• State Resolved
  • Locked Locked
  • Replies 1 reply
  • Subscribers 81 subscribers
  • Views 275 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.

TMS320F28388D: Question about TMS320F28388D

Jimmy Huang
Genius 3985 points

Part Number: TMS320F28388D

Hello:

The main frequency of this 28388 chip is 200M, but there is a weighted calculation method. I would like to ask, according to TI's weighted calculation method, does 28388 exceed 8.0 trillion floating-point operations per second? That is, 8.0 TFLOPS

  • +1
    TI__Mastermind 27895 points

    Jimmy,

    • We do not do any official TFLOP measurement as mandated by https://www.bis.doc.gov/index.php/documents/product-guidance/865-practioner-s-guide-to-adjusted-peak-performance/file
    • It will certainly not be anywhere near 8 TFLOPs. TFLOP is 10^12 .  200 Mhz CPU * 4 will be 8 * 10^8 (not 10^12).
    • The traditional MFLOPs would be more appropriate to use in the case of F2838.
      • The theoretical max FPU computation capability is as follows.
      • Two CPUs can do max of 2 F64 operations in parallel each. 
      • Two CLAs can do max of 2 F32 operations in parallel each.
      • So, that is roughly 200 * 2 * 2(CPUs) = 800 MFLOPS for F64 operation + (200 * 2 * 2(CLAs)) = 800 MFLOPS for F32 operations. (Please note that these are the theoretical Max possible). Please understand that the practical realization in real life code with the C compiler will be much lesser.

    Thanks,

    Sira