Filters








185 Hits in 7.4 sec

Finding optimum abstractions in parametric dataflow analysis

Xin Zhang, Mayur Naik, Hongseok Yang
2013 SIGPLAN notices  
. • We formulate the optimum abstraction problem for parametric dataflow analysis.  ...  We propose a technique to efficiently search a large family of abstractions in order to prove a query using a parametric dataflow analysis.  ...  This research was supported in part by DARPA contract #FA8750-12-2-0020, awards from Google and Microsoft, and EPSRC.  ... 
doi:10.1145/2499370.2462185 fatcat:3ex3uws25jedhc4kquz7wfstiy

Finding optimum abstractions in parametric dataflow analysis

Xin Zhang, Mayur Naik, Hongseok Yang
2013 Proceedings of the 34th ACM SIGPLAN conference on Programming language design and implementation - PLDI '13  
. • We formulate the optimum abstraction problem for parametric dataflow analysis.  ...  We propose a technique to efficiently search a large family of abstractions in order to prove a query using a parametric dataflow analysis.  ...  This research was supported in part by DARPA contract #FA8750-12-2-0020, awards from Google and Microsoft, and EPSRC.  ... 
doi:10.1145/2491956.2462185 dblp:conf/pldi/ZhangNY13 fatcat:5k5lpd5ipjhszi6srr4hxebmve

Computation of QoS While Composing Web Services

Khozema Ali, Dr. Tarun, Dr. Mohemmed
2017 International Journal of Advanced Computer Science and Applications  
Composition of web services is a process where a set of web services, heterogeneous in nature, are clubbed together in order to perform a specific task.  ...  Moreover, Effectiveness of different methods in terms of QoS while composing is also presented.  ...  At first, global QoS attributes are decomposed into local attributes in order to find the combination of optimum local QoS attributes for each of the service classes and a novel CGA optimization algorithm  ... 
doi:10.14569/ijacsa.2017.080343 fatcat:2xqd5yfkijfpbiv6sl2vu3vlx4

Towards Automatic High-Level Code Deployment on Reconfigurable Platforms: A Survey of High-Level Synthesis Tools and Toolchains

Mostafa W. Numan, Braden J. Phillips, Gavin S. Puddy, Katrina Falkner
2020 IEEE Access  
Dataflow descriptions can be defined at different levels of abstraction.  ...  For these a side-controller is generated using parametric polyhedral analysis to dynamically change the loop iteration speed at runtime such that these dependencies are not violated.  ... 
doi:10.1109/access.2020.3024098 fatcat:hk7s2deq6zgp5fnuwvm5k6jodu

A Model-Based Approach to Cognitive Radio Design

Jorg Lotze, Suhaib A. Fahmy, Juanjo Noguera, Linda E. Doyle
2011 IEEE Journal on Selected Areas in Communications  
She is currently the Director of CTVR, the Telecommunications Research Centre, a national research centre headquartered in Trinity College and based in five other universities in Ireland.  ...  Doyle is a member of faculty in the School of Engineering, University of Dublin, Trinity College, Ireland.  ...  Those could implement a genetic algorithm maximising an objective function given on a number of possible actions, to find the optimum radio configuration in a given situation.  ... 
doi:10.1109/jsac.2011.110217 fatcat:5zgyrpqtlbhcxmharxjkbnrkq4

A Highly Configurable High-Level Synthesis Functional Pattern Library

Lan Huang, Teng Gao, Dalin Li, Zihao Wang, Kangping Wang
2021 Electronics  
High-level synthesis (HLS) allows developers to design FPGA circuits more efficiently with a more familiar programming language, a higher level of abstraction, and automatic adaptation of timing constraints  ...  FPGA has recently played an increasingly important role in heterogeneous computing, but Register Transfer Level design flows are not only inefficient in design, but also require designers to be familiar  ...  The goal of the QPSO is to find the optimal solution for all particles in a multidimensional hypervolume.  ... 
doi:10.3390/electronics10050532 fatcat:weic35jgy5ccbplbfespsrcr3y

Abstraction refinement guided by a learnt probabilistic model

Radu Grigore, Hongseok Yang
2016 SIGPLAN notices  
The core challenge in designing an effective static program analysis is to find a good program abstraction -one that retains only details relevant to a given query.  ...  Our approach applies to parametric static analyses implemented in Datalog, and is based on counterexampleguided abstraction refinement.  ...  On abstraction refinement for program analyses in Datalog. In PLDI, 2014. [52] Xin Zhang, Mayur Naik, and Hongseok Yang. Finding optimum abstractions in parametric dataflow analysis.  ... 
doi:10.1145/2914770.2837663 fatcat:lr2g364qdrb7lmxkjzqubharf4

The EvoSpace Model for Pool-Based Evolutionary Algorithms

Mario García-Valdez, Leonardo Trujillo, Juan-J Merelo, Francisco Fernández de Vega, Gustavo Olague
2014 Journal of Grid Computing  
Figure 1 shows a graphical illustration of the main components and dataflow within the ESM.  ...  In this sense, what is particularly interesting about a Pool-EA is that it incorporates features from natural evolution that are abstracted away in common EA implementations.  ... 
doi:10.1007/s10723-014-9319-2 fatcat:fzybnosdlnedxln2ngudihrwwu

