What? There’s a lot of laptops that hit their top clocks with no issues. The main problem is that doing so seriously reduces your battery duration and emits significant noise.
Pick anything over the 800$ range that isn’t a macbook and you’re way more likely to hit clocks than not.
The problem isn't hitting the top clocks, but sustaining them. Only the biggest "desktop replacement" class laptops tend to be able to sustain 120W+ CPU dissipation.
Note that workstation-class (H) laptop CPUs also make compromises on performance - the Ryzen 9 4900H is 8C16T but only has 4MB L2$, 8MB L3$, and a max TDP of 54W. A desktop Ryzen 9 3950X by comparison is 16C32T and has 8MB L2$, 64MB L3$, and a 105W default TDP (and will go much higher with even basic PBO if your cooling allows). The differences on the Intel side are even starker.
Hmm, I suppose it's fallen a bit out of favor recently, I don't see it quite as much as I used to, but it's pretty much standard terminology in the semi industry showing up in everything from academic papers to data sheets (commonly you'll see that as D$ and I$ - data and instruction cache).
Perhaps why I've not seen it before is likely due to localization - I'm in the UK and of course the Pound has it's own symbol, thus the connection of $ -> Cash -> Cache may not be so readily made.
Ignoring the discussion around TDP figures, I’m well aware of the power limits, but that was (IHMO) not the point of OP.
It’s obvious that it’s impossible at the moment to get 3950X performance in a laptop format, but you can get laptops able to keep temps reasonable with 35-50W, and that’s what a lot of laptop SoCs target as total power.
Those SoCs hit (and sustain) their top clocks, whatever those are for that specific SKU.
What I understood from OP is a common complaint for macbooks, that fail consistently to sustain their specified to clocks, because Apple deliberately under specifies their cooling solutions for better ergonomics (and design reasons).
> Those SoCs hit (and sustain) their top clocks, whatever those are for that specific SKU.
This is actually completely wrong. Almost no laptops sustain their top (boost) clock on heavy workloads. Most usually only sustain max performance for minutes (or seconds!) before throttling. Here's an example chart that shows how various premium Athena/Evo U laptops perform: https://www.notebookcheck.net/Asus-Zenbook-S-UX393JA-Laptop-...
If you are interested in how modern Intel laptop chips throttle and what base and boost clocks mean, you want to do a search for PL1, PL2, and Tau. For AMD chips, you will want to look up STAPM, Fast and Slow PPT.
Note that while a i7-10875H's top "boost" clock is 5.1GHz, the sustained "base" clock is only 2.3GHz. This is so low to be meaningless as a top speed. In practice, unless your laptop's cooling is absolutely terrible, you'll probably end up mostly running in the 3-3.5GHz range under full load. In comparison, on a properly cooled desktop system, a same-gen i9-10900K desktop system should be able to maintain a sustained (all-the-time) clock of about 5GHz (very close to its 5.3GHz boost). AMD chips scale a little bit better due to 7nm having better power efficiency and how PPT works, but the same ratio roughly applies.
I’ve actually worked with Ryzen SoCs myself (I do board design).
This is the problem with all the marketing BS. When I talked about “top clocks”, I wasn’t referring about “boost” clocks. I’m talking of the clocks that the SoC is designed for (that won’t appear on the box), i.e. a lot of laptops are not leaving “performance gaps” due to bad cooling, those SoCs are designed for that level of performance and attaching a fat copper heatsink won’t do much difference.
I had a lot of trouble with a client that complained that our board was not properly designed because the performance they were seeing was not “as advertised”. In the end we had to ship the whole thing to AMD, and have them test the system with a thermal sink. Everything was as expected.
If anyone is interested in this kind of stuff, your explanation is really good, so I won’t add anything because I’d probably do a terrible job :)
I agree that there's a lot of misunderstanding on clocks - I've been on the other end - evaluation and validation of embedded boards, including V1000 Ryzen SoCs, but I think I'd disagree somewhat with the characterization of clocks as purely "marketing BS."
