Slashdot Mirror
Intel Removes "Free" Overclocking From Standard Haswell CPUs
crookedvulture writes "With its Sandy Bridge and Ivy Bridge processors, Intel allowed standard Core i5 and i7 CPUs to be overclocked by up to 400MHz using Turbo multipliers. Reaching for higher speeds required pricier K-series chips, but everyone got access to a little "free" clock headroom. Haswell isn't quite so accommodating. Intel has disabled limited multiplier control for non-K CPUs, effectively limiting overclocking to the Core i7-4770K and i5-4670K. Those chips cost $20-30 more than their standard counterparts, and surprisingly, they're missing a few features. The K-series parts lack the support for transactional memory extensions and VT-d device virtualization included with standard Haswell CPUs. PC enthusiasts now have to choose between overclocking and support for certain features even when purchasing premium Intel processors. AMD also has overclocking-friendly K-series parts, but it offers more models at lower prices, and it doesn't remove features available on standard CPUs."
Clear who pays your salary.
AMD also has overclocking-friendly K-series parts, but it offers more models at lower prices, and it doesn't remove features available on standard CPUs.
It is also significantly slower buck for buck in real life workloads.
That's because they are not number one. Like Avis, they have to try harder.
“He’s not deformed, he’s just drunk!”
Obvious sales pitch is obvious:
AMD also has overclocking-friendly K-series parts, but it offers more models at lower prices, and it doesn't remove features available on standard CPUs."
Feature #1 TSE: http://en.wikipedia.org/wiki/Transactional_Synchronization_Extensions I'd imagine nobody codes for this.
Feature #2 : http://software.intel.com/en-us/articles/intel-virtualization-technology-for-directed-io-vt-d-enhancing-intel-platforms-for-efficient-virtualization-of-io-devices
It can still do virtualizion just fine: http://forums.anandtech.com/archive/index.php/t-2133898.html
Not an Intel fanboy or anything, but they're not as arrogant as people are making them sound.
Is there anyone besides a small group of people who benefit from higher clock rates? Most people I know would pick battery life over performance on mobile devices. Desktops have been "powerful enough" for at least the past 5 years. Is it just about bragging rights at this point?
Now that AMD is no longer a threat to them, they can go back to their old tricks again.
Let's give no one what they want!
Shouldn't the unlocked multiplier version be a primium product? This is annecessary step backwards. I think most people who are interested in a K-series would be more willing to pay a premium. Who in their right mind would EVER give up VT-d for an unlocked multiplier? Maybe they just want to kill the tradition once and for all.
Well, "free" clock headroom aside, Intel removing features from the K series parts (VT-d, etc.) has been going on since Sandy Bridge I believe. Basically, if you want the best of both worlds you will want to invest in an Extreme Edition processor. As quick search on ark will show, the 3770K does not have VT-d while the 3930K does.
-Reed
This is why AMD can not die just think of what intel will do with out AMD in the market.
I've never found overclocking to be worth the trouble. Anytime there's a stability issue with an overclocked PC, there's always that nagging doubt that all my troubleshooting is for naught, because it was a fluke bit fail due to the overclocking. Life's too short- skip the anxiety and run your processor at it's rated speed.
makes soldered in cpus now a really bad a idea as if a MB makers puts in a faster CPU with that MB you may not be able to get that MB with a CPU that has transactional memory extensions and VT-d device visualization. Or OEM's will have to stock more MB then they really want as well.
The new Celeron?
those are enterprise features? why would you OC a chip in something that brings you revenue and risk a problem?
If Intel will ever be allowed to become monopoly again, it will produce extremely pricey and extremely limited processors. Everybody should love AMD, because it is the only thing stopping Intel from selling them shit wrapped in golden paper for thousands $$.
They will have to deal with the ARMs market than?
= short life span for your CPU.. so, I'm not too worried..
can that run todays X86 software?
