17 Hits in 5.6 sec

Stash directory: A scalable directory for many-core coherence

Socrates Demetriades, Sangyeun Cho
2014 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA)  
Sparse directory organizations represent the most energyefficient and scalable approach towards many-core coherence.  ...  Simulations on a 16-core CMP model show that Stash Directory can reduce space requirements to 1/8 of a conventional sparse directory, without compromising performance.  ...  Scalability A feasible directory design for coherent many-core CMPs must scale well across an increasing number of cores.  ... 
doi:10.1109/hpca.2014.6835928 dblp:conf/hpca/DemetriadesC14 fatcat:6f35kve4k5gxdodqhvcebz5k4y

Cuckoo directory: A scalable directory for many-core systems

Michael Ferdman, Pejman Lotfi-Kamran, Ken Balet, Babak Falsafi
2011 2011 IEEE 17th International Symposium on High Performance Computer Architecture  
Growing core counts have highlighted the need for scalable on-chip coherence mechanisms. The increase in the number of on-chip cores exposes the energy and area costs of scaling the directories.  ...  We propose the Cuckoo directory, a power-and area-efficient scalable distributed directory.  ...  In this work, we proposed the Cuckoo directory, a directory organization that eliminates set conflicts and enables energy-and area-scalable coherence for large core counts.  ... 
doi:10.1109/hpca.2011.5749726 dblp:conf/hpca/FerdmanLBF11 fatcat:bzf3oskp5zheblfdh4oti64ir4

Way Combination for an Adaptive and Scalable Coherence Directory

Ruben Titos-Gil, Antonio Flores, Ricardo Fernandez Pascual, Alberto Ros, Salvador Petit, Julio Sahuquillo, Manuel E. Acacio
2019 IEEE Transactions on Parallel and Distributed Systems  
Through detailed simulations of a 128-core architecture, we show that the way-combining directory closely approaches the performance of a non-scalable bit-vector sparse directory, and beats other scalable  ...  In this work we propose a novel organization for the coherence directory that builds on the brand-new concept of way combining.  ...  Two-level directory architectures have also been proposed as a scalable way of organizing the coherence directory [32] .  ... 
doi:10.1109/tpds.2019.2917185 fatcat:jt737xhk6jdmrj77nsqpr6vwzm

Flask coherence: A morphable hybrid coherence protocol to balance energy, performance and scalability

Lucia G. Menezo, Valentin Puente, Jose-Angel Gregorio
2015 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA)  
A non-inclusive sparse-directory is used to minimize energy requirements and guarantee scalability. Directory entries will be used only by the most actively shared blocks.  ...  This work proposes a mechanism to hybridize the benefits of snoop-based and directory-based coherence protocols in a single construct.  ...  We also thank Justin Gottschlich, Victor Luchangco, Jens Maurer, and Torvald Riegel for many helpful conversations about the Draft C++ TM Specification.  ... 
doi:10.1109/hpca.2015.7056033 dblp:conf/hpca/MenezoPG15 fatcat:4lssxzd2ozdf7eonk44s3dmsge

Persistent Memory Hash Indexes: An Experimental Evaluation

Daokun Hu, Zhiwen Chen, Jianbing Wu, Jianhua Sun, Hao Chen
2021 Proceedings of the VLDB Endowment  
To this end, this paper provides a comprehensive evaluation of persistent hash tables.  ...  Our evaluation was conducted using a unified benchmarking framework and representative workloads.  ...  We thank the anonymous reviewers for their valuable suggestions in improving this paper.  ... 
dblp:journals/pvldb/HuCW0021 fatcat:xifixwwcirc6vpnpr2aak4od2a

Incorporating cognitive/learning styles in a general-purpose adaptive hypermedia system

Natalia Stash
2007 ACM SIGWEB Newsletter  
Another format for storing of the DM/AM of AHA!, the mySQL database, was provided to ensure scalability.  ...  The created strategies files will be put into the author's directory, available only for himself/herself.  ...  Research Question 1: Is an AHS necessarily a special-purpose tool? In chapter 2 we derived a set of design requirements for a general-purpose tool.  ... 
doi:10.1145/1324960.1324963 fatcat:55xgs76jqfgp7eidvacnm2f4zq

Understanding I/O Direct Cache Access Performance for End Host Networking

Minhu Wang, Mingwei Xu, Jianping Wu
2022 Proceedings of the ACM on Measurement and Analysis of Computing Systems  
As numerous I/O devices and cores compete for scarce cache resources, making the most of DCA for networking applications with varied objectives and constraints is a challenge, especially given the increasing  ...  Direct Cache Access (DCA) enables a network interface card (NIC) to load and store data directly on the processor cache, as conventional Direct Memory Access (DMA) is no longer suitable as the bridge between  ...  Berger and anonymous SIGMETRICS reviewers for their valuable comments. The research is supported by the National Natural Science Foundation of China under Grant 61832013 and 61872426.  ... 
doi:10.1145/3508042 fatcat:3odacbr7lfamtg55inma76s6bu

