JoergF wrote:

Strange. My 1070 does not get better than 90% and the 1080 is even worse, maybe 75%. No matter how many tasks and the CPU/GPU ratio. As if the algorithm is not yet Pascal optimized.

But this gets off topic a little... maybe I should bring that question forward somewhere else.

FWIW my 1060 runs @ 95% with 2 tasks at a time at stock settings. What's truly amazing is that according to my UPS it's only pulling 45 watts.

One at a time ADRIA_1JWP_dist (Win8.1 OS) on GTX 1070 and GTX 1060 (3GB) have higher GPU usage than SDOERR CASP (a3d) or GERALD CXCL12.

ADRIA_1JWP_dist:
-- GTX 1070 (PCIe 3.0 x8) @ 2.1GHz: 78% GPU / 32% MCU / 52% BUS / 109W power
-- GTX 1060 (PCIe 3.0 x4) @ 2.1GHz: 82% GPU / 32% MCU / 63% BUS / 96W power

GTX 1070 ADRIA_1JWP_dist completed runtime will be ~30% faster. (8hr vs. 11.6hr)
Non-ADRIA (GTX 1060) WU's are closer to 20~25% slower than GTX 1070.

Pascal's power consumption really shine though even when the card OCed.
My 970's are starting to feel old as it's power consumption / performance ratio struggle keeping up with Pascal.
Pascal already have a very high out of the box boost negating overclocking. Even at 2.1GHz Pascal core scale for slight performance with PCIe 3.0 x4. For those who fine tune their cards locating it's highest stable operating point - Pascal is the easiest and least fun to manage.

Thanks,

The proof of concept CASP runs have fewer atoms, so GPU utilization is generally lower. It's probably the case that the bigger the GPU the lower the utilization for such work units. This might even be exasperated with the Pascals compared to Maxwell GPU's (or not)...

[..]The runs that include atomic contacts take longer because they involve calculating contact interactions too.
In theory these should utilize the GPU more (but I haven't looked to see if that's the case or not).

CASP runtimes (atom and step amount) vary so this just a general reference.

GTX 1070 (PCIe 3.0 x8) CASP runtimes:

-- 1ns (ntl9) 600 credits = 240/sec @ 2.1GHz / 59% GPU / 15% MCU / 37% BUS / 78W power
-- 1ns (a3d)= 1,350 credits = 330/sec @ 2.1GHz / 70% GPU / 24% MCU / 39% BUS / 96W power

-- 5ns (ntl9) 3,150 credits = 1,200/sec @ same usage and power numbers as 1ns
-- 5ns (a3d) 6,900 credits = 1,600/sec @ same usage and power numbers as 1ns

GTX 1060 (3GB) PCIe 3.0 x4 CASP runtimes:

-- 1ns (ntl9) 600 credits = 300/sec @ 2.1GHz / 63% GPU / 17% MCU / 51% BUS / 74W power
-- 1ns (a3d) 1,350 credits = 450/sec @ 2.1GHz / 74% GPU / 24% MCU / 59% BUS / 88W power

-- 5ns (ntl9) 3,150 credits = 1,500/sec @ same GPU usage and power as 1ns
-- 5ns (a3d) = 6,900 credits = 2.275/sec @ same GPU usage and power as 1ns

IMO: a (1152CUDA GTX 1060) is on par with (2048CUDA GTX 980) and ~20% faster than a (1664CUDA GTX 970). The (1920CUDA GTX 1070) is as (if not) ~5% faster than a (2816CUDA GTX 980ti).

CASP WU on (2) GTX 970 at 1.5GHz are 2.5~2.7x slower with PCIe 2.0 x1 compared to PCIe 3.0 x4.
WU's require PCIe 3.0 x8 for proper OC scaling.

-- 1ns: 900/sec vs. 350/sec
-- 5ns: 4770/sec vs. 1761/sec

-- PCIe 2.0 x1: 46% GPU / 7% MCU / 80% BUS usage / 75W GPU power
-- PCIe 3.0 x4: 57% GPU / 12% MCU / 40% BUS / 107W

For reference I'm seeing ~81% GPU utilization on a GTX970 on Linux (Ubuntu x64 16.04 LTS) crunching a CASP22SnoS_crystal_ss_contacts task. PCIE Bandwidth Utilization is ~17% (PCIE2 x16). It's a low-spec system but I'm not using the CPU for anything else. When I do the GPU's performance drops off. When I run a cartain mt CPU app on another system (W10) the GPU utilization drops to ~15%

Since the 9.14 app is CUDA 8.0, and there is a couple of CUDA8.0 drivers for Windows XP I've installed my GTX 1080 under Windows XP x64 with the latest XP driver available for GTX 960 (368.81), but the 9.14 app did not work with this setup. It said that the

Is there anyone, who is using a GTX 1080 or TITAN X (Pascal) under Linux with swan_sync on?
Is the new (9.14) Linux app supports swan_sync?

