Sett

Umm, hello? :taps the mic repeatedly: Anyone?

Hey y'all! tl;dr: Is there any way to limit Legion 5 Pro's GPU power budget? I have an R7 5800h / RTX3070 Legion 5 Pro laptop and it is a beast. The trouble is I like my silence, and even if this baby got uncle Linus' stamp of approval, it's still a jet plane. I mean laptop. I'm using Legion Fan Control to limit the noise to an acceptable level, letting it cap at ~85°C (GPU) and 90°C+ (CPU). So far so good. The problem is, the cooling in this laptop is designed in a way that the heat from GPU bleeds over to CPU. This makes sense, because the GPU is much more power hungry, but it actually leaves very little temp headroom for the CPU when GPU is capped at 85°C. Now, I don't mind sacrificing a bit of performance for the sake of sanity and/or longevity, so I've been looking for ways to tame it ever since I bought the thing. So far I was able to: - switch it to quiet mode (duh) - disable CPU boost - limit CPU TDP a bit with Ryzen Controller - make sad Pikachu face at the greyed out power slider in MSI Afterburner - edit V/f curve to cap the GPU at 1300MHz (goes from ~120W to 100W in Heaven) It all helps a bit, and without really impacting performance, but I'm afraid the only real solution would be to actually cap the power budget. So, Anybody know how? Thanks

True, DPC latency as shown in some tools doesn't really mean anything. It's just that it's the symptome (whether causally related or not), the last step on the path to figuring out "WTF is wrong with my computer?" that some people seemed able to make, so this is my attempt to lead them the rest of the way.

Google search tags: DPC Latency, dxgkrnl.sys ndis.sys latencymon Your system appears to be having trouble handling real-time audio and other tasks, nVidia GTX970 Hello, I'm posting this for others to find. Please disregard, if ýour GPU is anything other than GTX970. I've been experiencing arbitrary slowdowns/drops in responsiveness on my otherwise decent enough system. Sometimes when a browser tab with Facebook was open, often in Bluestacks, other times with no apparent link to anything. It wasn't much of a problem except audio/video desynchronisation which would be easily solved by just stopping and restarting playback. Sometimes the sound would glitch, but I usually wouldn't let it go that far and just restart. And then I hit a wall in Civilisation VI. I would easily have around 60-80FPS on one turn, then drop to 4-5 on the next. What? How? How indeed. If you are reading this, you probably already tracked the problem somewhere down the line of DPC latency and/or the dxgkrnl.sys driver. Well I have a bad news for you. After much research, much more testing and yet more money poured in, I found the common denominator to be the GTX970. You can read HERE, and under links provided there, why this exact chip does this. The oversimplyfied explanation is that this card has a severe bottle neck on one of it's memory chips. In an attempt to preserve in-game performance. nVidia avoids this chip in 3D and uses it to store other data. Unfortunately that means stuff like desktop composition. And it does so even when not in game. Normally this is not a problem as this data is rarely accessed and it's not very performance-sensitive. The problem here is, that when this data IS accessed it is mostly at least sometimes done so through a Deferred Procedure Call which is (without claiming I actually know anything) basically your good old interrupt request. Meaning your $350 CPU has to drop everything and serve the request ... while waiting for GPU to do it's part of the job and obtain data from this slow chip ... and THEN it can resume whatever it was doing. This can take anywhere from about 1ms (somewhat normal DPC latency, depending on your timer configuration) up to and over 16ms. Again, this is not much of a problem if it happens once in a while, as even 16ms more or less equals a single dropped frame. But then there is the wall. The wall happens when your GTX970 runs out of "regular" VRAM and it has to use the last chip for 3D. Then it has to access it on every single frame, back to back. And that means you're gonna have a bad time... What can you do? The wall has simple solution - just drop your texture resolution and/or antialiasing and other frame buffer effects, basically anything to stay below 3,5GB of VRAM usage (This incidentally equals about 4GBs of uncompressed data - the number shown by e.g. MSI Afterburner). For the arbitrary DPC calls you can do very little. Various people claim various things helped them, you can try: 1) Use something like TimerResolution to reduce your minimum and average DPC latency, but probably not the spikes 2) Disable powersaving features like C-states on your CPU and setting everything to maximum performance in Power Management and nVidia Control Panel. This is pure hearsay as I refuse to run my PC at full ~500W TDP 24/7 for the sake of saving few miliseconds once in a while.. 3) (untested, cumbersome, and probably above most people's computer-fu) You can also try and use intergated GPU as primary and only manually set your games (one by one) to render with the 970. No Idea IF, or HOW that would work OR if it would help OR be any better. But anyway... TL; DR: The only real solution is to get different GPU. Not necessarilly faster, just different. At least for me it was.

