Here is a screenshot. It is taken when all 3 gpu's are running guppi vlar on CUDA. The middle one is a GTX1080. Current NVIDIA linux driver does not name it correctly.

|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 980     On   | 0000:01:00.0      On |                  N/A |
| 44%   65C    P0   121W / 230W |   1009MiB /  4036MiB |     98%      Default |
+-------------------------------+----------------------+----------------------+
|   1  Graphics Device     On   | 0000:02:00.0     Off |                  N/A |
| 43%   63C    P0   104W / 215W |    812MiB /  8113MiB |     91%      Default |
+-------------------------------+----------------------+----------------------+
|   2  GeForce GTX 980     On   | 0000:03:00.0     Off |                  N/A |
| 41%   59C    P0   132W / 230W |    763MiB /  4037MiB |     93%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID  Type  Process name                               Usage      |
|=============================================================================|
|    0       855    G   /usr/bin/X                                     186MiB |
|    0      1433    G   compiz                                          59MiB |
|    0      4366    C   ...thome_x41zc_x86_64-pc-linux-gnu_cuda65_v8   757MiB |
|    2      4370    C   ...thome_x41zc_x86_64-pc-linux-gnu_cuda65_v8   757MiB |
+-----------------------------------------------------------------------------+

And the executable name is different from the actual version since I have a makefile that I update manually and I haven't changed the executable name accordingly.


And now they are running some non guppi work.

|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 980     On   | 0000:01:00.0      On |                  N/A |
| 45%   69C    P0   137W / 230W |   1021MiB /  4036MiB |     91%      Default |
+-------------------------------+----------------------+----------------------+
|   1  Graphics Device     On   | 0000:02:00.0     Off |                  N/A |
| 45%   68C    P0   125W / 215W |    812MiB /  8113MiB |     84%      Default |
+-------------------------------+----------------------+----------------------+
|   2  GeForce GTX 980     On   | 0000:03:00.0     Off |                  N/A |
| 43%   62C    P0   138W / 230W |    763MiB /  4037MiB |     90%      Default |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID  Type  Process name                               Usage      |
|=============================================================================|
|    0       855    G   /usr/bin/X                                     198MiB |
|    0      1433    G   compiz                                          59MiB |
|    0      5411    C   ...thome_x41zc_x86_64-pc-linux-gnu_cuda65_v8   757MiB |
|    2      5407    C   ...thome_x41zc_x86_64-pc-linux-gnu_cuda65_v8   757MiB |
+-----------------------------------------------------------------------------+

---

To overcome Heisenbergs:
"You can't always get what you want / but if you try sometimes you just might find / you get what you need." -- Rolling Stones

For those interested in electic bill and power consumption of GTX1080

Thanks for that.

20W less for Guppies, 10W less for non-Guppies; although I notice the GPU utilisation on the GTX1080 is slightly less than the other cards, the maximum power rating for that card is still less than the maximum for the GTX 980s.

All are running at their boost frequency?
And how many WU/hr for the GTX 1080 v GTX 980?

---

Grant
Darwin NT

For those interested in electic bill and power consumption of GTX1080

Thanks for that.

20W less for Guppies, 10W less for non-Guppies; although I notice the GPU utilisation on the GTX1080 is slightly less than the other cards, the maximum power rating for that card is still less than the maximum for the GTX 980s.

All are running at their boost frequency?
And how many WU/hr for the GTX 1080 v GTX 980?

GPU at 1825 MHz for the 1080
and
at 1300 MHz for the 980's.

Mem clocks 7210 MHz for the 780's and 10010 MHz for the 1080.

Some boost set up here and there but not too much.

---

To overcome Heisenbergs:
"You can't always get what you want / but if you try sometimes you just might find / you get what you need." -- Rolling Stones

And the software is heavily modified, so that the numbers can be compared only against eachother, but not with a current official software. I'm running my own builds and modifications.

---

To overcome Heisenbergs:
"You can't always get what you want / but if you try sometimes you just might find / you get what you need." -- Rolling Stones

GPU at 1825 MHz for the 1080
and
at 1300 MHz for the 980's.

Good to see.

And (roughly) how many WU/s per hour are they processing?

---

Grant
Darwin NT

GPU at 1825 MHz for the 1080
and
at 1300 MHz for the 980's.

Good to see.

And (roughly) how many WU/s per hour are they processing?

First number is gtx1080 and the latter is a 980.
High ar: 46 - 67 seconds per task. (78 to 53 per hour)
Mid ar: 132-209 seconds per task. (27 - 17 per hour)
Very Low ar: a way less than 500 seconds per task. (approx 215 240 sec to 360sec). (17-12 guppi per hour)

So the avg depends on the current Arecibo/guppi/whatever ratio.

and for the next questions an answer in advance:
AP:s see a 25% speedup with a gtx1080 compared to the gtx980. I have not had time to optimize the code for the gtx1080 yet.

---

To overcome Heisenbergs:
"You can't always get what you want / but if you try sometimes you just might find / you get what you need." -- Rolling Stones

First number is gtx1080 and the latter is a 980.
High ar: 46 - 67 seconds per task.
Mid ar: 132-209 seconds per task.
Very Low ar: a way less than 500 seconds per task. (approx 215 240 sec to 360sec).

So the speedup there is more (even if only slightly) than just the extra clock speed.

and for the next questions an answer in advance:
AP:s see a 25% speedup with a gtx1080 compared to the gtx980. I have not had time to optimize the code for the gtx1080 yet.

Never done AP myself, but i'm sure someone would have asked.
:-)
So the speedup there looks mostly clock related.
But given that the current CUDA50 application resulted in slightly less work done per/hr on Maxwell than on previous architectures, no drop in output for AP (and an increase for MB) using code meant for a previous architecture makes the outlook for Pascal very good indeed.
Thanks for the info.

---

Grant
Darwin NT

I infer that the power numbers shown in the first post are those for the card itself as self-reported. This won't be the total end-user impact power as it can't see additional power attributable to:

1. power supply imperfect efficiency
2. additional power consumed by the system CPU to run the support application
3. additional power consumed in other system components including memory and I/O as required by both the GPU and the CPU support application.

Nevertheless, as a comparison between the two generations of cards, this seems likely to be pretty fair, and unless I don't understand something suggests a rather substantial improvement of the electrical power productivity running the applications you tested, with perhaps some hope of additional advantage gained by a possible newer application employing more enhancements giving more benefit from Pascal attributes.

Overall this seems rather encouraging for the Pascal generation. Much depends on how Nvidia and the card suppliers price future cards (and perhaps adjust the prices of announced cards if competition warrants).

I have a 1070 on pre-order which I hope means it will arrive within a week. Your results give me better hope for it.

Thank you Petri33.

---

Ah bravo Petri, bravo! :)

I was thinking of creating one of these threads for Mark and any other multi-PC multi-GPU mega-crunchers but was waiting for all sorts of dust to settle. But seeing as the cat's outta the bag:

Quick back-of-the-napkin math (with the napkin being imagined inside my head) I'm seeing about a $30-$40 saving for every $100 in SETI electricity compared to the 980... Is that about right? Not to mention the 980 you are comparing it to was one of the kings in the performance-per-watt category... meaning older/other GPUs will perform worse (750Ti being the outlier).

HAL, you're the king of kWh and $ around here, care to have an early stab at this? :)