WDDM performance degradation versus Linux or XP is similar to PCIe width affecting runtimes. PCIe3.0 x4 runtimes can be ~10% slower if PCIe 3.0 x8 not an option. (Maybe the AMD Zen platform will have more than the 16/28/40 CPU PCIe3.0 lanes Intel currently offers.

WDDM performance degradation versus Linux or XP is similar to PCIe width affecting runtimes. PCIe3.0 x4 runtimes can be ~10% slower if PCIe 3.0 x8 not an option. (Maybe the AMD Zen platform will have more than the 16/28/40 CPU PCIe3.0 lanes Intel currently offers.

I admit that I did not work into the matter yet. Is there any way to bypass the WDDM degradation? It is somewhat frustrating to see a 1080 performing worse than a 1070 or 980ti just because of low utilization. Actually I dont get more than 75% load on my 1080.

Thanks... to my mind the config cannot be the bottleneck. I run 2 Tasks with 1 virtual CPU core per task [1CPU/0.5GPU] and utilize a i7-3770S which should be fast enough. But now that you mention it, I still have an old 1155 board in my primary PC that is PCIe2.0 only and therefore the GTX 1080 is linked by PCIe2.0x16 which is equal to PCIe3.0x8 in terms of throughput. Can this be the reason?

My other system is less affected, maybe because the board is a new 1151 and the GTX 1070 GPU therefore utilizes PCIe3.0x16. The CPU is also a little faster (6700K) but I guess it has nothing to do with it.

Besides, it would be of interesting to know how the task algorithms work. If there are large data blocks transferred, the bandwith doesn't really matter. (provided that the work time of the GPU per subtask is long enough). You would see some downward peaks in the GPU utilization occasionally. But in case the CPU/Memory and GPU are permanently exchanging little data slices, it could explain why limited bus bandwith would slow down the entire performance. If so, maybe something can be done on the code side in order to keep the Pascal (and the upcoming Volta) type GPU busy.
____________
I would love to see HCF1 protein folding and interaction simulations to help my little boy... someday.

Thanks ... the mainboard is an ASUS P8P67-M (socket 1155) and definitely PCIe2.0 only. Yes, the CPU does support 3.0 but the board doesn't and so it could be part of the issue, as you wrote.

No, i dont use the iGPU or VM in the background. So I guess I should simply upgrade my system components. Frankly I am waiting for AMD Zen or Intel Cannonlake in order to get noticable extra speed. Upgrading from Ivy Bridge to Kaby Lake now does not make much sense to me, maybe aside from DDR4 Memory which could be some advantage.

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

If I were you I would swap the 1070 with the 1080 or try to pick up a second hand PCIE3 1055 motherboard for now.

Noticed all the 1080's and 1070's are reporting 4GB graphics memory. IIRC it's not an issue.

A good upgrade time will be when the GTX1080Ti and Zen arrives and are available in sufficient quantities and with competition for prices to be reasonable. That might be in 6 to 9 months time, but possibly more depending on the competition.

Comparing two tasks; one which ran on the 970 and the second which ran on the 1060-3GB I can say on my setup that the 1060-3GB is ~ 3% faster than the 970 and uses ~9% more CPU.

Thanks. You have saved me the trouble. That is a nice improvement for the GTX 1060, but not enough to buy a new card. I will leave my GTX 970 on GPUGrid, and my 1060 on Folding, where it gets as much improvement, if not a little more, due to the Quick Return Bonus.

In this case the 1060-3GB is ~10% faster than the GTX970 and the CPU usage is also around 10% greater. As most tasks at GPUGrid tend to be longer, 10% might more accurately reflect the differences between the cards than the short tasks; which spend as much time loading but less time running. So ~10% faster for ~45% less energy ~60% better in terms of performance/Watt

When I start to crunch on the GPU the system uses ~125W, so the GPU is using ~75W.
Of note is that my 1060 only has one 6-pin power connector (which only delivers up to ~75W)! So perhaps I'm being power capped? It's a small PCIe-2x16 motherboard, and although there's a 12-pin ATX power connector I wouldn't be surprised if the GPU isn't drawing power from the PCIE slot.

13A per contact (16AWG wire in small connector) to 8.5A/contact (18AWG wire). This means that using common 18AWG cable, 6-pin connector specified for 17A of current (3 contacts for +12V power, 2 contacts for GND return, one contact for detect). 8-pin have 25.5A current specification (3 contacts for +12V power, 3 contacts for GND return and 2 contacts for detection). 6-pin is 204W at +12.0V level or 306W for 8-pin accordingly.

e9s8_e8s1p0f0-SDOERR_CASP22SnoS_crystal_contacts_50ns_ntl9_0-0-1-RND0969_0 : 14,398.54 7,695.54 63,750.00 v9.14 (cuda80)

e16s9_e9s9p0f217-SDOERR_CASP10_crystal_ss_50ns_ntl9_0-0-1-RND0343_0 : 19,631.24 6,984.46 63,750.00 v8.48 (cuda65)

