Open Access. Powered by Scholars. Published by Universities.®
- Keyword
- Publication
Articles 1 - 3 of 3
Full-Text Articles in Systems Architecture
Compiler Optimization Effects On Register Collisions, Jonathan S. Tan
Compiler Optimization Effects On Register Collisions, Jonathan S. Tan
Master's Theses
We often want a compiler to generate executable code that runs as fast as possible. One consideration toward this goal is to keep values in fast registers to limit the number of slower memory accesses that occur. When there are not enough physical registers available for use, values are ``spilled'' to the runtime stack. The need for spills is discovered during register allocation wherein values in use are mapped to physical registers. One factor in the efficacy of register allocation is the number of values in use at one time (register collisions). Register collision is affected by compiler optimizations that …
Senior Project Report - Doctest, Stephen Weessies
Senior Project Report - Doctest, Stephen Weessies
Computer Engineering
DocTest is a program that, simply put, allows a programmer or user to document STANAG 4586 (a standard for unmanned aerial vehicle interoperability) messages and test the vehicle system at Lockheed Martin [5]. The program is extensible to allow for further development aiding our software team to do what they do best and not get bogged down in tedious but necessary documentation. DocTest is also used to aid in testing, keeping track of the issues and bugs found and creating a document that captures each issue so an issue is not missed or forgotten. This program was made for use …
Cuda Web Api Remote Execution Of Cuda Kernels Using Web Services, Massimo J. Becker
Cuda Web Api Remote Execution Of Cuda Kernels Using Web Services, Massimo J. Becker
Master's Theses
Massively parallel programming is an increasingly growing field with the recent introduction of general purpose GPU computing. Modern graphics processors from NVIDIA and AMD have massively parallel architectures that can be used for such applications as 3D rendering, financial analysis, physics simulations, and biomedical analysis. These massively parallel systems are exposed to programmers through in- terfaces such as NVIDIAs CUDA, OpenCL, and Microsofts C++ AMP. These frame- works expose functionality using primarily either C or C++. In order to use these massively parallel frameworks, programs being implemented must be run on machines equipped with massively parallel hardware. These requirements limit …