This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Speed-up computing via coprocessor

Hello All!

Does anybody know if it's possible to speed-up computing if trigonometric functions (eg. sin/cos) by direct access to coprocessor functions via asm modules included in C code? For example, if I replace the C code:

y = sin (x);
- with the asm function which calls coprocessor Sin function:
y = sin_cor (x);
...
float sin_cor (float x)
{
#pragma asm
...
#pragma endasm
return x;
}