• State TI Thinks Resolved
  • Locked Locked
  • Replies 1 reply
  • Answers 1 answer
  • Subscribers 98 subscribers
  • Views 704 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.

TDA4VL-Q1: Deep-learning Performance Calrification btw TDA4 AL/VL/VE

Jack
Mastermind 9155 points
Part Number: TDA4VL-Q1
Other Parts Discussed in Thread: TDA4VE-Q1, TDA4VL

Hi TI

As ti.com has updated with TDA4VE-Q1 and variant devices, A customer begins to investigate this new deivce.

They found something to be clarified about Deep-learning Performance of those devices.

While We have promoted TDA4VE to the custoemr earlier, We said TDA4AL up to 8 TOPS, TDA4VL upto 4 TOPS, TDA4VE upto 8 TOPS according to below table.

Customer would like to get clarified the exact Deep-learning Performance of the respective devices to revise their business proposal to client.

Please answer to the question above regarding Deep-learning Performance.

Also make clarification on Datasheet too since many of customer would ask the same question to us in near future.

Thanks.

Regards, 

Jack

  • 0
    TI__Guru 54512 points

    Jack,

    The Deep Learning TOPS is dictated by the speed grade.  You can find which parts support which speed grade in the Device Comparison table:

    This table defines the C7x/MMA speed:

    The TOPS is equal to the C71SS speed multiplied by 8.  So, 1 GHz is 8 TOPS, 750 is 6 TOPS and 500 is 4 TOPS.

    Regards,

    Kyle