Locked Intel Skylake CPUs Can Be Overclocked After BIOS Update (techspot.com)

jjslash writes: For a few years now, Intel CPU overclocking has been limited to more expensive Core i5 and Core i7 'K' processors. Skylake launched this year with the rumor of strong non-K processor overclocking through an adjustable base clock, but that never eventuated... until now. In overclocking circles it was rumored that BCLK (base clock) overclocking might become a possibility in Skylake processors, but it would be up to motherboard manufacturers to circumvent Intel's restrictions. Asrock, Asus and a few other motherboard manufacturers are said to be issuing a BIOS update soon that will unlock base clock overclocking on Z170 motherboards. TechSpot has got an early look, overclocking a locked Core i3-6100 to 4.7GHz on air cooling.

Comments

Exploitable?

[Anonymous Coward]

I wonder if a rootkit could make the motherboard burn up the CPU? Poof! La computer muerte.

Re:Exploitable?

[Anonymous Coward]

Isn't that possible without overclocking anyway? Just being curious.

Re:Exploitable?

[kheldan]

I wonder if a rootkit could make the motherboard burn up the CPU? Poof! La computer muerte.

Depends on how the power delivery on the motherboard is designed, really. You'd have to be able to turn up the supply rails well beyond the margin the silicon is designed and tested for, and I don't think any competent manufacturer would design SMBus-accessible on-board switching regulators to do that; plus tune relevant PLLs for a higher output frequency, plus turn off the CPU cooling fan, plus disable all thermal management that would otherwise shut everything down. Much of this would have to be done at system power-on before everything gets locked down. You'd probably have to infect the BIOS itself, and aren't they all signed now to prevent such a thing from happening?

Re:Exploitable?

[madbrain]

I actually burnt a motherboard and CPU a few weeks ago during an overclocking experiment gone bad, after using a little bit too much voltage.
There was smoke coming out of the VRMs on the motherboard. The machine did shut down, and did not catch fire, thankfully.
This was an AMD FX-8350 on a Gigabyte GA-990FXA-UD3 . The chip was confirmed dead when I tried it in another identical motherboard.

So yes, if a rootkit could actually change those BIOS settings, it could potentially cause this.

Re:Exploitable?

[KGIII]

It might only have to access it and that can be done through the OS now. It might be possible to piggyback on that, no?

My first AMD was a K6-2 350 that I had OCed to 500 Mhz (a little less) and it was stable but it wouldn't be stable past that unless I put it in a fridge while it was running. I had it sitting in a mini-fridge for a while for my own amusement. Anyhow, maybe they trip automatically now and don't allow it? I could have cooked that thing for sure if I could have just kept it on and doing *something* because it was damned hot when it hit about 550 Mhz. It wouldn't even get into the OS all the way before you could smell it and it would shut off. If I'd kept doing that, over and over, I'm sure I could have cooked it - or if I'd stayed in DOS or something, maybe? (I never tried.)

So, maybe? They've got apps to change BIOS settings from inside the OS. I haven't really done much OCing since those days. Computers just got "fast enough." I'm not even sure why I keep buying new hardware. I don't really seem to see much of a difference in the things that I do. I could probably do just fine on an old dual core system with a few gigs of RAM though my documentaries might not like to play as well. It's not like I'm taxing the CPU when I edit a PHP file and upload it. I even off-load my VMs and connect via VNC.

Hmm... Yeah, I guess I too am sort of returning to the days of the dumb terminal.

Re:Exploitable?

[kheldan]

It might only have to access it and that can be done through the OS now. It might be possible to piggyback on that, no?

No, actually, not really. There are registers that, after a certain point of the bring-up process for the silicon, are locked out from access in production parts. In testing the boot process is halted at a certain point in order to 'unlock' parts and allow access to various registers. Once an OS is booted, it's no longer possible to access some of those registers.

Re:Exploitable?

[Shinobi]

There is potentially another way to kill either a CPU or mobo components too, if you do it right, and the OS doesn't watch hard for it, and it doesn't require changes to BIOS/UEFI. If you can trigger the right execution pattern to rapidly cycle between no load, full load on all cores, full load on 1 core and triggering turbo clocking if that's available, you can cause voltage regulators etc to overheat

Re:Exploitable?

