Orchestration paper accepted at VLDB
Published on in ORCHESTRATION (RECENT ACHIEVEMENTS)
"Adaptive Work Placement for Query Processing on Heterogeneous Computing Resources"
The hardware landscape is currently changing from homogeneous multi-core systems towards heterogeneous systems with many diﬀerent computing units, each with their own characteristics. This trend is a great opportunity for database systems to increase the overall performance if the heterogeneous resources can be utilized eﬃciently. To achieve this, the main challenge is to place the right work on the right computing unit. Current approaches tackling this placement for query processing in database systems assume that data cardinalities of intermediate results can be correctly estimated. However, this assumption does not hold for complex analytical queries. To overcome this problem, we developed an adaptive placement approach being independent of cardinality estimation of intermediate results. Our adaptive approach takes a physical query execution plan as input and divides the plan into disjoint execution islands at compile-time. The execution islands are determined in a way that the cardinalities of intermediate results within each island are known or can be precisely calculated. The placement optimization and execution is performed separately per island at query runtime. The processing of the execution islands takes place successively following data dependencies. With our novel adaptive approach, we can use heterogeneous computing resources more efficiently for query processing. The corresponding paper , which describes and evaluates our overall approach, has been accepted as full paper at the 43rd International Conference on Very Large Data Bases (VLDB, http://www.vldb.org/2017/). Generally, VLDB is the premier annual international forum for data management and database researches.
 Tomas Karnagel, Dirk Habich, Wolfgang Lehner: Adaptive Work Placement for Query Processing on Heterogeneous Computing Resources: Accepted at 43rd International Conference on Very Large Data Bases (VLDB, August 28 – September 1, Munich, Germany), 2017