CompuLab Turns An 8-Core/16-Thread Xeon, 64GB RAM, NVIDIA Quadro RTX 4000 Into Fan-Less Computer

[schmidtbag]

Recall that you credited them for the specs on their system and I pointed out that it's premature, as we don't actually have the data to know how well it performs. I didn't actually say it performs poorly - we just don't know.

Yes, you've made this point pretty clear. Still doesn't change the fact that you're really obsessing over something that isn't that big of a deal, which is the entire basis of this argument.

Not clocks - power. And you make it sound like it's a bad thing, when the point of it is for maximizing the CPU within the power and thermal capabilities of the system. I don't consider it foul play, unless they also advertised their system had no performance penalties relative to conventional cooling.

I stated from the beginning that they're probably meddling with the wattage. If the stock frequencies aren't meddled with, who cares? Why are you wasting your time arguing over how much power the CPU draws (which is probably less than Intel's specs) if that doesn't negatively hurt its performance?
The whole reason you're arguing with me is because you suspect the performance numbers are being deliberately hidden. We already know that the CPU isn't running hot enough to thermal throttle below its base clocks (yeah I know, you don't agree with that), regardless of whether or not they lowered the PL1 wattage. So the PL1 wattage is not a factor to consider here.

You're clearly out of your depth. The point of them having a separate set of boost parameters is because the ability of a cooling solution to handle boost is somewhat separate from its capacity for sustained heat transfer.

Where did I suggest otherwise?

My point was I shouldn't have to teach you science that the typical 10th grader should know.

Except I don't know what science specifically you're referring to. I'm not a mind reader, and seeing as we're in a disagreement here, I have no good reason to just know what it is you're thinking and why you're thinking it.

The setting is there to be configured. I think it would be a legit thing to do.

See, this is why I don't know what 10th grade science you're referring to. You're so inconsistent. You "apparently" were only talking about the PL1 wattage, which as I just said, doesn't inherently negatively impact performance. Now you're saying that it's legitimately possible they're tampering with the overall PL1 performance (which would include clock speeds).
Make up your mind.

This makes no sense.

Of course it doesn't make sense to you, because you're so caught up in your own view. Even though it is expected that you will have to sacrifice performance for this PC, all you care about is how it performs, thus failing to understand why this PC exists and who would buy it.

This is really the core issue. You act as if there's only one fanless PC in the world. That people have a binary choice, do I go fanless or not? Totally ignoring that there are other fanless PCs and that someone might want performance data to help them decide which to buy. Even within the offerings of a single vendor, they might want data to help them decide if a higher-end model is worth the additional money. And, if they don't need it to be completely fanless, they might be willing to consider other low-noise options, especially if they were a cheaper and offered more performance.

Uh... no? I'm saying there's only 1 PC in the world with decent workstation hardware that is both silent and small. You have a really annoying tendency to only listen to what you want to hear

The consequence of your position is that gaming PC reviews should not have acoustic noise or power consumption data, because gaming PCs are loud and burn a lot of power. And because they're a niche product and people should realize that they'll be louder and burn more power, that they shouldn't care about the specifics or have the ability to make an informed decision between various alternatives, even within the category.

Seeing as you aren't paying attention, no, that isn't a consequence of my position because that's not my position.

Another consequence of your position is that sports car buyers shouldn't care about fuel mileage or cargo capacity, because they know those parameters will be worse and therefore must completely abandon any concerns other than performance and handling.

Actually that's entirely right - if you buy a high-end sports car, most people legit don't care about fuel consumption or cargo. Don't believe me? Look at how wildly popular a car like the Lamborghini Gallardo is. That gets terrible fuel economy and can barely fit a suitcase for 1 person. There are cheaper cars that can have more cargo room and/or have a similar driving experience. And yet, people buy it anyway. They're willing to make sacrifices because they're looking for something niche. You seem to have a hard time grasping this.

