1) Message boards : Graphics cards (GPUs) : Maxwell now (Message 40061)
Posted 26 days ago by Profile skgiven
The 970 reminds me of the 660Ti, a lot.
2) Message boards : Graphics cards (GPUs) : Mixing gpu gnerations (Message 40057)
Posted 26 days ago by Profile skgiven
Speed loss compared to what?
If you are talking about an old motherboard, CPU, HDD and DDR2 vs a new-ish system then the considerations extend well beyond the PCIE bus speeds. In my experience DDR2 vs DDR3 = 10% loss in itself, but that was some time ago (different apps).

I would probably just get a new motherboard, CPU, RAM and take it from there.

WRT PCIE, basically, PCIE1 X16 = PCIE2 X8 = PCIE3 X4, so it should work, but the bigger the card the greater the loss.

BTW. You may still be able to sell your old (broken) 570, and get something for it, but make sure you get the postage right!
3) Message boards : Graphics cards (GPUs) : GTX 960 (Message 40056)
Posted 26 days ago by Profile skgiven
You appear to be crunching Einstein on your CPU.
Ask yourself a question - Why?

Huh? I did measure power draw.

It went from 320W down to 275W. Approx. -15% compared to my GTX 980. Both with lower power limit.

4) Message boards : Graphics cards (GPUs) : Maxwell now (Message 40004)
Posted 30 days ago by Profile skgiven
For here, the MCU usage is lower on the GTX970 than on the GTX980.
Although the 970's bus width is effective 224+32 and suggestions are that 224bits are predominately used, the lower MCU usage might still be explained by the marginally favourable (by 7%) shader to bus ratio of the 970 over the 980 (1664 over 224bits vs 2048 over 256bits) and slightly lower GPU clocks.
However, and despite some interpretations, I think its possible that all 256bits of the bus are actually used for accessing up to 3.5GB of GDDR5, after which it becomes 224bits for the first 3.5GB and 32 for the next 0.5GB.

While on the whole the 2MB to 1.75MB cache doesn't appear to have any impact, it might explain some of the relative performance variation of different WU types.
5) Message boards : Graphics cards (GPUs) : NVidia GPU Card comparisons in GFLOPS peak (Message 39983)
Posted 30 days ago by Profile skgiven
Updated with the GTX960 (approximate values):

    Performance GPU Power GPUGrid Performance/Watt 211% GTX Titan Z (both GPUs) 375W 141% 116% GTX 690 (both GPUs) 300W 97% 114% GTX Titan Black 250W 114% 112% GTX 780Ti 250W 112% 109% GTX 980 165W 165% 100% GTX Titan 250W 100% 93% GTX 970 145W 160% 90% GTX 780 250W 90% 77% GTX 770 230W 84% 74% GTX 680 195W 95% 64% GTX 960 120W 134% 59% GTX 670 170W 87% 55% GTX 660Ti 150W 92% 53% GTX 760 130W 102% 51% GTX 660 140W 91% 47% GTX 750Ti 60W 196% 43% GTX 650TiBoost 134W 80% 37% GTX 750 55W 168% 33% GTX 650Ti 110W 75%

Throughput performances and Performances/Watt are relative to a GTX Titan.
Note that these are estimates and that I’ve presumed Power to be the TDP as most cards boost to around that, for at least some tasks here.
I don’t have a full range or cards to test against every app version or OS so some of this is based on presumptions based on consistent range observations of other cards. I’ve never had a GTX750Ti, GTX750, 690, 780, 780Ti or any of the Titan range to compare, but I have read what others report. While I could have simply listed the GFLOPS/Watt for each card that would only be theoretical and ignores discussed bottlenecks (for here) such as the MCU load, which differs by series.

The GTX900 series cards can be tuned A LOT - either for maximum throughput or less power usage / coolness / performance per Watt:
For example, with a GTX970 at ~108% TDP (157W) I can run @1342MHz GPU and 3600MHz GDDR or at ~60% TDP (87W) I can run at ~1050MHz and 3000MHz GDDR, 1.006V (175W at the wall with an i7 crunching CPU work on 6 cores).
The former does more work, is ~9% faster than stock.
The latter is more energy efficient, uses 60% stock power but does ~ 16% less work than stock or ~25% less than with OC'ed settings.
At 60% power but ~84% performance the 970 would be 34% more efficient in terms of performance/Watt. On the above table that would be ~214% the performance/Watt efficiency of a Titan.

I expected the 750Ti and 750 Maxwell's also boost further/use more power than their reference specs suggest, but Beyond pointed out that although they do auto-boost they don't use any more power for here (60W). It's likely that they can also be underclocked for better performance/Watt, coolness or to use less power.

The GTX960 should also be very adaptable towards throughput or performance/Watt.

PM me with errors/ corrections.

6) Message boards : Graphics cards (GPUs) : PCIE Riser? (Message 39742)
Posted 36 days ago by Profile skgiven
Using one is likely to increase your error rate somewhat. They're not very reliable.

