Filters








208,392 Hits in 2.7 sec

Sampling Optimized Code for Type Feedback

Olivier Flückiger, Andreas Wälchli, Sebastián Krynski, Jan Vitek
2020 Zenodo  
Based on the sampled profiles, we are able to detect when the native code produced by \v{R} is specialized for stale type feedback and recompile it to more type-specific code.  ...  Once the program is running optimized code, there are no means to notice that an opportunity for optimization has been missed.  ...  With this additional profiler we specifically address the issue of optimized code being compiled for stale type feedback.  ... 
doi:10.5281/zenodo.4066844 fatcat:whrahuyljnf5xfop6yjkfw5qii

Sampling Optimized Code for Type Feedback [article]

Olivier Flückiger and Andreas Wälchli and Sebastián Krynski and Jan Vitek
2020 pre-print
Based on the sampled profiles, we are able to detect when the native code produced by Ř is specialized for stale type feedback and recompile it to more type-specific code.  ...  We show that sampling adds an overhead of less than 3 type feedback within milliseconds.  ...  With this additional profiler we specifically address the issue of optimized code being compiled for stale type feedback.  ... 
doi:10.1145/3426422.3426984 arXiv:2010.02080v1 fatcat:ochj4vgysfa63mgvxako32sbwi

Online feedback-directed optimization of Java

Matthew Arnold, Michael Hind, Barbara G. Ryder
2002 Proceedings of the 17th ACM SIGPLAN conference on Object-oriented programming, systems, languages, and applications - OOPSLA '02  
This profile information is used to drive several traditional optimizations, as well as a novel algorithm for performing feedback-directed control flow graph node splitting.  ...  This paper describes the implementation of an online feedback-directed optimization system. The system is fully automatic; it requires no prior (offline) profiling run.  ...  We also thank Stephen Fink, David Grove, and Peter Sweeney for the helpful discussions about adaptive optimization. We are grateful to Martin Trapp for supplying the loop unrolling implementation.  ... 
doi:10.1145/582431.582432 fatcat:gsl4mu5r2vh4znpftmomf5b6ta

Online feedback-directed optimization of Java

Matthew Arnold, Michael Hind, Barbara G. Ryder
2002 SIGPLAN notices  
This profile information is used to drive several traditional optimizations, as well as a novel algorithm for performing feedback-directed control flow graph node splitting.  ...  This paper describes the implementation of an online feedback-directed optimization system. The system is fully automatic; it requires no prior (offline) profiling run.  ...  We also thank Stephen Fink, David Grove, and Peter Sweeney for the helpful discussions about adaptive optimization. We are grateful to Martin Trapp for supplying the loop unrolling implementation.  ... 
doi:10.1145/583854.582432 fatcat:badoqwak2ng2vhgiizq7uhg4xi

Online feedback-directed optimization of Java

Matthew Arnold, Michael Hind, Barbara G. Ryder
2002 Proceedings of the 17th ACM SIGPLAN conference on Object-oriented programming, systems, languages, and applications - OOPSLA '02  
This profile information is used to drive several traditional optimizations, as well as a novel algorithm for performing feedback-directed control flow graph node splitting.  ...  This paper describes the implementation of an online feedback-directed optimization system. The system is fully automatic; it requires no prior (offline) profiling run.  ...  We also thank Stephen Fink, David Grove, and Peter Sweeney for the helpful discussions about adaptive optimization. We are grateful to Martin Trapp for supplying the loop unrolling implementation.  ... 
doi:10.1145/582419.582432 dblp:conf/oopsla/ArnoldHR02 fatcat:rymxxmbsd5eslkxxaxa5fqhzwa

Eliminating synchronization overhead in automatically parallelized programs using dynamic feedback

Pedro C. Diniz, Martin C. Rinard
1999 ACM Transactions on Computer Systems  
The generated code uses dynamic feedback to automatically choose the best synchronization optimization policy.  ...  We have also performed a theoretical analysis which provides, under certain assumptions, a guaranteed optimality bound for dynamic feedback relative to a hypothetical (and unrealizable) optimal algorithm  ...  ACKNOWLEDGMENTS We wish to thank the anonymous referees for their many useful comments and suggestions.  ... 
doi:10.1145/312203.312210 fatcat:jhbc6b6rbbcjlprtvqpg3fu7ji

Reconciling responsiveness with performance in pure object-oriented languages

Urs Hölzle, David Ungar
1996 ACM Transactions on Programming Languages and Systems  
Type feedback speculatively inlines dynamically-dispatched calls based on profile information that predicts likely receiver classes.  ...  Dynamically-dispatched calls often limit the performance of object-oriented programs since object-oriented programming encourages factoring code into small, reusable units, thereby increasing the frequency  ...  Acknowledgments: We are very grateful to Bob Cmelik for making it possible to run SELF under Shade, to Mark D. Hill for Dinero, and to Gordon Irlam for Spanner.  ... 
doi:10.1145/233561.233562 fatcat:twcp4w3hxjactdnqbkhlvexfrq