You live in a very strange universe, where people lack competitive alternatives and have only one single priority, to the exclusion of all else. Thankfully, this is not a world I recognize. I will leave you to inhabit this lonely world, bereft of non-overlapping categories and informed compromises.

Name 1 commercially available alternative to this PC. Something silent, equally small, and has similar or better specs. Just 1.

I might know that in a vehicle of similar power and weight, I have trouble maintaining speed up a particularly steep road or that I have trouble merging from a dangerous on-ramp. Numbers can be used to help compare things, even if they're harder to use entirely in the abstract.

Again, 0-60 / 0-100 times will tell you what you need to know better than power.

I understand that you don't care, because you seem to live in some kind of alternate reality.

No, it's because I've been a Phoronix reader for over a decade and I know Michael well enough to not have childish conspiracy theories.

[coder]

Still doesn't change the fact that you're really obsessing over something that isn't that big of a deal, which is the entire basis of this argument.

Your position is that those potentially considering this product do not need detailed knowledge of how it performs. I think that's fundamentally wrong, and that's not a small point.

Why are you wasting your time arguing over how much power the CPU draws (which is probably less than Intel's specs) if that doesn't negatively hurt its performance?

Of course modifying power draw affects its performance! How could you believe otherwise? Why are you wasting your time arguing over something you don't understand?

You "apparently" were only talking about the PL1 wattage,

In fact, I assume at least 4 of the parameters mentioned in the Anandtech article could've been tuned to their thermal solution. It's what I'd probably do, in their shoes. And not only adjusted for the worse - potentially better. That's why I want to see the data.

Uh... no? I'm saying there's only 1 PC in the world with decent workstation hardware that is both silent and small.

There are potential buyers for such a machine that don't require it to be so small or that don't require it to be fanless. If the performance is similar to a larger, air- or water- cooled workstation, someone could conceivably be convinced to buy this product, instead.

You talk about me having a narrow mind, but it seems you're the one who can only conceive of a person buying a thing who has a precise set of needs which only that product can satisfy, no matter the compromises or other factors.

Actually that's entirely right - if you buy a high-end sports car, most people legit don't care about fuel consumption or cargo. Don't believe me? Look at how wildly popular a car like the Lamborghini Gallardo is. That gets terrible fuel economy and can barely fit a suitcase for 1 person. There are cheaper cars that can have more cargo room and/or have a similar driving experience. And yet, people buy it anyway. They're willing to make sacrifices because they're looking for something niche.

The only examples you can find are extremes. And even this won't hold, as I'm sure there are potential buyers of that car who passed it up on pragmatic grounds. Just because some people buy it doesn't mean that its downsides don't put off others.

Name 1 commercially available alternative to this PC. Something silent, equally small, and has similar or better specs. Just 1.

There was another fanless PC maker already linked in this thread. It's incorrect to assume that buyers cannot abide something of a physically larger size:

https://www.deltatronic.de/en/pc-en

Again, 0-60 / 0-100 times will tell you what you need to know better than power.

You're splitting hairs. Worse, disagreeing just to be disagreeable. That said, I'm glad that we can agree that performance data of a fuel-efficient vehicle is a relevant concern for potential buyers.

No, it's because I've been a Phoronix reader for over a decade and I know Michael well enough to not have childish conspiracy theories.

So, why did he only post benchmarks, in that article, that mainly cast that SSD in a good light? He's frequently complaining about the lack of ad revenue, and I've seen a lot of online tech publications go downhill, in recent years. We all know there are bloggers and "influencers" who get paid to pitch vendors' products and we know that Michael is primarily dependent on vendor-supplied hardware. So, I think it's legitimate to point out when he picks benchmarks that seem to bias the perception of a product, whether or not that was his actual intent. I don't yet have enough data points to establish a trend, but readers need to be vigilant and let him know we're watching. I care about this site, which is why I care about Michael's credibility.

[coder]

This entire discussion has devolved into a "How many angels can dance on the head of a pin?" argument.

Opinion noted, but I dare say you haven't actually been reading our posts, in their entirety. Not that I'd blame you for it.

