当前位置: X-MOL首页全球导师 国内导师 › 马文静

个人简介

招生专业 081202-计算机软件与理论 085211-计算机技术 招生方向 并行计算,GPU计算,并行代码生成与优化,并行系统性能优化 加速器并行计算技术,并行系统任务调度 教育背景 2005-09--今 The Ohio State University, USA Ph.D 2000-09--今 南开大学 学士 工作简历 2011-04--今 Pacific Northwest National Laboratory, USA Postdoc Research Associate 2004-07--今 天津泛凯科贸有限公司 软件工程师 专利成果 (1) 一种基于异构加速平台的二维相位解缠绕方法,发明,2014,第2作者,专利号:201410101628.0 科研项目 (1) 异构系统上基于任务窃取的负载平衡研究,主持,国家级,2014-01--2016-12

近期论文

查看导师最新文章 (温馨提示:请注意重名现象,建议点开原文通过作者单位确认)

(1) High Performance Two-Dimensional Phase Unwrapping on GPUs,ACM International Conference on Computing Frontiers,2014,第2作者 (2) Optimizing tensor contraction expressions for hybrid CPU-GPU execution,Cluster Computing,2013,第1作者 (3) Parameterized micro-benchmarking: an auto-tuning approach for complex applications,ACM International Conference on Computing Frontiers,2012,第1作者 (4) Compiler and runtime support for enabling reduction computations on heterogeneous systems,Concurrency and Computation: Practice and Experience,2012,第2作者 (5) Data-driven fault tolerance for work stealing computations,International Conference on Supercomputing (ICS),2012,第1作者 (6) Practical Loop Transformations for Tensor Contraction Expressions on Multi-level Memory Hierarchies,International Conference on Compiler Construction (member conference of ETAPS),2011,第1作者 (7) AUTO-GC: Automatic translation of data mining applications to GPU clusters,IPDPS workshops,2010,第1作者 (8) Compiler and runtime support for enabling generalized reduction computations on heterogeneous parallel configurations,International Conference on Supercomputing (ICS),2010,第2作者 (9) An integer programming framework for optimizing shared memory use on GPUs,International conference on High Performance Computing ,2010,第1作者 (10) Acceleration of Streamed Tensor Contraction Expressions on GPGPU-Based Clusters,CLUSTER,2010,第1作者

推荐链接
down
wechat
bug