Even today, Intel removed existing SSE2 and SSE3 optimizations from their latest high-performance IPP libraries, reverting to compiler-generated scalar code. They only optimize SSSE3 for Atom and up. Guess how massive the AMD Phenom performance drop is!
This part fucking killed me, fucking Dell, a piece of shit PC maker, I knew these fucks are shitty but didn't know the extent of their shittiness. Holy F.
BTW spent half a day yesterday looking for 64-bit driver for my Vostro 1700 Ricoh 82c592 fucking memory stick controller, Dell fucks just don't give a shit about users upgrading to x64. Fuck.
I've been pretty happy with my Vostro 1700, the rare FULL-MATTE laptop, no fucking moronic glossy shit anywhere ever! Everything is matte! Keyboard is top notch, rivals best macbooks and vaios, and battery didn't die after 6 months like on my Alienware laptop, it's still running nice after 3 years of use, has lotsa juice, so quality wise Dell is pretty cool.
Well... until I tried to upgrade to win7 x64, this is where Dell clowns screwed me hard. But I found all the drivers on my own and problem's solved. Screw ya Dell scumbags, you think if you don't post your fucking 64-bit drivers for older laptops I'm going to run out and buy Dell 1720 with win7 preinstalled or something now?
How about you suck my dick again, Mikey Delley? :P Suck deep bitch, 'cause I gonna do it AGAIN when I'm about to upgrade to win8, har har har har harrrr
I'm not gonna buy your new laptops every time I upgrade windows, eat that bitch
I spent several years in the military so am used to bad language, but that doesn't mean I enjoy seeing it --- especially on tech sites where you'd expect something better. If you want to sound like you actually made it beyond grade school, act like a grownup.
Otherwise just stick to the non-tech sites where it seems to be popular these days to throw up toilet comments like your's.
If Anand wants to maintain a focus on technical comments and opinions, I'd expect him to delete this garbage
Well written for almost every level of reader. Appreciate the combining of details, some of which was only able to garner from financial sites postings, and putting them together clearly.
Substantial enough victories for AMD/Via. Nvidia may only claim partial victory, but foresee more lawsuits from them later, if they can afford it. Latest loss of patent issues combines with lower than expected sales of GF100 products may mean trouble for them. Wait and see.
First off, this is a fantastic article Ryan! I have read several since the announcement and none have nearly the technical depth.
One of the things not imposed by the FTC that I am very unhappy about is allowing 3rd parties to develop chipsets for current and future Intel CPUs.
Socket 1156 chipsets are flat out neutered - a wonderful business opportunity that could be addressed not only by Nvidia, but smaller companies as well like SiS that could compete on price. There is no need for P55 and H55 boards to cost what they do now that the GPU is on the CPU die, but the monopolist won't share the ball.
Hell, I'm looking at the result of this right at the side of my page in Anand's Twitter feed!
the best P55 boards for 6Gbps SATA would be any board that uses a PLX chip to bridge multiple PCIe lanes together
Don't buy Intel shit, buy AMD! I buy AMD 780 and 880 boards and I'm the happiest guy ever. Best IGP ever and very solid 4 and 6 core monster CPUs. Intel can suck my dick. For free.
Agreed. If this is the same "Pirks" user on DT, just go ahead and ban this troll. He rarely has anything constructive to add. Mod's keep an eye out, don't want AT to turn into the free fro all DT comments have become.
Since Anand and co. run this place, there really isn't any free speech here (or on any privately-owned site). They can delete whichever comments they want (and ban whomever they wish).
The First Amendment only applies to free speech and the *government.*
For Nvidia has to takeover Via to compete in the future with intel, it's their only option if they want to remain viable to go head to head with the competition.
I've been saying this for over a year now. NVIDIA needs to buy VIA, VIA needs to release an improved counter to Atom and NVIDIA needs to stop putting ION in netbooks with Intel processors.
NG-ION was really disappointing due to the chipset issue. Thanks to the limited PCIe lanes available to the GPU, the GT218 performs almost as poorly as a 9400M (not that the GT218 is a very good GPU anyway).
None of the new ION netbooks are as good as the HP Mini 311 is.
''It's a shame that AMD's 64 got crippled because of Pentium 4. AMD had a good run back then.''
It's not so much that AMD's 64 has gotten crippled by the crappy Netburst Pentium 4 as much as it has been crippled by Intel's very questionable way of doing business. What the quality of their product couldn't impose, their money did. Back then, AMD had clearly the best product but it seems that it didn't not suffice for obvious reasons. A lot of storms and bumpy roads can be weathered when you spread enough money around...
I think Intel's business practices are deplorable and this slap on the wrist is a slap in the face to the US consumer, but Anand is certainly entitled to be a fan of their engineering accomplishments.
I'm not sure where this is coming from. For a surprising amount of time, Intel has had the top spot in the CPU space (from Core2Duo through the i7's today) so there's no reason not to be a fan of Intel's CPUs.
It's also true that on the lower spectrum, AMD has done very well. They more or less toss Intel aside in the sub-200 dollar market.
I haven't detected any serious "fanboism" that you're accusing Anandtech of. Talking with industry professionals has been one of the highlights of reading Anandtech. The AMD 4xxx story alone was worth jumping to this site over many other ones. And that was pure AMD marvelousness.
Intel didn't really get in as much trouble as the FTC hoped. This won't really change anything, especially not between NVIDIA and Intel.
I'm disappointed that the FTC was unable to force Intel to license chipset makers for current-gen processors.
It's really a shame for consumers, because the GeForce 320M is an excellent IGP and I'd like to see it in more laptops with Arrandale CPUs, rather than just the Penryn-equipped Macbook Pro 13.
