Filters








132,081 Hits in 3.9 sec

Using annotations to reduce dynamic optimization time

Chandra Krintz, Brad Calder
2001 SIGPLAN notices  
Annotations consist of analysis information collected off-line and are incorporated into Java programs. The annotations are then used by dynamic compilers to guide optimization.  ...  The annotations we present reduce compilation overhead incurred at all stages of compilation and optimization as well as enable complex optimizations to be performed dynamically.  ...  Acknowledgments We would like to thank the anonymous reviewers for providing useful comments on this paper. This work was funded in part by NSF CAREER grant No.  ... 
doi:10.1145/381694.378831 fatcat:yhquuphqwnduldyxy2qymm7hky

Using annotations to reduce dynamic optimization time

Chandra Krintz, Brad Calder
2001 Proceedings of the ACM SIGPLAN 2001 conference on Programming language design and implementation - PLDI '01  
Annotations consist of analysis information collected off-line and are incorporated into Java programs. The annotations are then used by dynamic compilers to guide optimization.  ...  The annotations we present reduce compilation overhead incurred at all stages of compilation and optimization as well as enable complex optimizations to be performed dynamically.  ...  Acknowledgments We would like to thank the anonymous reviewers for providing useful comments on this paper. This work was funded in part by NSF CAREER grant No.  ... 
doi:10.1145/378795.378831 dblp:conf/pldi/KrintzC01 fatcat:qbzt3gdzxjeapgjwo7io25kuvm

The benefits and costs of DyC's run-time optimizations

Brian Grant, Markus Mock, Matthai Philipose, Craig Chambers, Susan J. Eggers
2000 ACM Transactions on Programming Languages and Systems  
The dynamic optimizations are preplanned at static compile time in order to reduce their run-time cost; we call this staging.  ...  costs. 1 We are referring to systems that dynamically optimize (or specialize) portions of programs and stage their analysis across static-compile and execution times.  ...  ACKNOWLEDGMENTS We owe thanks to Tryggve Fossum and John O'Donnell for the source for the Alpha version of the Multiflow compiler.  ... 
doi:10.1145/365151.367161 fatcat:bfdhmbxdyvcyjjxrgvlymynbwq

An evaluation of staged run-time optimizations in DyC

Brian Grant, Matthai Philipose, Markus Mock, Craig Chambers, Susan J. Eggers
1999 SIGPLAN notices  
Previous selective dynamic compilation systems have demonstrated that dynamic compilation can achieve performance improvements at low cost on small kernels, but they have had difficulty scaling to larger  ...  Polyvariant specialization allows multiple compiled versions of a division to be produced, each specialized for different values of the run-time-constant variables.  ...  Acknowledgments We owe thanks to David Grove and the anonymous PLDI reviewers for improving the quality of our discussion, and to Tryggve Fossum and John O'Donnell for the source for the Alpha version  ... 
doi:10.1145/301631.301683 fatcat:wjl6ahz2xngc5krqpleys5hwqq

An evaluation of staged run-time optimizations in DyC

Brian Grant, Matthai Philipose, Markus Mock, Craig Chambers, Susan J. Eggers
1999 Proceedings of the ACM SIGPLAN 1999 conference on Programming language design and implementation - PLDI '99  
Previous selective dynamic compilation systems have demonstrated that dynamic compilation can achieve performance improvements at low cost on small kernels, but they have had difficulty scaling to larger  ...  Polyvariant specialization allows multiple compiled versions of a division to be produced, each specialized for different values of the run-time-constant variables.  ...  Acknowledgments We owe thanks to David Grove and the anonymous PLDI reviewers for improving the quality of our discussion, and to Tryggve Fossum and John O'Donnell for the source for the Alpha version  ... 
doi:10.1145/301618.301683 dblp:conf/pldi/GrantPMCE99 fatcat:x5pwez5bzrdljegw2z5tyocieq

Pipelined Memory Controllers For Dsp Real-Time Applications Handling Unpredictable Data Accesses

Bertrand Le Gal, Emmanuel Casseau, Eric Martin
2005 Zenodo  
We show that our design flow allows the designer to freely optimize each unit of his design.  ...  CONCLUSION In this paper we have presented a new sequencer architecture for DSP applications with dynamic memory accesses.  ...  Computation Balancing Metric In a second time, the dynamic address computation balancing algorithm is applied to the previously annotated graph in order to move some dynamic address computations from datapath  ... 
doi:10.5281/zenodo.39127 fatcat:etyv4ql3dff7novwrpyphfsap4

Transient Typechecks Are (Almost) Free

Richard Roberts, Stefan Marr, Michael Homer, James Noble, Michael Wagner
2019 European Conference on Object-Oriented Programming  
A virtual machine can employ standard just-in-time optimizations to reduce the overhead of transient checks to near zero.  ...  This performance impact discourages the use of type annotations because adding types to a program makes the program slower.  ...  Being able to tie checks to the shapes in this way is critical for reducing the overhead of dynamic checking.  ... 
doi:10.4230/lipics.ecoop.2019.5 dblp:conf/ecoop/RobertsMH019 fatcat:mkkfuiwz2bbmbia4bxpgmwh2hi

