2,080 karma · joined May 20, 2024
Possibly a good addition to the article would be parallel development of an lkm. I guess it wouldn't have that windows interop but I would also be interested to see how this driver would be implemented on Windows. If it's idk 10x as many lines in the kernel vs userspace, that's a great benefit to the userspace approach.
I'll also note that I haven't had success with just more physical adapters. The drivers complain they can't create a CRTC for them.
That said, I'd much rather have the extra core.
Consider me educated on the mantissa. That's a nifty pedantry.
Typo in the c++?
> cout << "x =/= x: " << ((x=x) ? "true" : "false") << endl;
Should be x != x?
For the leading 0 counter, I've found it's even better for the tool if I use a for loop. Keeps things scalable and it's even less code. I'm not understanding this takeaway though
> Sometimes a good design is about more than just performance.
The good design (unless the author's note that it's easier to read and maintain makes it worse design?) was better performing. So sometimes a good design creates performance.
Likewise for pipelining: it would have been interesting to know if the tools can reorder operations if you give them some pipeline registers to play with. In Xilinx land it'll move your logic around and utilize the flops as it sees fit.
If you use PCIe, theoretically you don't need to reverse engineer how they implemented because you're not at the edge of the spec like they are here.
That said, I've thought about doing what they're doing countless times and it is nice to see it would work.
I'll also note that it has a ton of SRAM onboard which doesn't shrink well, so I'm not convinced just by that extrapolation that you could eclipse it with a simple lithography shrink. Unless you really meant several per wafer, which doesn't really feel like a hard target...
(Firefox, Android (which is Linux))