Efficient synchronization mechanisms for scalable GPU architectures

Xiaowei Ren
Third, we design HMG, a hierarchical cache coherence protocol for multi-GPU systems.  ...  The Graphics Processing Unit (GPU) has become a mainstream computing platform for a wide range of applications.  ...  Another challenge is scalability, since GPUs have large core counts and many concurrent warps in each core. This precludes, for example, mechanisms that collect and broadcast read/write signatures.  ... 
doi:10.14288/1.0394805 fatcat:aoyfyhwdyjbefp6yjyqk2p4tti

Replicated Data Management for Mobile Computing

Douglas B. Terry
2008 Synthesis Lectures on Mobile and Pervasive Computing  
A rich collection of topics lies at the intersections of mobile and pervasive computing with many other areas of computer science.  ...  These include unpredictable variation in network quality, lowered trust and robustness of mobile elements, limitations on local resources imposed by weight and size constraints, and concern for battery  ...  For example, current updates to a directory are resolved by merging the directory contents from the conflicting versions.  ... 
doi:10.2200/s00132ed1v01y200807mpc005 fatcat:fmgemdj5gnbofmmsbnqsrqqqli

Ghostor: Toward a Secure Data-Sharing System from Decentralized Trust

Yuncong Hu, Sam Kumar, Raluca Ada Popa
2020 Symposium on Networked Systems Design and Implementation  
We would also like to thank students from the RISELab Security Group and BETS Research Group for giving us feedback on early drafts, and David Culler for advice and discussion.  ...  Acknowledgments We thank the anonymous reviewers and our shepherd, Carmela Troncoso, for their invaluable feedback.  ...  The Ghostor object corresponding to a directory contains a mapping from name to PVK as a list of directory entries.  ... 
dblp:conf/nsdi/HuKP20 fatcat:nsze36dwsrcy5mms64s7gh5dlm

Scalable Emulation of Heterogeneous Systems

Emilio Garcia Cota
full-system, cross-ISA simulator with support for accelerators.  ...  Unfortunately, existing simulation tools that can support such system-level research are limited by the lack of fast, scalable machine emulators to drive execution.  ...  Implementing a standalone directory cache guarantees that recalls can be made infrequent (by having enough associativity in the directory cache), and dissociates coherence from the last-level cache; logical  ... 
doi:10.7916/d8-a78j-z392 fatcat:upxiu626fbgz3o7ywoczzq4ffy

Rapid SoC Design: On Architectures, Methodologies and Frameworks [article]

Adetutu Ajayi, University, My
While the GPU serves as a classical example, accelerators for machine learning, approximate computing, graph processing, and database applications have become commonplace.  ...  These specialized units improve the overall performance, power, and area (PPA) metrics across a wide variety of workloads and applications.  ...  Heterogeneous System Coherence (HSC) [109] uses a modified directory/interconnect and memory hierarchy for CPU-GPU systems.  ... 
doi:10.7302/1546 fatcat:hekqywqyznaihaisver5be4t4y

In polite company

Elizabeth Losh
2008 Proceedings of the 2008 International Conference in Advances on Computer Entertainment Technology - ACE '08  
A special thanks to the research assistants for handling the data 40 and the pictures as well as Alex Thayer for commenting the language of this paper.  ...  One of the many strategies used today by marketing business is customization.  ...  that much, it is in many cases a crucial factor for a game to be considered innovative.  ... 
doi:10.1145/1501750.1501832 dblp:conf/ACMace/Losh08 fatcat:cstvopas5jad7os5idmdt642ie

Dynamic deformables

Theodore Kim, David Eberle
2022 ACM SIGGRAPH 2022 Courses  
We also provide, for the first time, open-source C++ implementations of many of the described algorithms.  ...  This new formulation is only a starting point for creating a simulator that is up challenges of a production environment.  ...  The core issue is that we don't know how to obtain a tidy symbolic derivative for the numerical quantity R.  ... 
doi:10.1145/3532720.3535628 fatcat:64aso4dd5vbb5flouo5hsm5jva

Reinforcement Learning (Dagstuhl Seminar 13321) The Critical Internet Infrastructure (Dagstuhl Seminar 13322) Coding Theory (Dagstuhl Seminar 13351) Interaction with Information for Visual Reasoning (Dagstuhl Seminar 13352)

Peter Auer, Marcus Hutter, Laurent, Georg Carle, Jochen Schiller, Steve Uhlig, Walter Willinger, Matthias Wählisch, Thore Husfeldt, Ramamohan Paturi, Gregory Sorkin, Ryan Williams (+14 others)
Biological OFF rate can be studied, OFF rate is the time for A and B to stay attached. Then, they dissociate. Should attach long enough and go to the membrane for reaction.  ...  Is there a lesson for biology? Anja: We are working in this area. Yet, already agreeing on terminology is difficult. Marc: Sensors are underrated, ON and OFF rates need to be studied.  ...  Yet, in many application areas of multiscale imaging, there is a common core set of tools that could be used.  ... 
« Previous Showing results 1 — 15 out of 17 results