Calpa

Markus Mock, Craig Chambers, Susan J. Eggers
2000 Proceedings of the 33rd annual ACM/IEEE international symposium on Microarchitecture - MICRO 33  
order to select the most beneficial annotations.  ...  Calpa combines execution frequency and value profile information with a model of dynamic compilation cost and dynamically generated code benefit to choose run-time constants and other dynamic compilation  ...  help in using it.  ... 
doi:10.1145/360128.360158 fatcat:xygspnszy5b53ntjlk24ujl2ru

Dynamic compact visualizations for augmented reality

Markus Tatzgern, Denis Kalkofen, Dieter Schmalstieg
2013 2013 IEEE Virtual Reality (VR)  
We present methods to transfer compact visualizations to dynamic AR settings and achieve interactive frame rates even on limited-resource hardware, such as mobile phones.  ...  In this paper, we extend the approach to annotations, which are a major source of information in AR, and create compact layouts of annotations and annotated explosion diagrams.  ...  CONCLUSION AND FUTURE WORK We applied a combined filter and layout optimization to create compact annotations, a data type frequently used in AR applications.  ... 
doi:10.1109/vr.2013.6549347 dblp:conf/vr/TatzgernKS13 fatcat:bonx5reklrd5jngsfzxl5yu2vm

Transient Typechecks are (Almost) Free [article]

Richard Roberts, Stefan Marr, Michael Homer, James Noble
2019 arXiv   pre-print
A virtual machine can employ standard just-in-time optimizations to reduce the overhead of transient checks to near zero.  ...  This performance impact discourages the use of type annotations because adding types to a program makes the program slower.  ...  Being able to tie checks to the shapes in this way is critical for reducing the overhead of dynamic checking.  ... 
arXiv:1807.00661v3 fatcat:24rs4mcllbftzegbnckjfpr2pq

Server-side type profiling for optimizing client-side JavaScript engines

Madhukar N. Kedlaya, Behnam Robatmili, Ben Hardekopf
2015 Proceedings of the 11th Symposium on Dynamic Languages - DLS 2015  
In this paper we describe a method to significantly reduce the number of deoptimizations observed by client-side JavaScript engines by using ahead-of-time profiling on the server-side.  ...  Modern JavaScript engines optimize hot functions using a JIT compiler along with type information gathered by an online profiler.  ...  Acknowledgments We would like to thank the the anonymous reviewers and developers at Mozilla for their valuable input.  ... 
doi:10.1145/2816707.2816719 dblp:conf/dls/KedlayaRH15 fatcat:7eatq2o73jgnjajujf42uk4bau

Architectural and compiler strategies for dynamic power management in the COPPER project

Azevedo, Cornea, Issenin, Gupta, Dutt, Nicolau, Veidenbaum
2001 Innovative Architecture for Future Generation High-Performance Processors and Systems IWIA-01  
For a range of embedded system applications in mission critical and energy constrained scenarios it is important to be able to dynamically control power consumption in response to changing power availability  ...  In this paper, we present our approach to dynamic adaptation of system power consumption and application performance through microarchitectural and software strategies.  ...  The information computed by the compiler, such as time, energy profile and code characteristics, is also carried down to the run-time system using tables and code annotations.  ... 
doi:10.1109/iwia.2001.955194 fatcat:l6oyaaycqfbzzg76icbo6sdeti

Reducing the overhead of dynamic compilation

Chandra J. Krintz, David Grove, Vivek Sarkar, Brad Calder
2001 Software, Practice & Experience  
total time of 14 to 26%.  ...  Methods are compiled according to this priority scheme so that performance-critical methods are invoked using optimized code as soon as possible.  ...  Thanks also to the entire Jalapeño team for their contributions to the infrastructure used to obtain the experimental results reported in this paper.  ... 
doi:10.1002/spe.384 fatcat:koetg3glpfe5pkvobcclvkiauy

Server-side type profiling for optimizing client-side JavaScript engines

Madhukar N. Kedlaya, Behnam Robatmili, Ben Hardekopf
2015 SIGPLAN notices  
In this paper we describe a method to significantly reduce the number of deoptimizations observed by client-side JavaScript engines by using ahead-of-time profiling on the server-side.  ...  Modern JavaScript engines optimize hot functions using a JIT compiler along with type information gathered by an online profiler.  ...  Acknowledgments We would like to thank the the anonymous reviewers and developers at Mozilla for their valuable input.  ... 
doi:10.1145/2936313.2816719 fatcat:x2bcizve5vgavnguzbjcily7je

Improving performance of optimized kernels through fast instantiations of templates

Minhaj Ahmad Khan, H.-P. Charles, D. Barthou
2009 Concurrency and Computation  
It represents an effective solution in terms of reduced overhead incurring at static compile time and dynamic compile time.  ...  As the optimizations have already been performed at static compile time, the overhead of code generation is much reduced than the overhead of other dynamic code generation and optimization systems.  ...  Another dynamic optimization framework, ADORE [7] , is used to perform the dynamic cache prefetching.  ... 
doi:10.1002/cpe.1333 fatcat:75ko6bolenettatywc6jnqoaay
« Previous Showing results 1 — 15 out of 132,081 results