Improved type specialization for dynamic scripting languages

Madhukar N. Kedlaya, Jared Roesch, Behnam Robatmili, Mehrdad Reshadi, Ben Hardekopf
2013 Proceedings of the 9th symposium on Dynamic languages - DLS '13  
Type feedback and type inference are two common methods used to optimize dynamic languages such as JavaScript.  ...  Our results show significant speedups when using these low-overhead strategies, ranging from 1.2× to 4× over an implementation that does not perform type feedback or type inference based optimizations.  ...  Acknowledgments We would like to thank Cȃlin Caşcaval and the MCJS team at Qualcomm Research Silicon Valley (QRSV), as well as the anonymous reviewers for their valuable input.  ... 
doi:10.1145/2508168.2508177 dblp:conf/dls/KedlayaRRRH13 fatcat:lkoth7znezclfppthjgpzh6dgi

User-Advertisement Simulation: An Approach for Measuring the Accuracy of Collaborative Recommender Systems without Dataset

Niki Shakeri, Jinan Fiaidhi, Sabah Mohammed, Tia-hoon Kim
2014 International Journal of u- and e- Service, Science and Technology  
Recommender systems are now popular both commercially and in the research community, where many approaches have been suggested for providing recommendations.  ...  However, evaluating the affectivity of recommender systems is a challenging problem and most of the approaches used for evaluation are based on using some sort of a dataset.  ...  Equation 1 defines the Optimization Parameter, which indicates the accuracy of the sample.  ... 
doi:10.14257/ijunesst.2014.7.5.02 fatcat:sp5vlytrzvfo3h3zl2277kkk6a

Design of Differential Quantization for Low Bitrate Channel State Information Feedback in MIMO-OFDM Systems

Woon Hau Chin, Chau Yuen
2008 VTC Spring 2008 - IEEE Vehicular Technology Conference  
The feedback of channel state information have always posed a problem for the design of a communications system where the information is required at the transmitter.  ...  This paper discusses the use of differential quantization methods to reduce the number of feedback bits required.  ...  Wu for the helpful discussion on the IEEE 802.11n channel models.  ... 
doi:10.1109/vetecs.2008.180 dblp:conf/vtc/ChinY08 fatcat:pbxrmxu6bnbjpfe2zehg2xnctq

A Survey of Adaptive Optimization in Virtual Machines

M. Arnold, S.J. Fink, D. Grove, M. Hind, P.F. Sweeney
2005 Proceedings of the IEEE  
Today, mainstream virtual machine implementations include substantial infrastructure for online monitoring and profiling, runtime compilation, and feedback-directed optimization.  ...  His research interests include program language design and implementation, virtual machines, and adaptive optimization. Dr. Grove is a Member of the Association for Computing Machinery.  ...  ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers for their valuable feedback, P. Cheng for discussion of adaptive memory management, and L. Treacy for proofreading the paper.  ... 
doi:10.1109/jproc.2004.840305 fatcat:ryu35i6jjneztdaulv5uuozxhu

Memento mori: dynamic allocation-site-based optimizations

Daniel Clifford, Hannes Payer, Michael Stanton, Ben L. Titzer
2015 Proceedings of the 2015 ACM SIGPLAN International Symposium on Memory Management - ISMM 2015  
This paper presents a general approach for gathering temporal allocation site feedback that tackles both the general problem of object lifetime estimation and improves optimization of these problematic  ...  typed and untyped languages.  ...  The baseline code will warm up again and eventually be recompiled to new optimized code with new pretenuring and type feedback decisions.  ... 
doi:10.1145/2754169.2754181 dblp:conf/iwmm/CliffordPST15 fatcat:4k646jgtdjemrhkh5jteohfoey

Memento mori: dynamic allocation-site-based optimizations

Daniel Clifford, Hannes Payer, Michael Stanton, Ben L. Titzer
2015 SIGPLAN notices  
This paper presents a general approach for gathering temporal allocation site feedback that tackles both the general problem of object lifetime estimation and improves optimization of these problematic  ...  typed and untyped languages.  ...  The baseline code will warm up again and eventually be recompiled to new optimized code with new pretenuring and type feedback decisions.  ... 
doi:10.1145/2887746.2754181 fatcat:7o3cbwpjyfgr3b7mpfvzom3ebe

Subject index

1965 Information and Control  
VITERBI 80 Control Systems Feedback Control Optimization, A Computational Method for, C. W.  ...  SPINRAD 124 Pattern Recognition, An Asymptotic Simultaneous DiagonMization Pro- cedure for, JAC~ CAPON 264 S Sampling Theorem Sampling Theorem, Band-Limited Functions and the Sampling Theo- rem  ... 
doi:10.1016/s0019-9958(65)90462-6 fatcat:kevtbqzbbjckzmspvh43vss3jy

Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions [article]

Anvita Gupta, James Zou
2018 arXiv   pre-print
We apply the feedback-loop mechanism to two examples: 1) generating synthetic genes coding for antimicrobial peptides, and 2) optimizing synthetic genes for the secondary structure of their resulting peptides  ...  We propose a novel feedback-loop architecture, called Feedback GAN (FBGAN), to optimize the synthetic gene sequences for desired properties using an external function analyzer.  ...  We have demonstrated the usefulness of the feedback-loop mechanism in two use cases: 1) optimizing for genes that code for antimicrobial peptides (AMPs), and 2) optimizing for genes that code for alpha-helical  ... 
arXiv:1804.01694v1 fatcat:5r7qznqkbjcoxjhtn73qbksd6q
« Previous Showing results 1 — 15 out of 208,392 results