While not a paragon of discourse, on this site, it has largely remained on-topic and included supplemental information relevant to the article.

Drop it, guys. We don't care any more. We don't even READ any more--a major problem for Phoronix--when we see your names pop up.

You're free to add us to your "Ignore List". Just look at the bottom of this page:

https://www.phoronix.com/forums/settings/account

Michael Larabel needs to reign in this type of self-serving activity, or risk compromising point #1. Make no mistake about it: the only reason for the continuation of this circus, by two people, is ego.

If you really want something to complain about, how about policing the comments on the next article concerning Outreachy or a project's code of conduct?

In short, I think you're overreacting, just a bit.

[schmidtbag]

Your position is that those potentially considering this product do not need detailed knowledge of how it performs. I think that's fundamentally wrong, and that's not a small point.

There's a very big difference between me saying "they don't need to know" vs potential customers saying "I don't need to know". As I have stated over and over and over again: I agree with you that knowing the data would be nice. But here's what you just don't seem to grasp:
I'm not telling people they shouldn't care, because I have no right to say that. I'm telling you that most don't care.

Of course modifying power draw affects its performance! How could you believe otherwise? Why are you wasting your time arguing over something you don't understand?

Uh... have you ever overclocked a PC before? Or undervolted? Just because you increase the voltage, doesn't mean the CPU suddenly runs faster. Just because you lower the voltage, doesn't mean it suddenly slows down.

There are potential buyers for such a machine that don't require it to be so small or that don't require it to be fanless. If the performance is similar to a larger, air- or water- cooled workstation, someone could conceivably be convinced to buy this product, instead.

Yeah, no shit... those people will look elsewhere then. If they're seriously looking into this product, it's because it fits their niche. Nobody is forcing anyone to buy this computer. They're buying it because there's nothing else quite like it. If they don't like the fact that they're not going to maximize performance, they should get a larger PC, or a PC with fans.

You talk about me having a narrow mind, but it seems you're the one who can only conceive of a person buying a thing who has a precise set of needs which only that product can satisfy, no matter the compromises or other factors.

That's because you are narrow-minded. You only care about your interests. I acknowledge your interests (which you aren't wrong to have), while pointing out that they don't fit the demographic of people who seek a PC like this. I see your point, but you refuse to look beyond your own.

The only examples you can find are extremes. And even this won't hold, as I'm sure there are potential buyers of that car who passed it up on pragmatic grounds. Just because some people buy it doesn't mean that its downsides don't put off others.

That's because the extremes are analogous. Supercars are an extreme, just like this PC.
If you want a sporty car that's also practical, you can get something like a Mustang or a WRX. They're not as fast and they're not going to turn as many heads, but they're much cheaper, they can actually carry a decent amount of stuff, and they're easier to get fixed. PCs are no different - you can get a cheaper no-compromises PC, but you pick this one because it's special.

There was another fanless PC maker already linked in this thread. It's incorrect to assume that buyers cannot abide something of a physically larger size:

Um... I never said they couldn't get something larger... How are you this daft?
The Deltatronic PCs are huge in comparison. If you're ok with something bigger that offers better performance (which is a perfectly reasonable thing to want) then those are a fantastic option. But CompuLab is offering something a fraction of the size. You don't get a silent PC that tiny without making sacrifices.

You're splitting hairs. Worse, disagreeing just to be disagreeable.

And you are blowing everything out of proportion. So I guess we're even?

So, why did he only post benchmarks, in that article, that mainly cast that SSD in a good light? He's frequently complaining about the lack of ad revenue, and I've seen a lot of online tech publications go downhill, in recent years. We all know there are bloggers and "influencers" who get paid to pitch vendors' products and we know that Michael is primarily dependent on vendor-supplied hardware. So, I think it's legitimate to point out when he picks benchmarks that seem to bias the perception of a product, whether or not that was his actual intent. I don't yet have enough data points to establish a trend, but readers need to be vigilant and let him know we're watching. I care about this site, which is why I care about Michael's credibility.