[Anonymous Coward]

Yes, actually, really.
Most recent example was a pair of monitoring utilities killing S2011-3 CPUs on Asus X99 boards by setting Vcore to 1.95v when both were running simultaneously.

Re:Exploitable?

[drinkypoo]

Hey, that's exactly the combo I have. What settings did you fry your motherboard with? I've been thinking about going in there and trying to twiddle the settings to mitigate the massive vdroop problem and maybe OC a little more to get a few more FPS, and I don't want to let the smoke out. My board is a 4.0.

Re:Exploitable?

[kheldan]

That's programming a VR that lives on the SMBus, not accessing locked-down PLL registers to overclock the crap out of something, so no, actually, really, that's only one of the elements I was talking about.

Re:Exploitable?

[Anonymous Coward]

It might only have to access it and that can be done through the OS now. It might be possible to piggyback on that, no?

No, actually, not really. There are registers that, after a certain point of the bring-up process for the silicon, are locked out from access in production parts. In testing the boot process is halted at a certain point in order to 'unlock' parts and allow access to various registers. Once an OS is booted, it's no longer possible to access some of those registers.

Yes, actually, really. What do you even mean by "Once the OS is booted". What about everything from the first instruction fetched after the BIOS/UEFI?

Re:Exploitable?

[KGIII]

I've poked at a few of them and I think they required a reboot. They don't make any for Linux - that I know of and own, so I can't really double check that.

Re:Exploitable?

[billcopc]

There are numerous utilities designed specifically to tweak CPU settings while Windows is running. Enthusiast motherboards allow just about every option from the BIOS to be ajusted live, which is meant to facilitate fine-tuning by eliminating some of the reboot-tweak-test cycles in the search for a stable overclock.

If some random asshole app were to reprogram those values, you could most certainly cook a processor by setting the voltage absurdly high and disabling the thermal protection (another option on most OC bards). Run some heavy FPU loops across all threads and the chip will be dead within seconds.

The difficulty of course would be to detect and "support" a wide enough array of popular boards to render this attack effective, as I can only assume the interfaces are vastly different, even within the same brand.

Interessante

[Anonymous Coward]

Bom só resta esperar e ver como saira a potência do Core i7 novo

www.advenhost.com.br

Cat got your tongue? (something important seems to

[ourlovecanlastforeve]

Or you can spend a few more dollars and just buy a CPU that won't burn up and fail from overclocking.

Fake overclocking

[bluefoxlucid]

Old days: the processor should run at 200MHz. You can push 215MHz, but you need to modify the vcore. The processor might be unstable. You might need additional cooling. The gates might just not switch correctly at that speed (miller capacitance...) without a vcore high enough to blow the chip. It's stamped 200MHz for a reason.

Modern times: that's a 4.7GHz processor clocked at 3.8GHz. You buy it, you turn it up to 4.7GHz, don't mess with anything else, it runs 60C at full load under stock configuration. That processor came underclocked out of the box.

Re:Fake overclocking

[Grishnakh]

Um, I thought "binning" hadn't really changed, and that lower-clocked processors were usually sold that way because they didn't pass the higher-clock tests. Of course, you could get lucky because they probably also bin a lot of them at lower clocks just because there's more demand for cheaper CPUs, and to keep the prices of the high-clock versions high, but you're betting that you're getting a CPU binned for a lower clockspeed only for sales purposes rather than test purposes, and there's no way to know which yours is.

Re:Fake overclocking

[bluefoxlucid]

As a general rule, X processor model runs at Y speed these days. The processes are stable at high power outputs, but marketed as 80W CPUs. Most modern processors even run by default at a low clock and add 400-600MHz in "Turbo Mode" automatically when the CPU is running under sufficient load--meaning they just do regular old CPU scaling, but save the higher clock rate for when you're trying to use it. If you run SETI@HOME, they run in turbo mode 100% of the time.

Re:Fake overclocking

[Anonymous Coward]

You still need to Modify the Voltages, its still unstable at times.

And don't think YOU are the center of the universe, It could also sitting in a PC in Texas on a hot day in a PC shoved against a wall under a office workers desk, you need to build things for speck, not enthusiasts

Re:Fake overclocking

[GrandCow]

You're never guaranteed to be able to clock a chip purchased at 3.8GHz prices up to 4.7GHz. You are guaranteed a chip that will run at 3.8GHz.

