Filters








69 Hits in 6.2 sec

Concordia: Distributed Shared Memory with In-Network Cache Coherence

Qing Wang, Youyou Lu, Erci Xu, Junru Li, Youmin Chen, Jiwu Shu
2021 USENIX Conference on File and Storage Technologies  
In this paper, we propose CONCORDIA, a DSM with fast in-network cache coherence backed by programmable switches.  ...  Distributed shared memory (DSM) is experiencing a resurgence with emerging fast network stacks.  ...  In this paper, we present the CONCORDIA, a highperformance rack-scale DSM with in-network cache coherence.  ... 
dblp:conf/fast/WangLXLCS21 fatcat:3unjtt6rdnb73nhhd4arexhaoy

MIND: In-Network Memory Management for Disaggregated Data Centers [article]

Seung-seob Lee, Yanpeng Yu, Yupeng Tang, Anurag Khandelwal, Lin Zhong, Abhishek Bhattacharjee
2021 arXiv   pre-print
We find that centralizing memory management in the network permits bandwidth and latency-efficient realization of in-network cache coherence protocols, while programmable switch ASICs support other memory  ...  In this work, we show that emerging programmable network switches can enable an efficient shared memory abstraction for disaggregated architectures by placing memory management logic in the network fabric  ...  This work is supported in part by NSF Awards #2047220, #2016422, #1916817 and their REU supplements.  ... 
arXiv:2107.00164v1 fatcat:jzktsu2ygfduxhdrbd66wl7j3a

Sherman: A Write-Optimized Distributed B+Tree Index on Disaggregated Memory

Qing Wang, Youyou Lu, Jiwu Shu
2022 Proceedings of the 2022 International Conference on Management of Data  
This paper presents Sherman, a write-optimized distributed B + Tree index on disaggregated memory that delivers high performance with commodity RDMA NICs.  ...  Memory disaggregation architecture physically separates CPU and memory into independent components, which are connected via high-speed RDMA networks, greatly improving resource utilization of databases  ...  retries.When failing to acquire a lock, the client thread retries.Different from locks designed for shared memory with coherent cache, such retries in the RDMA environment require remote network accesses  ... 
doi:10.1145/3514221.3517824 fatcat:l2fe3nqrjrex3nszcarvfqcili

Sherman: A Write-Optimized Distributed B+Tree Index on Disaggregated Memory [article]

Qing Wang and Youyou Lu and Jiwu Shu
2021 arXiv   pre-print
This paper presents Sherman, a write-optimized distributed B+Tree index on disaggregated memory that delivers high performance with commodity RDMA NICs.  ...  Memory disaggregation architecture physically separates CPU and memory into independent components, which are connected via high-speed RDMA networks, greatly improving resource utilization of databases  ...  Different from locks designed for shared memory with coherent cache, such retries in the RDMA environment require remote network accesses, squandering limited throughput of NICs in both senders and receivers  ... 
arXiv:2112.07320v2 fatcat:rmxr2jgjyrgwjo2zfvsnsnhwvm

Invalidation-Based Protocols for Replicated Datastores [article]

Antonios Katsarakis
2021 arXiv   pre-print
Distributed in-memory datastores underpin cloud applications that run within a datacenter and demand high performance, strong consistency, and availability.  ...  Meanwhile, the opposite occurs in the world of multiprocessors, where data are replicated across the private caches of different cores.  ...  Concordia: Distributed shared memory with in-network cache co- herence. In 19th USENIX Conference on File and Storage Technolo- gies (FAST 21), pages 277–292.  ... 
arXiv:2112.02405v1 fatcat:toi3wflouvbzngpdfzypw3l4li

Table of Contents

2020 2020 54th Asilomar Conference on Signals, Systems, and Computers  
.418 Baturalp Buyukates, Sennur Ulukus, University of Maryland, United States TU1-1.2: Maximizing Information Freshness in Caching Systems with Limited Cache Storage ...................423 Capacity Melih  ...  , United States; Sneha Kasera, Mingyue Ji, University of Utah, United States TU2-1.2: Enabling Uncoordinated Spectrum Sharing in Millimeter Wave Networks Using ........................544 Carrier Sensing  ... 
doi:10.1109/ieeeconf51394.2020.9443278 fatcat:balvqqe4jzfy7nq2mdzhl4z3mu

An Exhaustive Survey on P4 Programmable Data Plane Switches: Taxonomy, Applications, Challenges, and Future Trends

Elie F. Kfoury, Jorge Crichigno, Elias Bou-Harb
2021 IEEE Access  
Despite the impressive advantages of programmable data plane switches and their importance in modern networks, the literature has been missing a comprehensive survey.  ...  Traditionally, the data plane has been designed with fixed functions to forward packets using a small set of protocols.  ...  [130] proposed CONCORDIA, a rackscale Distributed Shared Memory (DSM) with in-network cache coherence.  ... 
doi:10.1109/access.2021.3086704 fatcat:2jgbxj2cbfbp7fawkxwrztbbia

An Exhaustive Survey on P4 Programmable Data Plane Switches: Taxonomy, Applications, Challenges, and Future Trends [article]

Elie F. Kfoury, Jorge Crichigno, Elias Bou-Harb
2021 arXiv   pre-print
Despite the impressive advantages of programmable data plane switches and their importance in modern networks, the literature has been missing a comprehensive survey.  ...  Traditionally, the data plane has been designed with fixed functions to forward packets using a small set of protocols.  ...  [130] proposed CONCORDIA, a rackscale Distributed Shared Memory (DSM) with in-network cache coherence.  ... 
arXiv:2102.00643v2 fatcat:izxi645kozdc5ibfsqp2y2foau