Back in the day, most CPUs had had a fixed clock, but these days modern Intel and AMD chips simply don't - they all clock opportunistically, which depends on powers, thermals, but also workload (try running an AVX-512 loads for example). How do you characterize "clock" in this context? Base (minimum) and Boost (hard limit, now split to Max Turbo <2C and All Boost MC) seem to be reasonably sensible numbers.
Now we can argue semantics all day, but to bring it back around if you're just going to say "top clocks" is what the SoC was designed for at a specific workload/power envelope (In AMD's PB, that'd be PPT, TDC, and EDC) then every laptops will "hit their top clocks with no issues," but I'd say that argument (statement?) is a bit circular/pointless. ;P
Yes, but only with ear protection and while the battery can keep up. When the battery is out of power, the computer shuts off. Need to buy a better powersupply than the one it came with...
NVMe throttling from 2GB/s to 0.5GB/s is usually not thermal, it is an SLC cache exhaustion that brings a drive back to MLC/TLC packing mode. One can get samsung pro or a similar ssd and it will retain 2GB/s indefinitely. On cheaper drives, having a lot of free space (i.e. slc cache) may help. Not sure though what process can generate such sustained write bandwidth beyond few things like copying or video transcoding.
A well proven way to move heat out of a silicon package to prolong its ability to perform at its highest potential. And in a desktop, you've got room for 'em.
No, that's wrong. A heatsink on an NVMe helps to let it run its top speed longer, or forever. Has nothing to do with issues in your case, those things just get warm, and before it gets too hot the heat has to be transported away or they will throttle.
Specifically, a lot of NVMe are right next to GPU placed in PCI slot 1, which is a pretty constant source of heat under load.
I installed an EK spreader sandwich on my Samsung NVMe drive, and it made a massive (20° c) difference over stock. It was previously a bare stick with no surface area/thermal sink to pull heat away.
No. NVME's are rated to run at 0-70 degrees. If your case makes your NVME run at > 80+ degrees you should prob fix the airflow in your case as your prob running your CPU/GPU rather hot.
You do not need a case for that! The NVMe heats up on its own. There are a bunch of reviews going into that topic, because it just matters for high end NVMe drives. See for example https://www.computerbase.de/2020-09/samsung-980-pro-ssd-test... - though the 980 Evo did well without an additional cooler, and here it's indeed depending on the airflow.
You seem to assume it's the case that heats up to 80C or more, that's not true and also not necessary for NVMe SSDs to go over their limit. Your CPU/GPU has fans moving the heat away, that's a better position to be in...
I said if your nvme is reaching 80+ degrees then you should fix the airflow in the case. I did not say the case is 80 degrees. Any semi decent airflow is 100% capable of running an nvme without causing any performance issues.
Nope. That article states the the ssd was 'naked' which leads me to believe they removed the sticker off it. Those stickers/labels are use to dissipate heat from the controller, so you, you know, don't need a heatsink. They act as a heatsink.
No. Lol. Cooling anything other than the controller is pointless. You don’t get throttling from nand. I have the gigabyte x570 elite. That nvme cover does nothing. And unless you’re benchmarking the nvme I highly doubt you’re going to heat up the controller enough to notice it. So yup. I agree. You’re wrong. Let’s move on.
Man, they are benchmarking the whole SSD. I actually sent you the graph. The SSDs go over 80C and then throttle. Not all of them, but enough of them to be a real problem. The NVMe covers actually work in reducing the temperature, that's also in the graph. You are wrong and you seem to have no knowledge about this topic at all, you really should not be so confident.
Read and learn! And then accept when an initial assumption turns out to be wrong.
It’s not an assumption. NAND does not throttle. The controller does. Unless you run the SSD constantly like in a benchmark you are unlikely to heat the controller up to make it throttle. The airflow of a case is enough to keep an nvme within limits that everyday usage is not going to be hindered in anyway shape or form. You don’t need a heat sink. Linking to a constant load benchmark doesn’t change that. You’re wrong.
I do not understand how you can still think that after my explanation and after looking at the graph I sent you. One very last try - though I assume in the best case it's for potential other readers.
