Univ., Diplomarbeit, 2002--Frankfurt (Main) / Zsfassung in dt. und engl. Sprache

Chemnitz, Techn. Univ., Diplomarb., 2008.

At IAV GmbH, Chemnitz, an embedded platform for high-performance sensor data acquisition has been developed. Sensor data is gathered and preprocessed by two digital signal processors (DSP) which communicate bidirectionally via dual-ported memory with the central controlling instance, a Freescale MCF5484 microcontroller running uClinux. The goal of this thesis is to design, implement, analyze and optimize a real-time communication protocol between both DSPs and the microcontroller. The challenges of this thesis can be defined as follows: • A uClinux driver for the dual-ported RAM must be implemented. This driver has to employ the microcontroller’s internal DMA engine and should be integrated into the Linux kernel’s DMA framework. • The DMA engine must be thoroughly analyzed. Especially interesting is its behavior when concurrently performing data transfers. Potential influence factors onto data transfer performance and timing predictability should be experimentally identified and quantitatively characterized, if possible. • Sensor data from the DSPs to the microcontroller has to meet real-time demands and must be prioritized in some way over status and parameter data from and to the DSPs. • Correct and efficient synchronization is a must. If possible, different synchronization schemes should be compared to each other. • The achievable performance in terms of guaranteed and maximum data throughput between DSP and microcontroller as well as end-to-end bandwidth has to be estimated. • Apart from the DMA engine analysis, a general evaluation of potential and achieved performance, timing predictability and the remaining microcontroller’s processing capacity (if any) should be executed.

At IAV GmbH, Chemnitz, an embedded platform for high-performance sensor data acquisition has been developed. Sensor data is gathered and preprocessed by two digital signal processors (DSP) which communicate bidirectionally via dual-ported memory with the central controlling instance, a Freescale MCF5484 microcontroller running uClinux. The goal of this thesis is to design, implement, analyze and optimize a real-time communication protocol between both DSPs and the microcontroller. The challenges of this thesis can be defined as follows: • A uClinux driver for the dual-ported RAM must be implemented. This driver has to employ the microcontroller’s internal DMA engine and should be integrated into the Linux kernel’s DMA framework. • The DMA engine must be thoroughly analyzed. Especially interesting is its behavior when concurrently performing data transfers. Potential influence factors onto data transfer performance and timing predictability should be experimentally identified and quantitatively characterized, if possible. • Sensor data from the DSPs to the microcontroller has to meet real-time demands and must be prioritized in some way over status and parameter data from and to the DSPs. • Correct and efficient synchronization is a must. If possible, different synchronization schemes should be compared to each other. • The achievable performance in terms of guaranteed and maximum data throughput between DSP and microcontroller as well as end-to-end bandwidth has to be estimated. • Apart from the DMA engine analysis, a general evaluation of potential and achieved performance, timing predictability and the remaining microcontroller’s processing capacity (if any) should be executed.