Folding Forum

JimboPalmer wrote:

Endgame124 wrote:I am aware a cpu does fewer flops. However, it does work that a gpu literally cannot do.

I know it used to. I am unaware of what Core_a7 does that Core_22 can't do. Please explain.

What GPU can load A7 again?

Because Points do not reward importance in any way … Points are awarded as a "measure" of scientific throughput with a loading for Quick Return … GPUs have a higher throughput rate - simples. But GPUs have a 0 throughout on CPU only WUs, so CPUs are infinitely higher in throughout on thos...

Because Points do not reward importance in any way … Points are awarded as a "measure" of scientific throughput with a loading for Quick Return … GPUs have a higher throughput rate - simples. But GPUs have a 0 throughout on CPU only WUs, so CPUs are infinitely higher in throughout on thos...

So if cpu work is just as important, and the cpu work can’t be assigned to GPU, why aren’t they equivalent points?

Is there any reason to expect another 10x increase? Based on the folding stats page, F@H has lost about 200 petaflops from the peak 2 weeks ago - I imagine it will slowly decline, unless the new strain of Covid brings another wave of new / returning folders.

I guess startup peak RAM usage is not so important as it can be swapped temporarily. As long as you have enough swap space available. There have been reports of some of the larger WUs exceeding 5 GB of VM during startup, and not working because too little swap was available. I just caught one WU a ...

Hi everyone I just finished my latest set of benchmarks on the entry level Turing architecture cards. In summary, on Windows 10: GTX 1660 Super: 660K PPD (seeing 750K in Linux but that is only informally tested so far) GTX 1650: 310K PPD Not too bad for these little cards. Anyone else seeing simila...

I would do raspbian over Ubuntu as it’s lighter weight and easier to do things like turn off HDMI. There is a long thread on the Rosetta forums about setting up a pi 4:

https://boinc.bakerlab.org/rosetta/foru ... p?id=13732

...and that is the wholly unanswerable question :( Each of these efforts will be added to the knowledge, each will be adding value, but measuring the value of science is nigh impossible, and then comparing different values is atad bit harder than that. Contributing - wherever - is as far as I am co...

Until the servers can keep up with the current volunteers, I feel adding more frustrated volunteers is misguided. As I said in my previous post, I see really important science being done by the CPU client. Until the servers can keep up with the current volunteers, I feel adding more frustrated volu...

Do we still have an excess of users, relative to WUs? Would more users right now help? Nobody every likes to admit that "we don't want your help right now" but realistically, there is a lot of underutilized hardware out there; which is another way of saying we have an excess of users rela...

We could really use some 2060 and 2060 super numbers. It would really help with the points per watt purchasing decisions, especially when the next gen cards land

If I can figure out remote management, I can provide folding scores for:

APU (both CPU and integrated video)
A10-5800K
A10-7870K

Cpu:
Ryzen 7 2700X

GPU
R250X
Geforce 1080ti.

Is any compelling reason for me to collect any of those? If so, which ones?

Oh, and I'm not having any luck with getting remote monitoring of slot working. Is there any truly valuable data to be seen from seeing 80k ppd from a AMD R250X, or 30k ppd from the integrated R7 video in a A10-7870K?

1660 Super data uploaded (I think). The data set isn't amazing - it seems to have gotten a similar batch of low scoring work for most of the WUs, so similar scores for all but the last WU (around 680ppd). The last WU came in at 1.3M PPD, though, which is higher than I normally see (normally see more...