Filters








4,742 Hits in 4.3 sec

Transaction reordering

Gang Luo, Jeffrey F. Naughton, Curt J. Ellmann, Michael W. Watzke
2010 Data & Knowledge Engineering  
The advantages of the transaction reordering method are demonstrated through experiments with three commercial RDBMSs.  ...  , to improve the transaction throughput in an RDBMS.  ...  join operations [39] .  ... 
doi:10.1016/j.datak.2009.08.007 fatcat:uoowykxs2faflpagv5bzley2ui

Comparing Tail Duplication with Compensation Code in Single Path Global Instruction Scheduling [chapter]

David Gregg
2001 Lecture Notes in Computer Science  
When operations move above control flow joins, some code duplication is generally necessary to preserve semantics.  ...  Global instruction scheduling allows operations to move across basic block boundaries to create tighter schedules.  ...  Watson Research Center for providing us with the Chameleon experimental test-bed. Special thanks to Mayan Moudgill and Michael Gschwind.  ... 
doi:10.1007/3-540-45306-7_14 fatcat:dvbkexhrlrggpazdatybscgag4

Dynamic programming strikes back

Guido Moerkotte, Thomas Neumann
2008 Proceedings of the 2008 ACM SIGMOD international conference on Management of data - SIGMOD '08  
Our experimental results show that this reformulation of non-inner joins as complex predicates can improve optimization time by orders of magnitude, compared to known algorithms dealing with complex join  ...  Then, we present a technique to exploit this capability to efficiently handle the widest class of non-inner joins dealt with so far.  ...  We thank Guy Lohman for pointing out the importance of hypergraphs, Simone Seeger for her help preparing the manuscript, and Vasilis Vassalos and the anonymous referees for their help to improve the readability  ... 
doi:10.1145/1376616.1376672 dblp:conf/sigmod/MoerkotteN08 fatcat:t2jmpyxrvzckvhqorlbb2iikzq

A catalog of stream processing optimizations

Martin Hirzel, Robert Soulé, Scott Schneider, Buğra Gedik, Robert Grimm
2014 ACM Computing Surveys  
and a profitability experiment (when does it improve performance?).  ...  To make assumptions explicit and help with trade-offs, each optimization is presented with its safety constraints (when does it preserve correctness?)  ...  Join operators in particular have many implementation choices; for instance, an index lookup join may speed up join conditions like a > 5 with a B-tree.  ... 
doi:10.1145/2528412 fatcat:j56fyqw2hnazrjrdb2ogupmeme

4.-8. März 2019

Bernhard Radke, Thomas Neumann
2019 Datenbanksysteme für Business, Technologie und Web  
Large queries with, e. g., outer joins are quite common and having to fall back on simple greedy heuristics in this case is highly undesirable.  ...  Two developments have improved the situation: If we disallow crossproducts, graph-based DP algorithms have pushed the boundary of solvable problems to a few dozen relations.  ...  Another approach to incorporate the reordering constraints imposed by non-inner joins is to add compensation operators [WC18] .  ... 
doi:10.18420/btw2019-05 dblp:conf/btw/Radke019 fatcat:zqa43ctfbrfxjn5vujd36fn34a

Video encoder based on lifting transforms on graphs

E. Martinez-Enriquez, F. Diaz-de-Maria, Antonio Ortega
2011 2011 18th IEEE International Conference on Image Processing  
In this paper, we first consider a low complexity version of this transform, which can operate on subgraphs without significant loss in performance.  ...  We then study coefficient reordering techniques that lead to a more realistic and efficient encoder that the one we presented in our earlier work.  ...  This transform showed improvements in performance as compared to the LIMAT method [3] and to a motion compensated DCT video encoder.  ... 
doi:10.1109/icip.2011.6116471 dblp:conf/icip/Martinez-EnriquezDO11 fatcat:ty3qk6hnfjaflirzpdhaoxjwpq

Simulation of low-volume mixed model assembly lines: Modeling aspects and case study

Timm Ziarnetzky, Lars Monch, Alexander Biele
2014 Proceedings of the Winter Simulation Conference 2014  
This effect is more visible when we consider scenarios with high utilization. A lower reorder quantity is compensated by an increased reorder point.  ...  The effect of crew and spatial constraints in aircraft assembly operations to improve crew assignment, operation effectiveness, and cycle time is discussed in an early paper by Scott (1994) .  ... 
doi:10.1109/wsc.2014.7020055 dblp:conf/wsc/ZiarnetzkyMB14 fatcat:wfdyp5hamvgz5ducxvfeg7xbwi

Adapting to source properties in processing data integration queries

Zachary G. Ives, Alon Y. Halevy, Daniel S. Weld
2004 Proceedings of the 2004 ACM SIGMOD international conference on Management of data - SIGMOD '04  
Prior work in adaptive query processing has focused on compensating for delays and adjusting for mis-estimated cardinality or selectivity values.  ...  Skewed Uniform, 1% Reordered Skewed, 1% Reordered Skewed, 10% Reordered Skewed, 50% Reordered Data set Running Time (sec) Pipelined hash join Complementary joins Naive Priority  ...  join performance was slightly impeded by both skew (as would be expected) but also by reordering.  ... 
doi:10.1145/1007568.1007613 dblp:conf/sigmod/IvesHW04 fatcat:sibiouelijeozi4vwsdeitfq3u

