This workshop lasts 5 days.
In order to train more scientists to use graphics processor units (GPUs) for their research, training focused on this new level of parallelism is needed. We have partnered with Virtual School of Computational Science and Engineering (VSCSE), to provide such training. VSCSE classes broadcast over the web to a set of remote participating sites. To ensure that the education is done well, there is typically a facilitator located at each remote site to aid the class participants locally.
The goals for this class are:
Better utilization of the GPUs by enabling more scientists to use them
Better understanding of the efficiency in the GPU utilization by the application developers
As a result of both: A higher job throughput by enabling more resources and shortening job runtimes
In order to achieve the goal the class introduces all levels of parallelism as well as common approaches for parallelization over the course of five days. The class contains lectures and labs so that the participants immediately put the newly acquired knowledge to work.
Go to RT events for a complete list of RT related events.
Presented by the Indiana University Pervasive Technology Institute, UITS Research Technologies(RT) Division visiting scholar: Guido Juckeland, Technische Universität Dresden, Center for Information Services and High Performance Computing (ZIH).
There will NOT be a break for lunch. Short breaks will be taken. Bring something to snack on during break if you prefer.
You must provide your own laptop. We do not want this prerequisite to exclude anyone. Contact firstname.lastname@example.org if you need a loaner laptop for this course.
IT – Informatics & Communications Technology Complex (ICTC)
535 W. Michigan St.
Indianapolis, IN 46202
There are no upcoming dates for this event.