If you want to roll the dice and attempt to run it faster, more power to you, but if you want to guarantee that it'll run at the higher speed, you pay more.

What's the problem here?

Re:Fake overclocking

[Anonymous Coward]

That there is no Skylake processor guaranteed to run 4.7GHz at all.

Even 6700K is only guaranteed to run 4.2GHz.

On one core.

Re:Fake overclocking

[Ken_g6]

Most CPUs have been significantly overclockable for at least 15 years.

http://www.techrepublic.com/ar...

Re:Fake overclocking

[bluefoxlucid]

"Guarantee" is a funny word. No processor has a 100% probability of running at the rated speed--or even powering on at all. A guarantee only means someone is willing to make good on the defect.

The problem here is that they used to build processors to run at the rated speed, test them to make sure they run at the rated speed, de-rate them to a stable speed if they can only run at a lower speed, and sell them at a speed rated to design and, possibly, to testing. Today, they build processors to run at a high speed and rate them to run at a lower speed, then sell them as "overclockable". They don't build a 3.8GHz processor that can run at 4.2GHz if you're lucky; they build a 4.2GHz processor to high tolerances on a design meant to run at 4.2GHz reliably, and rate it as a 3.8GHz processor.

Modern processors are intentionally overbuilt. They're not built to run a service life at a rated level of performance; they're built to run a service life significantly above the rated level of service. It's like installing 120PSI cold water pipe in your house and rating your home's plumbing for 60PSI residential pressure: if you crank that pressure regulator up to 100PSI, your pipes won't burst, and you're not doing anything particularly special except running the system at a pressure it was purpose-built to handle.

Re:Fake overclocking

[Anonymous Coward]

speck

that's not a word

Re:Fake overclocking

[kheldan]

It's true. It's incredibly expensive to scrap silicon once it's been cut from the wafer, attached to the package, and tested. They'll fuse them differently and mark them differently and sell them. The consequence of just shit-canning everything but the cream-of-the-crop parts would be you'd pay $1000 for a CPU (or some such relatively astronomical figure). Also, there is such a thing as 'margining', where silicon is tested beyond the design parameters, but not 'officially' rated for operation outside those parameters, to ensure reliable operation if the silicon is in some circumstances pushed to extremes.

Re:Fake overclocking

[Anonymous Coward]

well, I am the center of the universe.

So are you.

It's perfectly reasonable to say you are the center of the universe because for all intents and purposes, this is actually true.

Re:Fake overclocking

[Blaskowicz]

This happened in old days too.
Take a Celeron 300A, itself a Pentium II variant that was as fast as a Pentium II anyway ; put the bus at 100MHz instead of 66MHz.

I had the Celeron 500 instead : put the bus at 75MHz instead of 66MHz. That wasn't as dramatic but directly translated to framerate increase in Quake 3 games. 83MHz worked at the cost of more or less slowly killing the motherboard.

In older days overclocking was about unheard of because it was pre-internet days (including all of the 90s in most countries because dial up was expensive). Could have had a DX2/66 @ 80 (and some upgrades)

Re:Fake overclocking

[bluefoxlucid]

Try reading that article. It mentions you need to get some higher-grade coolant (read: a bigger heat sink and fan), validate the airflow in your case, raise the voltage, etc.

Today, you put in the stock heatsink and fan that came in the same Intel Core I7 3.8GHz box as your processor, you go into the stock BIOS, and you say "make me 4.2GHz." Done. Works in a cheap case.

Re:Fake overclocking

[Anonymous Coward]

Speck is an English word meaning "fat" or "blubber"

Re:Fake overclocking

[Anonymous Coward]

1. It's i7, not I7.
2. There hasn't been a 3.8 GHz overclockable i7 for nearly 3 years. 6700K is 4.0 base/4.2 turbo. 4790K was 4.0/4.4, 4770K 3.5/3.9, 3770K 3.5/3.9. The only one that remotely fits is the 2600K at 3.4/3.8, discontinued in February 2013.
3. Boxed 6700K doesn't come with a heatsink anymore.

Re:Fake overclocking

[Anonymous Coward]

Old days: the processor should run at 200MHz. You can push 215MHz, but you need to modify the vcore.

Modern times: that's a 4.7GHz processor clocked at 3.8GHz. That processor came underclocked out of the box.

