Intel: We 'Forgot' To Mention 28-Core, 5GHz CPU Demo Was Overclocked (tomshardware.com)

At Computex earlier this week, Intel showed off a 28-core processor running at 5GHz, implying that it would be a shipping chip with a 5.0GHz stock speed. Unfortunately, as Tom's Hardware reports, "it turns out that Intel overclocked the 28-core processor to such an extreme that it required a one-horsepower industrial water chiller." From the report: We met with the company last night, and while Intel didn't provide many details, a company representative explained to us that "in the excitement of the moment," the company merely "forgot" to tell the crowd that it had overclocked the system. Intel also said it isn't targeting the gaming crowd with the new chip. The presentation did take place in front of a crowd of roughly a hundred journalists and a few thousand others, not to mention a global livestream with untold numbers watching live, so perhaps nerves came into play. In the end, Intel claims the whole fiasco is merely the result of a flubbed recitation of pre-scripted lines, with the accidental omission of a single word: "Overclocked." Maybe that's the truth, but there's a lot of room for debate considering how convenient an omission this is.

Comments

Really?

[orlanz]

I was pretty sure it was way overclocked. Kind of thought it was obvious. They aren't working on anything in the 4GHz range so why would they suddenly jump to 5 for release?

Re:Really?

[Narcocide]

Pointy-haired bosses will nonetheless believe this is what they're getting when they buy their next round of office desktops without even considering AMD solutions.

Re:Really?

[iggymanz]

well IBM power8 has 5GHz chip, what's Intel's problem

Re:Really?

[Z80a]

As far i know, this translator is actually quite tiny.

Re:Really?

[MrL0G1C]

The AC has probably been saying that for a couple of decades without noticing that transistor counts have increased a thousand -fold since it was an issue.

Re:Really?

[Joe_Dragon]

to lock people into Intel it's not like you can put an amd chip in an intel system or that your raid key will be needed.

Re: Really?

[Bing Tsher E]

PHBs seldom are buying from the 'tip' of the leading edge of processors. They buy what the PC vendors are integrating at a reasonable price, and based on a long term track record.

Re:Really?

[edwdig]

They demoed the system in public. The case was open. There were large pipes running into it for the water cooling, and a large water chiller unit next to it. There were pictures of the setup included in the initial articles about it.

They didn't explicitly state that it was overclocked because it couldn't possibly be more obvious.

Re: Really?

[jimbo]

Intel tried with the i860 which was launched with great fanfare and became a huge failure. Later they tried again with the Itanium which actually reused some of the i860 marketing material and also failed, though it did manage to indirectly kill some competing architectures, like HP PA RISC and Digital Alpha.

Part of the reason for Intel failing with Itanium was AMD64 which was easy to deploy and in fact turned out to perform very well. It might be an ugly instructionset but it seems to have trivial impact. Perhaps it is a different story on very low power systems (ARM).

Re:Really?

[spire3661]

As the manufacturer, Intel doesn't get the luxury of showing off overclocked perf. They are obligated to show what they can actually deliver and warranty. No consumer or business setup would run what Intel demoed. The chiller alone drew 1500 watts.....The PSU was rated at 3300 watts....https://pc.watch.impress.co.jp/docs/news/event/1126665.html

Re:Really?

[Anonymous Coward]

You dare say that the glorious and progressive company such as Intel which laid off 1500 of its skilled engineers and staff to pave way for Women's Outreach and Inclusiveness programs introduced around the same time, and started doing stup- INTELLIGENT fraudu- TRUSTWORTHY shit since then, is involved in spreading fake news? You sir, are a misogynist homophobic transhating bigot. To criticize Intel is to criticize the LGBTP+BBQ that they represent and to undermine the necessary existence of inclusiveness programs and the necessary elimination of the prospect of meritocracy.

Re:Really?

[zippthorne]

Why? Overclock performance might be interesting to some use-cases, and if it runs stably, I'm not sure you can even say it is overclocking just because it's not running at the most efficient clock speed. Maybe the fancy high TDP setup is the design point and all the other uses are under clocking.

Why shouldn't they demo whatever speed they want, as long as they don't try to hide the power and support infrastructure required to operate at that speed or use a specially-crafted use case that disguises stability problems.

Re:Really?

[Anonymous Coward]

Maybe because it is unknown how long this system will be stable? You know - You can drive electronic devices like processors beyond their limits for a certain time, but operating all time beyond limits shortens the life expectancy dramatically. On top of that, the number of hardware faults will also increase. You certainly do not want to have that that in production/reliable environments.

