Vladimir

Looking at the surrounding code there's already a `inline recursive` pragma before each call to this function. Does that get ignored? Is inlining itself a problem (that messes with the...

is this the same issue that was observed in #878?

I'm reviewing it. Slowly :smiley: . But it's next in line, then HGQ.

This PR was refactored to introduce the new unrolled implementation as a "strategy", to be an alternative to existing latency and resource strategies. This allowed the the matrix-vector multiplication kernel...

> its very important for me to solve this problem Is this homework assignment? :smile: Your model is too big, you need to reduce the number of filters, a lot....

Try with 10-50k parameters, not half a million. All weights will be stored on chip, so you can't really go large

Why do we need multidimensional weights here? Passing pointers doesn't work as expected? I like the idea, we'll need it in the future for Vitis, but the `keep_dims` approach feels...

There's a fix for this in #961 (that PR needs bit more work to clean up)

`ReuseFactor: 1` -> everything will be unrolled, every multiplication will use a separate DSP. You don't have that many DSPs on your board. Not a bug.

`Project/solution path '/home/abdo/PycharmProjects/lenet5/new test/model_hls4ml/myproject_prj' contains illegal character ' '.` explains itself. Try changing your output path to not include spaces.