Avoidance and suppression of compensation code in a trace scheduling compiler

Stefan M. Freudenberger, Thomas R. Gross, P. Geoffrey Lowney
1994 ACM Transactions on Programming Languages and Systems  
Our implementation of trace scheduling improves the SPECmark rating by 30% over basic block scheduling, but restricting trace scheduling so that no compensation code is required improves the rating by  ...  If an operation is moved across basic block boundaries, one or more compensation copies may be required in the off-trace code.  ...  We appreciate discussions with Cindy Collins, Tom Karzes, Woody Lichtenstein, and John Ruttenberg during the design and implementation of the compensation code optimizations.  ... 
doi:10.1145/183432.183446 fatcat:jkxrafjkfrc4pof23vcxt6bwwq

A Multipath TCP model for ns-3 simulator [article]

Bachir Chihani, Collange Denis
2011 arXiv   pre-print
MPTCP is a promising extension of TCP currently considered by the recent eponymous IETF working group, with the objective of improving the performance of TCP, especially its robustness to variable network  ...  We indeed notice that such mechanisms highly improve the performance of MPTCP.  ...  Our contribution consists of the proposal of a model of MPCTP with a better fidelity, and also the proposal of enhancing the current version of MPTCP with packet reordering mechanisms to cope with the  ... 
arXiv:1112.1932v1 fatcat:zvtgfkr3e5fd5dpsylvxmexujm

80-Mb/s QPSK and 72-Mb/s 64-QAM flexible and scalable digital OFDM transceiver ASICs for wireless local area networks in the 5-GHz band

W. Eberle, V. Derudder, G. Vanwijnsberghe, M. Vergara, L. Deneire, L. Van der Perre, M.G.E. Engels, I. Bolsens, H. De Man
2001 IEEE Journal of Solid-State Circuits  
With the advent of mobile communications, voice telecommunications became wireless.  ...  Joint development of signal processing algorithms and architectures along with on-chip data transfer, control, and partitioning leads to a low-power, yet flexible and scalable implementation.  ...  Wireless burst operation requires an FFT with low latency and power consumption.  ... 
doi:10.1109/4.962306 fatcat:u3urhi336vfkhilbliuk2zpi5e

Canonical abstraction for outerjoin optimization

Jun Rao, Hamid Pirahesh, Calisto Zuzarte
2004 Proceedings of the 2004 ACM SIGMOD international conference on Management of data - SIGMOD '04  
Previous work has studied this problem and provided techniques that allow certain reordering of the join sequences.  ...  It is challenging to optimize queries that contain outerjoins because outerjoins do not always commute with inner joins.  ...  further compensation), and Q2 bm where part is joined with partsupp first and a final β operator is needed.  ... 
doi:10.1145/1007568.1007643 dblp:conf/sigmod/RaoPZ04 fatcat:f5lj7wpctjeqhbi2ed35qpp2ua

Informed prefetching of collective input/output requests

Tara M. Madhyastha, Garth A. Gibson, Christos Faloutsos
1999 Proceedings of the 1999 ACM/IEEE conference on Supercomputing (CDROM) - Supercomputing '99  
Unfortunately, collective interfaces require an application to disclose its entire access pattern to fully reorder I/O requests, and cannot flexibly utilize additional memory to improve performance.  ...  Optimizing collective input/output (I/O) is important for improving throughput of parallel scientific applications.  ...  Both approaches improve throughput through request reordering.  ... 
doi:10.1145/331532.331545 dblp:conf/sc/MadhyasthaGF99 fatcat:edlf55vnuvf5jmatowgup2ngvu

Scalable Multi-Query Execution using Reinforcement Learning

Panagiotis Sioulas, Anastasia Ailamaki
2021 Proceedings of the 2021 International Conference on Management of Data  
Sharing work across queries presents an opportunity to reduce the total cost of processing and therefore improve throughput with increasing query load.  ...  RouLette scales by replacing sharing-aware optimization with adaptive query processing, and it chooses opportunities to explore and exploit by using reinforcement learning.  ...  CONCLUSION We have presented RouLette, an adaptive multi-query multi-way join operator that tackles the limitations of online and offline sharing.  ... 
doi:10.1145/3448016.3452799 fatcat:sjt5akmfufc37honzmywh7e5jq

MPEG-2 decoding in a stream programming language

M. Drake, H. Hoffmann, R. Rabbah, S. Amarasinghe
2006 Proceedings 20th IEEE International Parallel & Distributed Processing Symposium  
StreamIt is an architecture-independent stream language that aims to improve programmer productivity, while concomitantly exposing the inherent parallelism and communication topology of the application  ...  It implements the zig-zag descrambling necessary to reorder the input stream generated by the run-length encoding of quantized DCT coefficients. Typically, the zig-zag scan operates on an 8x8 matrix.  ...  Split-Join. The splitjoin construct distributes data to a set of parallel streams, which are then joined together in a roundrobin fashion.  ... 
doi:10.1109/ipdps.2006.1639343 dblp:conf/ipps/DrakeHRA06 fatcat:otarq37ihrg53i2mqkp7q2wlia
« Previous Showing results 1 — 15 out of 4,742 results