And third (and this is important) - If they do such a thing, it is obvious they choose a "perfect" sample from the batch, but it is very likely that "standard" users will get an average processor, that will never reach that performance. In that sense it is completely misleading. They present something that a "standard" user is not able to do, even if they use above normal cooling.

Intel used this misleading presentation in hopes it will "stuck" in the brains of the decision makers, even after they admit they represented a false image of performance. In my opinion Intel is scared that the AMD upcoming processors take a bite out of their market, and goes for this kind of misleading stuff to keep their hold.

Re:Really?

[Bert64]

New processor architectures are always going to fail to enter existing markets so long as closed source code is prevalent.
Whatever advantages they have are lost once they're forced to emulate an x86 chip in order to run legacy code, the hardware ends up being perceived as slow even if the slowness is only due to emulation overhead, so this hurts sales and with low sales proprietary vendors won't port their code to the platform.

Alpha and IA64 made great linux servers, but they were always a small niche.

ARM is huge in embedded, and yet it's going very slow at making inroads into the server market even tho a large proportion of the server market is open source code that's already been compiled for ARM.

Re:Really?

[Rockoon]

As far i know, this translator is actually quite tiny.

Not only is it tiny, its a necessary thing for chips to approach optimality that they have instructions that produce more than one "minimalist" operation. The rate that they could feed the execution units on pure RISC chips was THE bottleneck, and probably still is, that keeps RISC from winning the performance game.

It isnt just the lack of read-modify-write instructions either, but it is a fine example of the RISC problem. On x86 an instruction like "add [dword ptr address], eax" is turned into 3 uops within the decoder that are equivalent to a RISCy implementation of the 3 inherent "simple" operation. The thing is the RISCy version requires 3 times as much instruction fetch as the x86 equivalent.

During the height of the RISC vs CISC war, processors were limited to 8 bytes of bandwidth per clock cycle for the instruction fetcher while at the same time were introducing "super scaler" features. If you wanted your architecture to execute 2 operations per clock cycle, then it had better be able to fit their encoding into the 8 bytes of the fetcher. In this example RISC requires that the address be stated twice in the instruction stream and that alone is already 8 bytes for 32-bit systems. The read-modify-write x86 equivalent only requires that the address be stated once, AND ALSO only needs to encode 1 instruction. So on x86 the 3 operations could be pipelined in one cycle with instruction bandwidth to spare while on say ALPHA it required multiple cycles due to its instruction fetch bottleneck.

RISC is a label for one of the extreme ends of architecture design, and its not optimal. Nobody is doing the other extreme end, which also isn't optimal.

Re: Really?

[Rockoon]

RISC is a solution looking for a problem at this point. While you dont need a complicated decoder on RISC, If you want to perform as well as x86 while being RISCy then you need more instruction fetch bandwidth going into the decoder than x86 needs. Its a tradeoff that does not favor RISC, which is why it lost. RISC was winning up until the moment that CPU's went super-scaler, at which point the instruction fetch shortcoming becomes a losing burden.

Re:Really?

[thegarbz]

well IBM power8 has 5GHz chip, what's Intel's problem

It's not Intel. It's those pesky customers who don't want a 190W TPD chip in their computers.

Re:Really?

[thegarbz]

The instruction set has nothing to do with clock speed.

Re:Really?

[TheRaven64]

It's a bit more subtle than that. Since about 2007, we've not been seeing Dennard scaling, so although transistor counts have gone up, the number that you can power at any given time has not increased by nearly as much. This is what people mean when they talk about 'dark silicon'. The problem with the x86 decoder is that it needs to be powered most of the time, because any time you're executing instructions that are not in the trace cache, it's necessary. The same is true for caches (though you can turn off some of the ways in a set-associative cache when you're seeing that they're not used - not sure if anyone does this in commercial processors) and the register rename engine. All of the execution pipelines can be power gated so you can turn some of them off depending on the instruction mix (for example, powering down the AVX pipes in scalar workloads).

It doesn't matter much to Intel at the high end, because it isn't a huge part of the total power consumption, but it is a problem at the low end when reducing the power consumption of everything else makes it start to dominate again.

Re:Really?

[Kjella]

They didn't explicitly state that it was overclocked because it couldn't possibly be more obvious.

True, but they also announced they'd bring it to market. It's a bit like demoing a customized race edition car and saying it's going on sale, while not explicitly saying that the street version will be much slower. If you search the net you'll find lots of false headlines like Intel to launch a 28-core monster CPU running at 5GHz later this year which makes it a PR goof. Some think it was done with malice to steal AMD's thunder but I doubt the backlash is worth it, but those who do are now trying to make as big a stink as possible about it.

Re:Really?

[Megol]

Simple: overclocked = clocked higher than specified as the normal operating range. Specified is the important part.

