serv VS riscv-cores-list

In short: it works, though the implementation lacks the crystal clarity of FemtoRV32 and PicoRV32. The core is larger than SERV but has higher IPC and (very arguably) a more conventional implementation. The compressed instruction set is easier to expand into regular RV32I instructions than it is to execute directly.

https://github.com/olofk/serv

As for the size advantage: this mattered more when LUTs were precious and when PicoBlaze's competition was either similarly unorthodox (J1 Forth CPU) or several times larger (MicroBlaze). Nowadays, there are very small RISC-V cores like FemtoRV32 Quark or SERV. RISC-V benefits from mainstream open-source tooling and has momentum that's hard to beat.

The RISC-V spec does allow non-trapping behavior and SeRV in particular has non-trapping behavior, which is an important part of how it can fit into 200 4-input LUTs.

https://github.com/olofk/serv#good-to-know

SERV has an RV32I ISA. It is really light. I am sure it will fit.

I have tested SERV on Verilator. It was working without any problems.

Along the same lines of minimizing the amount of logic used at the cost of cycles, there's SERV which uses a bit-serial implementation with a 1-bit data path: https://github.com/olofk/serv

From time to time, I have been tempted to design a RISC-V implementation out of discrete TTL components. Sure, there are plenty of projects out there to build your own processor from scratch, but most of them aren't LLVM targets!

The 32-bit datapaths and need for so many registers makes it a bit daunting to approach directly. That approach would probably end up similar in scale to a MIPS implementation I once saw done like that. (Can't find the link, but it was about half a dozen A4-sized PCBs).

Retreating to an 8-bit microcoded approach and lifting all the registers and complexity into RAM and software is a very attractive idea. It's not like it would ever be a speed demon, either way.

I'm planning to start my Master's thesis on RISC-V verification, so I'm looking for a core that I can use to simulate. I came across this list of cores on github and out of these which would you recommend is ideal for my application. I have only worked on ARM cores before in my internship so the designs were already set up by the company there, but now I am having trouble doing this on my own. I decided to go with the Hummingbirdv2 e203 core as I have experience with verilog, but I am unable to even simulate the test code because of some syntax error. Is there someone who has experience using this core before or can recommend some other core that is straightforward with the setup?

There are 108 RISC-V cores that have been created so far (according to this list), but only a couple are 64 bit, open source and powerful enough that you would want to use them (like Shakti, CVA6 and NutShell)