HI,
I have a hand-tuned ASM routine I wrote that is highly efficient.
_my_speedy_ASM_routine(float*, float*, int, int)
However, it gets called within a loop that my goal is to have it be SW pipelined:
for (i=0; i<numChans; ++i)
{
<i1>
<i2>
...
_my_speedy_ASM_routine(pIn, pOut, size, length)
}
Can I inline this ASM routine in the loop to get the advantages of SW pipelining?