• State Resolved
  • Locked Locked
  • Replies 3 replies
  • Subscribers 82 subscribers
  • Views 1489 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.

CCS/TMS320F28379D: TMU usage and float strict directive

Colombo Carlo
Mastermind 24650 points
Part Number: TMS320F28379D


Tool/software: Code Composer Studio

Hi everybody , 

i m on latest CCS and using latest compiler 

on processor wiki here : http://processors.wiki.ti.com/index.php/C2000_Performance_Tips_and_Tricks

I foudn this :

When TMU support is enabled and the --fp_mode=relaxed option is selected, the compiler will automatically replace library calls to these operations with hardware instructions. If the floating point mode is strict (the default setting, --fp_mode=strict), the compiler will issue performance advice if it encounters any opportunities for replacing library calls with TMU instructions

I was expecting to see warnings by compiler if  mode =strict , but they do not happen .

if I put  "relaxed "  instead  TMU is used 

coudl you kindly clarify me how to get warnings  when using STRICT   and  why you need this strict/relaxed  option  ?

thank you 

bets regards

Carlo

  • 0
    TI__Guru**** 251270 points

    For the source file you build when this happens ...

    Colombo Carlo said:
    I was expecting to see warnings by compiler if  mode =strict , but they do not happen .

    ... please follow the directions in the article How to Submit a Compiler Test Case.

    Thanks and regards,

    -George

  • 0 in reply to George Mock
    TI__Mastermind 24650 points

    Hi George , 

    I was able to generate warnings , it was my fault .

    please coudl you tell me about  strict vs restricetd  for the float  to get TMU used by compiler ?

    thakn you 

    bets regards

    Carlo

  • 0 in reply to Colombo Carlo
    TI__Guru**** 251270 points

    Colombo Carlo said:
    please coudl you tell me about  strict vs restricetd  for the float  to get TMU used by compiler ?

    I think you mean to ask about the effect of the compiler options --fp_mode=strict and --fp_mode=relaxed.  This quote comes from the C28x compiler manual.

    The default floating-point mode is strict. To enable relaxed floating point mode use the --fp_mode=relaxed option. Relaxed floating-point mode causes double-precision floating-point computations and storage to be converted to integers where possible. This behavior does not conform with ISO, but it results in faster code, with some loss in accuracy.

    Thanks and regards,

    -George