Well, like I said, It's technically correct. The issue I have is that it might be somewhat misleading, just adding up the bandwidth - kind of like just adding up VRAM. You can do neighter, that's not how it works. A cards performance is a cards performance. You can sort of add up the results in SLI, but if a card has some issue, SLI won't fix it. Anyways, that's just nitpicking on my part. I learned quite a bit here, and will definitely be redirecting people with questions this way. ?

Just because GPU doesn't run at 100% load doesn't mean CPU is the problem, especially if it's more pronounced at higher resolution. CPU load does not scale with resolution. On the contrary; because the GPU is puting out fewer FPS, there is less work for CPU preparing them. In HB, @80-ish FPS I get around 6-8% utilisation of my i7-8700k meaning, worst case scenario, about 50% use of one 4,8GHz core. I'm positive I5-7500 can put out more than that. It COULD be, however, that the OP still gets CPU bottlenecked in "easier" (for GPU) scenes, where the FPS can spike to well over 300 on that card and that might just be too much for a 3,2GHz CPU. Might be some lost points there, but probably not a problem in general. Seeing as temps are not a problem, i'd suggest overclock (at least with "enhanced turbo" or whatever) and see if it makes any difference.. PS: on ARK the i5-7500 is listed as 3,4/3,8 GHz, not 3,2??

Excellent (if quite old) guide. But There is a slight issue, and that's the "SLI memory bandwidth doubling". No, technically it IS true, but.. The total number doubles, because now there are two GPUs accessing two sets of VRAM chips over two sets of copper lines.. But each GPU only has access to it's own copy of VRAM so the respective GPUs don't benefit at all (this is different from some Quadro/NVlink applications AFAIK),. From a different point of view it means that there is double bandwidth, but also double demand for bandwidth, so you're breaking even, not doubling your assets. The actual benefit is that each card only has to render half of the frames, so in total you can do more with the same ... times two. Therefore even if you are bandwidth limited for some reason, you should see some improvement from SLI. For the 970 that means, that you WILL get SLI scaled performance when it comes to the last 1/2GB. So 13FPS instead of 8. Yay.

Err... One thing's for sure, and that's that you are not bottlenecked by somewhat modern mainstream CPU in old GPU benchmark, that uses about 10% of it. I'd start by making sure you are set to "prefer maximum performance" and not "Optimize compute performance" disabled for Heaven in NVCP, and that you don¨t have a browser open in the background. If that doesn't help, you might want to upload the benchmark run with some metrics shown (via e.g. Afterburner), namely GPU & CPU utilisation and temperatures nad RAM usage.

mAYBE i'L... ... ??? Maybe I'll try a different approach. Since I basically only ever use Caps Lock in Eplan, maybe I can just turn it on in that window and off in any other (Or at least Outlook, Firefox, Word, Excel). I think AHK can do that?

I have a problem. With caps lock. I'm an electrical engineer. Many of our customers demand, that all text in electrical drawing be all upper case, so I often work with caps lock on. And then an email comes in, and I have to answer it. And I do. And then... I don't often look at the creen when typing, but when I do ... See where this is heading? There are a bunch of sites that offer case conversion, but opening a web page every time I misstype something due to caps lock isn't exactly handy. I believe I've seen some app, that let user convert any selected text, pretty much anywhere, just by pressing some key combo. TL;DR: Anyone know what it was called, or any other moderately ergonomic way to fix "A cAPS lOCK tYPO"?

Yeah... that's what I thought. Guess it's top down intake then, Thanks guys.

How bad is it? I have an old Seidon 120. I'm in the middle of a little makeover and would like to mount the rad at the bottom. Thing is: there's air inside (there's audible sloshing when handling the radiator). That's probably not a problem when the radiator is on top (aside from hampering performance), but i'm afraid if I move it to bottom, the air bubbles will aggregate in the pump and eat it up. Am I right to worry?

There should be filename of the crashing driver displayed right under that KMODE line. If it's not, or you are not sure and don't want to wait, you might try disabling fast start-up in the mean time. As quoted from Tom's hardware: 1. Navigate to Control Panel, System and Security and Power Options. 2. Select ‘Choose what power buttons do’. 3. Click ‘Change settings that are currently unavailable’. 4. Uncheck the box next to ‘Turn on fast start-up’ and Save changes.

You could alway call the person and tell them you ended up with few extra bucks, and give them options... If it's your family, or good friend, adding an extra core or stick of RAM will help the build remain usable for longer (GPU - in a gaming build - is likely to be upgraded before anything else anyway). If it's a random person, upgrade GPU to increase wow factor, or save them some money to increase content(ness?). Either way, you wanna make them come back to you sooner *MWAHAHAHA* Oh, and don't change anything that would result in notably worse price/performance ratio, ever.

Apples and oranges? MSI Afterburner is a GPU monitoring/overclocking utility. But a GPU overclok is unlikely to cause BSOD. CPU or RAM overclock can, but if you went through the process of overclocking those, you likely know your way around system stability. So in your case it's probably a driver error or faulty hardware. Next time it crashes on you make a note of the error code and/or device listed, that can help narrow it down a bit.