I hope AMD's new crop of mobile CPUs actually let them break into the business in a real way. The battery life figures for the new quad-cores are really surprising considering AMD's history for poor power efficiency in mobile CPUs.
Intel being Intel, and having such a powerful commanding lead, this is what has really happened.
SEC will be back.
What is said about the Intel Fortran Compiler is true. It has terrible performance on AMD processors. And as far as I know, it still is addled for AMD processors. That takes a deliberate act where the code queries the processor, and if its AMD, disables certain optimizing features. This is notorious where I work.
Am I alone in that how this settlement affects Nvidia was the primary concern to most enthusiasts here? The FTC is supposedly after making things fair with this suit, but like Ryan said all the points the FTC won on were already being done/not done and won't change much for Intel.
However, Nvidia is actively getting screwed by Intel every day that they are not allowed to make a chipset for i7 forward. Its the most blatant anti-competitive move in all of this and there is barely a mention or reason for not forcing Intel to give the license to Nvidia. FTC honchos probably were paid off by Intel.
Cmon Intel, well we don't want to have to make reasonably priced boards so we will just take a monopoly on it. I mean its not like Intel still wouldn't sell a bunch of X58 P55 etc boards. Its such BS and it really pisses me off. I have been using an EVGA 680i board for 3 years and never had a problem with it, and it looks like it will be the only high end Nvidia chipset I will ever be allowed to buy..
This really is a big deal, because we all know Nvidia's IGP's have been and will always be superior to Intel's. If I was AMD I would worry about ever having a better performing CPU then Intel. Next day x86 license might disappear after FTC gets paid off again!!!!!
Ryan, do you think Nvidia will press on with a suit of their own about this?
The NVIDIA vs. Intel suit in Delaware over NVIDIA's chipset license is still ongoing. So yes, NVIDIA will still be pressing on. However the trial got pushed back from August to December, so that case still has quite a long time to go. Unless NV and Intel settle ahead of time, it won't be until Sandy Bridge (or later) before the Nehalem chipset issue is ruled on.
Since this doesn't do anything to get Intel to license the technology necessary for third parties to make chipsets, this does very little for consumers. Intel will keep on illegally using their CPU monopoly to strongarm themselves a GPU monopoly (the chipset monopoly already being a fait accompli), and since they have no chipset competition they have no reason to innovate or even bring decent products to the table in this space (native USB3 delayed until 2012).
Intel does not have a CPU or chipset monopoly with AMD around.
And lets not forget the nonsense nVidia has about licensing SLI for Intel products.
Intel has restricted access to DMI/QPI technology so only Intel Designed chipsets are available for i3/i5/i7 processors. Its not illegal but I feel Intel is actually restricting their competitiveness.
Fundamentally, there are too many IT and enthusiasts too obsessed with performance and priced be damned. And Intel really exploits this with stunts like restricting access to DMI/QPI.
If you find this too objectionable, there is always AMD. AMD produces CPU and Chipsets that offer great value (performance/dollar).
I agree that it's hard to believe that Intel sells below costs. In fact, to be more plain, I just don't believe it. Intel's margins have been >50%. Even AMD's margins had been >40%. To sell below cost, especially for the tiny Atom when wafer costs are fixed, would mean selling it for <$10, I think. It's a lot smaller than standard CPUs. Chipsets are even cheaper than CPUs. The accusations (from NVidia) that Intel is selling some Atoms below cost are ridiculous
The point I believe is that Intel is giving away their chipsets essentially by selling them at below cost in order to move much higher margin CPUs. So NVIDIA can't complete with Intel because Intel is giving OEMs super cheap chipsets and NVIDIA doesn't have a CPU to bundle with. And as for Atom, Intel charges more for an Atom processor alone than it does for an Atom + chipset bundle.
How many copies of gcc can you buy for $10 million?
If AMD doesn't want to create their own compiler, maybe they could contribute tweaks to gcc, thus creating an AMD-friendly compiler that, unlike Intel's, is also free.
My whole feeling is, when AMD/Nvidia cannot compete with Intel, FTC steps in to help.
Is there anything Intel did illegal? If it is, then we need to regulate many,. virtual all business area. When I was trying to find a guy to mow the lawn, the one mowering my neighbours told me that he could offer the service at a lower price since he will work on two house. It would be even lower if the whole street (8 families) switch to him.
When I tried to find a contractor to do wood floor and tile, the 2nd guy I interviewed said he can give me 15% discount if he got both jobs.
Perhaps you're not fully grasping the details of market functionality. Let me explain it this way - keeping in tune with the lawn mower analogy: You have 10 lawns, and each of them is a bit peculiar and requires a slightly different approach. Intel comes up to you and says: "I can do 9 of them, at a very good price, only if you don't let AMD do the 10th one, which I'm unable to mown. If you do let AMD do the tenth one, you'll pay double to me." Intel is frightened you'll like AMD, because then you might let AMD do the 4 lawns it offers you to do, leaving only 6 to Intel in the future. Ofcourse, this situation is not optimal, like say, let AMD do 2 lawns and Intel 8, having all lawns mown. No, in this situation one lawn will never be mown, because it can only be done by AMD.
Each lawn is a market niche, and the lawns AMD can do better are for instance the "chipset+gpu+cpu" market, or the "cheap-ass quad core" market, or the "bang 4 bucks" market, or simply the "AMD-fanboy/Intel haters" market (which Intel will never be able to address). However, Intel abuses it's monopoly, because it forces OEM's to choose between Intel OR amd, while oem's would rather like Intel AND amd. And ofcourse, OEM's will choose Intel over AMD, because Intel has a de facto monopoly.