So if Intel said that their processor could run at 5GHz when kept at (let's say) 20 degrees Celsius maximum and still be within specifications it wouldn't be overclocked.

That's what everyone was thinking this was about, cherry picked processors from the very top bin deemed reliable if coupled to some extreme cooling system.
The difference here is that Intel failed to mention that despite their heroic cooling efforts the system wasn't guaranteed to actually work at that clock speed.

Not obvious to me at least. And very dishonest _even_ if the presenter was expected to scream of the top of his lungs that the system was overclocked.

Re:Really?

[bws111]

Well IBM z14 has 54 years of instruction set history, is about as un-RISC as you can find with over 1000 instructions, and manages to run at 5.2GHz

Re:Really?

[Z80a]

Kinda but not really.
As we're dealing with a pipelined CPU here, it is just another stage, which means that while the CPU is translating instruction X, it is already running instruction Y and Z and W and... (good thing this is not a pentium 4 description, or i would run out of letters half way in).

Re: Really?

[DontBeAMoran]

Nevertheless, they will remember to buy "Intel" because of this impressive 5GHz demo.

Re: Really?

[LWATCDR]

Yea look at the flop Arm is. No one buys that anymore.

Re:Really?

[DontBeAMoran]

I'm pretty sure 100% of the Raspberry Pi-powered servers are ARM-based.

Re: Really?

[JDeane]

Win on Sunday sell on Monday? I think it was NASCAR or something to do with racing. (not a race fan but I do remember that saying being said on TV or in a movie or something)

Re: Really?

[dgatwood]

RISC is a solution looking for a problem at this point. While you dont need a complicated decoder on RISC, If you want to perform as well as x86 while being RISCy then you need more instruction fetch bandwidth going into the decoder than x86 needs. Its a tradeoff that does not favor RISC, which is why it lost. RISC was winning up until the moment that CPU's went super-scaler, at which point the instruction fetch shortcoming becomes a losing burden.

Not at all true. RISC didn't lose. PowerPC lost because Apple didn't have the marketshare to be worth IBM's time. IBM wanted to focus on building hardware for gaming consoles where they thought they could get better volume, and didn't want to spend the R&D effort to build a version of the G5 that could thermally survive in a laptop. The gaming console designs mostly paired lots of DSP hardware with a really minimal (603e-quality) main core, so those designs were unsuitable for Apple's needs.

But RISC itself has basically won at this point. The most popular CPU architecture on the planet, by a large margin, is ARM, which is RISC. There are on the order of 250 times as many ARM chips built every year as x86/x86-64 chips from AMD and Intel combined. Pretty much every cell phone out there uses the ARM ISA, and more and more tablets are switching to ARM every year. Why? Because CISC doesn't scale nearly as well as RISC in terms of CPU horsepower per unit heat/power, which is the most critical thing for mobile devices, laptops, etc.

I expect CISC to be basically dead in twenty years, and possibly sooner.

Re:Really?

[Narcocide]

Clearly one of us is wrong about this assertion. How does that feel?

Re:Really?

[Narcocide]

They've got you brainwashed so badly that you forgot that PHBs run OEMs like Dell, too. Read your statement carefully again. See how the logic only works if you forgot there was a possibility that "Dell" (for example) could one day ship an AMD solution if they perceived enough demand...

Re: Really?

[edwdig]

Because CISC doesn't scale nearly as well as RISC in terms of CPU horsepower per unit heat/power

What you're seeing has nothing to do with CISC vs RISC and everything to do with the design philosophy behind x86 and ARM.

x86 chips were designed for decades to favor raw power over efficiency. ARM was designed from the start to optimize for power efficiency.

Any time you add a feature or an optimization to a chip, the designers ask if it's worth the cost both in terms of transistors required and power usage. Intel focused on chips running off wall power that sold for hundreds of dollars, so it was generally pretty easy to justify adding things. ARM focused on chips that cost tens of dollars and had to run off small batteries. Features don't get added to ARM chips unless they add a lot of performance for the transistor/power cost.

If you look at Power or Sparc instead of x86, you'll find similar results. If anything, those RISC chips are probably even more power inefficient, as they were designed for customers who demanded top of the line performance and were willing to pay a lot for it.

Re: Really?

[zippthorne]

You seriously woudn't want to see that demo?

Re:Really?

[iggymanz]

there are xeon with 140+ watt TPD....and much less compute power, of course.

Re: Really?

[iggymanz]

or we could say the major "CISC" chips now use RISC architectural innovations under the hood anyway

Re: Really?

[dgatwood]

If you look at Power or Sparc instead of x86, you'll find similar results. If anything, those RISC chips are probably even more power inefficient, as they were designed for customers who demanded top of the line performance and were willing to pay a lot for it.

