-interactive ARgument of Knowledge (zkSNARK), has been deployed in various privacy-preserving applications such as cryptocurrencies and verifiable machine learning. Unfortunately, zkSNARK like Groth16 has a high overhead on its proof generation step, which consists of several time-consuming operations, including large-scale matrix-vector multiplication (MUL), number-theoretic transform (NTT), and multi-scalar multiplication (MSM). Therefore, this paper presents cuZK, an efficient GPU implementation of zkSNARK with the following three techniques to achieve high performance. First, we propose a new parallel MSM algorithm. This MSM algorithm achieves nearly perfect linear speedup over the Pippenger algorithm, a well-known serial MSM algorithm. Second, we parallelize the MUL operation. Along with our self-designed MSM scheme and well-studied NTT scheme, cuZK achieves the parallelization of all operations in the proof generation step. Third, cuZK reduces the latency overhead caused by CPU-GPU data transfer by 1) reducing redundant data transfer and 2) overlapping data transfer and device computation. The evaluation results show that our MSM module provides over 2.08x (up to 2.94x) speedup versus the state-of-the-art GPU implementation. cuZK achieves over 2.65x (up to 4.86x) speedup on standard benchmarks and 2.18× speedup on a GPU-accelerated cryptocurrency application, Filecoin.

14 September 2017 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
XLXue Liu
Xue Liu
XYXin-Xin Yan
Xin-Xin Yan
ZWZe-Ke Wang
Ze-Ke Wang
QDQing-Xu Deng
Qing-Xu Deng
This brief presents a field-programmable gate array-based implementation of a reconfigurable digital down converter (DDC) that can process input bandwidth of up to 3.6 GHz and provide a flexible down-converted output. The proposed DDC consists of a mixer and a resampling filter. The resampling filter can work at much higher clock rate. The reason is that all the single-cycle recursive loops in the resampling filter are pipelined by using either real/imaginary part-time multiplexing or parallel processing technique. With features like arbitrary sampling rate conversion, and dynamic configuration, the proposed design is highly flexible, so that it can generate a down-converted output with sampling rate, selectable within the range of 1 kS/s–225 MS/s. Moreover, the flexibility is further improved by being able to specify the output sampling rate and center frequency to a resolution of less than 1 S/s. The experimental results show that the proposed design can achieve the same functionality as the existing work but with fewer hardware resources.

10 September 2023
Verified
Conference Paper
Open access
CWChengkun Wei
Chengkun Wei
XLXing Li
Xing Li
YYYe Yang
Ye Yang
XJXiaochong Jiang
Xiaochong Jiang
TXTianyu Xu
Tianyu Xu
WCWenzhi Chen
Wenzhi Chen


30 July 2021 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
JJJiantong Jiang
Jiantong Jiang
ZWZeyi Wen
Zeyi Wen
ZWZeke Wang
Zeke Wang
BHBingsheng He
Bingsheng He
JCJian Chen
Jian Chen
Structured Support Vector Machines (structured SVMs) are a fundamental machine learning algorithm, and have solid theoretical foundation and high effectiveness in applications such as natural language parsing and computer vision. However, training structured SVMs is very time-consuming, due to the large number of constraints and inferior convergence rates, especially for large training data sets. The high cost of training structured SVMs has hindered its adoption to new applications. In this article, we aim to improve the efficiency of structured SVMs by proposing a parallel and distributed solution (namely FastSSVM ) for training structured SVMs building on top of MPI and OpenMP. FastSSVM exploits a series of optimizations (e.g., optimizations on data storage and synchronization) to efficiently use the resources of the nodes in a cluster and the cores of the nodes. Moreover, FastSSVM tackles the large constraint set problem by batch processing and addresses the slow convergence challenge by adapting stop conditions based on the improvement of each iteration. We theoretically prove that our solution is guaranteed to converge to a global optimum. A comprehensive experimental study shows that FastSSVM can achieve at least four times speedup over the existing solutions, and in some cases can achieve two to three orders of magnitude speedup.