YOU are arguing semantics - the point was that they can do it.
Also, just because Eth is better on GPU than most FPGA doesn't mean shit - it CAN be done on FPGA, it's just not as good. It's better for some things, not for others.
They can do it if they're capable of actually doing it. That was the whole point of what we're talking about, you're taking a position that a FPGA is just a better GPU. I took the position that a FPGA is somewhere in between a GPU and a ASIC, in that it can do more then a ASIC, but not nearly as much as a GPU (hence a different class they represent and why you can't actively compared a FPGA to a GPU).
Literally just proved the point by showing that FPGAs can't do everything a GPU can do, you said it's semantics.
FPGAs are in a completely different class... You could lump ASICs into that comparison too. They also can mine multiple algos... They just have to be built from the ground up each and every time. To that extent, so do miners for GPUs (depending on how different the algo is from other ones already made), but the time requirement is quite a bit different.
The whole memory bit was about needing to buy different FPGAs for different algos, much like ASICs, because depending on what you're mining, a FPGA can't always do it. You don't need a new FPGA for every algo, but you do for others... Still once again somewhere in between GPUs and ASICs.
And a 2GB 370X can't do everything a 390X can do -- are they in different "classes" now?
I didn't say an FPGA was a GPU, far from it - I took the point that they are similar from a MINING standpoint.