10/29(四)邀請Dr. Greg Malewicz來系演講

各位老師、同學：
系上郭耀煌老師邀請 Google, USA的Dr. Greg Malewicz至系上演講，機會難得，請大家踴躍參加!

主辦單位：國立成功大學 資訊工程系/工程科學系
日    期：10月29日(四)
時    間：2:00pm~4:30pm
地    點：成功大學工程科學系 41104教室
對    象：資訊及相關系所教師及研究所學生
題    目：The Reduce Straggler Problem in MapReduce
主講人：Dr. Greg Malewicz
服務單位：Google, USA

內容摘要：
  MapReduce is a distributed computing framework used to run a wide range of computations on clusters with ease. The framework has extensive applications within Google and growing usage outside. Users identified the reduce straggler problem -- a form of load imbalance which can dominate MapReduce running time -- as one of the hardest performance problems to solve while running production  workloads. This talk characterizes the failures and load imbalances within clusters and the data imbalances in computations as the causes of stragglers; shows how reduce stragglers can be addressed through dynamic load balancing techniques including shard replication and  subsharding; and explains using microbenchmarks why these techniques work. This talk demonstrates the impact of the techniques on a production workload from Google: the running time of a MapReduce from our web indexing system was decreased by 13% to 20%.
 
個人簡介：
  Dr. Grzegorz Malewicz received the BA degrees in computer science and in applied mathematics in 1996 and 1998, respectively, and the MS degree in computer science in 1998, all from the University of Warsaw. He received the PhD degree in computer science from the University of Connecticut in 2003 with his last year at Massachusetts Institute of Technology. He is an engineer at Google designing simple and expressive models of computation and realizing them as scalable systems so as to make data processing in the cloud simple. He co-founded the Pregel project for graph processing and earlier worked on MapReduce, which lead to the first successful 1PB sort. He has had internships at the AT&T Shannon Laboratory (summer 2001) and Microsoft Corp. (summer 2000 and fall 2001). He was a visiting scientist at the University of Massachusetts, Amherst (summer 2004) and Argonne National Laboratory (summer 2005), and an assistant professor at the University of Alabama, where he taught computer science (2003 until 2005). His research focuses on high-performance parallel and distributed computing, experimental and theoretical algorithmics, combinatorial optimization, and scheduling. His research appears in top journals and conferences and includes a singly authored SIAM Journal on Computing paper that solves a decade-old problem in distributed computing.

  Dr. Malewicz is very active and highly recognized in the field of Cloud Computing. He is a keynote speaker of Cloud Computing 2009 and was invited to MIT and University of Warsaw etc. Dr. Malewicz has been serving as panelist, technical committee member, and invited speaker at IEEE or ACM conferences such as PODC. 

相關網址：無
公告人員：系辦人員
公告日期：2009-10-22
附加檔案：無附加檔案