This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

What difference among CORE0 and others



Hi,

When the same image is loaded to all 8 cores in C6678, I coarsely suspect that CORE0 should have some difference among others. Otherwise it may deadlock in the communication. Because of so many documents, I have not seen that. If some docs talk about similar things, could you point me to which doc?

 

Thanks.

  • Hi Robert,

    There is no any hardware or architecture difference between Core0 and the others. Commonly, the process of EVM initialization which is defined by GEL file is only executed in core0, you can get more detail by reviewing the GEL file. I think the difference is mainly shown in the software design, we often take Core0 as the master core.

    Allen

  • There are a few slight differences.  Core0 is the core the comes up and out of reset after a PORz, the other cores remain in reset until released from reset to execute by Core0.  Each core has it's own Privileged ID, which can be used to know that it should or should not be executing something (this needs to be programmed into the code if running common code.)  But other than that, it's pretty much as Allen has stated. There is a HW Semaphore block available for sharing of resources which require multiple cores using an IP that cannot handle multiple accesses simultaneously. 

    Best Regards,

    Chad

  • And to add to what Allen said, since the gel file uses core 0 for all single core initialization, many (if not all) application examples use core 0 for further initialization when only one core initialization is needed.

     

    Ran