Why is this arithmetic question considered opinion based?

Question

What’s the fastest known Koblit’z curve addition or substraction law for fpga that maximizes the per lut throughput?

I’m not asking how to implement it, but how adding or substracting 2 points on an elliptic curve is done at the mathematical level when the target is a fpga instead of regular computer hardware.

It’s also not a pure computer science question : on fpga, faster stuff can use more area and thus be slower : using primes in elliptic curves for example allows faster cpu/gpu computation because those machines typically lacks carryless multiply instructions. Folks at SuperUser or Crypto.stackechange would close this as a hardware question, especially since they might never did hear about what is a fpga or an asic while on the reverse course, crypo accelerating chips are common.

I might be wrong, but I’m sure a question that would have asked the same thing for floating points instead of elliptic curve would not have been closed. At least not for this reason.

Answer 1

This is the wrong community to be asking, about 90% of the people here do circuits, there are a few that do DSP and FPGA. We closed it for your benefit as well as ours since it's about crypto and options on coding/HDL algorithms (HDL is on topic, in depth on a cyrpto algorithm is outside the scope) . Yes you could argue that it is on topic, but I don't think anyone can answer it on this site and it doesn't really fit the mold, so it was closed.

We want the questions here to be answered and a good set of questions for circuit design/EE.

Edit:

This is not a fit on cryptography.SE

Do we accept questions asking for cryptanalysis of your cipher (hash function, ...) design?

No, we do not. If you want peer review of your full cryptographic scheme, here is not the place to acquire it. However, you might like to break your problem down into specifics, such as "under these conditions, does structure X have desired security property Y?" which would be a perfect fit for us.

Answer 2

My honest reason, being one of the voters:

Because there is no longer a generic "off-topic" close button

You're asking a pure computer science question but there's no way to close it as such, so I probably just took whatever was the first reason someone else used. In this case it happened to be "opinion-based".

I have no idea why I can't close a question as "off-topic" but for some reason I can vote to move it to Superuser, but here we are. On another place where I have close-vote privileges I can do "This question does not appear to be about retrocomputing, within the scope defined in the help center." but not here.