I would argue that PowerPC itself is a counterexample. It's very close to being Power (and the 601 and 970 are Power, for all intents and purposes, IIRC), and they definitely produced amazing amounts of horsepower per watt relative to other hardware available at the time. The biggest problem there, IMO, was that they optimized for floating point performance, which turned out to make for amazing graphics and audio crunching, but a very sluggish UI.

Re:Really?

[Xnet Project]

Here are our thoughts on the whole scenario. It looks like Intel was caught off guard with no previously planning for a reveal because they weren't prepared to show a new CPU for future launch. It also looks like they are scrambling to design a processor so they can show something in Q3 when AMD decides to launch its new CPU line. In the process of this Intel decided to use a bit of a smoke screen with an 8176 Zeon processor to boast similar stats. It would have been more adventitious for Intel to state they have something coming soon rather than throw a sleight of hand hoping people wouldn't notice it. Not only was it purposely deceptive, but it was a dirty play pull peoples attention from AMD's new release.

Re:Really?

[yagiz]

thanks
Aksaray'da öyle felekten bir gece çalmak isteyeceiz birbirinden güzel bayanlara bu site araclyla size ulama frsat veriyoruz.Top sizde.

Re:Really?

[samwichse]

I mean, you can buy an AMD processor that runs at 4.7ghz with turbo to 5ghz right now at newegg:

https://www.newegg.com/Product...

Released 5 years ago, June 2013.

And it was a 32 core machine ...

[perpenso]

We 'Forgot' To Mention 28-Core, 5GHz CPU Demo Was Overclocked

They probably also forgot to mention that it was a 32-core device with 4 faulty cores. ;-)

Re:And it was a 32 core machine ...

[Ecuador]

And that you can't use it to divide floating point numbers if you care about the accuracy of the result ;)

Re:And it was a 32 core machine ...

[alvinrod]

I would have assumed this was the case as well, but this is almost certainly one of their Skylake XCC (Extreme Core Count) chips that are used for the high-end Xeon processors that retail for around $10,000 depending on clock speeds. The cores are laid out on a 5 x 6 grid, but two of the spots are used for the memory controller. Here's a site with a good shot of the die and a diagram of the parts of the chip.

I don't know what they intend to charge for this thing, but it's a full chip and utterly massive at almost 700 mm^2. I don't expect it to normally run anywhere close to 5 GHz as one of the tech sites pointed out that Intel was using a stand alone water cooler rated for about ~1700W and that the power supply for their demo was a 1600W job, but even having 28 cores at 3.5 GHz is an insane amount of computational power. I expect it to be priced similarly.

Re:And it was a 32 core machine ...

[perpenso]

I agree with "an insane amount of computational power" but I think of it more in terms of a highly specialized application. For most users diminishing returns as you add cores will likely make the more powerful/expensive CPU not worth it. And for things that could benefit from highly parallel computation a GPU may have a better cost/benefit. Perhaps a virtual machine host would be an appropriate specialized application? Just speculating.

Re: And it was a 32 core machine ...

[Xenx]

When you're talking about systems that need(truly make use of) 32 cores, the math isn't that simple.

Re:And it was a 32 core machine ...

[Ramze]

This wasn't a new chip -- it was a rebranded server chip overclocked to 5 Ghz using external -10 C (14 F) temp cooling system and a modified motherboard that could use non-ECC memory.

No one would seriously purchase that abomination. It was meant as a distraction and a bit of marketing to compete with AMD's upcoming 32 core Threadripper 2 that was announced shortly after. It was literally a "hey, we got something that can compete with that!" pony show where no one talked about the cooling system needed to overclock it that high -- or even that it was overclocked. Inexperienced reporters ran with a headline that this was a new desktop CPU we might be seeing in the near future. Nope.

They are already now fessing up that if this thing sees daylight, it won't be stock clocked to 5 Ghz -- you'd be lucky to see it at 3.7 Ghz with boost to 4.2 Ghz on some cores. It's literally nothing new and worse than AMD's threadripper model with more cores and made with a better manufacturing process.

It's beyond BS when you take a chip already in use in servers, cherry pick one that has the best (almost miracle perfect) overclock capability and use what was basically a refrigerator to cool the water cooling system and hype it as a DEMO for some upcoming product. Tis vaporware to compete on paper with a soon-to-be shipping AMD product.

Re: And it was a 32 core machine ...

[Rockoon]

Even quad channel memory cant keep up with the demands of 32 x86 cores on most of the things people want 32 cores for. This is due to the design of the x86 caches leaning towards lower latency instead of towards higher bandwidth. GPU's with lots of "cores" of course have the opposite problem, terrible latency.

