• State
  • Locked Locked
  • Replies 1 reply
  • Subscribers 98 subscribers
  • Views 271 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.

OMAP-L137: Can ARM926E run AES Encryption algorithm on four VoIP channels (each at 64Kbps)?

Electrons4me
Intellectual 530 points
Other Parts Discussed in Thread: OMAP-L137

Hello,

My customer is using the OMAP-L137 in their system. They would like to know if they can AES encrypt 4x VoIP channels (each at 64Kbps) using the ARM9 CPU. Would TI or the community have some benchmarking on this?

I did find a research paper showing a side by side comparison of AES encryption ran on a C6201 and a Pentium-Pro, both running at 200MHz. The throughput was well above 50Mbps for the Rijndeal Algo. In comparison, the four channels VoIP traffic at a total of 256Kbps (4x64Kbps) is well below 1% of what either the C6201 and the Pentium-Pro were able to encrypt/decrypt. I believe it might be safe to assume that the ARM9 at 375MHz-456MHz can do this with lots of headroom but some benchmarking data would be welcome.

Thanks
Electrons4me

 

  • 0
    TI__Genius 14545 points

    Electrons4me said:
    I believe it might be safe to assume that the ARM9 at 375MHz-456MHz can do this with lots of headroom but some benchmarking data would be welcome.

     

    We don't have benchmarking for this specific application, however if the algorithm is in C you can use the Cycle-Accurate Simulator in Code Composer Studio to determine what is the theoretical load on the ARM926 as compared to the C674x DSP. and bench mark this compared to your paper.