I wonder then how implementable this is in an FPGA for accelerating the whole thing? This could be a killer use of the FPGA instances on AWS and similar cloud services.
Well, no, other way around more likely - the most practical way of building programs for these systems would probably be through VHDL/Verilog with a specialized toolchain.
(edit: although actually FPGAs could be useful simply because they can be very good at running FFTs (as are GPUs), not because of the gate-programmable nature of them)
HDLs have no special advantage in evaluating boolean operations in simulation. Most simulators are significantly slower than native code unless they use compiler infrastructure used by mainstream languages and even then they still have the penalty of maintaining the simulation environment which serves no purpose in this application.
They don't describe logic gates directly. They are used to formulate boolean expressions which are mapped into gates or an equivalent structure by synthesis software. Outside of special circumstances, no one is manually crafting individual gates when writing with an HDL. that is left to the back end tooling. If the target isn't hardware then normal programming languages are just as good. There is no magic speedup when HDLs are simulated and you just pay the penalty of keeping track of simulated time and sequencing of events that don't matter if you just want to compute an answer.
(edit: although actually FPGAs could be useful simply because they can be very good at running FFTs (as are GPUs), not because of the gate-programmable nature of them)