Search Results - "Xiao, Liquan"

Communication optimization strategies for distributed deep neural network training: A survey by Ouyang, Shuo, Dong, Dezun, Xu, Yemao, Xiao, Liquan

“…Recent trends in high-performance computing and deep learning have led to the proliferation of studies on large-scale deep neural network training. However,…”
Get full text

MilkyWay-2 supercomputer： system and application by LIAO, Xiangke, XIAO, Liquan, YANG, Canqun, LU, Yutong

“…On June 17, 2013, MilkyWay-2 （Tianhe-2） supercomputer was crowned as the fastest supercomputer in the world on the 41th TOP500 list. This paper provides an…”
Get full text

SMRC: An Endurable SSD Cache for Host-Aware Shingled Magnetic Recording Drives by Xie, Xuchao, Xiao, Liquan, Ge, Xiongzi, Li, Qiong

“…Host-aware shingled magnetic recording (HA-SMR) drives deliver higher disk capacity and expose internal zones to host, but their performance can be severely…”
Get full text

Natural Background Level and Contamination of Shallow Groundwater Salinity in Various Aquifers in a Coastal Urbanized Area, South China by Bi, Pan, Han, Dongya, Liu, Chunyan, Xiao, Liquan, Wu, Heqiu, Zhang, Meng

“…Assessing natural background levels (NBLs) of chemical components in groundwater is useful for the evaluation of groundwater contamination in urbanized areas…”
Get full text

Acceleration for computer-generated hologram in head-mounted display with effective diffraction area recording method for eyes by 陈志东 桑新柱 蔺巧娟 李瑾 于迅博 高鑫 颜玢玢 余重秀 窦文华 肖立权

“…Holographic head-mounted display（HHMD） is a specific application of holography. The previous conventional computer-generated hologram（CGH） generation method…”
Get full text

On the Shoulders of Giants: Incremental Influence Maximization in Evolving Social Networks by Xiao, Liquan, Huang, Chenlin, Zhang, Jingying, Lin, Bin, Zheng, Si, Li, Shanshan, Liao, Xiangke, Liu, Xiaodong, Shao, Lisong

“…Influence maximization problem aims to identify the most influential individuals so as to help in developing effective viral marketing strategies over social…”
Get full text

Optimize the Power Consumption and SNR of the 3D Photonic High-Radix Switch Architecture Based on Extra Channels and Redundant Rings by Jian, Jie, Xiao, Liquan, Lai, Mingche

“…The demand from exascale computing has made the design of high-radix switch chips an attractive and challenging research field in EHPC (exascale…”
Get full text

CER-IOS: Internal Resource Utilization Optimized I/O Scheduling for Solid State Drives by Xie, Xuchao, Wei, Dengping, Li, Qiong, Song, Zhenlong, Xiao, Liquan

“…Modern Solid State Drives (SSDs) integrate more internal resources to get higher performance and capacity. Improving internal resource utilization by…”
Get full text

Synthesizing Complementary Circuits Automatically by Shen, ShengYu, Qin, Ying, Wang, KeFei, Xiao, LiQuan, Zhang, JianMin, Li, SiKun

“…One of the most difficult jobs in designing communication and multimedia chips is to design and verify the complex complementary circuit pair ( E , E -1 ), in…”
Get full text

A Halting Algorithm to Determine the Existence of the Decoder by Shen, ShengYu, Qin, Ying, Xiao, LiQuan, Wang, KeFei, Zhang, JianMin, Li, SiKun

“…Complementary synthesis automatically synthesizes the decoder circuit of an encoder. It determines the existence of the decoder by checking whether the…”
Get full text

Reliable Opto-Electronic Hybrid Interconnection Network by Liquan Xiao, Kefei Wang

“…The interconnection network plays a critical role in the cost and performance of a high performance parallel computer and it is closely related with signaling…”
Get full text

A survey of machine learning for Network-on-Chips by Zhang, Xiaoyun, Dong, Dezun, Li, Cunlu, Wang, Shaocong, Xiao, Liquan

Get full text

A clustering ensemble algorithm for handling deep embeddings using cluster confidence by Zeng, Lingbin, Yao, Shixin, Liu, Xinwang, Xiao, Liquan, Qian, Yue

“…Abstract Clustering ensemble, which aims to learn a robust consensus clustering from multiple weak base clusterings, has achieved promising performance on…”
Get full text

Multiple-Mode-Supporting Floating-Point FMA Unit for Deep Learning Processors by Tan, Hongbing, Tong, Gan, Huang, Libo, Xiao, Liquan, Xiao, Nong

“…In this article, a new multiple-mode floating-point fused multiply-add (FMA) unit is proposed for deep learning processors. The proposed design supports three…”
Get full text

The bioaccessibility and fractionation of arsenic in anoxic soils as a function of stabilization using low-cost Fe/Al-based materials: A long-term experiment by Hou, Qinxuan, Han, Dongya, Zhang, Ying, Han, Mei, Huang, Guanxing, Xiao, Liquan

“…Arsenic (As)-contaminated soils occur widely worldwide. In the present study, three low-cost Fe/Al-based materials, including red soil (RS), sponge iron filter…”
Get full text

A Low-Cost Floating-Point FMA Unit Supporting Package Operations for HPC-AI Applications by Tan, Hongbing, Zhang, Jing, He, Xiaowei, Huang, Libo, Wang, Yongwen, Xiao, Liquan

“…The convergence of HPC and AI has brought about a diversification of precision, posing significant hardware implementation challenges. This brief aims to…”
Get full text

A Cost-Efficient Router Architecture for HPC Inter-Connection Networks: Design and Implementation by Dai, Yi, Lu, Kai, Xiao, Liquan, Su, Jinshu

“…High-radix routers with lower latency and higher bandwidth play an increasingly important role in constructing large-scale interconnection networks such as…”
Get full text

A 56-Gb/s,0.708 pJ/bit single-ended simultaneous bidirectional transceiver with hybrid errors cancellation techniques for die-to-die interface by Ren, Bolin, Lv, Fangxu, Lai, Mingche, Xiao, Liquan, Zhang, Geng, Zheng, Xuqiang, Luo, Zhang, Xu, Jiaqing

“…This paper presents a low-power Simultaneous Bidirectional (SBD) transceiver with a power consumption of 0.708 pJ/bit, supporting a 56-Gb/s single-ended…”
Get full text

A Low-Cost Floating-Point Dot-Product-Dual-Accumulate Architecture for HPC-Enabled AI by Tan, Hongbing, Huang, Libo, Zheng, Zhong, Guo, Hui, Yang, Qianmin, shen, Li, Chen, Gang, Xiao, Liquan, Xiao, Nong

“…The dot-product ∑i=1NAi×Bi is one of the most frequently used operations for a wide variety of high performance computing (HPC) and Artificial Intelligence…”
Get full text

Hardware-Based Multicast with Global Load Balance on k-ary n-trees by Quanbao Sun, Minxuan Zhang, Liquan Xiao

“…The multicast operation is used commonly in parallel applications and can be used to support several other collective communication operations. A significant…”
Get full text