Because Chipzilla would never ....

[UnknownSoldier]

/sarcasm Chipzilla would never resort to benchmarking shenanigans ... Oh wait.

Re:Because Chipzilla would never ....

[Anonymous Coward]

"Intel will pay affected consumers $15 if they purchased a Pentium 4 system between November 20, 2000 and June 30, 2002."

LOL. Thats like getting a voucher to buy the next overpriced thing by the same company that just ripped you off.

And cooled to -10C

[Billly Gates]

Even then it is doubtful it can run at 5 ghz. It also is skylake technology and a 2 year old server chip. My citation is here.

Re:And cooled to -10C

[Anonymous Coward]

No need to cite anything - one of Intel's engineers involved with the demo admitted as much already.

Re:And cooled to -10C

[fahrbot-bot]

Even then it is doubtful it can run at 5 ghz. It also is skylake technology and a 2 year old server chip. My citation is here.

Wouldn't be the first time someone got suckered by a modified demo. My citation is here.

Re:And cooled to -10C

[Carewolf]

Even then it is doubtful it can run at 5 ghz. It also is skylake technology and a 2 year old server chip. My citation is here.

Even today Skylake is still the newest and fastest architecture Intel has. Kaby Lake is Skylake with upgraded process and slightly upgraded GPU. Coffeelake is Skylake-E and thus with slightly higher core count.

Totally a marketing stunt

[Anonymous Coward]

To try and underplay AMD's 32 Core announcement.

Didnâ(TM)t they put âoeTURBOâ in th

[l0ungeb0y]

I recall getting a turbo 486 back in the 90s, was shipped oveclocked. But didnâ(TM)t require a freaking mini fridge to make it sustainable

Top secret water chiller

[AHuxley]

Was the secret water chiller covered by national security?

In Soviet Union Siberia cool smuggled western CPU for you.
In Capitalist west secret water chiller design use kept from you.

Re:Top secret water chiller

[l0ungeb0y]

Cool fact (no pun intended), the cooler tech used for Intel's overclocked Pentium chip uses the same tech invented in the early 1900's to cryogenically preserve Rasputin's penis in a secret vault in the Kremlin

Comment removed

[account_deleted]

Comment removed based on user account deletion

Re:in other news

[iggymanz]

leave Burger King alone, the deep fried fries taste better

Re:28 cores?

[RackinFrackin]

I meant to check the "post anonymously" box on that. oops!

starter pack

[sjames]

So will the new CPU come with a bottle of two stroke oil so you can gas up the chiller and try it out right away?

We've been stuck below 4GHZ for 15+ years now.

[suso]

Since we've been stuck just below 4GHz on production consumer CPUs for like 15 years now, getting above that would be a pretty significant achievement worthy of a Nobel Prize or something (exaggerating), omitting saying it's over clocked is pure marketing trickery. Fucking marketers, I hate em.

Not a chance this works

[Tester99]

Intel just wants a PR win so bad

Re:Not a chance this works

[HiThere]

It probably works. The question is at what price and for how long.

Re: Not a chance this works

[Bing Tsher E]

Intel doesn't care much. The 'opponent' AMD may produce a fine product, but not in a significant enough market segment for Intel to bother caring about. I am not some big Intel fan saying this, just a disinterested observer (the first x86 processor that I can remember noticing I was running that was an AMD part was an 8088 chip).

AMD/Intel fanboys in threads like this are like dogs in the street chasing motorcycles. Get a clue, just get on an Intel or AMD bike and go for a ride. It's much more fun than huffing tailpipe fumes.

Re: in other news

[Anonymous Coward]

How do you know what sh1t tastes like?

I forgot

[sjames]

I forGOT.....that robbing the liquor store is illegal

-Steve Martin

Updated: Intel's YEARS of insufficient management

[Futurepower(R)]

I've updated this from a comment I made before. To me, it seems like a more in-depth understanding of Intel's management in the past 15 years.

Intel's insufficient management: Intel has had many years of insufficient management, in my opinion. (Jan. 22, 2018)

Here is a comment of mine posted exactly 12 years ago: Lower prices are not the answer. Proposal. (June 9, 2006)

Intel's poor marketing: It is not difficult to find other evidence of insufficient management at Intel. Since the beginning of this year I've gotten 40 poorly considered, poorly written marketing emails from Intel. Whoever writes those ads seems to have almost no technical knowledge and no ability with sophisticated communication. This is an amazingly foolish sentence from emails I got from Intel on March 6 and March 8, 2018: "Up your marketing game with segment-focused campaigns..."