There's nothing wrong with offering discounts on large volumes, but there's something wrong with offering discounts to not sell other brands.
i noticed that intel closed their online store that sells their C++ compiler as of "JUNE 30th, 2010." hahaha. i wonder if this has anything to do with the new customer reimbursement fund?
''I wonder what would have happened if Intel had not (allegedly) paid off the OEMs to shut AMD out of the business?''
I was wondering the same thing a while ago. I think that in the end it wouldn't have changed the big picture but AMD might have end up in a better financial situation this allowing them to put more $$ in R&D. They had the better product for about like 2 years during the Athlon 64 era, that's a hell of a long time in the computer business. Anyways, you can speculate all we want we'll never know.
Intel has done nothing wrong. Evil rebate mongering corporations exist in every fucking facet of business; it's not Intel's fault, they're just playing the game and winning!
Fuck AMD, but first fuck Nvidia for ever venturing past GPU's. Intel needs to keep them AWAY from DMI and QPI. They totally FUCKED up 939, AM2, and 775 with their piece of shit NF4-7 bullshit, especially 775.
If a motherfucking software patch can enable SLI on ANY motherboard that has the electrical capability, because it is totally possible, then Nvidia can go get fucked and never engineer another motherboard, PLEASE.
AMD, well if they don't like being outcompeted by Intel, then stop making CPU's and chipsets and just stick to the ATI bullshit. Maybe if they weren't fucking around with bullshit CPU's and chipsets they could get a Catalyst release that didn't suck-off 100 donkeys simultaneously.
Fuck.
That was a last fuck for good measure you fucking fuckeddy fucks.
Don't tell me you don't like the cursing or that it offends you; you know you like it Shit Fuck.
Despite your obvious troll, perhaps you are merely too young to remember when nVidia offered the best AMD chipsets on the market during a time when AMD did not make chipsets of their own. Their onboard audio solution back in 2002 is still better than 99% of the onboard audio solutions provided by intel/AMD right now, it's too bad they had to drop it on the nForce 3's because of cost issues.
And maybe it's just me, but I remember my nForce 4 SLI board working quite well with my manchester 939..
Ok, I was a bit drunk when I posted that last bit; but you've still helped me prove my point.
Yes, I had two NF4 boards. One DFI LP UT NF4 Ultra-D and one Asus A8N32SLI-Deluxe. The DFI is my current HTPC. Couldn't agree with you more. The only reason I bundled NF4 in is for Nvidia's garbage software patches preventing SLI for running on any setup; the NF4 was guilty of that too.
Do you see it now?
One stupidly obvious point is that neither of those boards had QPI or DMI on them. Well, not exactly.
Still not catching it?
The IMC and pretty much everything else that needs to be stable was already designed and packaged on the physical CPU. (no, not 754 and before, but those NF2-3 boards were good for what, on-board sound is what you're telling me? Maybe they were good OC'ers, but AMD didn't shine until 939 and then only for a minute.)
Let me tie it together for you now.
That's the same as, you guessed it, the i3/i5/i7 CPU's that Intel has today.
The NF4 series worked fine, because Nvidia couldn't screw up what was designed by AMD. Mostly I am talking about the communication of the major parts in an x86 design: CPU, RAM, IMC.
No wonder Intel wanted Nvidia not designing parts to do those jobs. The Nvidia 775 IMC controllers were trash aside from hand selected boards given to review sites.
Maybe it was just the EVGA 775's I had; I've never like their BIOS releases.
If Intel is shady so is Nvidia, and so is AMD. The only reason anybody is looking at Intel like they are, is because they are on top. If AMD or Nvidia were on top, they would be the one's answering to the FTC.
Nothing any of us can do about it. Besides, AMD should be glad they have lasted this long after getting their start on Intel's coattails.
Silly Troll Scumbag. Being drunk does not excuse you for the worthless profane remarks about nVidia chipsets.
Nvidia chipsets were really meant for AMD parts. Nvidia chipsets for Intel parts were an afterthought that I believed did not recieve the same level of attention and testing as those for
I myself have used nForce 2 400 chipset with a nicely overclockable AMD XPM-2500.
I have also used an nForce 4 chipset with an Optron 175. Built in 2006, it still runs fine today.
I have been satisfied with the performance of both chipsets. What I was not satisfied with is the poor construction of motherboards associated with AMD chipsets. Since 2004, this has markedly improved.
Ryan, I read that Anandtech is still looking into the performance of Intel compiler with non-Intel chips. Here is Agner Fog's updated blog where he describes how Intel compiler treats AMD chips, and Intel dishonesty to him about it in 12/30/09. http://www.agner.org/optimize/blog/read.php?i=49#4... Intel's newly released beta June 2010 of its Math Kernel Library v.10.3 is still crippling AMD processors.http://www.agner.org/optimize/blog/read.php?i=49#1... Agner says that he is working on a list of software and benchmarks that are crippled on AMD processors due to the Intel Compiler or libraries. From a year ago at ArsTechnica, PCMark05 memory performance increased 47% by changing CPUID from VIA to Intel. http://arstechnica.com/hardware/reviews/2008/07/at...
Note they allege that Cinebench is compromised by using Intel compilers. Until Cinebench responds, I think that Anandtech should quit using it.
64. Several benchmarking organizations adopted benchmarks that measured performance of CPUs running software programs compiled using the Intel compiler or libraries. Intel’s deception affected among others, the Business Applications Performance Corporation (“BAPCo”), Cinebench, and TPC benchmarks.
67. Intel publicized the results of the benchmarking to promote sales of products containing its x86 CPUs even though it knew the benchmarks were misleading. For example: ...
