Prev: Possible Solution
Next: Kernel image size
From: Ari Okkonen on 21 Jan 2010 19:36 Thank you for the reference. I got the paper. There seems to be several design decisions to do for a multicore system. The current state of our project is: * Locking seems to work (for single processor systems) - Priority ceiling protocol -> no deadlocks, no priority inversion - Separate read only and read/write locking - You cannot inadvertently access shared data without proper locking. Locking policy is enforced by CASE tool, design language, and code generator support * We are now finalizing the installer for the development system. * The system will be released as ReaGeniX/ReaGOS version 2.2.4 Many thanks for all of you who have posted comments and tough questions for us to be considered. Contact me, if you are interested to evaluate or explore the solution. Best Regards Ari Okkonen Niklas Holsti wrote: > Ari Okkonen wrote: ,,, >> We have to do some redesign to our kernel for multi-processor systems, >> anyway. Any pointers to multi-processor PCP (or multi-processor mutex >> problem in general) texts are highly appreciated. > > Before writing my comment above, I looked at this report: > > Jim Ras, Albert M.K. Cheng, "An Evaluation of the Dynamic and Static > Multiprocessor Priority Ceiling Protocol and the Multiprocessor Stack > Resource Policy in an SMP System," Real-Time and Embedded Technology and > Applications Symposium, IEEE, pp. 13-22, 2009 15th IEEE Real-Time and > Embedded Technology and Applications Symposium, 2009. > > http://doi.ieeecomputersociety.org/10.1109/RTAS.2009.10 > > |