Technical sessions

2007 2007 12th IEEE Symposium on Computers and Communications  
Several schemes for the pre-distribution of keys have been proposed, however, they usually have high memory requirements or large communication overhead if sensor network is large.  ...  "In this paper we analyze how to reduce the time dedicated to network access control operations in mobile ad hoc networks (MANET) with Internet connectivity.  ...  Coordination Function (DCF) is the most popular Medium Access Control (MAC) protocol in distributed wireless networks, in which the wireless medium is shared.  ... 
doi:10.1109/iscc.2007.4381657 fatcat:bn67vm2cvvehvmqqxew4r2xkbe

The PARSEC benchmark suite

Christian Bienia, Sanjeev Kumar, Jaswinder Pal Singh, Kai Li
2008 Proceedings of the 17th international conference on Parallel architectures and compilation techniques - PACT '08  
This paper presents and characterizes the Princeton Application Repository for Shared-Memory Computers (PAR-SEC), a benchmark suite for studies of Chip-Multiprocessors (CMPs).  ...  Our characterization shows that the benchmark suite is diverse in working set, locality, data sharing, synchronization, and off-chip traffic. The benchmark suite has been made available to the public.  ...  It is a useful metric to estimate the requirements for the cache coherence mechanism of a CMP: A true shared write can trigger a coherence invalidate or update, and a true shared read might require the  ... 
doi:10.1145/1454115.1454128 dblp:conf/IEEEpact/BieniaKSL08 fatcat:mskdckm6urbknpxxt5c6hldlli

Ping-pong beam training for reciprocal channels with delay spread

Elisabeth de Carvalho, Jorgen Bach Andersen
2015 2015 49th Asilomar Conference on Signals, Systems and Computers  
A distributed consensus algorithm for estimating the number of nodes in a wireless sensor network in the presence of communication noise is proposed.  ...  In this work we revisit these penalized regression formulations in a Bayesian framework with suitable choice of supergaussian prior distributions.  ...  Track C -Networks Session: TPb3 -Caching in Wireless Networks Chair: Edmund Yeh, Northeastern University TP3b-1 3:30 PM Caching in Combination Networks Mingyue Ji, University of Southern California  ... 
doi:10.1109/acssc.2015.7421451 dblp:conf/acssc/CarvalhoA15 fatcat:mqokuvnh3zg45licnfbgxyvxfu

EGI-ACE D2.3 Technical specifications for compute common services

Enol Fernández, Gergely Sipos, Marica Antonacci, Valeria Ardizzone, Priyasma Bhoumik, Miguel Caballer, Amanda Calatrava, Ian Collier, Rose Cooper, William Karageorgos, Bartosz Kryza, Nicolas Liampotis (+11 others)
2021 Zenodo  
the distributed infrastructure.  ...  actual computing and storage infrastructure, and higher level Platform and Software as a Service layers that provide compute and data orchestration alongside tools to facilitate the execution of workloads in  ...  In order to keep the aforementioned components in sync with the state of the EGI infrastructure and coherently maintain the distributed information, AppDB has been integrated with various services of the  ... 
doi:10.5281/zenodo.5526125 fatcat:adyvqwxw7bdjhbq3dt3b7ehvki

EGI-ACE D2.3 Technical specifications for compute common services

Enol Fernández, Gergely Sipos, Marica Antonacci, Valeria Ardizzone, Priyasma Bhoumik, Miguel Caballer, Amanda Calatrava, Ian Collier, Rose Cooper, William Karageorgos, Bartosz Kryza, Nicolas Liampotis (+11 others)
2021 Zenodo  
the distributed infrastructure.  ...  actual computing and storage infrastructure, and higher level Platform and Software as a Service layers that provide compute and data orchestration alongside tools to facilitate the execution of workloads in  ...  In order to keep the aforementioned components in sync with the state of the EGI infrastructure and coherently maintain the distributed information, AppDB has been integrated with various services of the  ... 
doi:10.5281/zenodo.6602270 fatcat:co7eycltenblflscxlth2l4sra

A scalable distributed architecture for client and server-side software agents

Mirjana Ivanović, Milan Vidaković, Zoran Budimac, Dejan Mitrović
2016 Vietnam Journal of Computer Science  
Server side agents exist as EJB session beans on the JavaEE application server, while client-side agents exist as JavaScript Worker objects in the browser.  ...  On the client side this distributed architecture relies on HTML5 and related standards to support smooth running on a wide variety of hardware and software platforms.  ...  The preferred approach of inter-node communication and information sharing is given through the Infinispan cache system [3] .  ... 
doi:10.1007/s40595-016-0083-z fatcat:qbpci3l5q5ezhfnmyzyocq4kjm

Mobile Objects and Agents (MOA)

Dejan S Milojicic, William LaForge, Deepika Chauhan
1998 Distributed Systems Engineering  
Agents, as well as hosts, are vulnerable to mutual attacks, either over a network or locally.  ...  In the course of the project we added two further goals: compliance with the Java Beans component model which provides for additional configurability and customization of agent system and agent applications  ...  Our experience is that distributed shared state is very hard to support at the system level [5] , it is more appropriate to rely on distributed shared memory packages for such needs.  ... 
doi:10.1088/0967-1846/5/4/007 fatcat:tm3pefkiqndebjllikvxxsx2sm
« Previous Showing results 1 — 15 out of 69 results