activity
20182022
most citedOptimizing Memory Performance of Xilinx FPGAs under Vitis

7 citations · 19 across the 7 of their papers we have counts for

collaborators

7 papers

cs.AR2022★ 2 cited

CPSAA: Accelerating Sparse Attention using Crossbar-based Processing-In-Memory Architecture

Huize Li, Hai Jin, Long Zheng +7

The attention mechanism requires huge computational efforts to process unnecessary calculations, significantly limiting the system's performance. Researchers propose sparse attenti…

cs.LG2022★ 2 cited

GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction

Zixiao Wang, Yuluo Guo, Jin Zhao +5

In this paper, we propose a Graph Inception Diffusion Networks(GIDN) model. This model generalizes graph diffusion in different feature spaces, and uses the inception module to avo…

cs.LG2022★ 4 cited

Accelerating Backward Aggregation in GCN Training with Execution Path Preparing on GPUs

Shaoxian Xu, Zhiyuan Shao, Ci Yang +2

The emerging Graph Convolutional Network (GCN) has now been widely used in many domains, and it is challenging to improve the efficiencies of applications by accelerating the GCN t…

cs.AR2021★ 1 cited

ScalaBFS: A Scalable BFS Accelerator on HBM-Enhanced FPGAs

Kexin Li, Chenhao Liu, Zhiyuan Shao +5

High Bandwidth Memory (HBM) provides massive aggregated memory bandwidth by exposing multiple memory channels to the processing units. To achieve high performance, an accelerator b…

cs.DC2020★ 7 cited

Optimizing Memory Performance of Xilinx FPGAs under Vitis

Ruoshi Li, Hongjing Huang, Zeke Wang +3

Plenty of research efforts have been devoted to FPGA-based acceleration, due to its low latency and high energy efficiency. However, using the original low-level hardware descripti…

cs.DC2020★ 2 cited

A Survey of Non-Volatile Main Memory Technologies: State-of-the-Arts, Practices, and Future Directions

Haikun Liu, Di Chen, Hai Jin +4

Non-Volatile Main Memories (NVMMs) have recently emerged as promising technologies for future memory systems. Generally, NVMMs have many desirable properties such as high density,…

cs.AR2018★ 1 cited

Supporting Superpages and Lightweight Page Migration in Hybrid Memory Systems

Xiaoyuan Wang

Superpages have long been used to mitigate address translation overhead in big memory systems. However, superpages often preclude lightweight page migration, which is crucial for p…