Ke Wu

Ke Wu

Auto-generated profile, based on publicly available information

Ke Wu

College of Computer, National University of Defense Technology, Changsha, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 June 2023
Verified
Conference Paper
Open access
RWRuiqi Wang
Ruiqi Wang
DDDezun Dong
Dezun Dong
FLFei Lei
Fei Lei
JMJunchao Ma
Junchao Ma
KWKe Wu
Ke Wu
KLKai Lu
Kai Lu
The allreduce operation is the most commonly used collective operation in distributed or parallel applications. It aggregates data collected from distributed hosts and broadcasts the aggregated result back to them. In-network computing can accelerate allreduce by offloading this operation into network devices. However, existing in-network solutions face the challenge of high throughput, performance of aggregating large message and producing repeatable results. In this work, we propose a simple and effective router microarchitecture for in-network allreduce, which uses an RDMA protocol to improve its throughput. We further discuss strategies to tackle the aforementioned challenges. Our approach not only shows advantages in comparison with the state-of-the-art in-network solutions, but also accelerates allreduce at a near-optimal level compared to host-based algorithms, as demonstrated through experiments.

15 October 2019 in Behavioural Neurology
Verified
Journal Article
Open access
PDF file
JLJieqiong Liu
Jieqiong Liu
SCShi Cai
Shi Cai
DCDanni Chen
Danni Chen
KWKe Wu
Ke Wu
LYLiu Yang
Liu Yang
Xianchun LiXianchun Li
Xianchun Li
Selective attention refers to the selecting and preferential processing of specific information while simultaneously suppressing irrelevant distractors, activities linked to various cognitive skills and academic achievements. The influence of essential oils on the cognition of humans has been extensively explored. However, the effects of essential oils on human selective attention and the underlying neural mechanisms remain unclear. In the present study, participants were divided into a “blended essential oil” group and a “no essential oil” group and enrolled on a negative priming task, including a control condition and a negative priming condition. The event-related potential technique was used to examine the brain mechanisms underlying the blended essential oil effects on human selective attention. Behavioral results showed that individuals responded more quickly in the negative priming condition when exposed to the blended essential oil. In addition, the blended essential oil eliminated the differences in the P300 amplitude in the postcentral area of the brain between the negative priming condition and the control condition. Moreover, the blended essential oil led to stronger functional connectivity during the task. The present study thus suggests that blended essential oil can significantly change brain activity and functional connections in human beings, which may improve human selective attention.

14 September 2024 in ACM Transactions on Architecture and Code Optimization
Verified
Journal Article
Open access
KWKe Wu
Ke Wu
DDDezun Dong
Dezun Dong
WXWeixia Xu
Weixia Xu
RDMA (Remote Direct Memory Access) networks require efficient congestion control to maintain their high throughput and low latency characteristics. However, congestion control protocols deployed at the software layer suffer from slow response times due to the communication overhead between host hardware and software. This limitation has hindered their ability to meet the demands of high-speed networks and applications. Harnessing the capabilities of rapidly advancing Network Interface Cards (NICs) can drive progress in congestion control. Some simple congestion control protocols have been offloaded to RDMA NICs to enable faster detection and processing of congestion. However, offloading congestion control to the RDMA NIC faces a significant challenge in integrating the RDMA transport protocol with advanced congestion control protocols that involve complex mechanisms. We have observed that reservation-based proactive congestion control protocols share strong similarities with RDMA transport protocols, allowing them to integrate seamlessly and combine the functionalities of the transport layer and network layer. In this article, we present COER, an RDMA NIC architecture that leverages the functional components of RDMA to perform reservations and completes the scheduling of congestion control during the scheduling process of the RDMA protocol. COER facilitates the streamlined development of offload strategies for congestion control techniques —specifically, proactive congestion control —on RDMA NICs. We use COER to design offloading schemes for 11 congestion control protocols, which we implement and evaluate using a network emulator with a cycle-accurate RDMA NIC model that can load Message Passing Interface (MPI) programs. The evaluation results demonstrate that the architecture of COER does not compromise the original characteristics of the congestion control protocols. Compared with a layered protocol stack approach, COER enables the performance of RDMA networks to reach new heights.

2 October 2024 in Journal of Parallel and Distributed Computing
Verified
Journal Article
Closed access
KWKe Wu
Ke Wu
DDDezun Dong
Dezun Dong
WXWeixia Xu
Weixia Xu

4 May 2022 in Computer Networks
Verified
Journal Article
Closed access
KWKe Wu
Ke Wu
DDDezun Dong
Dezun Dong
CLCunlu Li
Cunlu Li
WXWeixia Xu
Weixia Xu

29 June 2023
Verified
Conference Paper
Open access
BLBinyan Lan
Binyan Lan
FLFei Lei
Fei Lei
KWKe Wu
Ke Wu
DDDezun Dong
Dezun Dong