>strange result - where? Firebird 2.5 SS can't use SMP, so, it
>definitely work slower with parallel threads than 3.0 SMP.

Not in my case, that why it is strange. I mean in your test 2.5 SS is worser than 2.5 Classic. I've set up CPU AffinityMask and as far as documentation says, it allows to process on multiple cores. And in my Case 2.55 SS was two times faster on 4 threads than 2.5 Classic.

uycuFg> I doubt it because it works without any problems on 2.5 SS.
uycuFg> But it does not surprise me that your tests are passing
uycuFg> because you have a different application with different performance results.

well, we did only pure inserts, in one transaction (for each thread),
and connection per one thread.

30000 record per one transacion per one thread is quite a lot (I mean about the case of 32 threads). That might be the cause of a slow down. When I was testing with different thread counts I've found a sweet spot around 4-6 threads (on my i5 machine).

Best regards.