Go to https://www.computerbase.de/2020-09/samsung-980-pro-ssd-test.... look at the graph. You see that a bunch of them go to the 80C line or hover above. All of them throttle (what you said does not happen). In that graph are shown, going above the limit:
1. FireCuda 520 1TB
2. Patriot Viper VP4100 1TB
3. Samsung 970 Evo 1TB
4. WD Black SN750 1TB (+ the same one with a cooler)
This is only a small part of the market of course, but it goes to show that the throttling is a real thing that happens with multiple models.
Then you had a moving goalpost there, that those SSDs do not throttle under realistic workloads. However, this is a sequential read that's only 5 minutes long. Hardly unrealistic. The hour long constant load benchmark is a different graph, however, constant load is also realistic if it's longer than 5 minutes.
If you activate the other chart modes you see the measured performance, which shows the drops linked to the too high temperature, and that they did the same thing for write performance.
You can counteract this with a lot of targeted airflow and/or a heatsink, the heatsink will at least help move the throttling to a later moment. Gamersnexus had a very impressive demonstration of this, one where they did get this wrong: They had an article about a MSI SSD heatsink where they claimed it did not help (so the SSD did throttle! Again something you said does never happen), where it then turned out that it did not work only because their applied temperature sensors (glued them to the heatsink), and IIRC they also missed the higher performance they got regardless. GN often gets it right, stuff like that happens, but it made this one memorable and highlighted the positive effect of these heatsink coolers.
I'm into this topic professionally for years now. I'm not wrong here. If you can't take my word for it, look at professional SSD reviews, they have covered this also for years now.
And sure: There are scenarios where this does not matter. Gaming. Browsing. But: In those workloads there is no significant difference to a SATA SSD anyway. These NVMe SSDs are only interesting if you have large (and thus: long) file transfers. This is what they have to get right (and some do, but not all of them).
By the way, by repeating that I'm wrong and by starting with a straight "No", by always commenting without reasoning and politeness, you made sure that I will correct you - and that I'm not buying into your strange attempts to correct your statements to something that is correctish. They don't work anyway, these SSDs throttle.
But you don't know what causes the throttling. Its stupid to shove a heatsink on nand. It does not help. Not a single bit. Period. Under any normal daily usage, or even if you had a workstation, you're not going to be reading/writing so constantly frequently that you're ever going to cause the controller to heat up and cause throttling. If you experience any excessive heat. You have bigger issues in your case. Period. Your only proof of throttling is benchmarks running constant read/writes over a period of time. This is not real world usage and doesn't make it necessary to go out and start shoving heatsinks on every single nvme drive. If that was the case then all the laptops which have space between the nvme and the case, or motherboards which lack a 'heatshield' like the gigabyte board you linked to, would have throttling issues. Which they don't.
> You should change your tone around here.
So now you're threatening me?
-----
Anyway I'm done, not gonna sit here an argue anymore.
Unless you compile multi-gigabyte targets, all writes will likely fit in a ram cache and thus cannot be a real bottleneck. That is assuming your compiler farm can read and compile at GB/s level, which is pretty unrealistic.
To test that, one can try it with ramdisk first, before getting an expensive ssd.
And that is something else that is alien to laptops. Best laptop I could find (for when I am away from my desktop) is 8c16t, that makes a massive difference for compilation.
> I mean, hardware wise they are not much faster, but cooling is a different story.
The highest spec macbook comes with a 9980HK and starts at 2800 $. A 3900X has approximately twice the performance in multi-threaded workloads and you can easily build an entire quiet workstation with it for less than 1000 $. Half the performance, thrice the price. Great deal.
Yes, there are also "laptops" with a 3900X in them. But even those still have lower performance than a desktop with a 3900X because of thermals.
There are obviously many ways to do this comparison, but going off Wikipedia's pricing for most recent Intel processors. Their highest end mobile processor is currently the i7-1185G7 which apparently retails for $426. Let's compare it with the closest desktop processor to that price, the i9-10900 ($438).
Cores (Threads): 4(8) vs. 10(20).
Base Freq: 3.0ghz (At 28w TDP) vs. 2.8ghz.
