Toward compiler-driven adaptive execution and its application to GPU architectures
Abstract
A major shift in technology from maximizing single-core performance to integrating multiple cores has introduced a new, heterogeneous arena to high-performance computing communities. Among several new parallel platforms, hardware accelerators, such as General-Purpose Graphics Processing Units (GPGPUs), have emerged as promising alternatives for high-performance computing. While a GPGPU provides an inexpensive, highly parallel system to application developers, its programming complexity poses significant challenges for developers. This dissertation explores compile-time and runtime techniques to improve programmability and to enable adaptive execution of programs in such architectures. First, this dissertation examines the possibility of exploiting OpenMP shared memory programming model on stream architectures such as GPGPUs. This dissertation presents a compiler framework for automatic translation and optimization of standard OpenMP applications for executing on GPGPUs. Second, this dissertation studies runtime tuning systems to adapt applications dynamically. In preliminary work, an adaptive runtime tuning system with emphasis on parallel irregular applications has been proposed. Third, this dissertation focuses on creating an integrated framework where both the compiler framework and the tuning system are synergistically combined, such that compiler-translated GPGPU applications will be seamlessly adapted for the underlying system. For this goal, a new programming interface, called OpenMPC - OpenMP extended for CUDA, is proposed. OpenMPC provides an abstraction of the complex CUDA programming model and offers high-level control over the involved parameters and optimizations. We have developed a fully automatic compilation and user-assisted tuning system supporting OpenMPC. Experiments on various programs demonstrate that the proposed system achieves performance comparable to hand-coded CUDA programs.
Degree
Ph.D.
Advisors
Eigenmann, Purdue University.
Subject Area
Computer Engineering
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.