When viewing the Technical Program schedule, on the far righthand side
is a column labeled "PLANNER." Use this planner to build your own
schedule. Once you select an event and want to add it to your personal
schedule, just click on the calendar icon of your choice (outlook
calendar, ical calendar or google calendar) and that event will be
stored there. As you select events in this manner, you will have your
own schedule to guide you through the week.
You can also create your personal schedule on the SC11 app (Boopsie) on your smartphone. Simply select a session you want to attend and "add" it to your plan. Continue in this manner until you have created your own personal schedule. All your events will appear under "My Event Planner" on your smartphone.
Parallel Communication and I/O Interfaces for Accelerators: HPC Advisory Council Special Interest Group
SESSION: Parallel Communication and I/O Interfaces for Accelerators: HPC Advisory Council Special Interest Group
EVENT TYPE: Birds of a Feather
TIME: 5:30PM - 7:00PM
SESSION LEADER(S):Gilad Shainer, Sadaf Alam
ABSTRACT: The session will be the base for the official launch of a special interest group (SIG) as part of the HPC Advisory Council for identifying communication and I/O requirements and proposing standard interfaces for accelerators based HPC. A further aim is to establish an educational and dissemination portal. The speakers from vendor institutions will provide roadmaps for existing technologies e.g. GPUDirect, which is a significant step for lowering overheads for GPU to GPU internode communication. The related research and development efforts at the academic institutions will also be presented at the session including MVAPICH2 extensions for GPUs and the rCUDA effort for virtualizing GPU devices over the interconnect. The expected deliverables of the session include: launching of the SIG through the HPC advisory council, agenda items for upcoming HPC Advisory council training workshops, and a draft proposal on standard interfaces for facilitating message-passing and remote memory communication from accelerator devices.