[SOLVED] What's the FPGA technology status for y = x ^ (1/N) (N is limited range floating)

[legendbb]

Without having any floating point processing unit in a CPU per say.

I can only imagine of using LUTs to provide limited resolution.

Are there any better technology?

Thanks,

8-O

 

[pbernardi]

Have you considered a DSP soft core?

 

[legendbb]

Have you considered a DSP soft core?

"DSP soft core" is it, floating point processing unit in a soft core CPU like MicroBlaze?
If so, I am afraid of it's out of consideration, since I need deterministic latency.

 

[FvM]

FPGA vendors have log() and exp() floating point IP with single or double accuracy. They should work for the application. I expect that they are using some kind of "hybrid" algorithm, combination of tables with interpolation and separate handling of exponents.

 

[legendbb]

FPGA vendors have log() and exp() floating point IP with single or double accuracy. They should work for the application. I expect that they are using some kind of "hybrid" algorithm, combination of tables with interpolation and separate handling of exponents.

Thanks for your comment, I think you hit the point right on.

 

[phongphanp]

Engineering is hard to say than science ,ever.