Buy AMD based laptops and notebooks/netbooks ! Let the dealer know that you're interested in AMD. Unfortuntately in India, one can still see HP selling underpriced Intel laptops with overpriced AMD laptops. eg here. Compaq Presario range http://is.gd/eiUXo , Essentials http://is.gd/eiV0n and EliteBook http://is.gd/eiV20
The same sad story repeats with Vostro, Acer, Sony, Benq laptop models in India.
"In reality most of the things Intel is being barred from doing are things that they discontinued doing long ago if they did them at all (note that this settlement is not an admission of guilt on Intel’s part)."
Uh, ok... then why was Intel sued by the FTC and fined by the European Commision and going to be under such scrutiny and regulation by the FTC for years to come??!!
There is probably a whole crap ton of other despicable and undermining business practices Intel could be held accountable for that no one but top Intel execs know about.
AMD had the capacity to continue with lawsuits with a great chance of winning up to 7 billion USD from Intel ALONE. Forget the FTC, forget the European Trade Commission, forget any other entity that can claim from Intel. Nvidia, on the other hand should settle differences with Intel soon so that viable Intel/nvidia solutions can be available. I'm a huge AMD fan but I do admit to the i7 engineering feat that still today blows AMD's solutions out of the water performance-wise. Though I admit I feel that performance gap would be bridged by getting myself a x6 1090T by finding a good batch and OC'ing past the 4 Ghz barrier.
As we know from history, Intel almost immediately cut the number of PCIe lanes from their mobile CPUs from 20 (16+4) down to 4 (0+4) after this ruling. Everything, even to the most modern Comet Lake-U and Ice Lake-U derives all of the PCIe lanes from the chipset. One could make a very, very feeble argument that Ice Lake-U added 4 TB3 controllers onto the CPU die, though TB3 on laptops is still 100% locked to Intel (find me one AMD APU laptop with TB3 that actually shipped as of April 2020... you'll find none whatsoever).
"Not limiting the PCIe performance" indeed. Lies all abound.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
64 Comments
Back to Article
Ric902 - Thursday, August 5, 2010 - link
Even today, Intel removed existing SSE2 and SSE3 optimizations from their latest high-performance IPP libraries, reverting to compiler-generated scalar code. They only optimize SSSE3 for Atom and up. Guess how massive the AMD Phenom performance drop is!Pirks - Thursday, August 5, 2010 - link
This part fucking killed me, fucking Dell, a piece of shit PC maker, I knew these fucks are shitty but didn't know the extent of their shittiness. Holy F.BTW spent half a day yesterday looking for 64-bit driver for my Vostro 1700 Ricoh 82c592 fucking memory stick controller, Dell fucks just don't give a shit about users upgrading to x64. Fuck.
justaviking - Thursday, August 5, 2010 - link
I think you need to expand your limited vocabulary.Pirks - Thursday, August 5, 2010 - link
"Intel is under no obligation to license QPI or DMI"nVidia is fucked too
Nataku - Thursday, August 5, 2010 - link
and... stop the swearingcknobman - Thursday, August 5, 2010 - link
I couldnt agree more. Fuck those fucking fuckers!!!Dell can rot in hell, never have and never will buy their overpriced and under featured pieces of sh!t.
Pirks - Thursday, August 5, 2010 - link
I've been pretty happy with my Vostro 1700, the rare FULL-MATTE laptop, no fucking moronic glossy shit anywhere ever! Everything is matte! Keyboard is top notch, rivals best macbooks and vaios, and battery didn't die after 6 months like on my Alienware laptop, it's still running nice after 3 years of use, has lotsa juice, so quality wise Dell is pretty cool.Well... until I tried to upgrade to win7 x64, this is where Dell clowns screwed me hard. But I found all the drivers on my own and problem's solved. Screw ya Dell scumbags, you think if you don't post your fucking 64-bit drivers for older laptops I'm going to run out and buy Dell 1720 with win7 preinstalled or something now?
How about you suck my dick again, Mikey Delley? :P Suck deep bitch, 'cause I gonna do it AGAIN when I'm about to upgrade to win8, har har har har harrrr
I'm not gonna buy your new laptops every time I upgrade windows, eat that bitch
icrf - Thursday, August 5, 2010 - link
Didn't the majority of the consumer PC market not do so well around then, too, meaning it was likely more contributory than causal?Pirks - Thursday, August 5, 2010 - link
In 2007? Are you serious?IlllI - Thursday, August 5, 2010 - link
tell us how you really feelHector2 - Friday, August 6, 2010 - link
I spent several years in the military so am used to bad language, but that doesn't mean I enjoy seeing it --- especially on tech sites where you'd expect something better. If you want to sound like you actually made it beyond grade school, act like a grownup.Otherwise just stick to the non-tech sites where it seems to be popular these days to throw up toilet comments like your's.
If Anand wants to maintain a focus on technical comments and opinions, I'd expect him to delete this garbage
crazylocha - Thursday, August 5, 2010 - link
Well written for almost every level of reader. Appreciate the combining of details, some of which was only able to garner from financial sites postings, and putting them together clearly.Substantial enough victories for AMD/Via. Nvidia may only claim partial victory, but foresee more lawsuits from them later, if they can afford it. Latest loss of patent issues combines with lower than expected sales of GF100 products may mean trouble for them. Wait and see.
JMS3072 - Thursday, August 5, 2010 - link
Above in the table, I think you mean "recompense", not "reprimands".Taft12 - Thursday, August 5, 2010 - link
First off, this is a fantastic article Ryan! I have read several since the announcement and none have nearly the technical depth.One of the things not imposed by the FTC that I am very unhappy about is allowing 3rd parties to develop chipsets for current and future Intel CPUs.
