On Wednesday March 31st, Dalvan Griebler (GMAP researcher), presented his Phd thesis at the Faculty of Informatics of the Pontifical Catholic University of Rio Grande do Sul.
The presentation took place in the ODL room, building 40, at 10.00 am.
Dissertation title and abstract:
Title: Domain-Specific Language Support Tools for High-Level Parallelism Stream
Abstract: Stream-based systems are representative of Several different application domains including video, networking, audio, graphic processing, etc. Stream parallel programs may run on different kinds of parallel architectures (desktop, servers, cell phones, and supercomputers) and represent significant workloads on our current computing systems. Nevertheless, most of Them are still not parallelized. Moreover, When a new one has to be developed, programmers have to face the trade-off between productivity coding, coding portability, and performance. To solve this problem, We provide a new Domain-Specific Language (DSL) que naturally / on-the-fly and captures Represents parallelism is stream-based applications. The aim is to offer a set of attributes (through annotations) que preserves the source code of the program and is not architecturedependent. We used the C ++ attribute mechanism to design a "de-facto" standard C ++ embedded DSL named the spar. However, the implementation of DSLs using compiler-based tools is Difficult, complicated and Usually requires a significant learning curve. This is even harder for que Those are not familiar with compiler technology. Our motivation is, Therefore, to simplify this path for other Researchers (experts in Their domain) with support tools (our tool is CINCLE) to high-level implement DSLs and productive through powerful and aggressive source-to-source transformations. In fact, parallel programmers can use Their expertise without having to design and implement the low-level code. The main goal of the thesis was to create a DSL and support tools for high-level stream parallelism in the context of the programming framework que is compiler-based and domain-oriented. Thus, we Implemented Spar using CINCLE. SPAR supports the software developer with productivity, performance and code portability while CINCLE Provides sufficient support to generate new DSLs. Also, SPAR targets source-to-source transformation producing parallel pattern code Implemented on top of FastFlow and MPI. Finally, we have a full set of experiments shows que que SPAR Provides better coding productivity without significant performance degradation in multi-core systems as well as transformation rules que are able to Achieve code portability through its attributes.
Doctor Advisor: Prof. Dr. Luiz Gustavo Leão Fernandes
Co-advisor: Prof. Dr. Marco Danelutto (Università di Pisa)
Examining Committee: Professor Dr. César Augusto Fonticielha De Rose (PPGCC / PURS), Prof. Dr. Marco Aldinucci (University of Turin) and Prof. Dr. José Daniel García Sánchez (Universidad Carlos III de Madrid).
The student has passed with merit.
Photo taken by occasion of Doctor degree presentation of student Dalvan Griebler's thesis.
Left to right, Prof. Dr. Luiz Gustavo Fernandes, student Dalvan Griebler, Prof. Dr. Marco Danelutto and Prof. Dr. César Augusto Fonticielha De Rose.