From past experience I would agree, but you can keep the slightly higher error rate down by using a good PSU, not overclocking, and running cool (which is easier anyway).
Well made (copper wire/connector) risers are ok, but there are some low-grade (cheap alloy) versions. If it looks as cheap as tin, it is.
As GPU's take power from the PCIE slot it's a good idea to get a riser with a power cable (often molex). This covers the PCIE power loss from the cable length and additional connection.
Overclocking on a riser would be pushing it, but I expect the Maxwell's are a lot more power resilient and reliable on a riser than the Keplers and previous generations.
7) Message boards : News : WARNING/CHALLENGE: VERY LONG WU (VERYLONG_CXCL12_confAna) (Message 39648)
Posted 39 days ago by Profile skgiven

6) Search the file for that GERARD_VERYLONG_CXCL12_confAna text we started with. There will be many search hits: we are looking for a <file>...</file> section like this:

<file> <name>2x23-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3250_0_9</name> <nbytes>0.000000</nbytes> <max_nbytes>128000000.000000</max_nbytes> <status>0</status> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file>

7) Make sure you have exactly the right section: the last number before </name> should be _9, and there should be an <upload_url> line.

8) Change the first three numbers after <max_nbytes> from 128 to 256. Just those three numbers - don't accidentally delete any punctuation, change the number of zeroes, or make any other change.

9) Repeat steps (6), (7) and (8) for each separate VERYLONG task that you have on the system.

10) Save the file, restart BOINC, and relax. All done.

Why is it that max_nbytes only needs to be change for the _9 file, and not the others? - TIA

<file> <name>2x10-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3907_1_1</name> <nbytes>0.000000</nbytes> <max_nbytes>50000000.000000</max_nbytes> <status>0</status> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file> <file> <name>2x10-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3907_1_2</name> <nbytes>0.000000</nbytes> <max_nbytes>50000000.000000</max_nbytes> <status>0</status> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file> <file> <name>2x10-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3907_1_3</name> <nbytes>0.000000</nbytes> <max_nbytes>50000000.000000</max_nbytes> <status>0</status> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file> <file> <name>2x10-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3907_1_4</name> <nbytes>0.000000</nbytes> <max_nbytes>256000000.000000</max_nbytes> <status>0</status> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file> <file> <name>2x10-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3907_1_5</name> <nbytes>0.000000</nbytes> <max_nbytes>10000000.000000</max_nbytes> <status>0</status> <gzip_when_done/> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file> <file> <name>2x10-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3907_1_6</name> <nbytes>0.000000</nbytes> <max_nbytes>10000000.000000</max_nbytes> <status>0</status> <gzip_when_done/> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file> <file> <name>2x10-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3907_1_7</name> <nbytes>0.000000</nbytes> <max_nbytes>10000000.000000</max_nbytes> <status>0</status> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file> <file> <name>2x10-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3907_1_8</name> <nbytes>0.000000</nbytes> <max_nbytes>256000000.000000</max_nbytes> <status>0</status> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file> <file> <name>2x10-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3907_1_9</name> <nbytes>0.000000</nbytes> <max_nbytes>256000000.000000</max_nbytes> <status>0</status> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file> <file> <name>2x10-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3907_1_10</name> <nbytes>0.000000</nbytes> <max_nbytes>10000.000000</max_nbytes> <status>0</status> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file> <file> <name>2x10-GERARD_VERYLONG_CXCL12_confAna-0-1-RND3907_1_11</name> <nbytes>0.000000</nbytes> <max_nbytes>5000000.000000</max_nbytes> <status>0</status> <upload_url>http://www.gpugrid.org/PS3GRID_cgi/file_upload_handler</upload_url> </file>
8) Message boards : News : Important: No new work for pre-Fermi GPUs (Message 39565)
Posted 41 days ago by Profile skgiven
In terms of compute capability and performance/Watt anything before a GTX400 series GPU is like trying to crunch with a hot fossil.
You simply can't expect to advance science if you crunch with dark ages technology; everything that could be done pretty much was.

Don't feel obligated to crunch on new kit however, upgrade as and when you choose and contribute if and when you choose - it's your choice.
We experienced crunchers, mods and researchers just give free expert advice to people with a common interest - take it or leave it.
9) Message boards : Graphics cards (GPUs) : Big Maxwell GM2*0 (Message 39520)
Posted 45 days ago by Profile skgiven
CC5.5 would make sense.

To equal Kepler for DP performance a 3072shader GM200 card would need to have 1/4 DP capable shaders and then it would still be likely have a ~250W TDP. There would be no purpose in doing that (possibly 1/3 but I doubt it). So I agree that GM200 is probably not going to be a high end DP card to replace GK Titans, and is going to be a lot more like a GM104 than you would expect from a big version of Maxwell.
I'm just expecting a slightly more refined architecture tweaked to use up to 12GB DDR5 and not much else unless it adds DirectX 12.1, OpenGL 4.6, or some updated port version.

So 50% bigger than a GTX980, a 384bit bus, 12GB GDDR5 (& likely a 980Ti version with 6GB) and a fat price tag.

NV could still launch a 990 and another dual Titan at a later date; performances would be well spaced out.

According to NV, the successor to Maxwell will be Pascal (previously called Volta) and this is still due in 2016, so I think GM200 is 28nm and a 16nm Pascal is more likely than what would be a fourth generation Maxwell by then. 1/2 to 1/4 DP might reappear on 16nm.

Off topic, Pascal is supposed to introduce 3D memory and Unified memory (CPU can access it) and NVlink for faster GPU to CPU and GPU to GPU communications. These abilities will widen possible research boundaries, making large multi-protein complex modelling (and similar) more accurate and whole organelle modelling possible.
10) Message boards : Graphics cards (GPUs) : GTX 960 (Message 39517)
Posted 45 days ago by Profile skgiven

Probably an FOC, but if its a base clock, 1266 is 12.4% higher than that of a Ref. GTX980 (1126MHz), and I'm running a 970 at 1350, so that scales (1350*1.124) to >1500MHz.

Next 10