P3Dv5 is single core AGAIN 🤦

[cwburnett 1,809]

5 minutes ago, Sethos said:

Can only speak for my own setup, but something is seriously messed up with HT under heavy load conditions, something I never saw under the previous iterations. HT on / off made no measurable difference, it was all based on feel and placebo for my own part. However, under v5 it's like night and day, with some very odd spiking and utilization of the cores with "HT on" i.e no mask, default conditions. Under "normal" conditions they both seem smooth but once you apply pressure with a full OrbX region (SoCal), flying out of Klax, a real machine killer, the cores just start to choke.

I would be really interested to see what you find if you set your AM to just take out your second core, but leave HT on for the rest.  So, I think 111111111101 (4093).

I'd love to know how that compares with your HT off performance.

[Sethos 4,266]

9 minutes ago, cwburnett said:

I would be really interested to see what you find if you set your AM to just take out your second core, but leave HT on for the rest.  So, I think 111111111101 (4093).

I'd love to know how that compares with your HT off performance.

I'll have to owe you that test, as I just did a clean installation of the newest Windows 10 2004 RTM update last night, figured I'd then hold off on installing P3D until HF1 drops next week. Then I'll definitely be trying out some more combos, see if its still an issue as well. 

[anden145 2,273]

Could someone please close this thread (or better yet change it's title), as it's kinda misleading, IMO. 

No offense. 🙂

[Mace 1,902]

1 hour ago, cwburnett said:

There are really only three use cases for AM from my perspective - and I agree that when in doubt, don't use one.

I tend to agree with this.  Sometimes we see mis-use of an AM, with no insight as to the ramifications.  People shouldn't underestimate the Win10 thread scheduler nor, as it seems so far, P3Dv5's ability to work magic.

I can say in v5, I am noticing something very odd with core usage and my 8700K (6-core, HT on).  I'm not sure if I posted anything about it yet.  It is similar to what you said earlier in this thread, about Core1 and 3 being seemingly masked off from terrain loading by default.  I haven't had time yet to really see if that was an anomaly I saw, or if it is a normal consistent thing in v5.  Maybe it was just something specific to my 6-core and the flight I had going.

That is with a completely default/ vanilla P3Dv5, no AM, 60hz refresh with vsync on and framerate unlimited.   

Anders is really right.  The thread title is more than misleading, it is factually incorrect.   OP's pic has the "typical" core usage we're used to when on the ground, but with the added caveat that OP likely is not configuring their sim correctly (that core0 usage probably isn't ideal).  In my view LM should, during the install of P3D, give the user information as to refresh rate vs. settings, or....not give it to them, but instead actually set their sliders and boxes accordingly.  That would also help guys like Boomer/Chris, who have g-sync and high refresh rates, who have trouble getting the smoothness lower refresh users get.

The thread isn't entirely useless though.  Anytime we discuss things like this, it is a good thing.  I know for my part I don't feel like I have had time to really get into v5 enough to comment on things like core usage yet.

[lownslo 592]

3 hours ago, Sethos said:

Can only speak for my own setup, but something is seriously messed up with HT under heavy load conditions, something I never saw under the previous iterations. HT on / off made no measurable difference, it was all based on feel and placebo for my own part. However, under v5 it's like night and day, with some very odd spiking and utilization of the cores with "HT on" i.e no mask, default conditions. Under "normal" conditions they both seem smooth but once you apply pressure with a full OrbX region (SoCal), flying out of Klax, a real machine killer, the cores just start to choke.

 

To clarify... this is not a comparison of HT ON vs. HT OFF.  Rather, this is a comparison of running the sim with HT ON and using all Logical Processors (LP) (the left side video) and using HT ON and using an Affinity Mask (1365 for this 6Core/12Thread CPU) to run the sim on the first LP of each core (the right side video).  Running the sim with HT OFF (disabled in the motherboard BIOS) may yield performance closer to the right side video, (depending on OS/Sim configuration) and will most likely require less power delivered to the hardware.

I've decided to stay with v4.5HF2 for a while (if it ain't broke, don't fix it ) but certainly all of us would benefit from a nicely done V5 video comparison as above but done with HT ON vs HT OFF.

Cheers,

Greg

[YVRLHRDXB 321]

I can't disable HT on my 9900k Alienware so what CPU's should I enable in the affinity settings?

Edit:

So my BIOS did have an option to turn off HT. What a MASSIVE difference. My sliders are basically to the right, with HT my FPS would be get very choppy almost like there was a program running the background. WIthout HT my FPS are fluid and I'm averaging 40fps.

Edited April 24, 2020 by YVRDXBLHR

[GodAtum 69]

13 hours ago, cwburnett said:

I noticed changed behavior from v4.5 to v5 with respect to core utilization and asked LM about it on the prepar3d.com forum.  Beau Hollis explained a bit about what the cores do in his reply:

I would encourage any/all of you with experiences on this to contribute to that thread because it would be nice to have a better understanding of how best to configure our processing hardware to maximize performance.  https://www.prepar3d.com/forum/viewtopic.php?f=6312&t=137087

I had shared these two images with him:

Framerate unlimited, vsync to 30hz monitor:

Framerate limited to 30:

It continues to be clear that with framerates locked, we can expect the main thread (typically core0) to be fully saturated because the sim engine uses all the processor power available to both render the frames and perform tasks related to scenery loading (this is directly related to the many FFTF discussions over the years).  Meanwhile, with frames unlimited and using vsync or other external framerate limiter, the main thread only works as hard as it needs to based on the FFTF setting + the number of frames that need to be rendered.

I had raised the issue, however, because my cores 2 and 4 are never utilized above 50% (like @Sethos noticed as well), which is changed behavior from v4.5.  V5 is using net less processor power than v4.5 at the same settings and I was specifically wanting to be sure I wasn't missing something that could improve performance.  I'm guessing cores 1 and 3 are the ones Beau is referencing when he says "two additional cores set aside for per-frame rendering related work."

I think "yes to all" is the answer here. It really needs at least 4 cores to do what it needs to do, but obviously the faster those cores can process, the better.  What I think doesn't help is having more than maybe 8-ish cores.  @SteveW has shared a lot on this subject and I've been a diligent student of his writings on affinity, here and on the codelegends.com forum as well.  In my case, I have 6 cores running at 5ghz and P3D isn't using them all to their potential, so I don't think adding more cores would buy me any more performance.

What does seem clear from my experience is that (a) @vl1 is correct that the main thread, typically found on core0, continues to be the primary driver of framerate from the CPU side of the equation and (b) that overall CPU usage is lower in v5 at the same settings as compared with v4.5, namely that in 4.5 I saw five of my six cores average above 80%, while now it is only 4 cores that exhibit that behavior.

Thanks for taking the time to do this. I have an Intel Xeon Platinum 8259CL @ 2.50GHz, 32GB RAm and an Nvidia P6000. Sitting in FSDT KJFK V2 with Orbx LC I get around 20 fps on medium settings.

[vl1 11]

On 4/24/2020 at 11:11 AM, GodAtum said:

Thanks for taking the time to do this. I have an Intel Xeon Platinum 8259CL @ 2.50GHz, 32GB RAm and an Nvidia P6000. Sitting in FSDT KJFK V2 with Orbx LC I get around 20 fps on medium settings.

That's because you have very low CPU Ghz