GPUPI - 1B Vs points

[K404]

This is no benchers fault, so I don't want to discuss this is connection with a specific result.

 

Why are WR points being awarded to a 3.5 second benchmark? How is that going to help increase/improve the perception and respect for overclocking?

Edited April 16, 2015 by K404

[Rasparthe]

I'm not saying I disagree with you since the eventual progression means you will see sub 1sec times, but I'm not seeing how it hurts? The length of the benchmark ties into how highly respected the hobby is?

[K404]

There is no way I can take such a short benchmark seriously. What does 3.5 seconds prove? I can't tell any of my non-benching friends about this and expect any of them to be happy for me or my "achievement" ...... and these are the people who actually care about my happiness.....

How is anyone supposed to "sell" this benchmark to an event promoter or PR guy?

 

 

Who is going to attend an OC event as a spectator for this? Did you sneeze? Sorry, you missed a WR run.

 

Do you see what I mean?

 

 

 

There might also be something very wrong with the benchmark is 1600/1500 is only a fraction faster than 1250/1400, as currently shown in the leaderboard.

Edited April 17, 2015 by K404

[skulstation]

There is no way I can take such a short benchmark seriously. What does 3.5 seconds prove? I can't tell any of my non-benching friends about this and expect any of them to be happy for me or my "achievement" ...... and these are the people who actually care about my happiness.....

How is anyone supposed to "sell" this benchmark to an event promoter or PR guy?

 

 

Who is going to attend an OC event as a spectator for this? Did you sneeze? Sorry, you missed a WR run.

 

Do you see what I mean?

 

 

 

There might also be something very wrong with the benchmark is 1600/1500 is only a fraction faster than 1250/1400, as currently shown in the leaderboard.

 

did you notic that sofos1990 runs 4 gpu's while oldcomer runs 5 gpu's

 

but i am whit you about points for a spalsh and dash benchmark,maybe they whil go for the 32B if the time gose down below 2seconds to run it.

stil waiting for the first to make a run whit 3 or more dual gpu card's

Edited April 17, 2015 by skulstation

[K404]

5? Oh....sorry. All I saw was the "4x" as listed by HWB

[_mat_]

Massman and I have discussed this topic for some time and it was a difficult decision. But I would dare to say, that we came to an understable conclusion. Please hear me out.

 

This benchmark is very different to others that currently receive points. It scales very well with frequency and the number of graphics cards (up to 8 GPUs as theoretical limit). Additionally it likes some cards more than others. So a 290X is more than twice as fast than a GTX 980 ... and those are top modells for gamers and overclockers right now. That enables a huge performance spectrum ranging from an entry card like the HD 7770 or GTX 650 Ti at more than 2 minutes to the current world record of about 4 seconds.

 

Yes, that's too short so let's look at other options: The next official choice would be 32B. The current single card record is 17 minutes, the world record is at about 6. All slower graphics cards will have to crunch for hours to get a result. Clearly the time for 32B as the main category that receives points has not come yet.

 

It would also be possible to introduce a new bench target like 2B or maybe the existing 10B. I didn't propose them, because they are not that magical. 1B and 32B are the analogy to 1M and 32M of our beloved SuperPI and that's why I thought of them as the main categories. But whatever, let's take 10B for example. A GTX 980 with 1200 MHz needs 30 seconds for 1B and about 13 minutes to calculate 10B. Wait a minute ... why 13 and not only 5 minutes (10 times 30 seconds)? That's the problem here. For 1B the benchmark calculates the partial results up to 500 million with a way more efficient kernel. Higher numbers have to use arithmetic with more precision and that will slow down the calculation a lot. So 10B is actually more than 25 times slower than 1B. Too slow to be fun, no doubt.

 

Just for the fun of it I added 2B to the next version of the benchmark. A GTX 980 with 1200 MHz needs about 2 minutes to calculate the result and it may push 4x 290X back to ~20 seconds or so:

 

 

2B might be a good alternative and we should dig into that. It would help the world record time indeed, but would it be more fun for most of us? No, because most of us will bench single card, maybe dual. And that's where 1B is currently the most fun and will be for some time in the future. So fark PR and their theatrics. I wrote this benchmark so overclockers have fun with it and that's all that matters to me. And without any doubts that's also what mattered most to our Turrican.

Edited April 18, 2015 by _mat_

[Rasparthe]

Thanks for the explanation, much appreciated.

[K404]

I agree, much appreciated

 

My questions in reply: Why enable WR points for it, knowing how long it takes a 4+ GPU setup to complete it on day 0?

 

Why code the bench in such a way that it will complete in less time with each new generation of hardware? The benchmark, by design, has a limited shelf-life in terms of stress.

[Gunslinger]

it shouldn't take longer to take the screeenshot than run the bench

[Mr.Scott]

it shouldn't take longer to take the screeenshot than run the bench

 

Doesn't really matter. There's no way to identify multiple cards being used. Only the newest one.

It's a cheats dream come true.

Points for this bench should be discontinued until all the flaws are worked out.

[_mat_]

I agree, much appreciated

 

My questions in reply: Why enable WR points for it, knowing how long it takes a 4+ GPU setup to complete it on day 0?

 

Why code the bench in such a way that it will complete in less time with each new generation of hardware? The benchmark, by design, has a limited shelf-life in terms of stress.

Nobody knew how fast 4x 290X would be on LN2. I had a a guess, but below 4 seconds is surpising nonetheless. In a good way though, the faster the better!

 

I implemented the benchmark like SuperPi so getting faster with each generation is part of the game. Yes, that introduces some problems but it's better than having some batches/second counter. Don't you think?

 

The only thing that comes to my mind is to reverse the problem. We could make the main category 20 or whatever seconds and the end result the number of digits the system was able to crunch in that time. Where I do see a problem is to validate those digits and how to handle them inside the HWBOT system.

[_mat_]

Doesn't really matter. There's no way to identify multiple cards being used. Only the newest one.

It's a cheats dream come true.

Points for this bench should be discontinued until all the flaws are worked out.

The fastest one counts. Try to find a loop hole, then we can talk about discontinuance of points.

[K404]

Yes, that introduces some problems but it's better than having some batches/second counter. Don't you think?

 

 

Well.... I don't feel the same Hence the thread

 

The only thing that comes to my mind is to reverse the problem. We could make the main category 20 or whatever seconds and the end result the number of digits the system was able to crunch in that time. Where I do see a problem is to validate those digits and how to handle them inside the HWBOT system.

 

This was what I was thinking... instead of using the time to completion as the score, have it run for a fixed time and take the average/peak/min iterations per second or run length or similar.

 

 

 

I don't know enough about coding and manipulation to know how easy or hard that is to protect from cheats.

[Mr.Scott]

The fastest one counts. Try to find a loop hole, then we can talk about discontinuance of points.

Or....I could keep it to myself and jump on the GPUPI global points train and wait for the wreck.

Just like UCBench.

That's fine. I'm good with that. Thanks for the time.

[_mat_]

Well.... I don't feel the same Hence the thread

 

I don't know enough about coding and manipulation to know how easy or hard that is to protect from cheats.

No benchmark is really safe from cheating currently.

 

Or....I could keep it to myself and jump on the GPUPI global points train and wait for the wreck.

Just like UCBench.

That's fine. I'm good with that. Thanks for the time.

You are welcome to add your constructive thought here to this discussion. You're right with the rest ... keep it to yourself. Edited April 18, 2015 by _mat_