COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Computer Laboratory Systems Research Group Seminar > Productive parallel programming with Unified Parallel C
Productive parallel programming with Unified Parallel CAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Eiko Yoneki. Programming for large-scale, multicore-based architectures requires adequate tools that offer ease of programming and do not hinder application performance. In the last years, the research community has initiated different efforts to create a suitable and robust programming model for such architectures. In this talk I will present the Unified Parallel C (UPC) language. UPC is a Partitioned Global Address Space (PGAS) language (other PGAS languages include Titanium and Co-Array Fortran). PGAS languages provide a shared-memory-like programming model, where the address space is partitioned and the programmer has control over the data layout. The programmer is able to exploit data locality to achieve performance. An advantage of the UPC language is that it extends an existing language (C) with constructs to express parallelism and data distribution, thus it is easier to learn than a completely new language. I will discuss the UPC strengths, weaknesses as well as our research work and achieved results. bio: Dr. Montse Farreras received her PhD degree in computer science at UPC (Universitat Politecnica de Catalunya) in 2008. She worked as an associate professor at the same University, and she joined to the Programming Models research line at BSC (Barcelona Supercomputing Center). In this research group she conducted research about Parallel Programming Models for High Performance Computing (HPC), focusing on productivity, performance and scalability. She has been collaborating with the Programming Models and Tools for Scalable Systems group at IBM TJ Watson Research Institute since 2004, working on a scalable Runtime System for the XLUPC compiler and she has participated in European projects (HPC-Europe2, PRACE ) exploring the usability of the UPC language. In 2012 she moved to the UK and she currently works at Numerical Algorithms Group (at Oxford) as part of the HPC team, giving support and training to HEC ToR users. This talk is part of the Computer Laboratory Systems Research Group Seminar series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsResearch Seminar Series, Faculty of Education, University of Cambridge Yundi: Chopin masterclass and 'musical dialogue' Public Engagement in the 21st Century Industrial Sustainability Global Food Futures Social Anthropology Post-Doc SeminarOther talksFormation and disease relevance of axonal endoplasmic reticulum, a "neuron within a neuron”. Reconstructing deep ocean circulation pathway and strength using sediment dispersion Complement and microglia mediated sensory-motor synaptic loss in Spinal Muscular Atrophy Practical Steps to Addressing Unconscious / Implicit Bias Huntington´s disease and autophagy - insights from human and mouse model systems Fluorescence spectroscopy and Microscale thermophoresis Singularities of Hermitian-Yang-Mills connections and the Harder-Narasimhan-Seshadri filtration Autumn Cactus & Succulent Show Towards bulk extension of near-horizon geometries Graph Legendrians and SL2 local systems The formation of high density dust rings and clumps: the role of vorticity |