9 Hits in 0.79 sec

Heterogeneous placement optimization for database query processing

Tomas Karnagel, Dirk Habich
2017 it - Information Technology  
Tomas Karnagel Database Systems Group, Technische Universität Dresden, Dresden, Germany Tomas Karnagel is currently a Ph.D. student at TU Dresden, working on heterogeneity-aware  ... 
doi:10.1515/itit-2016-0048 fatcat:accqkgmvl5eshc2hkyfvleh73u

Demonstrating efficient query processing in heterogeneous environments

Tomas Karnagel, Matthias Hille, Mario Ludwig, Dirk Habich, Wolfgang Lehner, Max Heimel, Volker Markl
2014 Proceedings of the 2014 ACM SIGMOD international conference on Management of data - SIGMOD '14  
The increasing heterogeneity in hardware systems gives developers many opportunities to add more functionality and computational power to the system. As a consequence, modern database systems will need to be able to adapt to a wide variety of heterogeneous architectures. While porting single operators to accelerator architectures is well-understood, a more generic approach is needed for the whole database system. In prior work, we presented a generic hardwareoblivious database system, where the
more » ... operators can be executed on the main processor as well as on a large number of accelerator architectures. However, to achieve fully heterogeneous query processing, placement decisions are needed for the database operators. We enhance the presented system with heterogeneity-aware operator placement (HOP) to take a major step towards designing a database system that can e ciently exploit highly heterogeneous hardware environments. In this demonstration, we are focusing on the placement-integration aspect as well as presenting the resulting database system.
doi:10.1145/2588555.2594526 dblp:conf/sigmod/KarnagelHLHLHM14 fatcat:nil6zmxs2rgszeqhfgoma4sxuy

A Sudoku-Solver for Large Puzzles using SAT

Uwe Pfeiffer, Tomas Karnagel, Guido Scheffler
n<sup>2</sup> x n<sup>2</sup> Sudoku puzzles can be straightforwardly encoded as SAT problems. However, solving such puzzles for large n requires a significant amount of optimization. We present some ideas for reducing the number of clauses, for improving the encoding, and for the selection of suitable SAT solvers.
doi:10.29007/79mc fatcat:hqczimue7vcqziyotdifareagy

Table of contents

2015 2015 31st IEEE International Conference on Data Engineering Workshops  
Karnagel, Wolfgang Lehner, Nils Asmussen, Marcus Vdlp, Benedikt Ndthen, Gerhard Fettweis) 161 m Flash-Aware Index Scan in PostgreSQL (Da-som Hwang, Woon-hak Kang, Gihwan Oh, Sang-won Lee) 1 m CloudDM  ...  Gruenwald) 149 m Optimizing CPU Cache Performance for Pre gel-Like Graph Computation (Songjie Niu, Shimin Chen) 155 m Query Processing on Low-Energy Many-Core Processors (Annett Ungethiim, Dirk Habich, Tomas  ... 
doi:10.1109/icdew.2015.7129527 fatcat:qx6n4vxvfbhqvmoudli5b26ufa

Detailed author index

2015 2015 31st IEEE International Conference on Data Engineering Workshops  
l1 Flash-Aware Index Scan in PostgreSQL Karnagel, Tomas 00 155 '!l1 Query Processing on Low-Energy Many-Core Processors Kay, Judy 30 '!  ... 
doi:10.1109/icdew.2015.7129529 fatcat:4vkbzbkin5fvhmiibrbqxegjaq

Report on the International Workshop on Big Data Management on Emerging Hardware (HardBD 2015)

Shimin Chen, Qiong Luo, Xiaofeng Meng
2015 SIGMOD record  
Karnagel, Wolfgang Lehner, Nils Asmussen, Marcus Völp, Benedikt Nöthen and Gerhard Fettweis.  ...  experiments on a real machine show that the proposed technique can achieve about 2x speedups for PageRank computation. (3) "Query Processing on Low-Energy Many-Core Processors" by Annett Ungethüm, Dirk Habich, Tomas  ... 
doi:10.1145/2854006.2854018 fatcat:ylomwrnmerahhncfsd4oclkvni


Zhou Shao, Muhammad Aamir Cheema, David Taniar, Hua Lu
2016 Proceedings of the VLDB Endowment  
Tomas Karnagel, Dirk Habich, Wolfgang Lehner 733 LFTF: A Framework for Efficient Tensor Analytics at Scale ........................................................ .  ... 
doi:10.14778/3025111.3025115 fatcat:2vi4x3dmlvfohndw5iw2xoibnq

TCUDB: Accelerating Database with Tensor Processors [article]

Yu-Ching Hu and Yuliang Li and Hung-Wei Tseng
2021 arXiv   pre-print
Fast Join Project Query [45] Tomas Karnagel, René Müller, and Guy M Lohman. 2015. Optimizing GPU- Evaluation Using Matrix Multiplication. In SIGMOD.  ... 
arXiv:2112.07552v1 fatcat:y6furfuc7nh5jml3cew7mqngry

Data processing on heterogeneous hardware [article]

Max Heimel, Technische Universität Berlin, Technische Universität Berlin, Volker Markl
Broneske, Bingshen He, Tomas Karnagel, Holger Pirk, Hannes Rauhe, Kaibo Wang, Haicheng Wu, Yuan Yuan, Steffen Zeuch, and Shuhao Zhang have all made significant contributions to this field.  ...  Karnagel et al. suggested to split the operator tree at compile time into so-called islands for which accurate cardinality estimates will be known at runtime.  ... 
doi:10.14279/depositonce-7255 fatcat:ymjwoicorzaylpwzkjktvmhjge