[QUOTE=S485122;118203]The credit FFT sizes are based on non SSE2 processors, they are a bit higher : cross over to 2560KB at 40250000, while in the program you find the cross over at 39500000.

Jacob[/QUOTE]

Thx for the explanation.

So people will feel their machines a little bit "slow down" (adding fewer P90 years) as they crunching in between 39500000 and 40250000 :squash:

[quote=nngs;118241]Thx for the explanation.

So people will feel their machines a little bit "slow down" (adding fewer P90 years) as they crunching in between 39500000 and 40250000 :squash:[/quote]
Yes. Best not to publicize this, or even more people will abandon
exponents in this range than are are doing so already:smile:

[QUOTE=davieddy;118430]Yes. Best not to publicize this, or even more people will abandon
exponents in this range than are are doing so already:smile:[/QUOTE]

What if M45 in that region? :wink::wink:

[QUOTE=davieddy;118430]Yes. Best not to publicize this, or even more people will abandon
exponents in this range than are are doing so already:smile:[/QUOTE]

I'll get to them...eventually...=].

So one would be better off putting exponents in the range 39.5M-40.25M on an older CPU that doesn't have SSE2 (in terms of maximizing throughput)?

[quote=Kevin;118488]
So one would be better off putting exponents in the range 39.5M-40.25M on an older CPU that doesn't have SSE2 (in terms of maximizing throughput)?[/quote]
Yes. That would make the best of GIMPS resources, and result
in credit where it's due.