On 09/09/2014 11:21 AM, Ricardo Nobre wrote:
> I would love to be able to benchmark the LatticeMico32.

Don't forget to include the LUT count, something that your simulations
will not show. From my tests with Coremark, LM32 and mor1kx have similar
maximum clock frequencies in FPGAs, and run at roughly the same speed
(in coremark iterations per second).
But mor1kx uses a lot more LUTs than LM32 (this is the "bloat" I've been
complaining about on IRC and this mailing list), even though its
performance and functionality are not better.

By the way, if you use MiSoC, you can switch between LM32 and mor1kx
with a single command-line parameter of build.py. System-level
simulations are not implemented though (only synthesis, with ISE, Vivado
and Quartus).

Sébastien

_______________________________________________
OpenRISC mailing list
[email protected]
http://lists.openrisc.net/listinfo/openrisc

Reply via email to