frame

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Sign In

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

How to use the shave to get the square root of a 32-bit float ?

I see this in the documentation, but there are no samples or documentation for how to use it:

/* 3.3.13 SAU.SQT /
/
Square root function */

half __builtin_shave_sau_sqt_f16_l_r ( half ); /* SAU.SQT.f16_l /
half __builtin_shave_sau_sqt_f16_h_r ( half ); /
SAU.SQT.f16_h */

We're using this in an embedded product. I can use inline assembly or the C++ moviCompile compiler.

The objective is to do a square root of a 32-bit float, on the shave, as fast as possible.

Since this has a 'high' and 'low', is that for two bytes of the float at a time? How is it used?

There are a dozen other functions like this that I'd like to use as well, but can't because of poor documentation.

Thank You,
Jeff

Comments

Sign In or Register to comment.