Sieving drive for k=1003-2000 n=500K-1M

[gd_barnes]

Originally Posted by PCZ

I could do 5T in 30 days yes.
It's just a matter of allocating more tin.

20 fast cores will be 15 days with a bit of time in reserve.
10 fast cores will be 30 days with a bit of time in reserve.

10 cores in 30 days is fine. Your choice. Let me know and I'll put you down for whatever ETA you choose.

Thanks for the final boost!

[PCZ]

Gary
I see that you have Bruce penciled in for a May 15th finish.
If David and I were to finish on or before that date then it all would sync up yes ?

David
I stopped using my VC's for F@H as they get too darn hot.
295's are very expensive as well so i wouldn't want to ruin one running DC clients on it.

[mdettweiler]

Originally Posted by gd_barnes

Max, go ahead with the care package to David as originally discussed...312G for 16 cores and 313G for 16 cores.
...
If so, then we have a plan as Max suggested:
P=30T-40T for David
P=40T-45T for Brian

Okay, care package coming right up.

Edit: just realized I've still got one last question about the distribution of the ranges that I'm not quite clear about yet; I've sent it to you guys via email.

[gd_barnes]

Originally Posted by PCZ

Gary
I see that you have Bruce penciled in for a May 15th finish.
If David and I were to finish on or before that date then it all would sync.

That would work perfect. If you guys want to coordinate amongst yourselves, that works for us.

Max does have the package set up and sent to David for the P=30T-40T range on 32 cores so if anything changes, just be aware of how that could affect the ranges on his various cores.


Gary

[gd_barnes]

Originally Posted by mdettweiler

Okay, care package coming right up.

Edit: just realized I've still got one last question about the distribution of the ranges that I'm not quite clear about yet; I've sent it to you guys via email.

David,

It will likely be a little later than "coming right up". lol

I let Max know in an Email that it should be spread across 32 cores, not 8.


Gary

[IronBits]

I see that... He just needs to edit the below for the right ranges and file name, and do that 4 times and he's done.


start-all1.bat
start "sr2sieve-1" sr2sieve.exe -p 7200e9 -P 7325e9 -i sieve1005-2000-200K-500K.txt -u a -z
start "sr2sieve-2" sr2sieve.exe -p 7431645640543 -P 7450e9 -i sieve1005-2000-200K-500K.txt -u b -z
start "sr2sieve-3" sr2sieve.exe -p 7557141800911 -P 7575e9 -i sieve1005-2000-200K-500K.txt -u c -z
start "sr2sieve-4" sr2sieve.exe -p 7681844285719 -P 7700e9 -i sieve1005-2000-200K-500K.txt -u d -z
start "sr2sieve-5" sr2sieve.exe -p 7807126872287 -P 7825e9 -i sieve1005-2000-200K-500K.txt -u e -z
start "sr2sieve-6" sr2sieve.exe -p 7932031607561 -P 7950e9 -i sieve1005-2000-200K-500K.txt -u f -z
start "sr2sieve-7" sr2sieve.exe -p 8056736819699 -P 8075e9 -i sieve1005-2000-200K-500K.txt -u g -z
start "sr2sieve-8" sr2sieve.exe -p 8181472759337 -P 8200e9 -i sieve1005-2000-200K-500K.txt -u h -z

[Flatlander]

After the rally I will start sieving on two 64-bit cores.
I've lost track off the status here. Is 40-40.5T the first available range?

[Brucifer]

Originally Posted by Flatlander

After the rally I will start sieving on two 64-bit cores.
I've lost track off the status here. Is 40-40.5T the first available range?

I can give you a range of part of my 25000e9 to 30000e9 if you want to help. Like 25000e9 to 26000e9, which should keep your two cores going to approximately the scheduled/anticipated end point for the sieving effort. Talk with Gary and get the data file from him, and I'll leave that range open for you until I hear otherwise.

Bruce

[PCZ]

Flatlander
IB is sieving 30-40I
I am sieving 40-45T

Better get back to it now the rally is over.

[IronBits]

Throttle back on cruise until the sieve job is done.

[Flatlander]

I will start sieving tomorrow when Gary has replied to my PM re. where to sieve.