当前位置 >>  首页 >> 通知公告

关于异构系统上性能可移植性的报告

撰稿: 摄影: 发布时间:2014年11月10日
  Title: Towards Performance Portability for Heterogeneous Systems (a Unified View of Algorithmic Choices and Hardware Optimisations)
Abstract:
Computing systems have become increasingly complex with the emergence of heterogeneous ardware combining multicore CPUs and GPUs. These parallel systems exhibit tremendous computational power at the cost of increased programming effort. This results in a tension between achieving performance and code portability / ease of programming.In this talk I will present a novelapproach that offers high-level programming, code portability and high-performance. It is based on algorithmic pattern composition coupled with a powerful, yet simple, set of rewrite rules. This enables systematic transformation and optimization of a high-level program into a low-level hardware specific representation which leads to high performance code. I will show how a subset of the OpenCL programming model can be mapped to low-level patterns and how to automatically generate high performance OpenCL code on par with highly tuned implementations for multicore CPUs and GPUs.
Short bio:
Christophe Dubach received his Ph.D in Informatics from the University of Edinburgh in 2009 and holds a M.Sc. degree in Computer Science from EPFL (Switzerland). He is a Lecturer (Assistant Professor) in the Institute for Computing Systems Architecture at the University of Edinburgh (UK). In 2010 he spent one year as a visiting researcher at the IBM Watson Research Center (USA) working on the LiquidMetal project. His current research interests includes high-level programming models for heterogeneous systems, co-design of both computer architecture and optimising compiler technology, adaptive microprocessor, and the application of machine learning in these areas.
 
 时间:2014年11月18日(周二)下午2:30
地点:446会议室

报告人: Dr. Christophe Dubach


Title: Towards Performance Portability for Heterogeneous Systems (a Unified View of Algorithmic Choices and Hardware Optimisations)

Abstract:
Computing systems have become increasingly complex with the emergence of heterogeneous ardware combining multicore CPUs and GPUs. These parallel systems exhibit tremendous computational power at the cost of increased programming effort. This results in a tension between achieving performance and code portability / ease of programming. In this talk I will present a novelapproach that offers high-level programming, code portability and high-performance. It is based on algorithmic pattern composition coupled with a powerful, yet simple, set of rewrite rules. This enables systematic transformation and optimization of a high-level program into a low-level hardware specific representation which leads to high performance code. I will show how a subset of the OpenCL programming model can be mapped to low-level patterns and how to automatically generate high performance OpenCL code on par with highly tuned implementations for multicore CPUs and GPUs.

Short bio:
Christophe Dubach received his Ph.D in Informatics from the University of Edinburgh in 2009 and holds a M.Sc. degree in Computer Science from EPFL (Switzerland). He is a Lecturer (Assistant Professor) in the Institute for Computing Systems Architecture at the University of Edinburgh (UK). In 2010 he spent one year as a visiting researcher at the IBM Watson Research Center (USA) working on the LiquidMetal project. His current research interests includes high-level programming models for heterogeneous systems, co-design of both computer architecture and optimising compiler technology, adaptive microprocessor, and the application of machine learning in these areas.

附件下载: