Shponglefan wrote on 2024-01-04, 18:54:

zuldan wrote on 2024-01-04, 08:00:

Is there some bug that can distort these numbers? Or something I can turn off in the BIOS to get the real benchmark speed?

Just based on my own testing, changing the cache write timing from 1 WS to 0 WS resulted in changing the Norton SI CPU benchmark from 132 to 198.

It also resulted in a general performance improvement, but not nearly as dramatic as that Norton SI benchmark would indicate. 😆

Is the machine stable with a WS of 0?

zuldan wrote on 2024-01-04, 21:04:

Is the machine stable with a WS of 0?

I don't know yet. Benchmarking went fine, but I haven't done much testing beyond that.

Yes, Norton SI is really a bad benchmark as far as I know. I believe it runs completely in L1 cache, it does not even make a difference if you have 8kB L1 or 16kB.
As long as you have fast L1 cache access, you have good values. So as already mentioned for L1 cache, L2 cache and memory speed ctcm from Heise is better.