Tell that to the Intel fanboys who did not by their first pcs until the 2000's. Remember the gold old days when the Pentium 3 1000 was 800 bucks until AMD came along and started spanking that ass? Lets hope they don't go away as we don't need the evil empire to be the sole provider of chips again. Buy AMD!
Lets get this over with... Fuck Off
The K-series parts lack the support for transactional memory extensions and VT-d device virtualization
Yeah, well, fun fact... a lot of enthusiasts like myself like things like VMWare, which depend on this kind of thing. Deleting those features from the unlocked line means I just won't buy them... one of the big drivers for overclocking is to run virtualization. You might think it's "just gamers" doing this, but a lot of us do network and system administration and deployment and like the ability of having a "lab in a box" offered by current processors. You take that away and you're going to find your bottom line hurting, possibly more than a little.
I don't know which of your marketing assclowns came up with this idea as a revenue generating measure, but it's going to backfire in their face and I hope when it does you fire their ass, apologize, and never try this again. You're only succeeding in driving us towards commodity hardware like AMDs offerings... All they need to capitalize on the market you've just shit on now is offer mainboards with multiple sockets for their CPUs and make the mainboards cheap and the core system very energy efficient... and not only will the enthusiasts ditch you, but so will the data centers...
You're opening a can of worms here. Bad plan, darlings.
#fuckbeta #iamslashdot #dicemustdie
Just recompile for the other architecture. (What do you mean you don't have the source code?)
Current K rated CPU lose this and possibly some other features. I didn't pay attention to this and found out the hard way when I couldn't run an overclocked ESX-i Sandy machine. Pissed is an understatement! There's no good reason to do this other than to screw with the marketplace.
I've switched to a XEON CPU of Ivy heritage and GL finding a board for one of those that runs ESX-i and can be overclocked. Nearly every machine I own is overclocked and has been for many years and it pisses me off to get jerked around like this by Intel.
Build it, Drive it, Improve it! Hybridz.org
I thought AMD was the first to 1GHz, and so they had started spanking that ass before the P3-1GHz came along. But the general gist of your post is true; AMD coming out of nowhere knocked the pricing shit that Intel pulled right down.
I'd say hell yeah:
http://www.youtube.com/results?search_query=n900+windows
http://www.youtube.com/results?search_query=n900+os+x
http://www.youtube.com/results?search_query=n900+x86
Don't let them take our ARMS.
I actually think this makes sense from a business perspective since the virtualization features would be targeted towards their Xeon line vs. the home PC market. As for overclocking, I do it moderately on both Intel and AMD systems but this lock on the Haswell reminds me of the same debates around Sandy Bridge and Ivy Bridge and ... back to when they started locking the clocks on the Pentium IIs. The advantages of overclocking don't just go against getting the most speed out of the hardware, they also allow folks to not buy a K (or X) edition for example that has a much higher price point than the Non-K version while still reaping *most* of the benefits of the higher priced model. If Intel keeps the K prices competitive with the Non-K editions then I don't see a big deal but I don't think features getting removed is a good way to go. If you're charging me more for the K or X model, give me everything the lower end chip has and more. I guess all of this means we'll still have folks hanging on to Ivy Bridge and Sandy Bridge processors for a bit longer? Maybe not. Also since people are chiming on on AMD today, I'm also not sure that the New FX-9590 is all that great for the price either. The Vishera/Bulldozer line is 125w vs 220w TDP for the 9500 series as well as the price boost. You can easily get 4.8Ghz all day long out of a Vishera FX-8350 (just run water cooling). I'm not sure what the cooling systems will need to be for the FX-9xxx but it probably won't be as simple as an H100i..
Harrison's Postulate - "For every action there is an equal and opposite criticism"
give both the features and the unlocked multiplier... at a much higher price, of course.
Yes, I remember the good ol' days when you can get a $100 CPU and make it work like a $800 one. I remember in particular the days of buying a cheap Celeron and having it perform like much more expensive Pentium II or even P3.
