I would to add to you discussion at this point:

I run a ASUS GTX1070 Strix 8 gig and my work units complete in under 13 Hrs every time, this while running Universe@home on the CPU to keep it busy while crunching GPUGRID.

You will be very well of getting the 1070 and if you could get the 1080 do it.

Just ensure you get a GPU with Samsung RAM as there are manufacturers that used other RAM that is giving problems.

You will be very well of getting the 1070 and if you could get the 1080 do it.

One more comment from my side, if I may. From my experience the performance gain of the 1080 over the 1070 (OC) in terms of crunching is very little whereas the purchasing price is 50% higher. Retrospectively, I would not buy the 1080 again but stick to a good overclocked and silent 1070. The 1080 may have advantages in gaming.. but those are of little importance here.

---

I would love to see HCF1 protein folding and interaction simulations to help my little boy... someday.

I have two 1070s in my main rig because I took into consideration crunching speed, power consumption and SLI frame rates at 4k. So far, I'm very happy. Although my only complaint is when an exclusive application is running and then closes only one of the GPUs fires back up for a WU. Both WUs say they are running but one of them is at 1600mhz core but 0% gpu load. It never goes away on it's own and I have to restart the computer to get the 2nd card to do any crunching.

Sometimes if I have extra work units on one machine and one isn't doing anything I abort the spares and quickly update GPUGrid on the idling system, seems to work pretty well.

And bone dry again... seems that we can go over to crunching even more complex molecules, can't we? Cut them into slices and we get plenty of work for everyone... hopefully.

---

I would love to see HCF1 protein folding and interaction simulations to help my little boy... someday.

I tried moving some hardware to GPUgrid again but no work again.

Hell, I'm even struggling to get short units, most of my GPUs are idle or doing other projects unfortunately just to keep my house warm.

The tasks are very low at the moment, only 73 to send. I hope this doesn't mean the start of another shortage again.

We are almost at the critical point again where people's GPUs will be idling due to lack of work, we only have 2200 running with 0 tasks ready to send.

As usual - folding@home is the answer ;)

I woke this morning and checked the status of processing only to find the system idling, is there currently a work shortage? I set the system to run Seti Institute date, however, I would much prefer to be running protein simulations.

is there currently a work shortage?

yes, there is.
This happens once in a while.

Theoretically I am sure there could be other groups/people wanting to simulate on GPUGRID instead of us having it idle, it is however quite complicated to organize collaborations, simulation priorities etc.

One more question, Stefan, if I may. Can your students possibly be involved in this kind of distributed computing? Maybe in the course of a laboratory tutorial, making their own simulations and evaluations on simple proteins, using spare power of GPUGRID. There are quite a few benefits from that approach,

- you could feed the (frequently empty) short run queue.
- you may save work time by outsourcing some minor problems to students
- you may benefit from creative thinking of students
- future researchers can familiarize with this kind of simulation and become group members occasionally

and eventually even distinguish between long runs, short runs and short "student" runs so that crunchers may choose between purely scientific and educational application. And in case the interface to GPUGRID is not yet open to students, that provides an opportunity for a diploma thesis.

In view of the recurrent lack of GPU jobs ... I would like to get back to my previous proposals, see above. Even if students dont make every experiment right, I would really prefer running those "educational" tasks on my machine and help young scientists to work into the matter instead of creating ballooned prime numbers or looking for Aliens in space. Just a thought.

---

I would love to see HCF1 protein folding and interaction simulations to help my little boy... someday.