I know this is the Rosetta forum but I find the folding@home forum annoying, and I know that some people participate in both, so I'll ask it here.
The ATI x1600x, x1800x and x1900x graphics cards are usable for folding, and I heard talk that the R600 cards (with nearly half a T-flop of power each) will be used too. Which would give a massive boost to the project (and possibly used for other projects). Does anyone know why nothing has been done yet?

---

I know this is the Rosetta forum but I find the folding@home forum annoying, and I know that some people participate in both, so I'll ask it here.
The ATI x1600x, x1800x and x1900x graphics cards are usable for folding, and I heard talk that the R600 cards (with nearly half a T-flop of power each) will be used too. Which would give a massive boost to the project (and possibly used for other projects). Does anyone know why nothing has been done yet?

Here are some snippest from their own website that could be why.
"There are only certain types of calculations which are well-suited to GPUs. GPus can not run explicit solvent calculations
FAH has to balance the points based on both speed and the flexibility of the client. The GPU client is still the fastest, but it is the least flexible and can only run a very, very limited set of WU's. Thus, its points are not linearly proportional to the speed increase."

---

Jmarks

While the subject of Folding@Home is on the table, I was wondering, is the GPU client separate from the CPU client, i.e. is it a separate executable file? Or is it all integrated into one package? As long as they're separate then one could theoretically use the Folding GPU client, and BOINC for the CPU (as contrasted to the usual configuration of Folding for both CPU and GPU).

---

While the subject of Folding@Home is on the table, I was wondering, is the GPU client separate from the CPU client, i.e. is it a separate executable file? Or is it all integrated into one package? As long as they're separate then one could theoretically use the Folding GPU client, and BOINC for the CPU (as contrasted to the usual configuration of Folding for both CPU and GPU).

I think they are trying that in a beta they just started. They are using only users that have been with the project for 2 years and meet the hardware requirements.

---

Jmarks

While the subject of Folding@Home is on the table, I was wondering, is the GPU client separate from the CPU client, i.e. is it a separate executable file? Or is it all integrated into one package? As long as they're separate then one could theoretically use the Folding GPU client, and BOINC for the CPU (as contrasted to the usual configuration of Folding for both CPU and GPU).

I think they are trying that in a beta they just started. They are using only users that have been with the project for 2 years and meet the hardware requirements.

Are the release versions of the GPU client standalone, though?

---

While the subject of Folding@Home is on the table, I was wondering, is the GPU client separate from the CPU client, i.e. is it a separate executable file? Or is it all integrated into one package? As long as they're separate then one could theoretically use the Folding GPU client, and BOINC for the CPU (as contrasted to the usual configuration of Folding for both CPU and GPU).

I think they are trying that in a beta they just started. They are using only users that have been with the project for 2 years and meet the hardware requirements.

Are the release versions of the GPU client standalone, though?

I am not sure look here.
http://folding.stanford.edu/

---

Jmarks

The answer to that would be yes.

---

While the subject of Folding@Home is on the table, I was wondering, is the GPU client separate from the CPU client, i.e. is it a separate executable file? Or is it all integrated into one package? As long as they're separate then one could theoretically use the Folding GPU client, and BOINC for the CPU (as contrasted to the usual configuration of Folding for both CPU and GPU).

I think they are trying that in a beta they just started. They are using only users that have been with the project for 2 years and meet the hardware requirements.

Are the release versions of the GPU client standalone, though?

Much better to ask them on their forum but last I remember they where not, it used CPU time as well.

---

Team mauisun.org

While the subject of Folding@Home is on the table, I was wondering, is the GPU client separate from the CPU client, i.e. is it a separate executable file? Or is it all integrated into one package? As long as they're separate then one could theoretically use the Folding GPU client, and BOINC for the CPU (as contrasted to the usual configuration of Folding for both CPU and GPU).

I think they are trying that in a beta they just started. They are using only users that have been with the project for 2 years and meet the hardware requirements.

Are the release versions of the GPU client standalone, though?

Much better to ask them on their forum but last I remember they where not, it used CPU time as well.

It only uses about 25% CPU time, even though it looks like more.

---

While the subject of Folding@Home is on the table, I was wondering, is the GPU client separate from the CPU client, i.e. is it a separate executable file? Or is it all integrated into one package? As long as they're separate then one could theoretically use the Folding GPU client, and BOINC for the CPU (as contrasted to the usual configuration of Folding for both CPU and GPU).

I think they are trying that in a beta they just started. They are using only users that have been with the project for 2 years and meet the hardware requirements.

Are the release versions of the GPU client standalone, though?

Much better to ask them on their forum but last I remember they where not, it used CPU time as well.

It only uses about 25% CPU time, even though it looks like more.

Yeah, I picked that up when I was trying to find the answer to my question from their web site, but I was still quite confused. Okay, I guess my question is answered now: So, the GPU client is standalone, but uses some CPU time in the process of utilizing the GPU. Since my graphics card is kinda wimpy, I guess it probably wouldn't be worth the dent it would put in CPU time. Thanks for all your answers, though!

---

When you say wimpy, which card are you referring to. Because I have another question...
As the F@H FAQ says it works on the ATI x1600x, x1800x and x1900x . Does that mean it works on the ATI x1650x and x1950x. Has anybody tried this or know anything about it?

---

When you say wimpy, which card are you referring to. Because I have another question...
As the F@H FAQ says it works on the ATI x1600x, x1800x and x1900x . Does that mean it works on the ATI x1650x and x1950x. Has anybody tried this or know anything about it?