Socket 1156 chipsets are flat out neutered - a wonderful business opportunity that could be addressed not only by Nvidia, but smaller companies as well like SiS that could compete on price. There is no need for P55 and H55 boards to cost what they do now that the GPU is on the CPU die, but the monopolist won't share the ball.
Hell, I'm looking at the result of this right at the side of my page in Anand's Twitter feed!
the best P55 boards for 6Gbps SATA would be any board that uses a PLX chip to bridge multiple PCIe lanes together
FAIL chipset from a scum company.
Pirks - Thursday, August 5, 2010 - link
Don't buy Intel shit, buy AMD! I buy AMD 780 and 880 boards and I'm the happiest guy ever. Best IGP ever and very solid 4 and 6 core monster CPUs. Intel can suck my dick. For free.Swivelguy2 - Thursday, August 5, 2010 - link
Yeah... your comments on this article so far sure make you sound like the happiest guy ever.bah12 - Thursday, August 5, 2010 - link
Agreed. If this is the same "Pirks" user on DT, just go ahead and ban this troll. He rarely has anything constructive to add. Mod's keep an eye out, don't want AT to turn into the free fro all DT comments have become.Pirks - Thursday, August 5, 2010 - link
don't you stifle the freedom of speech, poo-bahsynaesthetic - Monday, August 9, 2010 - link
Since Anand and co. run this place, there really isn't any free speech here (or on any privately-owned site). They can delete whichever comments they want (and ban whomever they wish).The First Amendment only applies to free speech and the *government.*
Hector2 - Friday, August 6, 2010 - link
stay away from tech sites, Pirks, until you learn some better english. Stick to the 'tweener sites that oogle Lindsay & Britney.crimson117 - Thursday, August 5, 2010 - link
It's frustrating that the SEC can just settle over such a severe issue.We'll never know the extent of the payments or how badly Dell and Intel misled their investors because Dell bought off the SEC for $100 million.
Although the FTC didn't prove anything, at least they made Intel promise not to do those things in the future.
Unless a settlement establishes accountability and responsibility, and sets things straight, it's just a bribe.
AmdInside - Thursday, August 5, 2010 - link
I think the real winner in all of this was Intel. They did not have to concede much nor pay a heavy penalty.AMD came second for their CPU businesses.
The settlement almost does nothing for the GPU business so NVIDIA got screwed.
Does Via do anything today with their x86 license?
Taft12 - Thursday, August 5, 2010 - link
yes they do - the C7 is lacking in performance, but you can run x86 Windows and Linux on it no problem:http://www.newegg.ca/Product/Product.aspx?Item=N82...
Unfortunately the Atom really made this stuff from Via obsolete.
Rayb - Friday, August 6, 2010 - link
For Nvidia has to takeover Via to compete in the future with intel, it's their only option if they want to remain viable to go head to head with the competition.synaesthetic - Monday, August 9, 2010 - link
I've been saying this for over a year now. NVIDIA needs to buy VIA, VIA needs to release an improved counter to Atom and NVIDIA needs to stop putting ION in netbooks with Intel processors.NG-ION was really disappointing due to the chipset issue. Thanks to the limited PCIe lanes available to the GPU, the GT218 performs almost as poorly as a 9400M (not that the GT218 is a very good GPU anyway).
None of the new ION netbooks are as good as the HP Mini 311 is.
sotoa - Thursday, August 5, 2010 - link
This was a great article. An easy read too.Interesting how Dell is now not turning a profit. LOL! But that's big business for ya.
It's a shame that AMD's 64 got crippled because of Pentium 4. AMD had a good run back then.
Wurmer - Saturday, August 7, 2010 - link
''It's a shame that AMD's 64 got crippled because of Pentium 4. AMD had a good run back then.''It's not so much that AMD's 64 has gotten crippled by the crappy Netburst Pentium 4 as much as it has been crippled by Intel's very questionable way of doing business. What the quality of their product couldn't impose, their money did. Back then, AMD had clearly the best product but it seems that it didn't not suffice for obvious reasons. A lot of storms and bumpy roads can be weathered when you spread enough money around...
tejas84 - Thursday, August 5, 2010 - link
Well Anand you are a self confessed Intel fanboy and I can imagine you are not too happy at what has transpired with Intel.Intel now have to play on level terms and I think that Nvidia and AMD are going to show what they are made of.
No more swooning over people like Pat Gelsinger any more for you Anand. The Intel joyride was fun but is now coming to an end.
Anand I would like you to meet the future.... AMD and Nvidia please step forward
Pirks - Thursday, August 5, 2010 - link
"Nvidia please step forward"then bend over and open your gape hole wider, Intel has some more QPI/DMI love for ya, HARDcore style!
Taft12 - Thursday, August 5, 2010 - link
I think Intel's business practices are deplorable and this slap on the wrist is a slap in the face to the US consumer, but Anand is certainly entitled to be a fan of their engineering accomplishments.I am too, even if I won't buy any.
erple2 - Thursday, August 5, 2010 - link
I'm not sure where this is coming from. For a surprising amount of time, Intel has had the top spot in the CPU space (from Core2Duo through the i7's today) so there's no reason not to be a fan of Intel's CPUs.It's also true that on the lower spectrum, AMD has done very well. They more or less toss Intel aside in the sub-200 dollar market.
I haven't detected any serious "fanboism" that you're accusing Anandtech of. Talking with industry professionals has been one of the highlights of reading Anandtech. The AMD 4xxx story alone was worth jumping to this site over many other ones. And that was pure AMD marvelousness.
synaesthetic - Monday, August 9, 2010 - link
Intel didn't really get in as much trouble as the FTC hoped. This won't really change anything, especially not between NVIDIA and Intel.I'm disappointed that the FTC was unable to force Intel to license chipset makers for current-gen processors.
