648 Hits in 3.5 sec

Evaluation of the Task Programming Model in the Parallelization of Wavefront Problems

A J Dios, R Asenjo, A Navarro, F Corbera, E L Zapata
2010 2010 IEEE 12th International Conference on High Performance Computing and Communications (HPCC)  
Precisely, we think that it is better to formulate the parallelization of this wavefront-based programs in terms of logical tasks, instead of threads for several reasons: more efficient matching of computations  ...  This paper analyzes the applicability of the task programming model in the parallelization of generic wavefront problems.  ...  This technique works by analyzing the points of entry and exit of all program and library functions. It can detect program modules when they are loaded at runtime.  ... 
doi:10.1109/hpcc.2010.78 dblp:conf/hpcc/DiosANCZ10 fatcat:sxymh6juenf43m2g4a4zulqp2u

High-level template for the task-based parallel wavefront pattern

Antonio J. Dios, Rafael Asenjo, Angeles Navarro, Francisco Corbera, Emilio L. Zapata
2011 2011 18th International Conference on High Performance Computing  
This paper analyzes the applicability of the task-programming model to the parallelization of the wavefront pattern.  ...  Computations for this type of problem are characterized by a data dependency pattern across a data space.  ...  Introduction Wavefront is a programming pattern that appears in scientific applications such as those based on dynamic programming [1] or sequence alignment [2] .  ... 
doi:10.1109/hipc.2011.6152717 dblp:conf/hipc/DiosANCZ11 fatcat:cur7su6h4fceljj3n6rjgw2hgy

Dual-state systolic architectures for up/downdating RLS adaptive filtering

S.F. Hsieh, K.J.R. Liu, K. Yao
1992 IEEE transactions on circuits and systems - 2, Analog and digital signal processing  
A dual-state up/downdating systolic array for the recursive residual estimation is also shown in Fig. 1 . V.  ...  This paper considers design of high-speed architectures for two classes of tree-based decoders: the Huffman decoder [3], and the Viterbi decoder (which is based on dynamic programming calculations) [4]  ... 
doi:10.1109/82.145296 fatcat:ztsmvhbstng5xos5bevsnsikn4

Compiler Techniques for Massively Scalable Implicit Task Parallelism

Timothy G. Armstrong, Justin M. Wozniak, Michael Wilde, Ian T. Foster
2014 SC14: International Conference for High Performance Computing, Networking, Storage and Analysis  
Swift/T is a high-level language for writing concise, deterministic scripts that compose serial or parallel codes implemented in lower-level programming models into large-scale parallel applications.  ...  We present a comprehensive set of compiler techniques for data-driven task parallelism, including novel compiler optimizations and intermediate representations.  ...  That is, program logic can be expressed without explicit concurrency, communication, or data partitioning.  ... 
doi:10.1109/sc.2014.30 dblp:conf/sc/ArmstrongWWF14 fatcat:fn5th2mbljhavelopcxrrhljte

Temporal State Machines: Using temporal memory to stitch time-based graph computations [article]

Advait Madhavan, Matthew Daniels, Mark Stiles
2020 arXiv   pre-print
Race logic, an arrival-time-coded logic family, has demonstrated energy and performance improvements for applications ranging from dynamic programming to machine learning.  ...  We leverage analog memristor-based temporal memories to design a such a state machine that operates purely on time-coded wavefronts.  ...  Each cell consists of two transistors, one for programming and the other for operation, and a level shifter.  ... 
arXiv:2009.14243v1 fatcat:ej432mptcbhc5psojpachbo564

Using Tasks to Create Your Own Algorithms [chapter]

Michael Voss, Rafael Asenjo, James Reinders
2019 Pro TBB  
But there is nothing that prevents us from venturing into these deeper waters and starting to code our algorithms directly with tasks, from building our own high-level templates for future use on top of  ...  Should we just give up and remain prisoners of the high-level features of the programing model? Of course not!  ...  Wavefront is a programming pattern that appears in scientific applications such as those based in dynamic programming or sequence alignment.  ... 
doi:10.1007/978-1-4842-4398-5_10 fatcat:ispyjf36z5eabgwewvieyynz7a

Constructing Induction Rules for Deductive Synthesis Proofs

Alan Bundy, Lucas Dixon, Jeremy Gow, Jacques Fleuriot
2006 Electronical Notes in Theoretical Computer Science  
Synthesis of programs with iteration or recursion requires inductive proof, but standard techniques for the construction of appropriate induction rules are restricted to recycling the recursive structure  ...  We describe novel computational techniques for constructing induction rules for deductive synthesis proofs.  ...  Programs will be represented as recursive functions and specifications as formulae within the same higherorder, typed, constructive logic.  ... 
doi:10.1016/j.entcs.2005.08.003 fatcat:wgcdnm2yxvdl3bxrt2wptuuezi