Accelerating Machine-Learning Algorithms on FPGAs using Pattern-Based Decomposition

Karthik Nagarajan, Brian Holland, Alan D. George, K. Clint Slatton, Herman Lam
2009 Journal of Signal Processing Systems  
Three such principal algorithms are the Parzen window-based, non-parametric estimation of Probability Density Functions (PDFs), K-means clustering and correlation.  ...  Machine-learning algorithms are employed in a wide variety of applications to extract useful information from data sets, and many are known to suffer from superlinear increases in computational time with  ...  Acknowledgement This work was supported in part by the I/UCRC Program of the National Science Foundation under Grant No. EEC-0642422.  ... 
doi:10.1007/s11265-008-0337-9 fatcat:gv567gkoxfajbelmaghfv224dy

Adding data parallelism to streaming pipelines for throughput optimization

Peng Li, Kunal Agrawal, Jeremy Buhler, Roger D. Chamberlain
2013 20th Annual International Conference on High Performance Computing  
In this paper, we consider the problem of mapping streaming pipelines -streaming applications where the graph is a linear chain -onto a set of computing resources in order to maximize its throughput.  ...  In both cases, we consider two network topologies -unidirectional chain and clique.  ...  For each chain, we can use the dynamic programming algorithm of Section V to compute an optimal mapping in polynomial time, but finding the global optimum requires n! such calls.  ... 
doi:10.1109/hipc.2013.6799119 dblp:conf/hipc/LiABC13 fatcat:x2pqxgzbsrer5imgcmxd5f5mqq

JobPruner: A machine learning assistant for exploring parameter spaces in HPC applications

Bruno Silva, Marco A.S. Netto, Renato L.F. Cunha
2018 Future generations computer systems  
The tool was evaluated with three real-world use cases from different domains including seismic analysis and agronomy.  ...  We observed the tool reduced 93% of jobs in a single experiment, while improving quality in most scenarios.  ...  Their algorithms can prune search spaces and find relationships in massive datasets. Weiss et al.  ... 
doi:10.1016/j.future.2018.02.002 fatcat:2ulyfldn5bedbc3wyv2k2pby5a

ASC: a stream compiler for computing with FPGAs

O. Mencer
2006 IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems  
Oskar Mencer received the B.Sc. degree in computer engineering at the Technion-Israel Institute of Technology, Haifa, Israel, and the M.S. and Ph.D. degrees from the  ...  Fig. 2 shows the levels of abstraction in ASC, which are described in detail below. 1) Algorithm analysis layer.  ...  For example, ShiftQ [2] , the nonprogrammable accelerator (NPA) for program-in-computer-out [1] (PICO) systems enables the user to quickly find an optimum hardware solution.  ... 
doi:10.1109/tcad.2005.857377 fatcat:4ccpxhmrijgcfg4cwqo6kiry6a

Buffer merging---a powerful technique for reducing memory requirements of synchronous dataflow specifications

Praveen K. Murthy, Shuvra S. Bhattacharyya
2004 ACM Transactions on Design Automation of Electronic Systems  
1 In this paper, we develop a new technique called buffer merging for reducing memory requirements of synchronous dataflow (SDF) specifications.  ...  Previous work on minimizing these buffer sizes has used two models: implementing each buffer separately (for example, in [1][2][18]), or using lifetime analysis techniques for sharing buffers (for example  ...  We modify this technique slightly to give an optimum, polynomial time algorithm for finding an MWMPC in a MERGE GRAPH.  ... 
doi:10.1145/989995.989999 fatcat:mnrt5e6xcfcpxe6xs4xare6um4

When polyhedral transformations meet SIMD code generation

Martin Kong, Richard Veras, Kevin Stock, Franz Franchetti, Louis-Noël Pouchet, P. Sadayappan
2013 SIGPLAN notices  
analysis can be performed.  ...  The stride optimization objectives yield the optimum value of σ 1 = 1 and σ 2 = 1. σ 1 = 1 implies that µ 2 = 1, which in turn makes γ 2,2 = 1.  ... 
doi:10.1145/2499370.2462187 fatcat:dzup6ptj6fdexpizsuow5xtpbi

When polyhedral transformations meet SIMD code generation

Martin Kong, Richard Veras, Kevin Stock, Franz Franchetti, Louis-Noël Pouchet, P. Sadayappan
2013 Proceedings of the 34th ACM SIGPLAN conference on Programming language design and implementation - PLDI '13  
analysis can be performed.  ...  The stride optimization objectives yield the optimum value of σ 1 = 1 and σ 2 = 1. σ 1 = 1 implies that µ 2 = 1, which in turn makes γ 2,2 = 1.  ... 
doi:10.1145/2491956.2462187 dblp:conf/pldi/KongVSFPS13 fatcat:2cqpl2tqobcjvbdlpoarmfbx3u
« Previous Showing results 1 — 15 out of 185 results