Yes, it is legitimate to point out. I didn't say otherwise. I'm just saying I don't really care. That doesn't mean "you're wrong" it means "go ahead and have your opinion, I'm not arguing it".

[coder]

Uh... have you ever overclocked a PC before? Or undervolted? Just because you increase the voltage, doesn't mean the CPU suddenly runs faster. Just because you lower the voltage, doesn't mean it suddenly slows down.

It doesn't work by simply modulating voltage, as you'd know if you actually read the Anandtech article.

If they're seriously looking into this product, it's because it fits their niche.

And here we go again. You assume the only ones who buy it are those who need all of its attributes. There's no room in your worldview for someone who "steps up" from a lower-end model, after judging the relative performance vs. cost, or decides that it performs close enough to another workstation they're considering and simply likes the idea of going fanless and finds its aesthetic appealing.

That's because you are narrow-minded. You only care about your interests.

This is cute. I'm clearly not the one deficient in empathic imagination. At least I'm not claiming clairvoyance.

I acknowledge your interests

Really? Then, what are they?

So I guess we're even?

If you're trying to settle a score, that'd make one of us.

[schmidtbag]

It doesn't work by simply modulating voltage, as you'd know if you actually read the Anandtech article.

"It" being what?

And here we go again. You assume the only ones who buy it are those who need all of its attributes. There's no room in your worldview for someone who "steps up" from a lower-end model, after judging the relative performance vs. cost, or decides that it performs close enough to another workstation they're considering and simply likes the idea of going fanless and finds its aesthetic appealing.

Because who the hell else is going to buy this PC? It's a very niche product. Do I really need to spell it out for you?
There are other silent PCs that are faster, but bigger
There are other non-silent PCs that are just as small
There are faster and cheaper PCs than this
There are smaller but slower PCs than this.
So, why buy this PC? Because of the combination it offers, which nothing else has. It's got good specs (for its size), it's silent, and it's small. Just because you don't want to step to a lower-end model, doesn't mean this product doesn't fit someone's needs. Not everyone wants a bigger tower or has the room for it. Not everyone wants fan noise (or perhaps they work in a dusty environment). Not everyone needs the CPU to run at its maximum capacity 24/7. The fact you can't seem to wrap your head around any of this is why I'm arguing with you. You really can't seem to grasp that someone actually has a need for each of this product's traits. All you seem to care about is how fast it runs, and that's not the point of it.

This is cute. I'm clearly not the one deficient in empathic imagination. At least I'm not claiming clairvoyance.

There you go again, jumping to conclusions and exaggerating things. Where did I say I was clairvoyant, or even imply it? I'm saying there are viewpoints and preferences other than your own.

Really? Then, what are they?

Facts and data showing the product on all angles inside and out, so people get a complete picture of what they're getting.

[danmcgrew]

Correction: one mule.

[coder]

"It" being what?

Read the article, and you'll understand how those parameters work. They don't simply modulate voltage, as you claimed. They do have an impact on performance - that's sort of the point.

Pro tip: if you need more context, you can always scroll back (or click the blue [>>] icon, in the quote block), to the see the previous message in the discussion.

Because who the hell else is going to buy this PC? It's a very niche product. Do I really need to spell it out for you?
There are other silent PCs that are faster, but bigger
There are other non-silent PCs that are just as small
There are faster and cheaper PCs than this
There are smaller but slower PCs than this.
So, why buy this PC? Because of the combination it offers, which nothing else has. It's got good specs (for its size), it's silent, and it's small.

Okay, so no influence from price, aesthetics, features, brand loyalty, and emotional influences?

I don't pretend to speak for Compulab, but I'd imagine they would appreciate you sharing your extensive market research with them. Perhaps they'll quite like to know just how much they've decreased their total addressable market by making it so small.

Just because you don't want to step to a lower-end model, doesn't mean this product doesn't fit someone's needs.