Yes it does

---

Jmarks

When you say wimpy, which card are you referring to. Because I have another question...
As the F@H FAQ says it works on the ATI x1600x, x1800x and x1900x . Does that mean it works on the ATI x1650x and x1950x. Has anybody tried this or know anything about it?

By "wimpy" I mean that it was one of the cheapest AGP graphics cards I could find for my homebrew system. I figured since I don't play much in the way of 3D games, I wouldn't need anything fancy--but then Windows Vista came along and my graphics card can't run Aero. :-( Oh well, XP is fine. Anyway, enough with the off-topic rambling--I don't know exactly what model my card is, all I know is that it's an ATI. I could find out if I dug into Device Manager or the ATI Catalyst software, but then I'm guessing that my CPU time is probably more valuable than my GPU time anyway, so since the GPU Folding app cuts into the CPU time, it's probably not worth it anyway.

---

OK...

#1) You must dedicate a CPU core for each GPU you have crunching. Otherwise, performance stinks. You can use a low-end CPU core such as Pentium D. You can't crunch anything on this CPU core. If you have dual-core CPU, you could use your 2nd core to crunch.

#2) No R600 client for several reasons. (a) remember the GPU client is still in beta. (b) lead GPU programmer was focusing on a PhD thesis. (c) Apparently, it's not simple to "port" from X1950 to R600. The shader processing units are different.

However, Vijay Pande (the director of Folding@Home) just assigned two people to the GPU client. They will also be porting to the GPU client an algorithem they just implemented for the PS3 which will boost performance.

---

OK...

#1) You must dedicate a CPU core for each GPU you have crunching. Otherwise, performance stinks. You can use a low-end CPU core such as Pentium D. You can't crunch anything on this CPU core. If you have dual-core CPU, you could use your 2nd core to crunch.

#2) No R600 client for several reasons. (a) remember the GPU client is still in beta. (b) lead GPU programmer was focusing on a PhD thesis. (c) Apparently, it's not simple to "port" from X1950 to R600. The shader processing units are different.

However, Vijay Pande (the director of Folding@Home) just assigned two people to the GPU client. They will also be porting to the GPU client an algorithem they just implemented for the PS3 which will boost performance.

Ah, I see now. If I would have to dedicate a CPU core to utilize my GPU...not to mention that the GPU can only be utilized when you're not using the computer...then I think I'll just stick with BOINC and other CPU-based distributed computing projects. :-)

---

Not to mention that the R700 is supposedly just around the corner:

"ATI was reported to have a deadline for the Radeon R700, and was slated for the first quarter (Q1) of 2008 release or the second quarter (Q2) of 2008"

Apparently with a new architecture:

"A cluster of smaller GPUs, which will be comprised of modular designed units and connected through an interconnect such as HyperTransport or a FSB, will replace the current single large GPU design used in current high-end graphics cards. Therefore, the R700 will be more modular and more scalable than previous GPUs, paving the way for GPU cores incorporating into CPU cores (the Fusion project)."

GPU vs CPU crunching...

#1) You can't game and GPU crunch at the same time. You can surf the 'net and GPU crunch. You can watch videos and GPU crunch but it slows down the WU by 50% (even once you're done watching the videos).

#2) If you're taking money out of your pocket to buy dedicated folders, it makes sense to go with some GPU or PS3 crunchers. Check out my first post on this page:

http://forum.folding-community.org/ftopic18624-30.html

Basically the total dollar outlay per gigaflop (from upfront purchase cost to ongoing power costs from 24/7 crunching), is much lower for GPU crunching; or stated differently, performance per dollar spent is much higher. My comparison was generous in estimates to the PS3 (to prove a point). GPU > PS3 > CPU.


PS3) The DC programs that do not utilize the PS3's 7 or 8 extra chips (SPEs) are a waste. You can run Boinc on PS3 through linux, but you won't be using the full power, so you're better off with Cure@PS3.


#3) ;) We still need CPU crunchers because there's a limit to the types of units/calculations that the GPU crunchers can do for now. So what I'm doing is putting current dollars to work as GPU crunchers and saving dollars for future CPU crunchers. :)

---

...
PS3) The DC programs that do not utilize the PS3's 7 or 8 extra chips (SPEs) are a waste. You can run Boinc on PS3 through linux, but you won't be using the full power, so you're better off with Cure@PS3.
...

The PS3GRID BOINC project utilizes the PS3's SPE chips, according to their website.

---

I guess what I'm trying to say is that Folding@Home is a worthy project. Though we may not be as excited about their way of doing the protein folding science, I still consider them #2 to Rosetta in their approach. I guess I worry that folks will spread themselves over many projects so that all projects do not have enough computing power for a first definitive BREAKTHROUGH. I wish folks would just stick to either Folding or Rosetta. Oh well.

If Rosetta were to able to fully utilize PS3 or GPUs, then I would commit (on the spot) to donating 6% of my income to build and upgrade a crunching farm just for Rosetta.

---

I guess what I'm trying to say is that Folding@Home is a worthy project. Though we may not be as excited about their way of doing the protein folding science, I still consider them #2 to Rosetta in their approach. I guess I worry that folks will spread themselves over many projects so that all projects do not have enough computing power for a first definitive BREAKTHROUGH. I wish folks would just stick to either Folding or Rosetta. Oh well.

If Rosetta were to able to fully utilize PS3 or GPUs, then I would commit (on the spot) to donating 6% of my income to build and upgrade a crunching farm just for Rosetta.

Lets see 6% of $ 0.00 = 0.00
:)

---

Jmarks