PDA

View Full Version : Someone explain why RealBench downclocks my graphics card during test



KeithMyers
03-07-2017, 02:48 AM
Can someone explain how RealBench works? I am wondering why during the benchmark test that it only uses one graphics card. In my case, a GTX1070FE. Also why does it downclock the video clock speed from its normal 1.92 Ghz to 1.5 Ghz. I have a mild memory and video core overclock set on both cards through NVI. However, I notice that when you stress test the system, it is using both cards at their normal overclocks. It doesn't touch the memory clock during the benchmark, just the video clock. Can someone explain the benchmark methodology please. I can't find any help file or text document explaining what and how RealBench works.

I can't link to any benchmark result yet since it appears that the latest available version 2.44 is broken and not able to log a user in to upload their result file.:confused:

MMikhail
03-09-2017, 03:04 AM
I think there is nothing special happening here, just normal overheating and the card relaxes a bit to keep alive at heavy load.

KeithMyers
03-09-2017, 04:26 AM
I think there is nothing special happening here, just normal overheating and the card relaxes a bit to keep alive at heavy load.

Uhhh.... not the case. I never have exceeded 65C. on any of my 1070's. They are under SIV control with a 6 point fan control curve. They run flat out all the time 24/7 on BOINC projects crunching math. They are running 60C. right now as I type crunching for SETI at 95-100% utilization with +40 Mhz core clock boost and +400 Mhz memory clock boost. They have never clocked down. Video clock is right now at 1.92 Ghz and memory clock is at 4.2 Ghz.

When I run the benchmark test, the memory clocks don't clock down, just the video clock. When I run the stress test both cards stay where I put them and never cross 60 C. When I run the benchmark, the temps are only 48C. It's almost as if the benchmark wants to standardize on 1.5 Ghz for all tests. That is why I asked the question is that how it is supposed to work? I couldn't find any documentation on the methodology of the benchmark. What is it supposed to do and how does it achieve it.:(

Nodens
03-15-2017, 07:45 AM
RB does not downclock your card at all. If your card downclocks it happens by the hardware directly or the driver and I have no control over it. Have in mind the Luxmark load is a "COMPUTE" OpenCL load and not regulard 3D load and cards behave differently on these loads than they would on a game or 3dmark for example.

KeithMyers
03-15-2017, 04:30 PM
RB does not downclock your card at all. If your card downclocks it happens by the hardware directly or the driver and I have no control over it. Have in mind the Luxmark load is a "COMPUTE" OpenCL load and not regulard 3D load and cards behave differently on these loads than they would on a game or 3dmark for example.

That still doesn't make sense to me since the cards are never doing anything OTHER than pure compute. I don't game and have never gamed. The cards are running 24/7 doing pure compute, OpenCL tasks for SETI@Home, MilkyWay@Home and Einstein@Home. All that work is pure compute. I run two tasks per card which makes them run at 95-100% utilization all the time. I have never had any of my cards, six total across three machines downclock either the core clock or memory clock.

I guess I will have to to run this Luxmark test outside of your benchmark suite and see if it alone can downclock my cards. You don't have a handy link sitting around so I don't have to go searching for it do you.:(

Nodens
03-15-2017, 05:24 PM
Like I said if downclocking happens it happens at the hardware or driver level. Indeed the distributed computing apps you are using are also compute loads which make them not entirely unrelated like 3d game/benchmark loads BUT still they are not very relevant either. I am guessing you are using the CUDA client on BOINK and not OpenCL (if not you should since the performance is way higher) so that in itself makes what you are currently running entirely irrelevant. If you are indeed using the OpenCL client and it does not exhibit the same behaviour then it's probably something specific to Luxmark's dataset (although it's quite possible that it will if you test that).