Recent background: Meltdown and Spectre: 'worst ever' CPU bugs affect virtually all computers (Jan 4, 2018) "Meltdown is currently thought to primarily affect Intel processors manufactured since 1995, excluding the company's Itanium server chips and Atom processors before 2013."

Linus Torvalds Calls Intel Patches 'Complete and Utter Garbage'. (Jan. 22, 2018)

Two previous errors in design of Intel processors: Pentium FDIV bug (1994) and the Pentium F00F bug (1997)

More EXTREME evidence of insufficient management at Intel: Intel was aware of the chip vulnerability when its CEO sold off $24 million in company stock. (Jan. 3, 2018)

Will Intel be allowed to PROFIT from many years of producing processors with vulnerabilities? Will Intel be treated like U.S. banks in 2008, when many banks profited and many finance system managers got bonuses after the financial crash?

If vulnerabilities are profitable, would Intel deliberately allow vulnerabilities in its products? Were the previous vulnerabilities deliberate? Did the CEO know about the vulnerabilities previously? Do others at Intel profit from the vulnerabilities?

Re:Updated: Intel's YEARS of insufficient manageme

[MrL0G1C]

This would explain why they're going through bankruptcy proceedings. ~

Re: in other news

[mSparks43]

90% of taste is the smell.

Very imperfect management, huge worldwide demand

[Futurepower(R)]

Even though Intel is sloppily managed in many ways, Intel does well because there is a huge worldwide need for faster and better processors.

One story: Is Intel a Buy? The chip giant's stock should be due for a huge correction after soaring 48% higher over the last year, right? Well, not so fast.

Quote from that article: "Intel is experiencing 'an unrelenting demand for compute performance driven by the continuing growth of data and the need to process, analyze, store, and share that data.' "

Re: Didnâ(TM)t they put âoeTURBOâ i

[Bing Tsher E]

I accidentally overclocked my first 486 motherboard, back when a 486 motherboard was leading edge hardware. Basically, I hadet up the ISA bus clock multiplier wrong, so that the ISA bus was running at 12 Mhz. Because the cards I happened to have in my system worked, it made my system run with much faster bus i/o. (This was back in the era when motherboard settings had to have adjustments so that the isa bus would run at the correct 8 Mhz with varying CPU clocks)

Eventually I acquired a card where it crashed the system and I had to figure out why and fix it.

I sold my original Pentium 75 chip after I upgraded to a 133mmx processor. It went to a guy at work who was an overclocking enthusiast. A 'just becuz' enthusiast who could easily afford the latest faster tech. That was my first contact with 'overclocking' enthusiasts. Kind of like people who enjoy getting the most out of a 3.5 horsepower engine in a go cart. Have fun, people.

Halfassed SPARC

[nbvb]

So, Intel demos a halfassed SPARC chip.

Even freakinâ(TM) Oracle can ship a 32-core, 5GHz monster of a chip ...

Intel needs a gigantic cooler for a one-shot demo of a chip with less cores and no DAX accelerators.

My how the mighty have fallen.

Re:Halfassed SPARC

[TeknoHog]

Even freakinÃ(TM) Oracle can ship a 32-core, 5GHz monster of a chip ...

Yeah, but does it support Meltdown like Intel?

It might. Depends on the cooling setup.

Re: in other news

[Bing Tsher E]

You definitely have NOT tasted shit, if you think it's only 10% worse than a fart.

Re:Didnâ(TM)t they put âoeTURBOâ in

[e432776]

I remember those too! Turns out they were needed for backward compatibility with software expecting slower processing. So, it would be more accurate to say your computer back then had more of an underclock feature.

Of course, marketing made a hash of that.

Re:in other news

[scottrocket]

walmart "forgot" to mention the picture on the box was only representative and not the actual product. Flag as Inappropriate

Video game cartridges of the 1980's. Disappointment haunted all my dreams.

Re: in other news

[gravewax]

you actually taste with your sense of smell/nose for the most part. Your mouth/tongue is only capable of very basic senses ,sweet/sour/salty/bitter/savoury. Not that I want to try it but if you block your nose then I imagine shit would actually be in difficult to differentiate from many other foods you actually enjoy.

Re:I love an underdog...

[Anonymous Coward]

What a fun and relevant anecdote!

You can already have that, for $10k.

[Grog6]

It's a 2.5GHz Xeon server chip, overclocked to hell, with a 2000W chiller on it.

And a 1600W power supply.

Here's an interview with an intel engineer, later.

https://youtu.be/ozcEel1rNKM

Re: in other news

[Anonymous Coward]

I can tell you from (now ex) pals im the SM world, that blocking the nose is not enough, as the gases will slightly creep up into the nose from the back of your throat.
You need to be drunk as fuck too, literally numbing your senses ;)
But honestly, it was actually scientifically shown, that horniness raises the bar on what you find disgusting. Which is why all those dirty things become OK during sex.