Max All Core Turbo: 4.3ghz vs. 4.8ghz
Specs can never tell the true story, but it's clear that the mobile processor is going to be much slower for anything remotely processor intensive, and probably much more than twice as slow for anything making good use of multithreading.
Having had to go back and forth between a laptop and a desktop for a processor intensive application (AutoCAD) the difference was painful.
You also have to watch out for the powersupply of the laptop. Some companies give you a 70-90 W even though your computer needs 120 W at high load, counting on the battery giving the extra juice for the short bursts. If you do long processor intensive work, the computer just might shut down on you or if you are lucky, start throttling.
Yeah, this seems to be an unfortunate recent trend in some gaming laptops, presumably in a bid to save some weight and/or cost, but luckily, it still seems rare enough that any time it happens, the manufacturers still get called out on it in reviews. Usually, the power drain is when CPU+GPU are maxed out, not one or the other. I suppose if you did manage to get into a situation where this was an issue, you could find a bigger power supply. Up to about 180W these tend to be common and reasonably priced, then size and weight start going up dramatically.
While we're mentioning other minor gotchas, another one is memory latency and bandwidth. While desktop systems commonly have XMP and 1.35V support, very few laptops do (typically running at JEDEC timings at 1.2V). While there's diminishing returns, the difference between JEDEC 2933 CL21 or 3200 CL22 and say 3800 CL16 can actually be noticeable in certain workloads and is often effectively "free" (one-click in the BIOS) extra performance on the desktops.
MacBooks have terrible thermals. They will thermal throttle before most laptops, much less even compared to a desktop.
Also, laptops generally have CPUs that pull 15 watts. Whereas desktops have CPUs that can pull 95 watts or higher (sometimes up to 150). The difference is astounding.
The 15/16" MBPs have a 45W CPU TDP; they can run CPU continuously at at least 45W as long as your ambient temperature is normal-ish and the airflow isn't obstructed, and can do 60W+ if thermals are cooperative.
i3/i5/i7/i9 aren’t actually different processors, they make a handful of desktop/laptop/server... variants for each generation of Core architecture CPU and differentiate down the line by binning and restrictions added at time of production. So mobile i5 might have nothing to do with desktop i5, or i7 and Xeon can be taken from the same batch.
I have a >3 year old GPU that's still faster than any mobile GPU. I have been having 64 GB RAM in my desktop for ... 5 years now. Even in the summer my PC is completely quiet, even under heavy load. (Both the GPU and the CPU are water cooled with stock all-in-one coolers.)
If your fans are noisy buy better fans. We had some corsair fans that came with the AIO at work, replaced them with noctuas and the computer went from mildly annoying to dead silent.
Though with water cooling you might also have a lot of pump noise, especially if the radiator is mounted incorrectly.
The larger the diameter of a fan, the lower the RPM it can spin at to move the same amount of air (same cooling capacity) as a small fan. Provided you can put the air where it's needed (e.g. a 1 foot fan can't "focus" air onto a 6 inch radiator) a larger fan will just about always be quieter and more efficient.
Oh, and having a water cooled PC with the radiator and fan inside the PC itself is silly. If you run the pipes outside or into your basement, your PC is almost completely silent, plus the cooling capacity will usually be much, much higher, because not having to cram fans and a radiator into a small enclosure lets you make them bigger and more efficient.
Your parent commenter is talking about AIOs, which are premade water cooling systems. Fixed radiator, hard connected to a pump. Nothing you can route out of your PC.
And historically, bigger case fans have been problematic, those 200mm fans they tried to introduce some years ago. Bad static pressure if I recall correctly?
Also, I wouldn't call having a radiator and fan inside the PC silly. The case eats a lot of the noise already, it's the easy and the common setup, and good AIOs are quiet and cool well. But maybe you just wanted to share a cool big water cooling setup with everything noisy routed into the basement ;)
Best way I found to reduce pump noise is to insulate it.
In my case I have a DDC style pump, and its very quiet after I got a car wash sponge and cut a square hole in it and put the pump inside. It looks ghetto but its inside a case so who cares.
At first I was worried about heat, but its lasted 10 years so far.
