SCHEDULE: NOV 10-16, 2012
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.
Dataflow-Driven GPU Performance Projection for Multi-Kernel Transformations
SESSION: Performance Modeling
EVENT TYPE: Papers
TIME: 10:30AM - 11:00AM
SESSION CHAIR: Dimitris Nikolopoulos
AUTHOR(S):Jiayuan Meng, Vitali Morozov, Venkatram Vishwanath, Kalyan Kumaran
ROOM:355-EF
ABSTRACT:
Applications often have a sequence of parallel
operations to be offloaded to graphics processors; each operation can
become an individual GPU kernel. Developers typically explore
different transformations for each kernel.
It is wellknown that efficient data management is critical in
achieving high GPU performance and that fusing multiple
kernels into one may greatly improve data locality. Doing so,
however, requires transformations across multiple, potentially
nested, parallel loops; at the same time, the original code
semantics must be preserved. Since each
kernel may have distinct data access patterns, their combined
dataflow can be nontrivial. As a result, the complexity of
multi-kernel transformations often leads to significant effort with no
guarantee of performance benefits.
This paper proposes a dataflow-driven analytical framework to
project GPU performance for a sequence of parallel operations
without implementing GPU code or using physical hardware.
The framework also suggests multi-kernel transformations that
can achieve the projected performance.
Chair/Author Details:
Dimitris Nikolopoulos (Chair) - Queen's University Belfast
Jiayuan Meng - Argonne National Laboratory
Vitali Morozov - Argonne National Laboratory
Venkatram Vishwanath - Argonne National Laboratory
Kalyan Kumaran - Argonne National Laboratory
Click here to download .ics calendar file
Click here to download .vcs calendar file
Click here to add event to your Google Calendar
Dataflow-Driven GPU Performance Projection for Multi-Kernel Transformations
SESSION: Performance Modeling
EVENT TYPE:
TIME: 10:30AM - 11:00AM
SESSION CHAIR: Dimitris Nikolopoulos
AUTHOR(S):Jiayuan Meng, Vitali Morozov, Venkatram Vishwanath, Kalyan Kumaran
ROOM:355-EF
ABSTRACT:
Applications often have a sequence of parallel
operations to be offloaded to graphics processors; each operation can
become an individual GPU kernel. Developers typically explore
different transformations for each kernel.
It is wellknown that efficient data management is critical in
achieving high GPU performance and that fusing multiple
kernels into one may greatly improve data locality. Doing so,
however, requires transformations across multiple, potentially
nested, parallel loops; at the same time, the original code
semantics must be preserved. Since each
kernel may have distinct data access patterns, their combined
dataflow can be nontrivial. As a result, the complexity of
multi-kernel transformations often leads to significant effort with no
guarantee of performance benefits.
This paper proposes a dataflow-driven analytical framework to
project GPU performance for a sequence of parallel operations
without implementing GPU code or using physical hardware.
The framework also suggests multi-kernel transformations that
can achieve the projected performance.
Chair/Author Details:
Dimitris Nikolopoulos (Chair) - Queen's University Belfast
Jiayuan Meng - Argonne National Laboratory
Vitali Morozov - Argonne National Laboratory
Venkatram Vishwanath - Argonne National Laboratory
Kalyan Kumaran - Argonne National Laboratory
Click here to download .ics calendar file