Filters








74,774 Hits in 5.0 sec

End-to-end sequential consistency

Abhayendra Singh, Satish Narayanasamy, Daniel Marino, Todd Millstein, Madanlal Musuvathi
2012 SIGARCH Computer Architecture News  
Sequential consistency (SC) is arguably the most intuitive behavior for a shared-memory multithreaded program.  ...  This paper exploits the observation that hardware need not enforce any memory model constraints on accesses to thread-local and shared read-only locations.  ...  Acknowledgements We would like to thank Sarita Adve and anonymous reviewers for their valuable suggestions.  ... 
doi:10.1145/2366231.2337220 fatcat:ff42wovbhzaera2zmvtcwsc4ta

End-to-end sequential consistency

Abhayendra Singh, Satish Narayanasamy, Daniel Marino, Todd Millstein, Madanlal Musuvathi
2012 2012 39th Annual International Symposium on Computer Architecture (ISCA)  
Sequential consistency (SC) is arguably the most intuitive behavior for a shared-memory multithreaded program.  ...  This paper exploits the observation that hardware need not enforce any memory model constraints on accesses to thread-local and shared read-only locations.  ...  Acknowledgements We would like to thank Sarita Adve and anonymous reviewers for their valuable suggestions.  ... 
doi:10.1109/isca.2012.6237045 dblp:conf/isca/SinghNMMM12 fatcat:bmo7mpp465eohp2wm6odiyvs4q

Efficient high-level abstractions for web programming

Julien Richard-Foy, Olivier Barais, Jean-Marc Jézéquel
2013 Proceedings of the 12th international conference on Generative programming: concepts & experiences - GPCE '13  
One challenge comes from the fact that the application's logic is scattered into heterogeneous clients and servers, making it difficult to share code between both sides or to move code from one side to  ...  without trading this ease of engineering for performance?  ...  This approach shares the same benefits and limitations as embedded DSLs for defining language units.  ... 
doi:10.1145/2517208.2517227 dblp:conf/gpce/Richard-FoyBJ13 fatcat:x6c5nvjvurcwtai4ut7skezjsi

Efficient high-level abstractions for web programming

Julien Richard-Foy, Olivier Barais, Jean-Marc Jézéquel
2014 SIGPLAN notices  
One challenge comes from the fact that the application's logic is scattered into heterogeneous clients and servers, making it difficult to share code between both sides or to move code from one side to  ...  without trading this ease of engineering for performance?  ...  This approach shares the same benefits and limitations as embedded DSLs for defining language units.  ... 
doi:10.1145/2637365.2517227 fatcat:m24rrvcll5budgumnedglxt77u

Global tagging optimization by type inference

Fritz Henglein
1992 Proceedings of the 1992 ACM conference on LISP and functional programming - LFP '92  
The computed information can also be used for nnboxing and closure allocation (reference escape) analysis, although this is not pursued in this paper.  ...  Tag handling accounts for a substantial amount of execution cost in latently typed languages such as Common LISP and structured data, especially in lists: Steenkiste and Hennessy report that 80~o of all  ...  Thanks also to Thomas Breuel for sharing his thoughts on compile time optimization of dynamically typed languages with me.  ... 
doi:10.1145/141471.141542 dblp:conf/lfp/Henglein92 fatcat:36byej6fwzcytpm7ll6hinpym4

Global tagging optimization by type inference

Fritz Henglein
1992 ACM SIGPLAN Lisp Pointers  
The computed information can also be used for nnboxing and closure allocation (reference escape) analysis, although this is not pursued in this paper.  ...  Tag handling accounts for a substantial amount of execution cost in latently typed languages such as Common LISP and structured data, especially in lists: Steenkiste and Hennessy report that 80~o of all  ...  Thanks also to Thomas Breuel for sharing his thoughts on compile time optimization of dynamically typed languages with me.  ... 
doi:10.1145/141478.141542 fatcat:wprmxfry55gfti35lceaka2hza

Fast, Flexible, Polyglot Instrumentation Support for Debuggers and other Tools

Michael Van De Vanter, Chris Seaton, Michael Haupt, Christian Humer, Thomas Würthinger
2018 The Art, Science, and Engineering of Programming  
tools for high-performance languages.  ...  Truffle Instrumentation includes: (1) low overhead capture of execution events by dynamically adding "wrapper" nodes to executing ASTs; (2) extensions to the Language Implementation Framework that allow  ...  Acknowledgements We are indebted to members of the Virtual Machine Research Group at Oracle Labs and the Institute of System Software at the Johannes Kepler University Linz for creating the language implementation  ... 
doi:10.22152/programming-journal.org/2018/2/14 fatcat:zwne255nubhehdxv74vygx55ge

DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing [article]

Pengcheng He, Jianfeng Gao, Weizhu Chen
2021 arXiv   pre-print
For example, the mDeBERTa Base achieves a 79.8% zero-shot cross-lingual accuracy on XNLI and a 3.6% improvement over XLM-R Base, creating a new SOTA on this benchmark.  ...  We thus propose a new gradient-disentangled embedding sharing method that avoids the tug-of-war dynamics, improving both training efficiency and the quality of the pre-trained model.  ...  For pre-training, we use Adam [29] as the optimizer with weight decay [28]. For fine-tuning, we use Adam [29] as the optimizer for a fair comparison.  ... 
arXiv:2111.09543v2 fatcat:2hwqqhxr6jchtd63p4vgqodkc4