You young whippersnapper!

Old days: You bought a Celeron 300 and happily O/C to 450 for about 2 years until theOC'd CPU gives out - but by that time much faster and cheaper CPUs were available.

Re:Fake overclocking

[hairyfeet]

I personally really don't see the point of OCing anymore, I really don't. back when I had the Celeron 300, the one that would OC to 450Mhz? yes that made sense to try because we only had a single core and your CPU was being made obsolete almost before you got it out the box. I remember going from 400Mhz to 1200Mhz in like a 3 year period, it was insane.

But now what is the point? My AMD FX-8320E can easily have the base clocked cranked up to around 4.5Ghz-4.6Ghz.....and? What program am I gonna use that I'm really gonna feel that difference? Hell the stock is 3.2Ghz with a 4Ghz turbo and with 8 cores its not like I'm having to sit around waiting for tasks to complete like I was in the old single core days so all I'd be doing is blowing through power to shave a few seconds off a render, so what? I have yet to find a game or program that my chip can't just blow through and I have zero doubt that the same is true for every Intel made in the last 7+ years!

So there is really only 2 groups I can see where this might be a selling point...no scratch that as I was gonna say the first would be those doing heavy simulations like wave simulations or big engineering projects but those guys aren't running low price CPUs, they are running dual Xeon workstations, so I guess that just leaves the "gotta have a big ePeen!" types that don't know shit about CPU arches and think cranking an i3 is gonna somehow make them competitive with an i7, so for them...yay I guess?

Re:Fake overclocking

[jittles]

I think this has more to do with TDP than binning these days. They underclock the CPUs to mark it at a lower TDP. The ones that are capable of higher clock speeds get binned into 'overclockable'. That way they still get to advertise their energy star compliance but allow you to undo that with a flip of a switch in the BIOS. I know my desktop CPU is overclockable but I never bother. The thing will automatically increase its clock speed by ~30% if its really under load.

Re:Fake overclocking

[oh_my_080980980]

*Shh* No sense in blinding people with reality, it will burst their bubble.

Re:Fake overclocking

[oh_my_080980980]

You're missing the point - you're not over-clocking the CPU.

Re:Fake overclocking

[PRMan]

And what happens when the yields start providing 99% perfect chips but the demand curve is still the same?

Re:Fake overclocking

[PRMan]

"Guaranteed" isn't a funny word since if the 4.2 won't run at 4.2, Intel will give you another one. If the 3.8 won't run at 4.2, tough. Seems like the EXACT meaning of "guaranteed" to me.

Re:Fake overclocking

[PRMan]

And in 2009, I bought a $59 AMD 2-core Phenom X2 and turned on the other 2 cores on the motherboard to turn it into a $580 4-core Phenom X4. Stock cooler, no overvoltage. It's been running that way for almost 7 years no problem.

Re:Fake overclocking

[citizenr]

My AMD FX-8320E can easily have the base clocked cranked up to around 4.5Ghz-4.6Ghz..... I have yet to find a game or program that my chip can't just blow through

  types that don't know shit about CPU arches and think cranking an i3 is gonna somehow make them competitive with an i7, so for them...yay I guess?

oh, how wrong you are :)
try World of Tanks ( http://worldoftanks.eu/ ), SINGLE THREADED game written in python (and some ActionScript!) of all the languages :)
You will find your FX overclocked to 4.6GHz barely pushing 60fps, and being beaten by $30 Intel cpus. Doesnt really matter if its Core2, pentium, i3 i5 or i7, all that counts is MHz and raw IPC.

Re:Fake overclocking

[zwarte piet]

also German for bacon

Re:Fake overclocking

[Anonymous Coward]

Go play some Minecraft or KSP. Then try it on a stock sandy bridge. Then try it on the same SB @ 4.8. Whoops.

Re:Fake overclocking

[zwarte piet]

I had an official AMD 486dx280 except my computer would only run stable at 66Mhz or on 80Mhz with the secondary (on motherboard) cache disabled. I had better luck with the pentium II 266 I bought afterwards. It would run at 300Mhz (4x75) with no problem.

Re:Fake overclocking

[radarskiy]

And what happens when the yields start providing 99% perfect chips but the demand curve is still the same?

The unicorns will make up the difference.