It's really a shame for consumers, because the GeForce 320M is an excellent IGP and I'd like to see it in more laptops with Arrandale CPUs, rather than just the Penryn-equipped Macbook Pro 13.
I hope AMD's new crop of mobile CPUs actually let them break into the business in a real way. The battery life figures for the new quad-cores are really surprising considering AMD's history for poor power efficiency in mobile CPUs.
rickcain2320 - Thursday, August 5, 2010 - link
Remember all that matters is dollars. I will NEVER buy an intel chipped PC. I'm happy with my X2 but am needing an upgrade badly..I'm salivating over that 6-core AMD and its on my must-buy list before Christmas.
ClagMaster - Friday, August 6, 2010 - link
SEC to Intel : I'll be back.Intel being Intel, and having such a powerful commanding lead, this is what has really happened.
SEC will be back.
What is said about the Intel Fortran Compiler is true. It has terrible performance on AMD processors. And as far as I know, it still is addled for AMD processors. That takes a deliberate act where the code queries the processor, and if its AMD, disables certain optimizing features. This is notorious where I work.
Hector2 - Friday, August 6, 2010 - link
Fortran ? Really ? Does anyone still use that ?ClagMaster - Friday, August 6, 2010 - link
Yes.Fortran is still the heavy lifter for scientific and engineering codes.
n0x1ous - Friday, August 6, 2010 - link
Am I alone in that how this settlement affects Nvidia was the primary concern to most enthusiasts here? The FTC is supposedly after making things fair with this suit, but like Ryan said all the points the FTC won on were already being done/not done and won't change much for Intel.However, Nvidia is actively getting screwed by Intel every day that they are not allowed to make a chipset for i7 forward. Its the most blatant anti-competitive move in all of this and there is barely a mention or reason for not forcing Intel to give the license to Nvidia. FTC honchos probably were paid off by Intel.
Cmon Intel, well we don't want to have to make reasonably priced boards so we will just take a monopoly on it. I mean its not like Intel still wouldn't sell a bunch of X58 P55 etc boards. Its such BS and it really pisses me off. I have been using an EVGA 680i board for 3 years and never had a problem with it, and it looks like it will be the only high end Nvidia chipset I will ever be allowed to buy..
This really is a big deal, because we all know Nvidia's IGP's have been and will always be superior to Intel's. If I was AMD I would worry about ever having a better performing CPU then Intel. Next day x86 license might disappear after FTC gets paid off again!!!!!
Ryan, do you think Nvidia will press on with a suit of their own about this?
Ryan Smith - Friday, August 6, 2010 - link
The NVIDIA vs. Intel suit in Delaware over NVIDIA's chipset license is still ongoing. So yes, NVIDIA will still be pressing on. However the trial got pushed back from August to December, so that case still has quite a long time to go. Unless NV and Intel settle ahead of time, it won't be until Sandy Bridge (or later) before the Nehalem chipset issue is ruled on.jensend - Friday, August 6, 2010 - link
Since this doesn't do anything to get Intel to license the technology necessary for third parties to make chipsets, this does very little for consumers. Intel will keep on illegally using their CPU monopoly to strongarm themselves a GPU monopoly (the chipset monopoly already being a fait accompli), and since they have no chipset competition they have no reason to innovate or even bring decent products to the table in this space (native USB3 delayed until 2012).ClagMaster - Friday, August 6, 2010 - link
Intel does not have a CPU or chipset monopoly with AMD around.And lets not forget the nonsense nVidia has about licensing SLI for Intel products.
Intel has restricted access to DMI/QPI technology so only Intel Designed chipsets are available for i3/i5/i7 processors. Its not illegal but I feel Intel is actually restricting their competitiveness.
Fundamentally, there are too many IT and enthusiasts too obsessed with performance and priced be damned. And Intel really exploits this with stunts like restricting access to DMI/QPI.
If you find this too objectionable, there is always AMD. AMD produces CPU and Chipsets that offer great value (performance/dollar).
Hector2 - Friday, August 6, 2010 - link
I agree that it's hard to believe that Intel sells below costs. In fact, to be more plain, I just don't believe it. Intel's margins have been >50%. Even AMD's margins had been >40%. To sell below cost, especially for the tiny Atom when wafer costs are fixed, would mean selling it for <$10, I think. It's a lot smaller than standard CPUs. Chipsets are even cheaper than CPUs. The accusations (from NVidia) that Intel is selling some Atoms below cost are ridiculousAmdInside - Friday, August 6, 2010 - link
The point I believe is that Intel is giving away their chipsets essentially by selling them at below cost in order to move much higher margin CPUs. So NVIDIA can't complete with Intel because Intel is giving OEMs super cheap chipsets and NVIDIA doesn't have a CPU to bundle with. And as for Atom, Intel charges more for an Atom processor alone than it does for an Atom + chipset bundle.Calidore - Friday, August 6, 2010 - link
How many copies of gcc can you buy for $10 million?If AMD doesn't want to create their own compiler, maybe they could contribute tweaks to gcc, thus creating an AMD-friendly compiler that, unlike Intel's, is also free.
Quantumboredom - Friday, August 6, 2010 - link
AMD does have it's own compiler (a version of the Open64 compile), they just haven't bothered to support it on Windows yet.They currently have a poll where Windows support is on the list though, here: http://developer.amd.com/cpu/open64/Pages/default....
