Zobrazeno 1 - 10
of 61
pro vyhledávání: '"Holger Pirk"'
Publikováno v:
Proceedings of the VLDB Endowment. 15:361-374
Single-node multi-core stream processing engines (SPEs) can process hundreds of millions of tuples per second. Yet making them fault-tolerant with exactly-once semantics while retaining this performance is an open challenge: due to the limited I/O ba
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2c0b1f035a8267dba0ba9a92d79bd71
https://doi.org/10.14778/3489496.3489515
https://doi.org/10.14778/3489496.3489515
Autor:
Holger Pirk
Publikováno v:
ACM SIGMOD Record. 51:54-55
Motivation: Data science is increasingly collaborative. On the one hand, results need to be distributed, e.g., as interactive visualizations. On the other, collaboration in the data development process improves quality and timeliness. This can take m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::55d1e256c92fce935d25757970a1f486
https://doi.org/10.1145/3582302.3582316
https://doi.org/10.1145/3582302.3582316
Publikováno v:
SIGMOD Conference
Window aggregation queries are a core part of streaming applications. To support window aggregation efficiently, stream processing engines face a trade-off between exploiting parallelism (at the instruction/multi-core levels) and incremental computat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d9a5c87a80d933152574a1ca8542642a
https://doi.org/10.1145/3318464.3389753
https://doi.org/10.1145/3318464.3389753
Publikováno v:
FPL
The International Conference on Field-Programmable Logic and Applications (FPL) 2019
The International Conference on Field-Programmable Logic and Applications (FPL) 2019
We present an efficient, high-throughput and scalable hardware design for accelerating the merge phase of the sort-merge join operation. Sort-merge join is one of the fundamental join algorithms and among the most frequently executed operations in re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2c61a516e99cf2adba51a24619a7711e
https://doi.org/10.1109/fpl.2019.00025
https://doi.org/10.1109/fpl.2019.00025
Autor:
Holger Pirk
Publikováno v:
Proceedings of the 2019 International Conference on Management of Data.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd79cc10f19921f53cf5409c3b9cf118
https://doi.org/10.1145/3341280
https://doi.org/10.1145/3341280
Publikováno v:
Proceedings of the VLDB Endowment. 9:1707-1718
In-memory databases require careful tuning and many engineering tricks to achieve good performance. Such database performance engineering is hard: a plethora of data and hardware-dependent optimization techniques form a design space that is difficult
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8cecf08d87519d550f05f1e5498c46bf
https://doi.org/10.14778/3007328.3007336
https://doi.org/10.14778/3007328.3007336
Autor:
Holger Pirk
Publikováno v:
Proceedings of the 2018 International Conference on Management of Data.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b7587c2296cd8c6d6c9a756cdaae5b82
https://doi.org/10.1145/3258008
https://doi.org/10.1145/3258008
Autor:
Samuel Madden, Rahul Palamuttam, James J. Thomas, Deepak Narayanan, Matei Zaharia, Anil Shanbhag, Malte Schwarzkopf, Parimajan Negi, Shoumik Palkar, Pratiksha Thaker, Holger Pirk, Saman Amarasinghe
Modern analytics applications use a diverse mix of libraries and functions. Unfortunately, there is no optimization across these libraries, resulting in performance penalties as high as an order of magnitude in many applications. To address this prob
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::63ee6ffc3017fb75554bb2e3cb2d7851
http://hdl.handle.net/10044/1/71236
http://hdl.handle.net/10044/1/71236
Autor:
Holger Pirk
Publikováno v:
ACM SIGMOD Record. 44:53-58
Computer system architecture has changed: an assembly of autonomous components has replaced the omnipotent CPU and its legion of dumb devices. Database Management System (DBMS) architecture, however, does not yet reflect this change: it is still domi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ec6ff258224328db4f0743aa2be4b22e
https://doi.org/10.1145/2814710.2814720
https://doi.org/10.1145/2814710.2814720
Publikováno v:
SIGMOD 2018
SIGMOD Conference
SIGMOD Conference
A common operation in many data analytics workloads is to find the top-k items, i.e., the largest or smallest operations according to some sort order (implemented via LIMIT or ORDER BY expressions in SQL). A naive implementation of top-k is to sort a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d0c47cfdd860299dcf8fe3da72e8a912
http://hdl.handle.net/10044/1/58369
http://hdl.handle.net/10044/1/58369