Rafael Ubal, Byunghyun Jang, Perhaad Mistry, Dana Schaa, David Kaeli
2012 Proceedings of the 21st international conference on Parallel architectures and compilation techniques - PACT '12  
Accurate simulation is essential for the proper design and evaluation of any computing platform.  ...  Focusing on a model of the AMD Radeon 5870 GPU, we address program emulation correctness, as well as architectural simulation accuracy, using AMD's OpenCL benchmark suite.  ...  The authors would also like to thank Norman Rubin (AMD) for his advice and feedback on this work.  ... 
doi:10.1145/2370816.2370865 dblp:conf/IEEEpact/UbalJMSK12 fatcat:ixqg7hugsnarxph4vltnywkj2q

Formal methods for automated program improvement [chapter]

Peter Madden
1994 Lecture Notes in Computer Science  
For example, we are able to automate the identification of efficient recursive data-types which usua11y correspond to eureka steps in "pure" transformational techniques such as unfoldjfold.  ...  However, formal methods, and in partieular theorem proving, are providing a growing foundation of techniques for automatie program development (synthesis, improvement, transformation and verification).  ...  We have described two novel implemented techniques for the automatie generation of high quality (efficient and reliable) software using the proofs as programs paradigm.  ... 
doi:10.1007/3-540-58467-6_32 fatcat:jckmgdfumngshiffwn7ibcsc5q

Guest Editors' Introduction to Special Issue on Advances in DSP System Design

J. Takala, W. J. Gross, W. Sung
2013 Journal of Signal Processing Systems  
Lee and Sung propose a cell-to-cell interference (CCI) cancellation technique for multi-level NAND flash memory in their paper Least Squares Based Coupling Cancellation for MLC NAND Flash Memory with a  ...  In A Fast Recursive Algorithm and Architecture for Pruned Bit-Reversal Interleavers, Mansour describes an algorithm and architecture for implementing interleavers used in communications applications such  ...  In A Fast Recursive Algorithm and Architecture for Pruned Bit-Reversal Interleavers, Mansour describes an algorithm and architecture for implementing interleavers used in communications applications such  ... 
doi:10.1007/s11265-013-0731-9 fatcat:gzwdsy47ibcwjawy5oo5v55ka4

Adventures in Mathematical Reasoning [article]

Toby Walsh
2020 arXiv   pre-print
For instance, we proposed two new orderings which allow unblocking, definition unfolding, and mutual recursion to be added to rippling in a principled (and terminating) fashion.  ...  Proof planning An important idea explored within the DReaM group is the separation of logic and control.  ... 
arXiv:2008.09067v1 fatcat:d6lxjm6hy5axzjqulqlu47nitq

FastLSA: A Fast, Linear-Space, Parallel and Sequential Algorithm for Sequence Alignment

Adrian Driga, Paul Lu, Jonathan Schaeffer, Duane Szafron, Kevin Charter, Ian Parsons
2006 Algorithmica  
For two DNA or protein sequences of length m and n, full-matrix (FM), dynamic programming alignment algorithms such as Needleman-Wunsch and Smith-Waterman take O(m × n) time and use a possibly prohibitive  ...  To further improve the performance of FastLSA, we have parallelized it using a simple but effective form of wavefront parallelism.  ...  For each Fill Cache subproblem, the logical dynamic programming matrix is already split in k 2 smaller matrices, the logical sub-matrices introduced earlier.  ... 
doi:10.1007/s00453-006-1217-y fatcat:ymjzhw2uxfcbljm6yvwgzekz7u

Rippling: A heuristic for guiding inductive proofs

Alan Bundy, Andrew Stevens, Frank van Harmelen, Andrew Ireland, Alan Smaill
1993 Artificial Intelligence  
Smaill, Rippling: a heuristic for guiding inductive proofs, Artificial Intelligence 62 (1993) 185-253.  ...  This tactic significantly reduces the search for a proof of a wide variety of inductive theorems.  ...  We wish to thank our colleagues in the Edinburgh Mathematical Reasoning Group, three anonymous CADE-10 referees and two anonymous AIJ referees for feedback on this paper.  ... 
doi:10.1016/0004-3702(93)90079-q fatcat:aw3xcqu3zjezjlzae4o45kbwtq

Tutorial notes: Reasoning about logic programs [chapter]

Alan Bundy
1992 Lecture Notes in Computer Science  
They are an introduction to the techniques of reasoning about logic programs, in particular for synthesizing, verifying, transforming and proving termination of logic programs.  ...  These are tutorial notes for LPSS-92: the Logic Programming Summer School organised by the CompuLog Esprit Network of Excellence in September 1992.  ...  Introduction In this tutorial we will describe techniques for reasoning about logic programs Why should we want to reason about logic programs?  ... 
doi:10.1007/3-540-55930-2_18 fatcat:ca636fnvxrgerhtkmsyr54z5tu

Parallel Tiled Code for Computing General Linear Recurrence Equations

Włodzimierz Bielecki, Piotr Błaszyński
2021 Electronics  
The wavefront technique is used to achieve parallelism, and the generated code conforms to the OpenMP C/C++ standard.  ...  that program.  ...  The parallelism is achieved using the wavefront technique and presented with the code that conforms to the OpenMP standard.  ... 
doi:10.3390/electronics10172050 fatcat:dhvcgnpdmjeqlnyxaihxxnl7pe
« Previous Showing results 1 — 15 out of 648 results