SC13, SC14 Little Fe Workshop

LittleFe是一个完整的6节点Beowulf风格的可移植计算集群，支持共享内存并行(OpenMP)、分布式内存并行(MPI)和GPGPU并行(CUDA)。这些低成本的轻量级单元非常适合无法接入并行平台进行并行和分布式计算教育的机构和教学环境。在并行平台上教授加速、效率和负载平衡等关键概念要有效得多。该奖项是为了支持将LittleFe建筑工人作为SC13和SC14的HPC教育者计划的一部分。总体而言，这将使LittleFe项目能够在2013至2014年间在美国各地的教育机构额外安置16个LittleFe单元。这些单元将在另外16所学院和大学的本科计算机科学课程中支持并行编程和分布式计算。他们还将支持将在XSEDE13和XSEDE14会议上举办的学生编程竞赛，以及美国各地初中和高中的外联活动。

LittleFe is a complete 6 node Beowulf style portable computational cluster which supports shared memory parallelism (OpenMP), distributed memory parallelism (MPI), and GPGPU parallelism (CUDA). These low-cost light-weight units are well-suited for institutions and teaching environments that do not have access to parallel platforms for parallel and distributed computing education. Teaching key concepts such as speedup, efficiency, and load balancing are much more effectively done on a parallel platform. This award is to support hosting LittleFe buildouts as part of the HPC Educators Program at the SC13 and SC14. In total, this will enable the LittleFe project to place 16 additional LittleFe units at educational institutions throughout the United States during 2013 and 2014. These units will support parallel programming and distributed computing in the undergraduate CS curriculum at 16 additional colleges and universities. They will also support student programming contests which will be hosted at e.g. the XSEDE13 and XSEDE14 conferences, and outreach events at junior and senior high schools across the United States.