You can minimize noise with oversized radiator area and low fan rpm along with good flow/noise ratio fans like noctuas notoriously good 120mm design. You can compensate in one area for another, i.e. by having such a gigantic radiator that fans are hardly needed. Quiet setups cost extra, for sure.
I heard a story about a DIY PC that did nothing but circulate water through the cpu cooler from a fish tank; the tank was big enough to dissipate heat through evaporation and other means, only occasionally needing a top off.
I actually mounted an automotive transmission cooler to the outside of my PC and made it part of the watercooling loop, because it was inexpensive and large. There are no fans on it, but it still reduces the work the standard pc cooling radiator with the fans on it needs to do.
This will be true for a long time - the design constraints are so totally different it would be foolish to use the same design in desktop and laptop systems.
The most limiting thing is TDP, which in the highest performance laptop processors is still capped at 45W, whereas a maxed out desktop processor can draw 100W or more.
> The most limiting thing is TDP, which in the highest performance laptop processors is still capped at 45W, whereas a maxed out desktop processor can draw 100W or more.
Maybe a small desktop. My desktop processor is 180W TDP (Threadripper 1950x), while some others are 250W TDP. You can also get a dual-socket workstation, for 2x CPUs (both pulling 200W each).
Thermals and power are significantly higher on desktops, it ain't even funny. Laptops win in power-efficiency, but absolute performance is always going to be a Desktop.
My workstation has a 3990x in it. It may not be the fastest single threaded machine out there but there isn't a laptop available right now with 64 cores (128 with hyperthreading if that supports your workload). As a c++ developer, compilation speed is p0 to me and there isn't a laptop that comes even close.
The trend in laptops has been for longer battery life and less heat. Since there haven't been any major breakthroughs in battery technology or mobile processor power (at least from Intel), this means lower power for processors and generally lower performance in general. Almost all laptops are using ultra low voltage Intel chips. And even the ones that don't, except for high end gaming laptops, thermally throttle ALL the time.
As a result, your 10 year old desktop is probably 50-100% faster than the most expensive Macbook Pro or Thinkpad. It can be quite astonishing swapping to even an old desktop after using a laptop for a long time.
Eventually laptops will be so optimized for battery life, and display ads will be so aggressive, that you'll have to run chromium in the cloud and your thin client will be shut down the moment anyone accuses you of being a fascist. https://blog.cloudflare.com/browser-beta/
I know you put the Intel disclaimer in there, but I just bought a laptop with an AMD Ryzen 9 4900HS and am loving it. It has me pretty hyped to get an AMD processor for the first time for my desktop when the 5900 launches in November. But the laptop chip has far exceeded my expectations.
I have to agree that the latest AMD Renoir processors are beasts - I have 4800H in a laptop that can sustain 54W TDP OOTB and CPU benchmarks are within spitting distance of my 3700X workstation. Amazing for a 1.5kg portable package.
I'm planning to drop in a 5950X upgrade in the workstation in a couple weeks as well. Looking forward to both the huge multi-threaded and IPC gains.
What example configuration machine from a decade ago can match (or beat) a current-gen maxed-out Thinkpad or Macbook Pro in raw performance? Those laptops are quite speedy compared to something from 2010
Slight exaggeration on my part. I was thinking of my old desktop which is about 6 years old - taking about half the time to compile a project compared to my brand new MBP.
I mean it mostly depends on what you do no? But all I need is for my job is a terminal session open. A macbook from 2010 can (and does) do that fine for me. I don't need the 85% of the specs I never use and I suspect the same applies to the author.
not only is it still true, there's never been evidence it's not been true or that it's going away.
Time after time, as someone who's been working on his 10 year old desktop (with a replacement ssd + graphics card when the old one died), I meet devs and analysts using laptops who reason more or less: "well it says i7 and it says x GHz and it says ddr3/4 and it's got a gpu with the same marketing number, so laptops perform the same as desktops cause they have the same hardware in them don't they".
Clearly, what they really mean is "I've never worked with and compared with a desktop". I suppose one of the problems is that SOME of them that have 'used desktops' were actually using neutered VMs in a shared corporate environment that run really poorly and are pretty underspec'd in a shared environment.