Re:Fake overclocking

[Anonymous Coward]

You could just replace that with a cheap AMD or Intel chip and get better performance for less power and heat.

You could have probably done that years ago though.

Re:Fake overclocking

[epyT-R]

1. RTS games, esp with lots of units and cpu opponents.
2. FPS games during multiplayer. despite common belief, today's engines physics are heavily cpu dependent. The simplistic physics of quake are long behind us.
3. simulation - video encoding - ray tracing - faster multi core on the cheap (compared with your expensive xeons). a 4.7ghz 4core chip will do better than an 8 core at 2.6ghz, yet is much cheaper. You might be a rich bastard, but lots aren't.
4. emulation - very cpu heavy, it uses relatively few cores and wants them as fast as possible. low clocked xeons fail here too.

An oc cpu comes with higher IPS, faster cache, and faster IO. It's worth it if you know what you're doing and don't have a corporate sized budget.

Re:Fake overclocking

[epyT-R]

It also means something small. "A speck of dust."
http://www.merriam-webster.com...

Re:Fake overclocking

[toddestan]

I think a lot of it has to do with the emphasis on power usage. The chip is supposed to have a TDP of 75W. Sure, it will run at 4.2GHz just fine, but you have to crank up the voltage a bit and now it exceeds 75W. So they sell it as a 3.8GHz chip because it can run at that speed and meet the power requirements. If it was 10 years ago, it would be sold as 4.4GHz chip with a TDP of 130W, because MHz was king and a lot less attention was given to the power usage.

Because of this, with most chips nowadays you'll get a pretty good overclock just fine, so long as you've got a decent cooler on it.

Re:Fake overclocking

[toddestan]

Hardly. I'd say things have only been significantly overclockable since about 2009 (with Nehalem), though I have seen some people have some pretty good luck with the Core 2 chips. Overclocking the netburst (Pentium 4) chips like the article you linked to is tricky business. Almost all of them are multiplier locked, so your only option is to overclock the FSB. Which also overclocks the PCI/AGP bus and memory along with the CPU. This limits your ability to overclock significantly because you can only go up until your weakest component falters. Besides, it seems those chips were run a lot closer to their limits (even more so on the AMD side).

Nowadays, buy an unlocked 'K' processor, and you can overclock it 10% no problem without even trying, and 20-25% with only a minimum of fuss.

Re:Fake overclocking

[Grishnakh]

But *are* the yields that good? They keep pushing the process technology every generation, so I'd think they'd never get to 99% perfect chips. If they just stuck with 2010-era chips, then sure.

Re:Fake overclocking

[hairyfeet]

Yet isn't it funny that when you use code compiled with GCC instead of ICC you get these results? This is why you can't base shit on a single or even couple game benchmarks anymore, there is just too many ways to grossly affect the outcome. If you gave me the code to a popular game and let me control the compiler? I have ZERO doubt that I could make a 2003 Sempron beat an i7, its all about making sure the code supports the advanced features of the chip you want to win, while ignoring those features in the chip you want to lose, easy peasy. And that isn't even addressing just shitstain code written by a "works for me!" dev that doesn't est shit on anything but their own rig, which I really get the feeling is Wargaming in a nutshell.

And just for the record I play their World Of Warships as does my wife and despite her being on a Phenom II 925 from 6 years ago? Plays great with high framerates. BTW just FYI the biggest booster you can give to that game? Put it on an SSD as its code is really poorly optimized and even on the fastest HDD it'll lag, like Tera its shit code and "Hey my chip plays really shit code slightly faster!" is really not a selling point in my book.

Re:Fake overclocking

[Crosshair84]

WoWS, nice. Have you been playing Ranked? Lots of good rewards even if you don't make Rank 1. I got the pirate flag and now have enough Silver to afford my Gearing when I unlock it. Getting from Rank 10 to Rank 5 was harder than getting from Rank 5 to Rank 1 because the incompetents can get to Rank 10 without too much trouble, then you have to put up with them until you hit Rank 5

Re:Cat got your tongue? (something important seems

[Anonymous Coward]

Or you could just not overclock. These CPUs — including the non-K versions — automatically overclock themselves anyhow.

No

[ArchieBunker]

The temperature sensors would sense this and shut down. A long time ago some review website posted a video of them removing the heatsink from a P4 with a game running. Not much happened, the game froze up and the CPU shut down. They did the same thing to an AMD K7, it let off a wisp of smoke and died.

