<p>During the recent years, computer performance has increased dramatically. To measure </p><p>the performance of computers, benchmarks are ideal tools. Benchmarks exist in many </p><p>areas and point to different applications. For instance, in a normal PC, benchmarks can be </p><p>used to test the performance of the whole system which includes the CPU, graphic card, </p><p>memory system, etc. For multiprocessor systems, there also exist open source benchmark </p><p>programs. In our project, we gathered information about some open benchmark programs </p><p>and investigated their applicability for evaluating embedded multiprocessor systems </p><p>intended for radar signal processing. During our investigation, parallel cluster systems </p><p>and embedded multiprocessor systems were studied. Two benchmark programs, HPL and </p><p>NAS Parallel Benchmark were identified as particularly relevant for the application field. </p><p>The benchmark testing was done on a parallel cluster system which has an architecture </p><p>that is similar to the architecture of embedded multiprocessor systems, used for radar </p><p>signal processing.</p>

During the recent years, computer performance has increased dramatically. To measure the performance of computers, benchmarks are ideal tools. Benchmarks exist in many areas and point to different applications. For instance, in a normal PC, benchmarks can be used to test the performance of the whole system which includes the CPU, graphic card, memory system, etc. For multiprocessor systems, there also exist open source benchmark programs. In our project, we gathered information about some open benchmark programs and investigated their applicability for evaluating embedded multiprocessor systems intended for radar signal processing. During our investigation, parallel cluster systems and embedded multiprocessor systems were studied. Two benchmark programs, HPL and NAS Parallel Benchmark were identified as particularly relevant for the application field. The benchmark testing was done on a parallel cluster system which has an architecture that is similar to the architecture of embedded multiprocessor systems, used for radar signal processing.

Orientador: Marconi Kolm Madrid / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-10T03:57:30Z (GMT). No. of bitstreams: 1 Castro_EbervalOliveira_M.pdf: 4698124 bytes, checksum: 0a0a438cbad7212bdba90f2c96875871 (MD5) Previous issue date: 2007 / Resumo: A solução de modelos dinâmicos de robôs em tempo real é um dos principais desafios da robótica. Este trabalho propõe um multiprocessador de quatro núcleos fortemente acoplados, o SMM-4 (Sistema Multiprocessado Monolítico), consistindo de uma arquitetura de processamento paralelo monolítica sintetizada em FPGA para aplicações em controle de sistemas robóticos. Uma análise quantitativa e qualitativa é realizada em contraste a sistemas uniprocessadores, evidenciando os ganhos obtidos através desta abordagem em FPGA. O SMM-4 foi desenvolvido no Laboratório de Sistemas Modulares Robóticos (LSMR/Unicamp) como uma das alternativas para o cálculo das equações dos modelos de robôs em tempo real / Abstract: The solution of robots¿ dynamic models in real-time is one of major challenges of the robotics. This work presents a strongly coupled quad-core multiprocessor ¿ the MMS-4 (Monolithic Multiprocessor System) ¿ consisting of a monolithical parallel processing architecture synthesized on FPGA for applications on robotic control systems. A quantitative and qualitative analysis is performed in contrast with uniprocessor systems for the purpose of evince the benefits obtained choosing this approach in FPGA. The MMS-4 was developed at Robotic Modular Systems Laboratory (LSMR/Unicamp) as an alternative to calculate the equations systems of robots¿ models on real-time / Mestrado / Automação / Mestre em Engenharia Elétrica