The hurt starts, when you remove the nose blockage before washing your mouth thoroughly. ^^

Yeah, never do it to a slave, no matter how much you or he/she thinks he/she wants it. ^^

Re:in other news

[MrL0G1C]

Let's face it, 99% of 8bit games were dreadful cynical throw-togethers with some fancy artwork on the cover to sucker people into buying them. A bit like what Steam is becoming with their refusal to do anything about asset-flips and the like.

Hashtag No Shit

[Chas]

Is AMD REALLY causing you to fill your drawers that badly?

Re:Hashtag No Shit

[Khyber]

*looks in desk drawer, full of AMD CPUs*

Well, yea, until I can get some nitric acid to strip the gold off these bitches.

Re:Updated: Intel's YEARS of insufficient manageme

[ilguido]

Or perhaps we are simply hitting some technological roadblock. It seems to me that they (at Intel) are scraping the bottom of the barrel to stay on top, because the technological progress in the area (especially for the x86 architecture) is reaching a plateau.

Re:Very imperfect management, huge worldwide deman

[Rockoon]

Intel isnt making any of the current "compute performance" chips. Thats companies like Google contracting out to companies like TSMC to produce custom chips like the Tensor Processing Unit.

The big joke is that TPU's are coming off old 28nm fabs. Intel has been closing these while TSMC/etc are still making some big bucks on them.

Intels key problem is their vertical business structure. The rent-a-fabs are winning. Intels dirty business practices that forced AMD so spin off their fabs into a rent-a-fab that will be first to 7nm is pure fucking gold comedy. Intel is right fucked until it breaks itself up.

Re:I love an underdog...

[Rockoon]

Is it crazy that I am thinking of building a new system designed to be underclocked?

There are some serious advantages. The obvious is the sudden ability to not give any craps at all about cooling, but the not-so-obvious are the form factors such a system can then take. I am seriously considering this 7.56" x 8.27" x 2.44" case for a desktop system.

Re:in other news

[Rockoon]

Most if not all the 8-bit systems of the 80's had so little ram that it was actually not easy to write even bad games for them.

Re:in other news

[MrL0G1C]

Bubble Bobble, Bards Tale, Repton, Chuckie Egg & Chuckie Egg 2 and Magic Mushrooms are some of the ones I can remember as being good.

Re:LOL ... OMG ... WTF?

[Bert64]

Or you could buy the 32core AMD chips which are already on the market?

Re:in other news

[scottrocket]

Some were so bad they were good, like "Caber Toss" (from some Scottish Highland Games collection, iirc). It's weird the stuff you can find at yard sales...

Neil Armstrong flubbing in chip-space

[Sqreater]

Looks to be the same "leaving a word out" flub that left the "a" out of "One small step for "a" man...etc." But I don't buy it. Was the word used in any written data on what they were doing?

Just an aside: Who says the transistor concept has to be implemented in the physical world? Do switches and amplifiers actually have to be physical? Just wondering. It is a thought that occurred to me several years ago. Are there already non-physical "transistors" out there?

Intel sucks

[DaMattster]

I'll take an AMD EPYC 32 core and overclock that bitch!

one-horsepower industrial water chiller

[dfghjk]

How absurd. First off, what's with the "one-horsepower" nonsense? That's 750 watts, quite a bit for a cooling solution but well within what a single wall outlet provides and really not surprising. Second, what does "industrial" mean here? What would be "industrial" about any cooling equipment able to be powered off a residential wall outlet? Third, why call it a "water chiller"? They know what it is, down to the exact model, and it's not called that. It's not "industrial" either, it's a PC-class product used for its intended purpose.

I wonder how much power they think an active cooling solution would use for a system whose power supply is 1300 watts. They state "That means it took an incredibly expensive (not to mention extreme) setup to pull off the demo. You definitely won't find this type of setup on a normal desktop PC." Well no, it doesn't mean "incredibly extensive" or "extreme" and so what? What they used to demonstrate is not a statement of minimum requirements, nor is a 28-core 5GHz processor something you'd find in a "normal desktop PC" anyway. This is standard overclocking stuff and has been for many, many years.

The attempt here is to suggest that abnormally massive cooling equipment is required when that is not supported by the facts. OK, so it was overclocked and had active cooling, no need to lie about it.

