I currently only have my mac mini crunching, and would like to have my X2 Athlon64 crunching as well, unfortunately however, it seems you do not have a 64 bit client available, even though I've compiled the boinc client. (tells me that amd64 binary from your site is nonexistent) is there any way to get the source to this binary?

we will be making the source available within the next week, so stay tuned!

---

the 32bit client runs without problem (if left in memory) on my x2 4400+ on a 64bit windows atm, so you should be fine. (https://boinc.bakerlab.org/rosetta/show_host_detail.php?hostid=494)
results are not too many due to the db purge (funny the two 25 sept results are still there), but if you like you can monitor the computer and see most will be successful and valid.

---

--
Florian
www.domplatz1.de

we will be making the source available within the next week, so stay tuned!

looking forward :)
btw, what language is the app writen in? fortran or c/c++?

---

--
Florian
www.domplatz1.de

c++

nice, have no fortran compiler yet, whould have had to buy one ;)

---

--
Florian
www.domplatz1.de

c++

Just as a side question, how amenable to SSE type instuction sets is the Rosetta code?

There was quite the discussion over on the Find-a-drug boards about this, and the net result was that Keith's algorithm simply could not benefit from SIMD. That doesn't surprise me. I somehow suspect that since what you're up to is about second cousin to what he is doing, that the same holds true, meaning Rosetta can't get as much help from SSE as (for example) 3D rendering can.

---

c++

Just as a side question, how amenable to SSE type instuction sets is the Rosetta code?

There was quite the discussion over on the Find-a-drug boards about this, and the net result was that Keith's algorithm simply could not benefit from SIMD. That doesn't surprise me. I somehow suspect that since what you're up to is about second cousin to what he is doing, that the same holds true, meaning Rosetta can't get as much help from SSE as (for example) 3D rendering can.

rosetta is running quite good so. also w/o sse.
it's a fine running, VERY useful project.

---

@
http://www.bier-rat.de

always glad to hear that the source will be made available.

as for FZB: FWIW, I've also run a precompiled boinc on some other x86 boxen as well as this one, and i've noticed custom-compiled versions run much faster and are much more efficient.

(also: aside from the mac most boxen here run linux...)

---

gerrynjr, as soon as you get yours set up, give me a yell, and help me get mine going. I'll see you in IRC somewhere... thanks.

---

always glad to hear that the source will be made available.

as for FZB: FWIW, I've also run a precompiled boinc on some other x86 boxen as well as this one, and i've noticed custom-compiled versions run much faster and are much more efficient.

(also: aside from the mac most boxen here run linux...)

you mean the BOINC manager or the science apps? optimizing the science app should speed up things, optimizing the core manager should only impact the benchmark results (the rest should not be that noticable as the manager does not run that much).

---

--
Florian
www.domplatz1.de

well, I run a complete 64 bit install, that is, I purposely kill off 32 bit support. I have custom compiled the boinc manager software, however, the source was not avaialbe for the actual science app for rosetta.

This in effect meant I would be unable to crunch...

---

gerrynjr

Since you have decided to exclude all 32 bit code from running on your A64 then you will be able to run didly squat.
This is a mess of your own making so its unfair to expect the project to waste resources trying to cater to your wims.
64 bit computing is in it's infancy and it will be a long time till you can stop running 32 bit code.

---

Actually on my home computer I also run a pure 64bit system and try to avoid 32bit apps whenever possible (and it is basically possible most of the time).
I'd think it would be nice to have 64bit versions. As the application is pretty new I would expect that this shouldn't be much work, but basically be a recompile only. However depending on how much the application is optimized on assembly level I might be wrong.

---

I'd think it would be nice to have 64bit versions. As the application is pretty new I would expect that this shouldn't be much work, but basically be a recompile only.

I can't speak for Rosetta, but I know several people have at various times created 64 bit versions of the SETI app, and the basic opinion has always come back to "there is no point". There is no speed gain, because floating point is floating point and isn't helped. It requires yet another version of everything be maintained. 64-bit processors can run 32-bit applications perfectly well. If an application gains something by being compiled for a 64-bit path, great, but if the only reason to do it is for the 0.000001% of the users who have turned off 32-bit support...

---

I'd think it would be nice to have 64bit versions. As the application is pretty new I would expect that this shouldn't be much work, but basically be a recompile only.

I can't speak for Rosetta, but I know several people have at various times created 64 bit versions of the SETI app, and the basic opinion has always come back to "there is no point". There is no speed gain, because floating point is floating point and isn't helped. It requires yet another version of everything be maintained. 64-bit processors can run 32-bit applications perfectly well. If an application gains something by being compiled for a 64-bit path, great, but if the only reason to do it is for the 0.000001% of the users who have turned off 32-bit support...

It's not that FLOP calculations don't benefit, it's that the SETI program itself doesn't use the type of code to benefit from a 64 bit app.

Rosetta may or may not, it depends on the algorythms.

---

I'd think it would be nice to have 64bit versions. As the application is pretty new I would expect that this shouldn't be much work, but basically be a recompile only.

I can't speak for Rosetta, but I know several people have at various times created 64 bit versions of the SETI app, and the basic opinion has always come back to "there is no point". There is no speed gain, because floating point is floating point and isn't helped. It requires yet another version of everything be maintained. 64-bit processors can run 32-bit applications perfectly well. If an application gains something by being compiled for a 64-bit path, great, but if the only reason to do it is for the 0.000001% of the users who have turned off 32-bit support...

It's not that FLOP calculations don't benefit, it's that the SETI program itself doesn't use the type of code to benefit from a 64 bit app.

Rosetta may or may not, it depends on the algorythms.

Most applications don't benefit from the 64 bit adress space, but from the ability to use more registers in the 64bit modus (for example media encoding) http://www.linuxhardware.org/article.pl?sid=05/02/24/1747228&mode=thread

---

LUE

It's not that FLOP calculations don't benefit, it's that the SETI program itself doesn't use the type of code to benefit from a 64 bit app.

Rosetta may or may not, it depends on the algorythms.

Most applications don't benefit from the 64 bit adress space, but from the ability to use more registers in the 64bit modus (for example media encoding) http://www.linuxhardware.org/article.pl?sid=05/02/24/1747228&mode=thread

I was mostly commenting that the logic of "Seti and Rosetta both are heavily FLOP based, hence - If SETI wouldn't benefit, neither would rosetta" doesn't really apply in all circumstances.

---

I was mostly commenting that the logic of "Seti and Rosetta both are heavily FLOP based, hence - If SETI wouldn't benefit, neither would rosetta" doesn't really apply in all circumstances.

True, but the possible gain vs. cost (in time mostly) would not likely be profitable. So, based on prior experience, I would rather development efforts be placed elsewhere ...

---

we will be making the source available within the next week, so stay tuned!

Is there already some news about going open source of the client?
This week last long ;)
Or did I missed something?

---

Member of Dutch Power Cows