And I also remember days of headaches with stability issues, over heating and other stupid problems all to squeeze a few extra FPS out of Doom.
Nobody overclocks anymore, and if they do, it like getting a trophy for trolling a blog. Its completely unnecessary and doesn't really offer anything except a feel good, slap on the thy own back when you see your completely arbitrary and virtual benchmark numbers rise up while you ruin your CPU.
What needs the extra performance these days? You need to Tweet faster? Like on Facebook faster? Browse a website factions of milliseconds faster?
Games used to drive overclocking but GPU's are where game performance lies these days. Sure maybe overclocking your CPU by 50% might offer 1% more FPS, but who the fuck really cares, nobody with a life that is.
Intel realizes that the enthusiast market for PC's has nose dived and its obviously cheaper to produce CPU's where you don't have to worry about the kind of performance tolerances that are required for overclocking.
And I don't think "enterprise" level developers are buying cheap computers and then overclocking to get better VM performance. I mean really? If you consider yourself an "enterprise" developer then get the "enterprise" to buy you a decent workstation or VM server. I don't think your "enterprise" wants you to spend days trying to optimize performance on your workstation, I'd fire anybody that wastes any amount of time in a BIOS.
I would say Intel should focus on offering one "enthusiast" level CPU that is completely unlocked for overclocking. I mean if people want to burn out their CPU repeatedly its more money from a market segment that is drying up, but I think in general Intel or any CPU company should not have to worry about providing overclockable CPU's across their product line.
The bottom line is that benchmarks aside, if you ever looked at your Task Manager you'd probably realize that your CPU is idling at 1% usage 99% of the time, so you want to make the System Idle task run faster? I don't get it anymore.
I haven't thought of anything clever to put here, but then again most of you haven't either.
AMD hasn't been real competition to Intel for quite some years now. Though the fanboi butthurt would be amusing.
Since when is transactional memory is a mass consumer feature? Next to no one will notice or care.
You think AMD is any threat to Intel? They stopped having any real competitive pressure on Intel years ago.
AMD didn't come out of nowhere, they were making 8088's in 1975.
Sorry, teleporters just kill you and then make a copy. A perfect, soul-less copy.
The Pentium G860 is fast enough to do basically anything short of intense gaming or video editing. It's faster overall than the AM3 Phenom X4 quad core chip. I think the G2120 ivy bridge even beats Phenom x6 Deneb chips. So oh no, my brand new Haswell i7 isn't overclockable. It's so darn slow I just have to overclock it. With any i7 from the Haswell series, your hard drive and RAM are the bottlenecks so if you're trying to speed yourself up by overclocking, "you're doing it wrong."
The real reason for this change is fab yields.
It's how they do all the other processors as well:
o manufacture
o test
o blow fuses as needed for failed tests
o bin the part a an xxxyyyzzz part
One of the reasons Apple machines tend to be more expensive is they pay a premium for higher performance "speed burt" relative to other laptop vendors, so the chips that rate out at supporting a higher speed burst clocking go into the Apple bin.
Similarly, RAM chips get binned as well; those that bin out as supporting within tolerance frequency and volage following functions go into the Apple bin, the next best go into the Crucial bin, and the rest go into the "everybody else" bin.
By doing this, they can increase their effective fab yields per die, even if they fail to increase their yields of a particular high end chip.
This also allows re-binning; that when you have a bunch of medium-end parts, and get a buttload of orders for low end parts. In order to meet demand for the low end parts, you don't go out and manufacture low end parts based on the demand; instead you take a bunch of next-higher-up parts, and blow their fuses in order to make them into lower end parts, and re-bin them. Voila! Just In Time "manufacturing".
By making an explicit change to a classification, they are admitting to lower than expected successful fab yields for the areas of the CPU they are fusing off.