Re:one-horsepower industrial water chiller

[LWATCDR]

"This is standard overclocking stuff and has been for many, many years."
No, you are wrong.
"The attempt here is to suggest that abnormally massive cooling equipment is required when that is not supported by the facts."
No, you are still wrong.
Can you config it on PCPartspicker? Can buy it on newegg?
Let's just march down the line of overclocking, shall we?
Level 1. Aftermarket air cooler like the Cooler Master 212.
Level 2. Massive aftermarket air cooler like the NH-D15
Level 3. AIO water cooler like the H100. Yes level one and two can go back and forth a bit as to which is better.
Level 4. Custom loop.
Exterme phase change coolers, active coolers, dry ice, and LN2. The cut-off point is do you get the CPU below ambient. Or even better below freezing. What you do this as a demo and don't tell anyone that it is not a product and is being massivly overclocked you are trying to pull a fast one.

A mere technical oversight

[Indiana Joe]

Anyone could have made it.

Re:Updated: Intel's YEARS of insufficient manageme

[thegarbz]

Oh yeah Intel have a long history of management fuck-ups and their marketing is well and truly garbage directly contributing to killing some of their products.

But take off that tinfoil hat for a second and look at the history of it's processor bugs:
- The FDIV bug: A processor doing a normal operation can return an incorrect result. This is a breaking bug unrelated to a design feature and a recall was issued. Business as usual.
- The F00F bug: While the result of the processor, it only happens when it is fed a completely invalid instruction. It is not possible to test every possible combination of instructions against processors to see which will cause them to lockup, and why would it be expected that the processor receives such an instruction? The F00F bug is nothing compared to the many hundreds of errata that get published by ALL processor vendors detailing strange behaviour under certain conditions. If you don't use buggy software you won't hit this invalid instruction which has undocumented behaviour.

- Spectre: You write as if this was some nefarious bug that was introduced on purpose knowing the outcome. You write as if it actually affects people in meaningful ways. Take a deep breath, put the <b> tags down and let's see just what happened. A process used to speed up processors was put in place as part of the architecture long before side channel attacks were a thing demonstrated to work on CPUs. The bug affected multiple processors (SPARC, Powers and ARM's Cortex7 CPUs are affected by Spectre too). This is not a bug, it's a vulnerability exploiting a purposeful, documented and widely used feature. And who is affected? A few cloud providers. Whoop-de-do. If you get close enough to use Spectre on someone's computer then you already own them anyway.

Will Intel be allowed to profit? Why not? Do you punish car makers for producing vehicles that can be driven faster than the max speed limit leading to safety issues? There is absolutely no reason not to let Intel profit from this. To go after them at this point would be to basically say no one who programs for a living should ever turn a profit given the number of basic bugs that creep into most software. And while you try and strip Intel of profits, first prove to us how you were negatively impacted to the point where your purchasing decision would have been different given the advanced knowledge.

Intel: Sloppy communicating. Meltdown bug.

[Futurepower(R)]

I see some sense in what you said. However, when Steve Jobs was alive and healthy, he was good at making sure Apple was presented in a way that communicated well and efficiently. Part of the problem I see with Intel is sloppy communicating.

Here is a discussion of the problems with the vulnerability called Meltdown, which you didn't mention in your comment: Meltdown and Spectre FAQ: How the critical CPU flaws affect PCs and Macs.

Quote: Meltdown "breaks the most fundamental isolation between user applications and the operating system", according to Google. This flaw most strongly affects Intel processors because of the aggressive way they handle speculative execution, though a few ARM cores are also susceptible."

Re:Intel: Sloppy communicating. Meltdown bug.

[thegarbz]

Yes it does break that isolation. And it does so in a way that is almost impossible to exploit without someone having direct access to the computer already. Again if I were a cloud provider I would be pissed, general users, server administrators, and pretty much any scenario that doesn't involve handing your keyboard over to someone else while you leave them alone with your computer for a long time has nothing to worry about.

And even if they were more seriously exploitable, side channel attacks are still fundamentally different to the FDIV bug which was the processor not doing what it was supposed to.

Complete non-issue

[koomba]

The entire "controversy" around the initial presentation of the system before the details were known was a complete non-issue. Anyone who follows current pc hardware and CPU trends and news knew immediately that it was an overclocked system, or at least they should have.

There were of course a bunch of wishful thinking fanboys and ignorant forum warrior types who immediately started with the "omg I can't believe this, I can't wait to buy one!" crap, but they were all just being delusional. Intel had just shortly before this announced a special edition 6 core chip that would stick turbo to 5 ghz on ONE core, and that was a first for a stock click chip.

So of course a 28 core 5ghz chip is overclocked. Those who made such a big deal about Intel being dishonest were either drama queens who like to get outraged on the internet; or they were rabid AMD fanboys who regularly grasp at any and all straws to bad mouth Intel. So again, complete non-story generated to drive page views and/or typical internet outrage bullshit.