Archived
This content is available here strictly for research, reference, and/or recordkeeping and as such it may not be fully accessible. If you work or study at University of Kentucky and would like to request an accessible version, please use the SensusAccess Document Converter.
Date Available
12-7-2011
Year of Publication
2009
Document Type
Thesis
Degree Name
Master of Science (MS)
College
Engineering
Department/School/Program
Electrical Engineering
Faculty
Dr. Henry G. Dietz
Faculty
Dr. Stephen D. Gedney
Abstract
GPUs offer high-performance floating-point computation at commodity prices, but their usage is hindered by programming models which expose the user to irregularities in the current shared-memory environments and require learning new interfaces and semantics.
This thesis will demonstrate that the message-passing paradigm can be conceptually cleaner than the current data-parallel models for programming GPUs because it can hide the quirks of current GPU shared-memory environments, as well as GPU-specific features, behind a well-established and well-understood interface. This will be shown by demonstrating a proof-of-concept MPI implementation which provides cleaner, simpler code with a reasonable performance cost. This thesis will also demonstrate that, although there is a virtualization constraint imposed by MPI, this constraint is harmless as long as the virtualization was already chosen to be optimal in terms of a strong execution model and nearly-optimal execution time. This will be demonstrated by examining execution times with varying virtualization using a computationally-expensive micro-kernel.
Recommended Citation
Young, Bobby Dalton, "MPI WITHIN A GPU" (2009). University of Kentucky Master's Theses. 614.
https://uknowledge.uky.edu/gradschool_theses/614