In any case here is luxmark download site: http://www.luxrender.net/wiki/LuxMark#Binaries

RB up to 2.44 uses version 2 which underperforms on Nvidia cards anyway. Latest 2.54b beta uses 3.1

KeithMyers
03-15-2017, 05:47 PM
Like I said if downclocking happens it happens at the hardware or driver level. Indeed the distributed computing apps you are using are also compute loads which make them not entirely unrelated like 3d game/benchmark loads BUT still they are not very relevant either. I am guessing you are using the CUDA on BOINK and not OpenCL (if not you should since the performance is way higher) so that in itself makes what you are currently running entirely irrelevant. If you are indeed using the OpenCL client and it does not exhibit the same behaviour then it's probably something specific to Luxmark's dataset (although it's quite possible that it will if you test that).

In any case here is luxmark download site: http://www.luxrender.net/wiki/LuxMark#Binaries

RB up to 2.44 uses version 2 which underperforms on Nvidia cards anyway. Latest 2.54b beta uses 3.1

Thanks for the link. I will go to the link you provided. Thanks. Just FYI, on SETI with BOINC I am running only OpenCL work. I haven't run any CUDA work for almost two years. The OpenCL app is five times faster than the current CUDA app. On Windows that is. MilkyWay and Einstein have only OpenCL apps. No CUDA apps. If I was to move to a Linux platform for SETI, I could then get access to a beta CUDA 8.0 app which is five times faster than the OpenCL app on Windows. That app is 50 times faster than the old CUDA 5.0 app in Windows.

If the Luxmark test alone downclocks the card, then I will apologize for denigrating your benchmark suite. I just didn't understand why it only downclocked the video clock and left the memory clock alone. And stress testing the cards for 30 minutes didn't downclock either the video or memory clocks.

I see you mentioned 2.54b. I thought I had the latest at 2.53b. I will go find the latest. Thanks for your responses.:cool:

KeithMyers
03-15-2017, 07:37 PM
OK. I downloaded Luxmark 3.1 and ran it. No downclocks seen. I then tried running the new 2.54b Realbench suite. It wouldn't run H265 encoding properly. Said the first job would take 47 hours. Then ran the Luxmark part of the suite and it still downclocked for some reason. Then moved onto the multi-tasking part and it never completed the first job. And was only running one core at 12%. All the other cores were idle for some reason. I assume a multi-task test would run on all cores. All the tests in the 2.44 suite ran with no issues. I had downloaded the 2.53b suite version but I had not got around to running it yet.

I've attached some images of the Luxmark standalone test results along with a desktop image while the test was running showing the graphics cards at their full overclocked video and memory clocks via my SIV monitoring tool which I always have running on the desktop.

Can't explain yet why the difference in RB versus the standalone Luxmark test. Also, for me, the 2.54b version is a step backwards from the 2.44 version. I had wanted to run the 2.53b version because it was supposed to have the upload benchmark results problem fixed. I still have not accomplished that yet since I can't get 2.54b to run properly.
:confused:

jab383
03-15-2017, 10:29 PM
The clock slow-down seen in OpenCL is done by the nVidia driver, not Realbench. It has to do with the workload the driver sees:

nVidia graphics cards use various performance states for various tasks. P8 - performance level 8 - is standby and has very low idle clocks. P5 is 2D with clocks a little higher and is often the level for fallback when the driver crashes. P0 is high performance 3D - the highest level clocks. P2 is for direct compute applications like OpenCL and uses slightly lower clocks, including memory clock.

I often start an overclocked benchmark in P0, go through a driver reset and wind up with the really slow clocks of P5. I often takes a reboot to break out of P5 and be able to set clock speeds again.

GPUTweak and other graphic card tuning software (PrecisionX, Afterburner) work on the P0 clocks. In a direct compute benchmark like Luxmark, GPU clock speed sort of follows the GPUTweak setting but memory clock is locked at the lower level of the P2 performance level. nVidia Inspector is the only tuning software that will let us tweak P2 speeds directly. Check out nVidia Inspector. It shows the P-state running at the time and the overclocking tab can be set to operate on any of the P-states. You may have to experiment with setting voltages and clocks in the right tool and in the right order. Have fun.