The PABLO_SH2TRIPER took 3% longer on the 1060-3GB than it did on a 970, so there is a lot of performance variation. CPU usage was also 11% less when using the 1060:

e16s27_e15s14p0f22-PABLO_SH2TRIPEP_L_TRI_2-0-1-RND3725_0 : 22,123.02 7,779.86 145,800.00 v9.14 (cuda80)

e14s15_e12s4p0f72-PABLO_SH2TRIPEP_Q_TRI_1-0-1-RND5699_1 : 21,321.75 8,659.11 145,800.00 v8.48 (cuda65)

e21s26_e15s3p0f391-PABLO_SH2TRIPEP_F_TRI_2-0-1-RND2465_0 : 21,323.73 8,596.28 145,800.00 v8.48 (cuda65)

GTX 1060 6GB:

I had 88-92% utlization yesterday, now it's only 65%. I changed nothing in the system.

- Windows 10
- Gigabyte B150 mobo
- i5-6600, one core dedicated to GPU running at 3.6 GHz
- PCIE3 x16

Power consumption is 72W average at 65%.

I crunch WCG on this rig as well. When I enable WCG on the 3 other CPU cores, the GPU usage goes up to 75%. I have no idea why.

I had 88-92% utlization yesterday, now it's only 65%. I changed nothing in the system.

Power consumption is 72W average at 65%.

I crunch WCG on this rig as well. When I enable WCG on the 3 other CPU cores, the GPU usage goes up to 75%. I have no idea why.

Thanks, SWAN_SYNC seems to help, now utilization is at 72% even if only GPUGRID is running.

Moving to linux/win XP isn't possible, since this is my daily use PC.

Would getting a faster CPU help? (i5 6600k/i7 6700k)

Would getting a faster CPU help? (i5 6600k/i7 6700k)

If you want to maximize GPU usage on an operating system wich has WDDM (Windows 7, 8, 8.1, 10) you should:
- crunch only 1 CPU task (or do not crunch CPU tasks at all)
- not crunch on the iGPU
- use SWAN_SYNC environmental value to make the GPUGrid app use a full CPU thread
- use the app_config.xml to run two WU on a single GPU (it will double the runtimes, so do it only if your runtimes are well below 12h)
- put your GPU to a PCIe3.0x16 slot, which really runs at x16 (you can check it with the GPU-Z tool)

And now the "how-to" part: (TLDR)

To crunch only 1 CPU task you should reduce the percentage of the CPUs available for BOINC, or the number of CPUs in the cc_config.xml.
First you have to know how many CPU threads your PC has.
To find it you should use the CPU-Z tool, or start task manager (right click on the empty area of taskbar and choose "Task Manager"). Then on the performance tab you should see as many graphs on the "CPU usage history" panel as many "logical processors" your PC has (Windows 10 reports it numerically also). If you see only 1 graph, then you should switch view.
Then you should divide 100% by the number of "logical processors" aka "threads" your PC has, and multiply it by the number of GPU tasks you have plus 1 and round it up to the nearest integer, then type the result to the BOINC manager -> Options -> Computing preferences -> Use at most [...] % of the CPUs. The other field has to stay at 100% (use at most 100% of the CPU time).
For example:

Thanks, I'll try these solutions!

Thanks Retvari Zoltan, now my card works with utilisation 96-98% on windows 10 (driver 375.70) with 2 task.

I've successfully installed Ubuntu 16.04 LTS on one of my hosts.
Could someone please enlighten me how to make the SWAN_SYNC=1 setting noticed by the app? I'd appreciate it.
I've put it in /etc/environment, and when I try printenv it shows the SWAN_SYNC=1, but the app obviously does not take a full CPU thread.
The boinc and the GPUGrid app runs as user 'boinc' but I didn't find anything for this user in /home.
Is this environmental value handled by the new (9.14) Linux app?

Is this environmental value handled by the new (9.14) Linux app?

1fdq-SDOERR_OPMcharmm6-0-1-RND3215_1 longest WU I've encountered to date on GTX 1070.
Estimated completion 51,300/sec (14.28hr) at 54% GPU usage / 33% MCU / 24% BUS (PCIe 3.0 x8) / 45% GPU power (83W)

I've noticed if only my GTX 1070 is running GPU usage 3 to 6% higher on all WU compared to 2/3/4 GPU Pascal or Maxwell compute.

1fdq-SDOERR_OPMcharmm6-0-1-RND3215_1 longest WU I've encountered to date on GTX 1070.
Estimated completion 51,300/sec (14.28hr) at 54% GPU usage / 33% MCU / 24% BUS (PCIe 3.0 x8) / 45% GPU power (83W)

I've noticed if only my GTX 1070 is running GPU usage 3 to 6% higher on all WU compared to 2/3/4 GPU Pascal or Maxwell compute.

GPU Clocks?

Anyone knows how to force GPUGRID to work with two different cards : Pascal (cuda 80) and GTX 670 (cuda 65). When I put new card into computer my old card stopped work with GPUGRID. Do you know how to solve this problem?
Many thanks!