B
Bernhard Scholz
Researcher at University of Sydney
Publications - 108
Citations - 2099
Bernhard Scholz is an academic researcher from University of Sydney. The author has contributed to research in topics: Compiler & Datalog. The author has an hindex of 22, co-authored 101 publications receiving 1653 citations. Previous affiliations of Bernhard Scholz include Information Technology University & Vienna University of Technology.
Papers
More filters
Proceedings ArticleDOI
Probabilistic communication optimizations and parallelization for distributed-memory systems
Eduard Mehofer,Bernhard Scholz +1 more
TL;DR: This paper introduces a novel optimization technique in the context of High Performance Fortran (HPF) that is based on probabilistic data-flow information that considers statically undefined attributes which play an important role for parallelization and compute for those attributes the probabilities to hold some specific value during runtime.
Journal ArticleDOI
Predicated Partial Redundancy Elimination using a Cost Analysis
TL;DR: A predicated partial redundancy elimination (PPRE) approach which can potentially remove all partial redundancies is described which is applied selectively based on a cost model.
Proceedings ArticleDOI
Migrating operator placement for compositional stream graphs
TL;DR: This work introduces the migrating operator placement problem (MOPP) that places operators of stream graphs on sensor nodes, such that energy costs are minimized and a heuristic that reduces the search space to the proximity of the base station is introduced.
Journal ArticleDOI
Computing end-to-end delays in stream query processing
TL;DR: This work represents a stream query as a graph consisting of operators that process data and channels that transport data tokens between operators, and designs an algorithm to measure the end-to-end delays in a stream graph.
Proceedings ArticleDOI
Two concurrent data structures for efficient datalog query processing
TL;DR: The efficiency of Datalog engines has reached a point where engines such as Soufflé have reported performance results comparable to low-level hand-crafted alternatives.