KeithMyers
03-16-2017, 05:01 PM
Thanks for the comment. Guess I didn't make myself clear in my previous post. Don't see any slowdown in overclocks with the standalone OpenCL Luxmark benchmark. That is shown in the image I posted. I do see a downclock in the video clock though with RealBench.

I know about the Nvidia driver forcing the cards to P2 state for compute. That is why I have used Nvidia Inspector for over a year to set where I run the cards in P2 state. The overclocks are for P2 state. Never fall out of overclock in P2 state for my normal 100 % computer utilization for distributed computing which is 100% OpenCL based work. Didn't fall out of my P2 overclock for the standalone Luxmark benchmark. Still can't explain the difference in downclock between the standalone test and RealBench.

Cheers.:confused:

Nodens
03-16-2017, 11:36 PM
All RB does is run Luxmark with these parameters "--scene=LUXBALL_HDR --mode=BENCHMARK_OCL_CPUGPU --single-run"
If running 3.1 Luxmark with these parameters does not replicate the downclocking then there's only one answer for you: There is a bug in the application you use to monitor the downclocking. There is no other logical and technically plausible explanation. Either the downclocking happens on both cases but is properly reported on one or vice versa.

Also regarding the failing of the encoding test in 2.54b, this indicates there's something wrong with your system in general or a bug in handbrake that manifests only in your system. What exactly, I can't tell with vague information about the error.

KeithMyers
03-17-2017, 12:04 AM
All RB does is run Luxmark with these parameters "--scene=LUXBALL_HDR --mode=BENCHMARK_OCL_CPUGPU --single-run"
If running 3.1 Luxmark with these parameters does not replicate the downclocking then there's only one answer for you: There is a bug in the application you use to monitor the downclocking. There is no other logical and technically plausible explanation. Either the downclocking happens on both cases but is properly reported on one or vice versa.

Also regarding the failing of the encoding test in 2.54b, this indicates there's something wrong with your system in general or a bug in handbrake that manifests only in your system. What exactly, I can't tell with vague information about the error.

I don't know. Both SIV and GPU-Z reported the same clocks, but were different from RB. Only RB showed the downclock.

At this point I think I will just drop the issue. Maybe revisit RB further down the road. It works for many, but does not for me. I really don't have much use for a general benchmark program anyway as long as my computers pass AIDA64, Prime95 and OCCT without errors. If they do that I feel very comfortable in knowing that I am producing good science results for my distributed computing projects. That is all I really care about.

Thank you for your time in replying to my concerns. I only thought I was pointing out a possible flaw in your program.

Cheers.:cool::rolleyes:;)

JustinThyme
03-17-2017, 03:30 AM
Its not down clocking it, its just when it grabs the info at the beginning its not under load. Try setting your power state to performance while running the bench and have HW monitor running in the back ground to monitor the clock or even better AIDA64,

Also what are you using to clock your GPU?

KeithMyers
03-17-2017, 05:06 AM
Its not down clocking it, its just when it grabs the info at the beginning its not under load. Try setting your power state to performance while running the bench and have HW monitor running in the back ground to monitor the clock or even better AIDA64,

Also what are you using to clock your GPU?

Duh, that might explain everything:o I never thought of that. You are probably correct. I have tested RB by simply quitting BOINC and then shortly started running the RB benchmark suite. The cards probably started out the test still in P2 where they would have been in BOINC. I see the 1.5 Ghz clock reported in the log window right at the beginning. I really don't like unloading my systems from BOINC. I want them running all the time, 24/7. I don't stop running BOINC on my daily driver when I am doing normal computer stuff like browsing, email or financial work.

I believe when I ran the standalone Luxmark bencmark, the system had been idle for maybe 15 minutes or something like that. I use Nvidia Inspector to clock the cards. That program might have detected the drop in the normal P2 state compute load and pushed the cards into P0 state where they would run at stock boost speeds. That would explain perfectly me not noticing any drop in clock speeds. I never paid attention to what power state the cards were in when I ran the benchmark suites.:cool: