as far as to which is faster, they will switch back and forth as the new versions are released. ATI will release a card that is faster than the Nvidia latest. Then Nvidia will release another in a couple months that is faster than that. Same with Intel and AMD...

And there is going to be the ATI is faster on project A while NVidia is faster on project B to come...

Kinda moot really right now as ATI is not capable of doing BOINC ... yet ...

The thing that may help ATI in the long run is the fact that their GPUs will do double precision FP (NVidia is single precision only).

If a science application needs to validate results across multiple processors, then it can't use single precision on some apps, and double precision on others.

... either that, or you only validate CUDA results against CUDA and only validate Intel Core2 against Intel Core2, and AMD to AMD.

---

Really considering how buggy the app is faster just means it will return invalid results quicker.

Also I'm pretty sure Nvidia is quicker because there isn't an ATI app and it's not like people can port the Nvidia app to ATI until it is stable.

A lack of a working application doesn't mean that nVidia is/will be faster given proper coding for an ATi chip.

It does imply this discussion is pointless... Even more so because CUDA doesn't run on ATI it will not be a apples to apples comparison.

The discussion was simply about wishing ATi had an app, and it was speculating that it would be faster than nVidia, then the conversation quickly turned to people insisting that ATi would not be as fast as nVidia, to which I countered that we will not know until there is an app.

Of course the conversation is pointless, as all wishful thinking threads are, but that doesn't prevent people from dreaming.

ATI doesn't have CUDA because CUDA is NVIDIA's name for their hardware.

If ATI has something, it'll have a different name.

---

when are the graphics coming back for the screensaver ? I miss the scree saver graphics.

---

Jason Tobin
Alien Hunting Specialist

when are the graphics coming back for the screensaver ? I miss the scree saver graphics.

Why don't you post in more threads that should make the screen saver come back quicker.

---

already post it in 2 other threads

---

Jason Tobin
Alien Hunting Specialist

The discussion was simply about wishing ATi had an app, and it was speculating that it would be faster than nVidia, then the conversation quickly turned to people insisting that ATi would not be as fast as nVidia, to which I countered that we will not know until there is an app.

Of course the conversation is pointless, as all wishful thinking threads are, but that doesn't prevent people from dreaming.

I believe that with F@H Nvidia produces more PPD, I don't see a reason to think it would be any different with SETI.

---

already post it in 2 other threads

Yeah exactly my point.

---

already post it in 2 other threads

Yeah exactly my point.

LOL...

Agreed.

Be that as it may, would not generating a screensaver graphic kind of defeat the purpose of running the science app on the GPU in the first place? ;-)

Alinator

already post it in 2 other threads

Yeah exactly my point.

LOL...

Agreed.

Be that as it may, would not generating a screensaver graphic kind of defeat the purpose of running the science app on the GPU in the first place? ;-)

Alinator

Well, not necessarily ...

In the days when CPUs were on circuit boards a common practice was to hook an ocilloscope to a pair of D/A converters that were hooked to the address bus (one on high bits the other on the low bits) and the engineers could tell how the computer was running based on the trace patterns on the screen. When it was running properly the traces would have specific characteristics... when it was in distress or crashed, well, different traces.

Sea Story two:

When I was working a McClellan AFB one of the projects we worked on used an HP workstation to host the Oracle database. I used to sit in the conference room where the HP sat to work as much as possible. The project manager was annoyed by this as he wanted me to work in the cubicles on a terminal ... the only problem was that I continually proved that by sitting in the conference room I could immediately intervene when the system became "troubled". Even though I explained that it was relatively easy to tell, all you had to do was listen to the disk drives ... when the HP was in trouble the sounds out of the drives changed ...

I did similar things when working on an ATE system that used tape drives, keep an eye on the tapes from across the room and you can tell if the system is working normally ...

All that as prelude ...

I always thought one of the coolest screen-savers would be to have the data store be the actual visual memory ... as the values changed in the data store the pattern on the screen would change. I often wonder if we would not be able to detect proper vs improper processing of tasks by this means alone ...

Forth aside ...

This is one of the best ways to test random number generators ... pull numbers off and then plot them x,y ... good generators will eventually color the screen ... one of the other mods to this is to increment the color number as it hits the same points ... the Apple II had such a bad RND that it only produced 17,000 some numbers before repeating ...

---

LOL, this thread is kinda lame. Dudes with ATI cards shouting about how they can do better with something that does not even exist yet.

Best get yourselves fitted with Nvidia's then you could contribute something of use here !!!

Checkout this baby
http://www.guru3d.com/article/geforce-gtx-295-preview/

---

The discussion was simply about wishing ATi had an app, and it was speculating that it would be faster than nVidia, then the conversation quickly turned to people insisting that ATi would not be as fast as nVidia, to which I countered that we will not know until there is an app.

Of course the conversation is pointless, as all wishful thinking threads are, but that doesn't prevent people from dreaming.

I believe that with F@H Nvidia produces more PPD, I don't see a reason to think it would be any different with SETI.

Because the code written for F@H is custom, and as far as I know, ATi didn't even help develop it. Again, with a decent coder and compiler, amazing things can happen. nVidia has been very active in helping F@H and now S@H so that they can sell more chips (good business sense), but it has nothing to do with if ATi were to help code with their chips. Not to mention that the ATi code isn't even optimized for the Radeon HD 4xxx series, which is ATi's big winner right now.

So there's plenty of reasons right there that suggest it could be different on both F@H and S@H.

---

Sure a number of reasons other then an actual example where ATI is faster.

---

Sure a number of reasons other then an actual example where ATI is faster.

Gee...up until now, I thought my FX5200's were just fine....
I only wanted to see them to see the boot screen, not crunch......

---

"Time is simply the mechanism that keeps everything from happening all at once."

I hardly see how that has anything to do with anything actually. You could have bought the latest ATI cards and you would still be in the same possition.

The point is there are PPD comparison between ATI and Nvidia out there and I don't see one example in this thread saying ATI is faster. I also haven't heard of one else where either. Is there an example of ATI being faster? I'd like to see it, I think it would be great.

So other then a bunch of talk about something that might be and assumptions of things not being done right elsewhere when it comes to the ATI GPU client, there isn't much substance here.

---

I hardly see how that has anything to do with anything actually. You could have bought the latest ATI cards and you would still be in the same possition.

But I do not have any ATI cards......never have...

Nvidia cards have always booted and run fine for me...for what they were intended for...graphics........
What is YOUR point?

And I am happy in my position....dark side down....LOL.

---

"Time is simply the mechanism that keeps everything from happening all at once."

The point is everyone know what happens when they assume...

---

The point is everyone know what happens when they assume...

And just what have I assumed, my friend?

---

"Time is simply the mechanism that keeps everything from happening all at once."

Well your the one that quoted and responded to me when I was actually responding to OzzFan, I have no idea what your talking about.

Sure a number of reasons other then an actual example where ATI is faster.

Gee...up until now, I thought my FX5200's were just fine....
I only wanted to see them to see the boot screen, not crunch......

---

Well your the one that quoted and responded to me when I was actually responding to OzzFan, I have no idea what your talking about.

Sure a number of reasons other then an actual example where ATI is faster.

Gee...up until now, I thought my FX5200's were just fine....
I only wanted to see them to see the boot screen, not crunch......

Pardon me if I missed your quote and got into the middle of something....

My bad, my apology....carry on then......

---

"Time is simply the mechanism that keeps everything from happening all at once."