Re:No

[thechemic]

LOL

Re: No

[ArmoredDragon]

Therm-trip feature. Basically the CPU resets itself when its internal thermal sensor indicates that its a few degrees (I think 5?) centigrade below catastrophic temperature point (where the blue smoke is released.) Still possible to damage the CPU, just very unlikely, and its not good on it if you keep it up long term.

That won't prevent applications from crashing (you'll get electron migration well before catastrophic temps) hence the game crashed, and you're guaranteed either a system freeze or a reboot.

Re:No

[Anonymous Coward]

That was an old Tom's Hardware video from 2001. Can't find it on their site now, but here is a YouTube video of it:

https://www.youtube.com/watch?v=06MYYB9bl70

eventuated

[Anonymous Coward]

Is eventuated the new hip business buzzword?

Re:eventuated

[plover]

Is eventuated the new hip business buzzword?

It was necessitated.

Re:eventuated

[wbr1]

Soon you will receive a cease and desist from "Eventuated Technologies LLC", leaders in fusion, flying cars and holographic storage.

Re:eventuated

[Anonymous Coward]

This word surprised me too. I thought it was another 'conversate' come to make people who use language properly twitch.

Re:eventuated

[Anonymous Coward]

Do the needful to eventuate the necessitated.

Re:eventuated

[Anonymous Coward]

Some people will verbify any word.

Re:eventuated

[Anonymous Coward]

Eventuated is just the PHB response to teenagers who "can't even."

Strong?

[cerberusss]

Skylake launched this year with the rumor of strong non-K processor overclocking

Within the Skylake generation, these CPUs might be relatively strong. But from the first AnandTech reviews in Q3 this year, I gathered Skylake itself wasn't all that special. 5-7% improvements compared to Broadwell, including a couple of regressions in certain circumstances.

And we're still waiting for the equivalent of the Haswell with Iris Pro, for high end laptops, IIRC.

Re:Strong?

[PRMan]

And especially regression in the CPU-specific areas, like compiling, audio and video compression, etc. But hey, you get 1-2 more frames on the latest games!

Re:Strong?

[Moof123]

Yep, small bump in performance, modest drop in power. Check back in a couple years, you might get another 10-15%, still only 4 cores, probably still have to pay 2-3x to get 6 cores without the stupid integrated graphics, even though it will be the same process and silicon area as the 4 core that includes the stupid integrated graphics.

Re:Strong?

[cerberusss]

Yeah, it's a weird situation we're in. I got a MacBook Air with Haswell in 2013, and that was a biiig jump power-wise. But Intel has had so much trouble with Broadwell and Skylake :-/

In the old days

[Anonymous Coward]

I would overclock my celeron from 2.0ghz up to 3.0ghz and turn the fan speed to full. It worked fine except anything over 10% lost the audio.

Just Like The Dorks With ATV Vehicles

[Bing Tsher E]

The guys with the ATV vehicles go out and try to find places where they can 'mud.' They don't need to travel there, they go for the adventure of the trip.

Back when my main machine sported a Pentium 75 processor, I was ready for an upgrade. A guy at work (the QA manager, actually) jumped at the chance to buy my old Pentium 75 CPU. It wasn't because he needed the processing power for anything in particular, he just said it was 'a good processor to overclock.' It was a good deal for me because it paid for part of the Pentium-MMX 133 processor I put in it's place.

I guess I could mount some 25 Watt 1% resistors on an aluminum plate and dissipate 40 Watts of power out of them. Whoo. Whee!

Re:Just Like The Dorks With ATV Vehicles

[Anonymous Coward]

No, the guys with the ATV vehicles go to the ATM machine and enter their PIN number.

Re:Just Like The Dorks With ATV Vehicles

[Anonymous Coward]

I thought MMX started at 166 or 200 MHz. Maybe I'm wrong.

Re:Just Like The Dorks With ATV Vehicles

[toddestan]

There was a mobile Pentium MMX at 133 MHz. Slowest regular desktop processor was 166 MHz. There were also some overdrive MMX processors at various oddball speeds.

Overclocking?

[unixisc]

That's soooo last millenium!!! Ever since multi core CPUs became common, accompanied by SMP OSs supported by multi-threaded apps, there is nothing that overclocking can achieve that can't be more easily, reliably and inexpensively achieved by more cores.

