[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [MiNT] gcc 68000 vs 68020-60 vs 68060 comparison



On 1/15/10 10:52 AM, Vincent Rivière wrote:
Miro Kropacek a écrit :
or mintlib is
not very good testcase (since it uses a lot of external stuff)

As a good real-world benchmark, I propose you to try bzip2.
It is a quite small program, easy to recompile. At runtime, it is
notoriously slow on any machine. You can try to compress a file of some
size, let's say 1 MB, and see how much time it takes. You should try
with a file big enough no not be annoyed by the speed of disk access.
Then you can rebuild bzip2 with the different CPU options, and see the
timing differences.

You should run each test several times and take the last time probably to negate the effects of disk and cpu cache?

Thanks,
mark