ISOLATOR

Sriram Rajamani, G. Ramalingam, Venkatesh Prasad Ranganath, Kapil Vaswani
2009 Proceeding of the 14th international conference on Architectural support for programming languages and operating systems - ASPLOS '09  
We present ISOLATOR, an algorithm that guarantees isolation for well-behaved threads of a program that obey a locking discipline even in the presence of ill-behaved threads that disobey the locking discipline  ...  Our instrumentation scheme requires access only to the code of well-behaved threads.  ...  Acknowledgements We would like to acknowledge Ben Zorn, Darko and Rahul Nagpal for their inputs during the initial discussions.  ... 
doi:10.1145/1508244.1508266 dblp:conf/asplos/RajamaniRRV09 fatcat:gxqtxhjddvekrfvqlzvpamt3ny

The Wisconsin Wind Tunnel project

Mark D. Hill, James R. Larus, David A. Wood
1994 SIGARCH Computer Architecture News  
This document lists contributors to the Wisconsin Wind Tunnel Project, gives a brief description of the project, and presents references and abstracts to its principal papers, including how to obtain them  ...  Richards, R. Y. Wang, T. E. Anderson, and J. R. Larus. Experience with a language for writing coherence protocols.  ...  In Proceedings of the Sixth International conference on Architectural Support for Programming Languages and Operating Systems (ASP-LOS VI), Pages 61-75, October 1994. S. Chandra and J. R. Larus.  ... 
doi:10.1145/192537.192543 fatcat:rvtgkgeonnba3cdbociaiglrdq

Evaluation of a just-in-time compiler retrofitted for PHP

Michiaki Tatsubori, Akihiko Tozawa, Toyotaro Suzumura, Scott Trent, Tamiya Onodera
2010 Proceedings of the 6th ACM SIGPLAN/SIGOPS international conference on Virtual execution environments - VEE '10  
These results show that the acceleration of dynamic scripting language processing does matter in a realistic Web application server environment.  ...  This paper summarizes a study of the optimization of PHP script processing.  ...  Acknowledgments We thank anonymous reviewers of this paper for their insightful comments, constructive criticism, and advices, which were largely reflected on the final version of this paper.  ... 
doi:10.1145/1735997.1736015 dblp:conf/vee/TatsuboriTSTO10 fatcat:6bsphrtzh5gwdecqerhvskmyyq

NUMA policies and their relation to memory architecture

William J. Bolosky, Michael L. Scott, Robert P. Fitzgerald, Robert J. Fowler, Alan L. Cox
1991 Proceedings of the fourth international conference on Architectural support for programming languages and operating systems - ASPLOS-IV  
We compare the performance of our optimal policy with that of three implementable policies (two of which appear in previous work), on a variety of applications, with varying relative speeds for page moves  ...  They also indicate that programs for NUMA machines must be written with care to obtain the best performance.  ...  The optimal placement behavior for a shared page depends on the relative costs of page moves to local, global and remote references.  ... 
doi:10.1145/106972.106994 dblp:conf/asplos/BoloskySFFC91 fatcat:cf3yu7o5cbczvnannrxmuryyya

Multitasking Inhibits Semantic Drift [article]

Athul Paul Jacob, Mike Lewis, Jacob Andreas
2021 arXiv   pre-print
When intelligent agents communicate to accomplish shared goals, how do these goals shape the agents' language?  ...  We study the dynamics of learning in latent language policies (LLPs), in which instructor agents generate natural-language subgoal descriptions and executor agents map these descriptions to low-level actions  ...  Acknowledgments We thank Hengyuan Hu for assistance in reproducing the original work and MIT Supercloud for compute resources.  ... 
arXiv:2104.07219v1 fatcat:gbookl2nmzaadcnrwdg3efz7yq

An orchestration language for parallel objects

Laxmikant V. Kalé, Mark Hills, Chao Huang
2004 Proceedings of the 7th workshop on Workshop on languages, compilers, and run-time support for scalable systems - LCR '04  
This facility is used to optimize execution, including via dynamic load balancing. Having multiple sets of VPs for distinct parts of a simulation leads to improved modularity and performance.  ...  Charm++, a parallel object language based on the idea of virtual processors, has attained significant success in efficient parallelization of applications.  ...  Shared data is stored into pages which have their home processors, Local copies is allowed for the consumer of any particular page, and a synchronization step is required at the end of each phase.  ... 
doi:10.1145/1066650.1066658 fatcat:rp3nqz6djbafpm6apmqhjbbfzi

ReactiFi: Reactive Programming of Wi-Fi Firmware on Mobile Devices [article]

Artur Sterz, Matthias Eichholz, Ragnar Mogk, Lars Baumgärtner, Pablo Graubner, Matthias Hollick, Mira Mezini, Bernd Freisleben
2020 arXiv   pre-print
This impedes rapid prototyping and deployment of novel network services/applications and hinders continuous performance optimization in Wi-Fi networks, since expert knowledge is required for both the used  ...  Third, it limits dynamic changes of dependencies between computations to dynamic branching, in order to enable static reasoning about the order of computations.  ...  However, since Flask targets sensor networks, the semantics of Flask are optimized for a system that allows less control, leading to a language with fewer guarantees.  ... 
arXiv:2010.00354v1 fatcat:lygneoneanc53i7tsjd264vyky
« Previous Showing results 1 — 15 out of 74,774 results