Any results on this so far? Any beta-testers needed? :)
I would like to help on speed optimization, but i don't know what is the way of it. Probably i can put my code on a webpage, but i think it would be not legal. I didn't get any e-mails in connection with legitimacy.
This is my fault -- I got caught up in some urgent things at this end. I've just written to you off-list.
Yes. Akosf has done three things to speed up our executable. One of these optimizations is very clever: it eliminates large numbers of (slow) divisions. We're in the process of building and testing new executables (for all platforms) that incorporate these changes. They should result in very substantial speed-ups.
One of these optimizations is very clever: it eliminates large numbers of (slow) divisions. We're in the process of building and testing new executables (for all platforms) that incorporate these changes. They should result in very substantial speed-ups.
That's great news guys :)
I'll be running 100% Einstein for some time now, because I'm running out of network traffic (wtf) .. so this may be just in time.
Yes. Akosf has done three things to speed up our executable. One of these optimizations is very clever: it eliminates large numbers of (slow) divisions. We're in the process of building and testing new executables (for all platforms) that incorporate these changes. They should result in very substantial speed-ups.
Bruce
If you need someone to help test in Linux, just give a shout!
I am really looking forward to this.
such things just should not be writ so please destroy this if you wish to live 'tis better in ignorance to dwell than to go screaming into the abyss worse than hell
Yes. Akosf has done three things to speed up our executable. One of these optimizations is very clever: it eliminates large numbers of (slow) divisions. We're in the process of building and testing new executables (for all platforms) that incorporate these changes. They should result in very substantial speed-ups.
Bruce
If you need someone to help test in Linux, just give a shout!
I am really looking forward to this.
I'm also running Einstein exclusively in Linux and would love to help.
Yes. Akosf has done three things to speed up our executable. One of these optimizations is very clever: it eliminates large numbers of (slow) divisions. We're in the process of building and testing new executables (for all platforms) that incorporate these changes. They should result in very substantial speed-ups.
Bruce
Sounds really, really great. Looking forward to the new bins
We're in the process of building and testing new executables (for all platforms) that incorporate these changes. They should result in very substantial speed-ups.
Any news? Are new binaries arriving?
I'd like to suggest to make anyway an SSE2 optimized version of the albert application (expecially for Win).
For Seti, I saw that the best boost is done with SSE2 optimization, and a lot of people own an SSE2 enabled CPU.
It shouldn't be too time-expensive to build only one optimized version...
I'd like to suggest to make anyway an SSE2 optimized version of the albert application (expecially for Win).
For Seti, I saw that the best boost is done with SSE2 optimization, and a lot of people own an SSE2 enabled CPU.
Read below, in the same thread we are now, a post from Bernd Machenschalk. He has tested it, to find that SSE2 does not give a significant improvement over SSE in Linux compiling with gcc.
And for Windows, he says there is no significant improvement when using SSE or SSE2 over the default optimizations from MSVC compiler.
RE: RE: Any results on
)
This is my fault -- I got caught up in some urgent things at this end. I've just written to you off-list.
Cheers,
Bruce
Director, Einstein@Home
Any News?
)
Any News?
RE: Any News? Yes.
)
Yes. Akosf has done three things to speed up our executable. One of these optimizations is very clever: it eliminates large numbers of (slow) divisions. We're in the process of building and testing new executables (for all platforms) that incorporate these changes. They should result in very substantial speed-ups.
Bruce
Director, Einstein@Home
Sounds excellent! That's
)
Sounds excellent!
That's the spirit and why I like this Project alot :o)
RE: One of these
)
That's great news guys :)
I'll be running 100% Einstein for some time now, because I'm running out of network traffic (wtf) .. so this may be just in time.
MrS
Scanning for our furry friends since Jan 2002
RE: RE: Any News? Yes.
)
If you need someone to help test in Linux, just give a shout!
I am really looking forward to this.
such things just should not be writ so please destroy this if you wish to live 'tis better in ignorance to dwell than to go screaming into the abyss worse than hell
RE: RE: RE: Any
)
I'm also running Einstein exclusively in Linux and would love to help.
BORG
RE: RE: Any News? Yes.
)
Sounds really, really great. Looking forward to the new bins
RE: We're in the process
)
Any news? Are new binaries arriving?
I'd like to suggest to make anyway an SSE2 optimized version of the albert application (expecially for Win).
For Seti, I saw that the best boost is done with SSE2 optimization, and a lot of people own an SSE2 enabled CPU.
It shouldn't be too time-expensive to build only one optimized version...
RE: I'd like to suggest to
)
Read below, in the same thread we are now, a post from Bernd Machenschalk. He has tested it, to find that SSE2 does not give a significant improvement over SSE in Linux compiling with gcc.
And for Windows, he says there is no significant improvement when using SSE or SSE2 over the default optimizations from MSVC compiler.