But every time, it's actually been the case that not only is the desktop faster and cheaper, but things usually remained faster on an X year old desktop hardware vs more modern laptops for any serious workload.
Edit: and in case it needs to be said, I have both desktops and multiple portable devices in my household because the downside of desktops is clearly portability.
I usually build a desktop for $4-500, because I reuse parts from the older one, and don't need a gamer graphics card. I blow the money on the mobo, CPU, and lots of ram.
As a gamer I've fallen into upgrading my CPU/mobo/ram and GPU in an alternating fashion every 2ish years.
I might break the pattern this year though, I got a 3900x last year around launch and moved my 4670k to a home server. I've been pretty impressed with the 3900x while the 4670k has been maxing out all cores in the server for some tasks so was considering buying a second 3900X(T) to replace the 4670k again. But with the rumours about the 5900X, I might end up putting the 5900X in my desktop at the same time as a 3000 series GPU and moving the 3900x to my home server.
Same, I saved my ssd/hdd, gpu and case and built a ryzen 3700x with 16gb of ram for less than 400 dollars altogether. My 1k USD laptop has half of that computing power, easily.
My Aero 15 would never throttle, with a 7700HQ + 1060. There was a 700mhz penalty in that generation (3.5ghz vs 4.2ghz for the 7700k), but I kept it pegged for hours and it was rock solid.
Most laptop cooling is awful, but you can certainly find laptops that are well built if you look for it.
Not sure you should weigh bloatware, either. You can trivially install a fresh Windows or Linux and you have to on a custom built PC anyway. If you buy a premade PC, it probably comes with the same crap.
For what it's worth, I switched to a desktop once the core race heated up - now I've got a 12 core 3900X.
I can't believe how much faster it is when it's using all the cores. Night and day. Highly recommended. And 12 cores is barely scratching the surface of the crazy workstations you can build these days.
For tasks 4 threads and less, it would be a bit faster than a current gen Intel laptop chip, but I don't think it would have been worth the portability penalty to me personally if that's all I did with it.
You answered your own question: CPUs are throttled down when there is too much heat. That happens all the time in a laptop. A desktop with enough air flow never has that problem (unless overclocked).
It depends on your definition of throttled. A CPU that was totally unthrottled would just sit at its boost clock under sustained load, but even desktop CPUs can't manage that, dropping to their base if too much heat is generated. Of course, there are laptops that can't even sustain the base clocks, but some have enough cooling to match that.
The base clock rate is typically defined as the sustainable speed. Intel literally calls Turbo Boost "algorithmic overclocking".
The problem is this base clock speed is given by the CPU manufacturer not the laptop maker. And Intel wouldn't know what kind of laptop it's getting crammed into. So careful definitions don't really help. Desktops are already big clunky things that have to be kept plugged in, I can trust them a lot more to deliver the CPU's promised performance. Whereas laptops are notoriously making compromises because customers tend to be very unrealistic about noise, battery life, etc.
The amount of raw power you can drive will "always" be contingent upon your ability to dissipate heat. And the second law of thermodynamics being what it is, that ability is relative to the space you have (assuming you're using similar cooling technologies in both cases).
Laptops being power-conscious, they're usually much closer to the point of maximum efficiency on the power curve. In that sense you get better performance per watt. But that's negated by the increased front cost.
AFAIK mobile CPUs max out at 8 physical cores, whereas you can get 16 at the higher end of mainstream in desktops, and up to 64 in the enthusiast segment. Core count isn't the whole story, obviously, but an important consideration for many applications.
Now heat and power consumption is the bottleneck of laptop performance. Performance laptops uses same CPU silicon to desktop (even different SKU, especially Intel) but their performance is limited.
I didn't see any specific numbers in reply to your comment, so I just want to point out that base clock Ghz for Intel and AMD is much higher for desktop CPUs than laptops. For your average click-read cycle, this feels better.
At full load, it depends on the heat dissipation; Dell's Precision 7XX0 dissipates heat well enough to keep the CPUs from throttling, but the 5XX0 does not.