Heh, it's cute how you tried to flip that on me, but you can't wear both hats. I'm not the one saying who can't buy it - you've clearly staked out that position for yourself. I'm all about choice and giving people the information they need to make the best decision possible.

Not everyone wants a bigger tower or has the room for it. Not everyone wants fan noise (or perhaps they work in a dusty environment). Not everyone needs the CPU to run at its maximum capacity 24/7. The fact you can't seem to wrap your head around any of this is why I'm arguing with you. You really can't seem to grasp that someone actually has a need for each of this product's traits.

I never said any of that.

Perhaps you're delusional, in which case I offer my sympathies. Or, maybe you've come to doubt the tenability of your position, so you're building a straw man (link), which I don't much appreciate. Either one kinda derails any rational path towards a conclusion.

Where did I say I was clairvoyant, or even imply it?

You seem believe you know my mind so well...

All you seem to care about is how fast it runs, and that's not the point of it.

No, that's not all I care about. And how is that consistent with this:

Facts and data showing the product on all angles inside and out, so people get a complete picture of what they're getting.

Performance is undeniably an important piece of the puzzle - critical for some, less so for others. I don't presume to know what people's priorities are, so I believe they should have as much information as possible, to facilitate the best decision. A properly functioning free market requires equal access to information.

[coder]

Correction: one mule.

This is not even remotely trolling.

[schmidtbag]

Read the article, and you'll understand how those parameters work. They don't simply modulate voltage, as you claimed. They do have an impact on performance - that's sort of the point.

That's assuming they're doing as you say, which you don't have proof of.
And here I thought you said you weren't making assumptions?

Okay, so no influence from price, aesthetics, features, brand loyalty, and emotional influences?

I already mentioned price. Physical size is part of the aesthetic. This PC doesn't appear to be lacking any major features that you'd expect from a pre-built PC (in fact, it even has a front-panel USB-C connector). Compulab isn't a big enough brand to depend on loyalty. Who the hell gets emotional over an OEM workstation that they never got their hands on yet?

I don't pretend to speak for Compulab, but I'd imagine they would appreciate you sharing your extensive market research with them. Perhaps they'll quite like to know just how much they've decreased their total addressable market by making it so small.

Why do I need to? They clearly know what they're doing. You're the one who is skeptical and doesn't seem to understand what's going on. If anything it's you who wants their data.

Heh, it's cute how you tried to flip that on me, but you can't wear both hats. I'm not the one saying who can't buy it - you've clearly staked out that position for yourself. I'm all about choice and giving people the information they need to make the best decision possible.

Um.... I definitely did not ever say people couldn't buy this. I explicitly said I have no right to tell people what to do in my last post. Once again, you just interpret things the way you want to.
All you're about is data and nothing else.

I never said any of that.

Perhaps you're delusional, in which case I offer my sympathies. Or, maybe you've come to doubt the tenability of your position, so you're building a straw man (link), which I don't much appreciate. Either one kinda derails any rational path towards a conclusion.

I know you didn't say any of that. As you continue to exemplify your poor reading comprehension, I was saying how you don't realize any of it. So of course you didn't say any of that, dumbass.
That being said, you don't understand what a straw man fallacy is, because what I said is entirely relevant. In fact, it's the foundation of everything revolving around what I'm talking about.

You seem believe you know my mind so well...

Well, it's the only stuff you've been harping on about. So if you truly believe I'm wrong, you have either:
A. Failed at proving your point
B. Are a hypocrite, since at this point you're the one arguing for the sake of arguing.

Performance is undeniably an important piece of the puzzle - critical for some, less so for others. I don't presume to know what people's priorities are, so I believe they should have as much information as possible, to facilitate the best decision. A properly functioning free market requires equal access to information.

Because I also agree knowing the performance is important, just not critical for this PC. And of course you don't presume other people's priorities are - you're ignoring them. I never said your priorities are wrong, I'm just saying there's more out there that you are willfully ignoring.