Re:Overclocking?

[Lumpy]

too bad programmers never to that memo and still write 90% of all software as single threaded.

Re:Overclocking?

[Moof123]

There is a hockey stick in the price curve to go above 4 cores, both for the CPU and motherboard. Intel wants to charge a major premium.

Also these higher core Xeon's are often clocked much lower which can result in a major step down in performance for programs just using 1-4 cores. We recently went away from using a 14 core server for an electromagnetics simulator after finding that the stupid thing spent about half its time on one core, making our 6 core local machines 20% faster for the identical problem. Kind of maddening on all fronts.

Re:Overclocking?

[PRMan]

It doesn't matter. Write a single-core app on .NET and run it. Watch the CPU meters in Task Manager. Look at that! All 4 are within 10% of each other. Microsoft automatically puts the garbage collector on a different CPU as well as anything else that can run on separate threads already. This has been the case since at least Windows 7, even for a DOS batch file.

Re:Overclocking?

[Anonymous Coward]

75% is NOT written in .NET. and for good reason.

Re:Overclocking?

[Anonymous Coward]

Cause people are afraid to use something that will speed up their development for 95% of apps that don't need the performance boost of going native

Re:Overclocking?

[PRMan]

Lack of competition.

Re:Overclocking?

[Anonymous Coward]

Also these higher core Xeon's are often clocked much lower which can result in a major step down in performance for programs just using 1-4 cores. We recently went away from using a 14 core server for an electromagnetics simulator after finding that the stupid thing spent about half its time on one core, making our 6 core local machines 20% faster for the identical problem. Kind of maddening on all fronts.

Well, that's where the overclocking comes in. (This won't help you with the EM simulator, because you have a software issue, but for most users...) Used Xeon X5650-X5680s are dirt cheap on eBay as datacenters retire them and part out the chips to resellers. They are drop-in replacements for aging i7 920s and LGA1366 motherboards. 6 cores, more cache, less heat (32nm 95W TDP). And they OC at least as well as the old i7 chips did.

Re:Cat got your tongue? (something important seems

[Anonymous Coward]

Expecting overclockers to actually spend money... you must be new here.

WTF?

[Type44Q]

but that never eventuated

Your casualizing new usagenesses for words has me wondering if you ended up straight onto the Internet without actually attending through K-8th...

Re:WTF?

[Anonymous Coward]

The Recency Illusion strikes again!

Re:Cat got your tongue? (something important seems

[radarskiy]

Or you can spend a few more dollars and just buy a CPU that won't burn up and fail from overclocking.

If a processor could be guaranteed to work at a higher frequency, the manufacturer would just label it with a higher frequency and sell it like that.

Overclock + VT-d

[Anonymous Coward]

Little known fact: Intel K series processors don't support VT-d (Aka IOMMU) which allows routing your external device's DMA into a virtual address space. This is critical for security from external hardware (without it, your GPU that runs user code has full read write access to kernel memory among other things for example), and also vitalization. I assume this restriction is to prevent you from using overclocked desktop servers to replaces overpriced server processors. Its great to have a way around it though: the option to overclock your desktop and have improved security and PCIe pass-through to a VM is fantastic.

That said, I don't buy Intel anymore. AMD doesn't randomly fuse of useful security features and has more honest business practices. I know their processors are worse at what I need than Intel's, but I want to support their work (they do neat things like HSA), and would rather not fund Intel's business practices. As someone with cash to burn, I try to take the moral choice.

Re: Overclock + VT-d

[Anonymous Coward]

Not anymore. Overclock + VT-d works on i7-4790k, and 6th gen.

Re: Overclock + VT-d

[Anonymous Coward]

Thanks for the correction.

Re:Cat got your tongue? (something important seems

[billcopc]

Sure, and that's the very definition of binning, but they must also account for demand. If Intel's process improvements yield a higher ratio of top-binned chips than the market is willing to buy, those chips will be locked and sold as the faster-selling SKU. Better to sell the thing and still make a few bucks, than have it rot in a warehouse with a $1000 price tag.

Re:Cat got your tongue? (something important seems

[radarskiy]

Theoretically, sure. But back in the real world, every manufacturer is supply constrained at the top end. There's no down-binning doing on anywhere.