Skip to content

Conversation

@lukaszsobala
Copy link

Hi,

Thanks for developing FAMSA!

Firstly I must say that I am not a software engineer, I am just using the LLM coding tools. I am proposing these changes as is and I will not be able to answer technical questions about the approach. What I can say is that the changes are enough to port FAMSA to riscv64 (-march=rv64g). The program compiles (gmake PLATFORM=rv64g) and works.

Some simplification of the nested loop in refresh.mk is also proposed.

The specific riscv64 device I possess has the architecture rv64imafdvcsu, which also supports compressed and vector extensions (rv64gcv). It may be possible that they can make the program faster. I do not know which architecture target is most common for riscv64 software. If superflouous, the target rv64gcv can be removed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant