Someone explain why RealBench downclocks my graphics card during test

[KeithMyers]

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:

[KeithMyers]

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]

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]

Nodens wrote:
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]

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]

JustinThyme wrote:
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: