Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Does Vitis BLAS gemv support fixed point number(ap_fixed)? #207

Open
longcntn opened this issue Nov 12, 2024 · 0 comments
Open

Does Vitis BLAS gemv support fixed point number(ap_fixed)? #207

longcntn opened this issue Nov 12, 2024 · 0 comments

Comments

@longcntn
Copy link

Hi everyone,

I would like to ask if the vitis BLAS library GEMV supports hls ap_fixed type?

If it does, how do I use it correctly (template args, coding style..?)?

The situation is the gemv giving completely wrong output - not even because of the precision as it was completely different from the correct result (all csim, cosim, and hardware). Change the data type to C++ double and the gemv kernel works properly.

From what I understand, there are two implementations of the dot product method in xf:blas::DotHelper class. One of them use dot_dsp() for data types that are not float or double. That why I think it may work for fixed point as well. but so far, I have failed to make it work.

Best regards

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant