P
Paraskevas Yiapanis
Researcher at University of Manchester
Publications - 14
Citations - 221
Paraskevas Yiapanis is an academic researcher from University of Manchester. The author has contributed to research in topics: Speculative multithreading & Compiler. The author has an hindex of 8, co-authored 14 publications receiving 206 citations. Previous affiliations of Paraskevas Yiapanis include Manchester Metropolitan University.
Papers
More filters
Proceedings ArticleDOI
A Parallel Distributed Weka Framework for Big Data Mining Using Spark
TL;DR: By combining Weka's usability and Spark's processing power, DistributedWekaSpark provides a usable prototype distributed Big Data Mining workbench that achieves near-linear scaling in executing various real-world scale workloads - 91.4% weak scaling efficiency on average and up to 4x faster on average than Hadoop.
Journal ArticleDOI
Fundamental Nano-Patterns to Characterize and Classify Java Methods
TL;DR: This work presents a provisional catalogue of 17 fundamental nano-patterns, which are simple, static, binary properties of Java methods, such as ObjectCreator and Recursive, and presents a quantitative comparison of two popular Java benchmarking suites in terms of their relative object-orientedness and diversity.
Journal ArticleDOI
Optimizing software runtime systems for speculative parallelization
TL;DR: A novel compact version management data structure optimized for space overhead when using a small number of TLS threads is described and two novel software runtime parallelization systems that utilize this compact data structure are described.
Book ChapterDOI
Online non-stationary boosting
TL;DR: This work presents an algorithm called Online Non-Stationary Boosting (ONSBoost) that, like Online Boosting, uses a static ensemble size without generating new members each time new examples are presented, and also adapts to a changing data distribution.
Proceedings ArticleDOI
Toward a more accurate understanding of the limits of the TLS execution paradigm
Nikolas Ioannou,Jeremy Singer,Salman Khan,Polychronis Xekalakis,Paraskevas Yiapanis,Adam Craig Pocock,Gavin Brown,Mikel Luján,Ian Watson,Marcelo Cintra +9 more
TL;DR: Thread-Level Speculation facilitates the extraction of parallel threads from sequential applications by developing the compiler and architecture for this execution paradigm and assesses how well TLS performs if some architectural/ compiler constraint is relaxed.