Roy2001 - Friday, August 6, 2010 - link
My whole feeling is, when AMD/Nvidia cannot compete with Intel, FTC steps in to help.Is there anything Intel did illegal? If it is, then we need to regulate many,. virtual all business area. When I was trying to find a guy to mow the lawn, the one mowering my neighbours told me that he could offer the service at a lower price since he will work on two house. It would be even lower if the whole street (8 families) switch to him.
When I tried to find a contractor to do wood floor and tile, the 2nd guy I interviewed said he can give me 15% discount if he got both jobs.
Do you think these practices are illegal?
HolKann - Sunday, August 8, 2010 - link
Perhaps you're not fully grasping the details of market functionality. Let me explain it this way - keeping in tune with the lawn mower analogy: You have 10 lawns, and each of them is a bit peculiar and requires a slightly different approach. Intel comes up to you and says: "I can do 9 of them, at a very good price, only if you don't let AMD do the 10th one, which I'm unable to mown. If you do let AMD do the tenth one, you'll pay double to me." Intel is frightened you'll like AMD, because then you might let AMD do the 4 lawns it offers you to do, leaving only 6 to Intel in the future. Ofcourse, this situation is not optimal, like say, let AMD do 2 lawns and Intel 8, having all lawns mown. No, in this situation one lawn will never be mown, because it can only be done by AMD.Each lawn is a market niche, and the lawns AMD can do better are for instance the "chipset+gpu+cpu" market, or the "cheap-ass quad core" market, or the "bang 4 bucks" market, or simply the "AMD-fanboy/Intel haters" market (which Intel will never be able to address). However, Intel abuses it's monopoly, because it forces OEM's to choose between Intel OR amd, while oem's would rather like Intel AND amd. And ofcourse, OEM's will choose Intel over AMD, because Intel has a de facto monopoly.
There's nothing wrong with offering discounts on large volumes, but there's something wrong with offering discounts to not sell other brands.
Wurmer - Monday, August 9, 2010 - link
''There's nothing wrong with offering discounts on large volumes, but there's something wrong with offering discounts to not sell other brands.''Indeed, couldn't agree more. I have both Intel and AMD machines and I like it that way, competition is good far all of us.
softdrinkviking - Saturday, August 7, 2010 - link
i noticed that intel closed their online store that sells their C++ compiler as of "JUNE 30th, 2010." hahaha. i wonder if this has anything to do with the new customer reimbursement fund?http://software.intel.com/en-us/articles/intel-sof...
softdrinkviking - Saturday, August 7, 2010 - link
http://software.intel.com/en-us/articles/buy-or-re...softdrinkviking - Saturday, August 7, 2010 - link
it was fun to read the comments from this 2003 article for the Athlon 64!http://www.anandtech.com/show/1164/17
I wonder what would have happened if Intel had not (allegedly) paid off the OEMs to shut AMD out of the business?
The 64 VS 32 compiling benchmark is especially interesting since we are just now seeing a wider adaptation of 64 bit OSs.
Wurmer - Monday, August 9, 2010 - link
''I wonder what would have happened if Intel had not (allegedly) paid off the OEMs to shut AMD out of the business?''I was wondering the same thing a while ago. I think that in the end it wouldn't have changed the big picture but AMD might have end up in a better financial situation this allowing them to put more $$ in R&D. They had the better product for about like 2 years during the Athlon 64 era, that's a hell of a long time in the computer business. Anyways, you can speculate all we want we'll never know.
cesthree - Saturday, August 7, 2010 - link
I like my limited vocabulary, fucking fuckers.Intel has done nothing wrong. Evil rebate mongering corporations exist in every fucking facet of business; it's not Intel's fault, they're just playing the game and winning!
Fuck AMD, but first fuck Nvidia for ever venturing past GPU's. Intel needs to keep them AWAY from DMI and QPI. They totally FUCKED up 939, AM2, and 775 with their piece of shit NF4-7 bullshit, especially 775.
If a motherfucking software patch can enable SLI on ANY motherboard that has the electrical capability, because it is totally possible, then Nvidia can go get fucked and never engineer another motherboard, PLEASE.
AMD, well if they don't like being outcompeted by Intel, then stop making CPU's and chipsets and just stick to the ATI bullshit. Maybe if they weren't fucking around with bullshit CPU's and chipsets they could get a Catalyst release that didn't suck-off 100 donkeys simultaneously.
Fuck.
That was a last fuck for good measure you fucking fuckeddy fucks.
Don't tell me you don't like the cursing or that it offends you; you know you like it Shit Fuck.
rscoot - Sunday, August 8, 2010 - link
Despite your obvious troll, perhaps you are merely too young to remember when nVidia offered the best AMD chipsets on the market during a time when AMD did not make chipsets of their own. Their onboard audio solution back in 2002 is still better than 99% of the onboard audio solutions provided by intel/AMD right now, it's too bad they had to drop it on the nForce 3's because of cost issues.And maybe it's just me, but I remember my nForce 4 SLI board working quite well with my manchester 939..
cesthree - Sunday, August 8, 2010 - link
Ok, I was a bit drunk when I posted that last bit; but you've still helped me prove my point.Yes, I had two NF4 boards. One DFI LP UT NF4 Ultra-D and one Asus A8N32SLI-Deluxe. The DFI is my current HTPC. Couldn't agree with you more. The only reason I bundled NF4 in is for Nvidia's garbage software patches preventing SLI for running on any setup; the NF4 was guilty of that too.
Do you see it now?
One stupidly obvious point is that neither of those boards had QPI or DMI on them. Well, not exactly.
Still not catching it?
The IMC and pretty much everything else that needs to be stable was already designed and packaged on the physical CPU. (no, not 754 and before, but those NF2-3 boards were good for what, on-board sound is what you're telling me? Maybe they were good OC'ers, but AMD didn't shine until 939 and then only for a minute.)
