• State
  • Locked Locked
  • Replies 1 reply
  • Subscribers 98 subscribers
  • Views 367 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.

Question about C6678 SRIO sample project

g.f.
Guru 15520 points


Hi,

I have a question about C6678 SRIO sample program which is in MCSDK.

There is "SRIO_TputBenchmarkingTestProject" in pdk_C6678_1_1_2_6.
In SRIO_TputBechmarkingTestProject, there are five test scenarios supported.

My question is about the following test scenarios:
*5.3 Two EVMs connected using breakout cards
*5.5 Two EVMs connected using an external SRIO switch

What is the difference between this two scenarios?
I guess  the difference is whether it communicate via a switch.
Does a transfer rate have a difference by the case where a switch is used?

My opinion is that two EVM are directly connected with SRIO on breakout cards,
so that using breakout cards scenario is faster then SRIO switch scenario.
Am I correct?

best regards,
g.f.

  • 0
    TI__Genius 13235 points

    Hi g.f.,

    Below is some feedback on your questions.

    g.f. said:
    What is the difference between this two scenarios?
    I guess  the difference is whether it communicate via a switch.

    Yes, you are correct.

    g.f. said:

    Does a transfer rate have a difference by the case where a switch is used?

    My opinion is that two EVM are directly connected with SRIO on breakout cards,
    so that using breakout cards scenario is faster then SRIO switch scenario.
    Am I correct?

    Most likely there will be some latency introduced by the switch, but it may be negligible. You should not see a difference in the overall bandwidth.

    The effect that the presence or absence of a switch has on the system will really depend on the specific setup that you are testing. However, the throughput example is provided so that you can benchmark different configurations yourself.

    You can also take a look at the data presented in the SRIO section of the Throughput Performance Guide for C66x Keystone Devices (http://www.ti.com/lit/pdf/sprabk5).

    Please let us know if you have any other questions or comments.

    Thanks,

    Clinton