• State
  • Locked Locked
  • Replies 1 reply
  • Subscribers 98 subscribers
  • Views 151 views
  • Users 0 members are here
Support feedback
Options
Options
Related

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.

TDA4VM: Support of vector in custom kernels

Pooja R1
Intellectual 790 points
Part Number: TDA4VM

Hello all,

1. I would like to know exact memory section from where vectors are allocated memory, how does the board internally handle the memory fetching.

2. Observing memory issue when vectors of huge size like 463360 bytes with in function scope.

3. Also I would like to know if above memory fetching be also controlled  via some TI intrinsic (like tivxMemAlloc) where some argument related to memory location for fetching can also be passed while creating vectors.

Kindly let me know some suggestion on this.

Thanks and Regards

Pooja Krishna

  • 0
    TI__Genius 10355 points

    Hi Pooja,

    Every core has heap and scratch memories. Heap memory is typically large and shared with other cores as well, scratch memory is local to the core and the size depends on the application.

    tivxMemAlloc is the recommended utils function for allocating memory either on DDR heap/scratch, L3 or L2 for DSP targets.

    You can take a look at this file for various options,

    <PSDKRA_INSTALL_PATH>/tiovx/include/TI/tivx_mem.h tivx_mem_heap_region_e

    You can check the size of each core's heap/scratch memory here,

    <PSDKRA_INSTALL_PATH>/vision_apps/apps/basic_demos/app_tirtos/tirtos_linux/system_memory_map.html

    Regards,
    Shyam