Let me tie it together for you now.
That's the same as, you guessed it, the i3/i5/i7 CPU's that Intel has today.
The NF4 series worked fine, because Nvidia couldn't screw up what was designed by AMD. Mostly I am talking about the communication of the major parts in an x86 design: CPU, RAM, IMC.
No wonder Intel wanted Nvidia not designing parts to do those jobs. The Nvidia 775 IMC controllers were trash aside from hand selected boards given to review sites.
Maybe it was just the EVGA 775's I had; I've never like their BIOS releases.
If Intel is shady so is Nvidia, and so is AMD. The only reason anybody is looking at Intel like they are, is because they are on top. If AMD or Nvidia were on top, they would be the one's answering to the FTC.
Nothing any of us can do about it. Besides, AMD should be glad they have lasted this long after getting their start on Intel's coattails.
ClagMaster - Monday, August 9, 2010 - link
Silly Troll Scumbag. Being drunk does not excuse you for the worthless profane remarks about nVidia chipsets.Nvidia chipsets were really meant for AMD parts. Nvidia chipsets for Intel parts were an afterthought that I believed did not recieve the same level of attention and testing as those for
I myself have used nForce 2 400 chipset with a nicely overclockable AMD XPM-2500.
I have also used an nForce 4 chipset with an Optron 175. Built in 2006, it still runs fine today.
I have been satisfied with the performance of both chipsets. What I was not satisfied with is the poor construction of motherboards associated with AMD chipsets. Since 2004, this has markedly improved.
synaesthetic - Monday, August 9, 2010 - link
Is there a full moon or something tonight?The trolls are really coming out of the woodwork... comments on AT are usually very civil.
matt b - Thursday, August 12, 2010 - link
Ryan, I read that Anandtech is still looking into the performance of Intel compiler with non-Intel chips.Here is Agner Fog's updated blog where he describes how Intel compiler treats AMD chips, and Intel dishonesty to him about it in 12/30/09. http://www.agner.org/optimize/blog/read.php?i=49#4...
Intel's newly released beta June 2010 of its Math Kernel Library v.10.3 is still crippling AMD processors.http://www.agner.org/optimize/blog/read.php?i=49#1...
Agner says that he is working on a list of software and benchmarks that are crippled on AMD processors due to the Intel Compiler or libraries.
From a year ago at ArsTechnica, PCMark05 memory performance increased 47% by changing CPUID from VIA to Intel.
http://arstechnica.com/hardware/reviews/2008/07/at...
matt b - Thursday, August 12, 2010 - link
Note they allege that Cinebench is compromised by using Intel compilers. Until Cinebench responds, I think that Anandtech should quit using it.64. Several benchmarking organizations adopted benchmarks that measured performance of CPUs running software programs compiled using the Intel compiler or libraries. Intel’s deception affected among others, the Business Applications Performance Corporation (“BAPCo”), Cinebench, and TPC benchmarks.
67. Intel publicized the results of the benchmarking to promote sales of products containing its
x86 CPUs even though it knew the benchmarks were misleading. For example: ...
saifikhan - Sunday, August 15, 2010 - link
Buy AMD based laptops and notebooks/netbooks ! Let the dealer know that you're interested in AMD. Unfortuntately in India, one can still see HP selling underpriced Intel laptops with overpriced AMD laptops. eg here. Compaq Presario range http://is.gd/eiUXo , Essentials http://is.gd/eiV0n and EliteBook http://is.gd/eiV20The same sad story repeats with Vostro, Acer, Sony, Benq laptop models in India.
AMD is offering a large number of Notebook processors, please see the list here http://products.amd.com/en-gb/NotebookCPUResult.as...
thanks
Saifi.
India.
davidri - Friday, September 3, 2010 - link
"In reality most of the things Intel is being barred from doing are things that they discontinued doing long ago if they did them at all (note that this settlement is not an admission of guilt on Intel’s part)."Uh, ok... then why was Intel sued by the FTC and fined by the European Commision and going to be under such scrutiny and regulation by the FTC for years to come??!!
There is probably a whole crap ton of other despicable and undermining business practices Intel could be held accountable for that no one but top Intel execs know about.
Big B.S.
davidri - Friday, September 3, 2010 - link
p.s. The only other place I have seen more F-bombs is when worked for an AHL hockey team!!Onslaught2k3 - Saturday, December 4, 2010 - link
AMD had the capacity to continue with lawsuits with a great chance of winning up to 7 billion USD from Intel ALONE. Forget the FTC, forget the European Trade Commission, forget any other entity that can claim from Intel. Nvidia, on the other hand should settle differences with Intel soon so that viable Intel/nvidia solutions can be available. I'm a huge AMD fan but I do admit to the i7 engineering feat that still today blows AMD's solutions out of the water performance-wise. Though I admit I feel that performance gap would be bridged by getting myself a x6 1090T by finding a good batch and OC'ing past the 4 Ghz barrier.jeremyshaw - Thursday, May 28, 2020 - link
As we know from history, Intel almost immediately cut the number of PCIe lanes from their mobile CPUs from 20 (16+4) down to 4 (0+4) after this ruling. Everything, even to the most modern Comet Lake-U and Ice Lake-U derives all of the PCIe lanes from the chipset. One could make a very, very feeble argument that Ice Lake-U added 4 TB3 controllers onto the CPU die, though TB3 on laptops is still 100% locked to Intel (find me one AMD APU laptop with TB3 that actually shipped as of April 2020... you'll find none whatsoever)."Not limiting the PCIe performance" indeed. Lies all abound.