
handle: 2183/27091
[Resumen] En este trabajo se estudia una aplicación de los métodos de optimización poliédrica, que se basa en aplicar métodos matemáticos sobre estructuras de código afines que se caracterizan por utilizar bucles regulares de gran tamaño en donde el control y los datos dependen únicamente de las variables de inducción del bucle y constantes mediante funciones afines. Estas regiones, que se suelen llamar Static Control Parts (SCoPs), se modelan y optimizan usando técnicas de compilación poliédrica. El objetivo principal de este trabajo consiste en portar las aplicaciones de PolyBench/C, que conforman un conjunto de pruebas de rendimiento (benchmarks) empleadas para el desarrollo y validación de técnicas de optimización poliédrica en el lenguaje de programación C, al lenguaje de programación Python para de forma similar conformar un banco de pruebas estándar de cara al futuro desarrollo de optimizaciones poliédricas en este lenguaje.
[Abstract] This paper explores an application of polihedral optimization, which consists on using mathematical methods on affine code structures which are characterized by using large regular loops where control and data depend solely on loop induction variables and constants using affine functions. These regions, often called Static Control Parts (SCoPs), are modeled and optimized using polyhedral compilation. The main objective of this work is porting the applications present in PolyBench/C, which form a set of performance tests (benchmarks) used for the development and validation of polyhedric optimization techniques for the C programming language, to the Python programming language to form in a similar manner a standard test bench for future development of polihedral optimizations on this language.
Traballo fin de grao (UDC.FIC). Enxeñaría informática. Curso 2019/2020
Optimization, Compilers, Compiladores, Código fuente, Lenguajes de programación, Optimización, Computer languages, Source code
Optimization, Compilers, Compiladores, Código fuente, Lenguajes de programación, Optimización, Computer languages, Source code
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
