MATHLIB 3.1 cosinus code

David Oboeuf

Other Parts Discussed in Thread: MATHLIB, TMS320C6678

Hi all,

I test the MATHLIB 3.1 in my TMS320 and works very well. But when I recopy the code of cossp_i() in VisualStudio (with some variation to be able to compile the code), I have very different result from the TMS.

Here is one example :

x = 1.33763122558593750000
cosinus float MATHLIB in VS : 0.232292786

cosinus float MATHLIB in TMS320: 0.231057972

Why this difference with the same code?

Kind Regards,

David

over 9 years ago

0 Raja over 9 years ago

TI__Guru* 81335 points

Welcome to the TI E2E forum. I hope you will find many good answers here and in the TI.com documents and in the TI Wiki Pages (for processor issues). Be sure to search those for helpful information and to browse for the questions others may have asked on similar topics (e2e.ti.com). Please read all the links below my signature.

We will get back to you on the above query shortly. Thank you for your patience.

0 Raja over 9 years ago

TI__Guru* 81335 points

David,
Please provide the complete DSP part number.

0 David Oboeuf over 9 years ago in reply to Raja

Prodigy 20 points

Thanks Raja for your answer,

The DSP is a TMS320C6678. But I found my error, I I didn't understood correctly the DSP code, especially: N = _spint(X); /* N = integer part of X */

traducted in C ANSI code by : N = (int)Y;

then the asm insctruction SPINT perform an rounded conversion of Y. The correct C ANSI code is: N = ceilf(Y);

0 Raja over 9 years ago in reply to David Oboeuf

TI__Guru* 81335 points

Hi David,

Thank you so much for your update.

Processors

Processors forum

MATHLIB 3.1 cosinus code