What we should actually be asking ourselves is what this means for the future of transactional memory, if they are unable to get their yields up in order to meet demand, which may be high in certain government and scientific applications. If it exceeds capacity, expect either mutiple fab retools, or it being dropped as a feature at some point in the future.
At least the desktop version.
Runs hotter than Ivy Bridge
and has worse overclocking
10% more power consumption, with only 13% speed increase. Every other generation of Intel got a speed increase with at least the same, or less power consumption
AMD has superior FP capabilities. In both CAD and CAE benchmarks, honors always go to AMD for the math. But what really hit me as a big-ole liar fanboi comment was the one about CAD rendering. The majority of that is not related to your CPU, but your GPU. The portion of GPU that is CPU related still benefits from AMD chips which have the memory at the front end of the chip, compared to the Intel that has the memory pipeline as far back as possible in order to claim "we have more MHz than AMD".
Video compression really depends on who's chip the code has been modified for (if any). As with CAE math, native chip math functions are much faster on AMD.
I run annual benchmarks inside companies for Intel vs. AMD and have for over a decade. These benchmarks show real world performance of Unigraphics, CATIA, HyperMesh, MSC Patran, Ansys, and Muses. CATIA and Ansys are always the worst on AMD, as they have both been assimilated by DirectX over OpenGL with no option to force OpenGL. They still however slightly favor AMD over Intel.
I don't rely on Tom's hardware or someone else for opinion, since Tom's showed us long ago that you can't trust "independent" benchmarks for much. I have read benchmark reports from others that indicate the opposite, but have yet to have anyone recreate their results for me. I use real decks and models from real products, I don't use code exercising a subset of CPU instructions as fast as it possibly can.
-The wise argue that there are few absolutes, the fool argues that there are no probabilities.
And started selling direct to the public during the 386 days (remember i386 vs 80386?).
Peter predicted that you would "deliberately forget" creation 2000 years ago...
It could become a feature once mainstream, as it dramatically helps thread scaling. I will agree that it is not much of a current selling point and may not become one for a long while, depending on threaded programming up-take or OS advantages.
I remember paying twice as much for my Pentium-4 as I did for my i7. Yet when I bought the P4, AMD were competitive, and today they're not.
AMD are largely irrelevant; Intel's real competition is ARM.
Just to add a couple options.
As far as I know it's not available in VMware Workstation.
so it's not quite so rare as you make it sound.
More cores are useful if, and only if, you have software threaded out enough to use it. Some workloads are, many are not. This "OMG moar cores lol," attitude is silly, and to me reeks of fanboyism. "My chosen holy grail platform does this, therefore everyone should want it!"
Also more cores aren't necessarily useful if things over all are too much slower. For example, you'd expect a T1100 to be faster than a 2600 at x264 encoding. I mean it is all kinds of multi-threaded, and the T1100 has 50% more cores. Maybe the FX-8350 too. While it isn't 6 core, it does have 8 modules so 8 threads.
Well, the reality it that they are not (http://www.anandtech.com/bench/CPU/27). The T1100 and FX-8350 are behind pretty much all modern Intel CPUs. An i5-2400 beats them out. Despite the core advantage, the speed disadvantage per core is too much.
But go ahead and keep telling yourself that you are the only TRUE kind of computer user because you care more about cores than actual performance.
I was looking into upgrading my system when the Haswell CPUs came out, and I was disappointed. Then I ordered a socket 2011 motherboard with 4 full-length PCIe slots and quad-channel DDR3. It ended up being about $100 more than a comparable Haswell Z87 chipset build, with a faster (MHz) cpu.
I got the (sandybridge-E) core i7 3820 quad core for $249, which is 3.6GHz stock, 3.9GHz turbo. Overclockers have pushed it to 5.5GHz and it is not an "unlocked" K-series cpu. Socket 2011 allows for "old school" base-clock overclocking.
How dare they try to sell me something that runs at the specifications they quoted, rather than faster than the specifications they quoted? It's like they *lied* to me!
AMD. We're not as big a dicks as the other guys!*
*(But we are trying out one of those "pumps"...)
You have the right to remain sentient. If you give up the right to remain sentient, you will be elected to public office
Remember that the "overclocking" of the non-K chips actually isn't. Turboboost is precisely controlled. Intel gets to spec how high it can go, and under what conditions (thermal, electrical, etc). So the chip is tested and rated to work at that, they know the variables. With K series OCing, that is all out the window. The user gets to get all the variables. They can set max wattage draw, how fast it can go regular and turbo, all that shit.
Well, maybe that kind of thing causes problems with these technologies. I can for sure see it with VT-d, since that is offering hardware access to VMs.
I have trouble believing Intel is doing it to be dicks. They like people buying the K series CPUs, more money for them. They only offer the K series at the high end so it isn't like people buy them instead of buying the higher end chips, they ARE the higher end chips. If anything, I would expect intel to do the opposite and disable it on lower end stuff to try and get people to spend more.
I remember back in school when I was experimenting with extreme overclocking on some expendable hardware. Intel was always so much nicer to OC.
With Intel: you could keep cranking up settings until you finally reached a point when things stopped working, drop your settings back down a hair, and watch your proc scream along at max speed.
With AMD: you keep cranking up settings until you see blue smoke, then you install another proc and try really hard not to make that mistake again.
Let me make this very clear: back in the days of the Athlon versus the Pentium IV, Intel had the disadvantage because the damn thing was designed primarily for SSE2, and they had a decode imbalance in the design. The Athlon had 3 x87 FPU pipes which made it superior despite the P4's faster clock...but once developers targeted SSE2, the Pentium IV matched the Athlon in FPU, and outclassed it on ALU operations (since both chips had dual 64-bit SSE2 units).
With the introduction of the Core 2, Intel switched to a 4-wide decode and DUAL 128-bit SSE2 units, allowing 2 instruction / cycle throughput, TOASTING the Athlon 64 in all matters of performance. Almost two years later AMD countered with Barcelona, which also had dual 128-bit SSE2 units, but was castrated by their 3-wide decoder. It was a match for Core 2 at the same clocks, but they couldn't match the clocks Intel had.
With the new Core series of chips, and the reintroduction of Hyperthreading, Intel wiped the floor with AMD in anything multithreaded, and they steadily increased single-threaded performance with each new iteration. Dual AVX 256-bit units in Sandy Bridge also potentially DOUBLED Intel's FP throughput. At the same time, AMD moved away from FP performance with Bulldozer, which shared dual 128-bit AVX execution units between two cores. Even with twice the cores AMD still lagged behind in peak FPU throughput, because the shared decode units meant roughly two-wide decode when all cores were heavily-loaded.
So today AMD is not the destination for high FPU throughput, and they really have not been for a decade. I really cannot understand your claims to the contrary.
Man is the animal that laughs.
And occasionally whores for Karma.
Tell that to the Intel fanboys who did not by their first pcs until the 2000's. Remember the gold old days when the Pentium 3 1000 was 800 bucks until AMD came along and started spanking that ass? Lets hope they don't go away as we don't need the evil empire to be the sole provider of chips again. Buy AMD!
Buy AMD when it makes sense. Brother and a friend made their own machines and careful choosing of AMD CPUs left more money for other peripherals.
First, Bulldozer was not a high performance chip, and never intended to be a high performance chip. It was meant to be a PC based equivalent of a Niagra capable of massive threading. So let's compare apples to apples shall we?
AMD Still considers the Athalon to be the performance chip. Comparing apples to apples, maybe you are asking how a chip rated 300MHz lower be faster? First, the length of the bus needed to get from inbound to FPU is much longer on Intel. Cache is much larger on AMD, prefetch is superior especially for FP instructions. That has a lot to do with the bigger caches. Next, memory is also closer to the front of the chip. Most FPU based apps are also memory intensive. An Intel operation would start at the front of the chip and move to the back. Every memory or FPU operation requires traversing the full chip bus, then the same long ride back. That movement is not required in the AMD design, and that efficiency does make a difference.
If Intel had really doubled FPU performance AMD would have been out of business. Yet they are not, and I can still get exceptional performance off of them for heavy FPU loads. I/O and integer based, Intel beats them pretty solidly and has for quite a long time.
-The wise argue that there are few absolutes, the fool argues that there are no probabilities.
That's already been true. Even if the processor has the feature it may be disabled in Bios. My HPQ nw9440 ez901aba (?maybe) was like this but a BIOS update available shortly after I got it enabled VT. I still have a gateway machine with an Athlon 64 L110 with VT disabled in BIOS, and gateway wants consulting fees for a BIOS which I know already exists which enables it. Hope they DIAF
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
AMD is doing ok and profits are going up every year after year!
Look around at local stores that sell pre-made pc's, the ones most people buy for home. The cheaper units are mostly AMD and most people buy the cheapest that works. A few buy to show off, but show off on things like monitor size or fancy wording or brand name.
Neither care about specs important to most slashdoters.
Mycroft
https://signup.leagueoflegends.com/?ref=4c3ed6600b6ea
Because Opterons are not a network admins wet dream for a VM cluster. And the FX series certainly isn't popular...hell, they don't ship with the kind of extensions and overclock capacity that Intel charges you triple for...oh, wait, that's what we're discussing here. And the A series isn't popular either.
Face it, Intel's Marketing division is looked upon with envy by every other marketing division on the planet; they've managed to simplify an a complex issue like technology into a slogan "The right decision is Intel." It helps that careful management of biases, anti-competitive measures, and so on help foster this image -> some code performs better on Intel CPUs, some code will only run on Intel CPUs, some code performs better on AMD CPUs, some code will only run on AMD CPUs; factor in that OEMs typically sell AMD machines for less than Intel machines, and people think that something must be wrong with AMD chips (must be the in house VAL-U brand) to be priced so low...so they demand the Intel (premium in their minds) chips, because they're a "premium" (demanding the best of life, etc.) kind of person.
I am John Hurt.
I'm glad to hear AMD was selling 8088's before Intel developed them.
Please, pretty please let me see your 8088 based machine from 1975.
Damn am I getting that old!
Overclocking:
Used to be driven by the desire to make a $100 cpu perform like an $800 (or so) processor.
Now it is done either competitively (air, water and extreme categories) or as a hobby to see how much of a bump in performance can be gained.
My personal workstation is 4 years old, can hit 4Ghz but I run at 3.4... and is a 2.8 chip.
Been that way for quite a while now.
One of my ESXi hosts is a 2.8ghz running at 3.2, the other is bone stock (not an OC-able system.)
My HTPC is a 2.2ghz chip at 2.8.
The machines I run overclocked are 100% stable at their current speeds, and there IS a noticeable difference between stock and where I run them.
I always try to get SOME kind of overclock out of a system, just because I can. Do I NEED to?
No. I do it because I WANT to. And I like to do it without spending extra money for uber-overclocking components.
I have never bought a chip model that is "factory-prepped" for overclocking, nor would I.
But I DO use VT-d, of course.
And there are generally ways of overclocking even "locked" chips- and true overclockers do not hesitate to draw a pencil line across bridges on a cpu, or stick wires into the cpu socket to create a bridge, etc.
Old-school stuff, folks, not like it has become now when any bozo can by a $300 mobo, PC128000 ddr3 and hit 4.5Ghz on air with the overclocking software that came with the motherboard. lol.
Yes, people still overclock, quite a lot.
A boatload of us probably have systems that are more stable than your average beige-box OEM computer while we do it too.
All that said, I do understand why some of the market is pissed that the more easily OC'd chips won't have VT-d (and more)- overclockers are also some of the people most likely to screw with software that can utilize these extra features.
And some of the market WILL pay more for all of the feature set working and no restriction on overclocking built-in.
But the fact is that this is a small portion of the market.
Intel seems to be going for the most noticeable part of the market with the K-chips: Max Speed.
Often the unstable, benchmark only machines.
Yes, an even smaller niche, but far more noticeable than the 24/7, stable OC crowd, so it generates PRESS.
And for those who NEED the functionality, losing some overclocking options is less likely to be that huge a deal anyway: such machines need stability more than a MAX oveclock, and a modest boost in performance is still attainable.
And as others have said- since AMD has sadly not been truly competitive for quite a long time, Intel is back to doing what it wants with desktop chips again.
Fuck Artificial Scarcity.
Fuck Artificial Scarcity.
I want my money back. These ruby slippers are broken.
Considering that in "real life" you can get an AMD 64 core machine with 512GB of memory for around $8k and the Intel equivalent is more than five times that price it appears that your statement is a very long way from being true. At some points in the middle of the desktop market the gap closes, but looking across the full range of CPUs I have to point out that "real life", or more correctly reality, is different to what you are dreaming about.
One thing that's certainly happening been happening with the opertons and xeons for a while (so is bound to be in the desktop CPUs by now) is clocking idle cores down to a fraction of their speed. Some twelve core 2GHz+ CPUs I have in one three year old machine clock themselves down to 800MHz without any user intervention - I didn't even have to change a BIOS setting, it's a built in feature.
I don't understand why intel removed some nice features from the more expensive ones, maybe the extra features are in the way for overclocking? Not that I really need those features as they are more for remote usages..
Or what are the advantages of the extra features which the K series is missing?
Not being able to see 60 Hz on an LCD is a myth, if the LCD can pull it off (many can!). I can easily tell whether a game with fast motion e.g. a First Person Shooter like BF3 or Counter Strike is running at 60 Hz or 75 Hz, particular when panning, and probably wouldn't be satisfied completely until the refresh rate gets to 85 Hz (that's when I stop noticing flicker on CRTs like many other people).
The myth arises because LCDs don't flicker, and because studies that showed people can't tell the difference are based on watching movies on celluloid where there is motion blur. Where there is no motion blur (or good motion blur) like in most games, an object such as a cursor moving acrross the screen appears to the eye as teleporting at discrete locations accross the screen based on the amount the cursor can move in between frames at a given speed - not a continuous motion.
I have managed to get 75 Hz out of my pretty ordinary Samsung BX2440 1080p monitor using this:Custom Resolution Utility
The reason 60 Hz is usually given as the top refresh rate for LCD monitors is more to do with the DVI standard than capability, so by sacrificing a few margin pixels many monitors will be able to handle a higher frequency within the bandwidth specifications of DVI.
https://en.wikipedia.org/wiki/File:Intel_8080_Advertisement_May_1974.jpg
And it's the reason I have an i7-2600 and not an i7-2600K in my current home box; the 2600K lacks VT-d and has only VT-x.
I guess you had better clarify your claims next time you make them.
I will agree that STARS was the pinnacle of AMD performance per sq mm, but they have abandoned the architecture. While you can still buy old stock, eventually these parts will disappear, and all you will have left is Piledriver-derived parts. The world will have to wait to see if they can actually fix things with Steamroller, but until then it's a lost cause for floating-point. Piledriver does do well in mixed loads like software rendering and video encoding, so at least there is potential for more performance (if they can fix the front-end and I/O).
Also, I do not think I have ever seen a floating point intensive application that was not I/O bound. Not to say that it can't happen, but when you're modeling something, data tends to get tossed about casually. And sometimes extra I/O can have unforeseen benefit, so you can never have enough of it (see the Euler 3D test results for the i7 4950HQ)!
Man is the animal that laughs.
And occasionally whores for Karma.
FIXED LINK
Man is the animal that laughs.
And occasionally whores for Karma.
Be honest. It's the extra I/O bandwidth that has kept intel in the market for FPU heavy loads and not a better FPU or chip use of FPU. AMD has always had advantages there because of architecture principles that Intel does not have. AMD has always made efforts to make the FPU the fastest and easiest access for the CPU, and memory access second. I still think the AMD FPU is superior to Intel, which is why Intel shares a FPU between 2 cores. Gating is faster, and more instructions are allowed in the FPU at the same time. Not very advantageous for a single large problem, but threaded small problems see an advantage.
-The wise argue that there are few absolutes, the fool argues that there are no probabilities.
I do CAE work for a living,
AMD is not quicker than intel by a long shot especially since ansys implemented avx instructions.
First, Bulldozer was not a high performance chip, and never intended to be a high performance chip. It was meant to be a PC based equivalent of a Niagra capable of massive threading.
Are you on crack? Bulldozer absolutely was intended to be AMD's high performance chip architecture of the future, and indeed is just that.
It's not even mildly similar to Niagara, except in the most abstract sense (at which point you might as well consider Intel's designs equivalent to Niagara too). Niagara is a radically threaded processor, one which explicitly gives up on any chance of making one thread fast in order to support a shitload of cores and threads.
By contrast, Bulldozer was targeted at merely doubling the number of threads, without sacrificing single-thread performance. The idea was to add a second cluster of integer units so that a 2-thread core could run 2 threads at 80-90% of single-threaded speed, while only using about 10%-15% additional die area to support the second thread. It was supposed to give up no more than maybe 10% performance per thread when compared to AMD's previous x86 chips at equal clock frequencies. This nominal performance loss would then be turned into a gain by clocking the cores significantly faster (Bulldozer was designed for higher frequency targets).
They failed to meet all their goals. Bulldozer turned out to be more power hungry than anticipated, so they couldn't clock it as fast as they needed to. And the per-thread penalty was also larger than intended. Neither of these failures means it wasn't supposed to completely replace their old high performance core designs -- and in fact, it has done that.
So let's compare apples to apples shall we?
AMD Still considers the Athalon to be the performance chip.
It's "Athlon" you dunderhead. You're a pretty piss poor fanboy when you make that spelling mistake all the time. And AMD does not consider that to be true. If they did, they'd still be designing new products using those old cores. They aren't.
Comparing apples to apples, maybe you are asking how a chip rated 300MHz lower be faster? First, the length of the bus needed to get from inbound to FPU is much longer on Intel.
It is? What is this "length" you speak of? Clock cycles, millimeters? And how did you measure it? Can you point anyone to a single technical resource which corroborates this ludicrous claim?
Cache is much larger on AMD,
Free clue: size is not the only relevant parameter. You might want to look up how many cycles and/or nanoseconds it takes to access each level of the cache hierarchy. Last time I looked, it wasn't particularly close -- Intel's L3 was significantly faster than AMD's L2.
prefetch is superior especially for FP instructions. That has a lot to do with the bigger caches.
Prefetch effectiveness is orthogonal to cache size, because prefetch is about trying to predict future memory reads. The problem is never "is there enough cache", it's "do we do an accurate job of prefetching only information that was going to be read anyways" And you're telling a lie here; Intel's prefetcher is generally regarded as state of the art. Recent AMD designs have been playing catch-up.
Next, memory is also closer to the front of the chip. Most FPU based apps are also memory intensive. An Intel operation would start at the front of the chip and move to the back. Every memory or FPU operation requires traversing the full chip bus, then the same long ride back. That movement is not required in the AMD design, and that efficiency does make a difference.
Dude, you have no fucking clue what you're talking about. This is an imaginary problem you invented out of thin air because you want Intel to be bad and AMD to be good. In reality, both processor designs are quite similar in how memory accesses are hand
8080 != 8088. It's literally a different, incompatible instruction set.