Hard Light Productions Forums
Off-Topic Discussion => General Discussion => Topic started by: redmenace on June 29, 2005, 04:14:04 am
-
http://www.tomshardware.com/hardnews/20050628_153223.html
and
http://www.tomshardware.com/hardnews/20050628_102226.html
:eek2:
Now, I am a big fan of AMD. But I am just a little bit skeptical here. Last time AMD sued Intel, AMD recieved a huge payoff in the form of technology to level the playing field. Could this be what they are after again? Could AMD be after Intel's Hyper Threading Technology?
-
And what if they are? :D
-
That would be a total mockery of what anti-trust is all about. It was meant to encourage or restore competition. But honestly, the more I see of anti-trust law being used the more I see it being misused if you get my drift? Anti-Trust Law is not meant to allow individuals or companies to engage in corporate shakedowns, if that is infact what this is.
-
My impression was that AMD are actually several years ahead of Intel in terms of their memory management and its multicore design, so I don't think they'd even want hyper threading (IMO it's pretty useless because it requires specific hardware considerations to be placed upon programs/programming). Also AMD was far quicker and far more succesful at moving into the 64 bit market; it's now Intel who have to catch up, not AMD.
If Intel are and were abusing monopoly to effectively bribe customers into exclusivity, then they really should be punished for that, because it is unfair business practices. But I'm not sure how proveable it is.
-
Err... since when Intel had monopoly over the microprocessor business?
Damn idiotic lawers, they don't even know what a monopoly is...
This looks to me just a piss off attempt, even worser than the SCO case.
AMD might be making better desktop CPUs but it's Intel that is ahead everywhere else.
Next move we will see is Intel accusing AMD of bribing Microsoft into focusing software development on AMD 64bit CPUs (not too far from the thruth except for the bribing part of course)
-
Originally posted by Zarax
Err... since when Intel had monopoly over the microprocessor business?
Damn idiotic lawers, they don't even know what a monopoly is...
This looks to me just a piss off attempt, even worser than the SCO case.
AMD might be making better desktop CPUs but it's Intel that is ahead everywhere else.
Next move we will see is Intel accusing AMD of bribing Microsoft into focusing software development on AMD 64bit CPUs (not too far from the thruth except for the bribing part of course)
There's a strong arguement that a (IIRC) 90% market share constitutes a monopoly, especially if a company is able to use the profits of that monopoly to block out competitors (as a monopoly is defined by having complete market control).
Not that anti-trust constitutes a monopoly situation anyways; it concerns a company abusing a dominant position to gain an unfair advantage and undermine customer choice (the latter being key here IMO). If AMD was, for example, offering big bribes and discounts to Dell not to take Intel processors then they'd be guilty regardless of market share.
-
Originally posted by aldo_14
There's a strong arguement that a (IIRC) 90% market share constitutes a monopoly, especially if a company is able to use the profits of that monopoly to block out competitors (as a monopoly is defined by having complete market control).
Not that anti-trust constitutes a monopoly situation anyways; it concerns a company abusing a dominant position to gain an unfair advantage and undermine customer choice (the latter being key here IMO). If AMD was, for example, offering big bribes and discounts to Dell not to take Intel processors then they'd be guilty regardless of market share.
Meh, given its history and the court help it received AMD is overstretching a bit imho...
-
Originally posted by Zarax
Meh, given its history and the court help it received AMD is overstretching a bit imho...
why should the history matter? If Intel has been found guilty before and carries on with the same practices, doesn't that make a court case even more justified?
-
Originally posted by aldo_14
why should the history matter? If Intel has been found guilty before and carries on with the same practices, doesn't that make a court case even more justified?
First thing is that Intel hasn't never been found guilty of abuse of dominant position, last time they came in court with AMD was because they wanted to redefine their technology sharing agreement and AMD refused (logically for them given that they had access to a large amount of Intel's R&D data for desktop chips and they still have).
Second thing is that I (as student in economy) strongly disagree on the discounts = unfair school of thought as there is no real proof about it.
Third, if AMD really thinks it can compete on a price basis (it's been their stragegy until 2003) from a 16% market position this is foolishness as Intel got all the large scale economics on its side.
Finally, AMD rushed to get a technological advantage without any proper support for it, making the whole effort a moot point as advanced hardware without software support == little usefulness.
Add the fact that there is no real market demand for 64bit yet and there won't be for another year on the desktop market (not with 90% of systems equipped with 512mb RAM), you'll start to see why AMD sales haven't jumped yet.
That said, AMD might see a sales increase now that a potential killer app is coming in the guise of XP64 (Intel is waiting for LH instead), which may pull enough support for a short term growth.
Note: There are some long term benefits for AMD strategy but they are limited to niche markets for now and not likely to show before 18 months, but they are enough to make me wanting an opteron if I'll ever get the cash for it ;)
-
Originally posted by Zarax
First thing is that Intel hasn't never been found guilty of abuse of dominant position, last time they came in court with AMD was because they wanted to redefine their technology sharing agreement and AMD refused (logically for them given that they had access to a large amount of Intel's R&D data for desktop chips and they still have).
Second thing is that I (as student in economy) strongly disagree on the discounts = unfair school of thought as there is no real proof about it.
Third, if AMD really thinks it can compete on a price basis (it's been their stragegy until 2003) from a 16% market position this is foolishness as Intel got all the large scale economics on its side.
Finally, AMD rushed to get a technological advantage without any proper support for it, making the whole effort a moot point as advanced hardware without software support == little usefulness.
Add the fact that there is no real market demand for 64bit yet and there won't be for another year on the desktop market (not with 90% of systems equipped with 512mb RAM), you'll start to see why AMD sales haven't jumped yet.
That said, AMD might see a sales increase now that a potential killer app is coming in the guise of XP64 (Intel is waiting for LH instead), which may pull enough support for a short term growth.
Note: There are some long term benefits for AMD strategy but they are limited to niche markets for now and not likely to show before 18 months, but they are enough to make me wanting an opteron if I'll ever get the cash for it ;)
AMDs technical advantage doesn't just extend to 64-bit, it also includes having an integrated memory controller on-chip (for example). IIRC from reading benchmarks AMD have had a consistently better performance-for-price for something like the last 4 or 5 years.
Also, the JapaneseFair Trade Comission has already warned Intel over use of anti-competitive practices; specifically offering discounts to manufacturers (inlcuding NEC, Hitachi, Sony, Fujitsu and Toshiba) that promised not to purchase or limit their use of AMD products. The time period over which this occurred shown the AMD market share halving.
As an aside, the EU is investigating Intel for similar offenses, although that doesn't constitute being found guilty (as the Japanese ruling does).
Finally, the issue of whether offering discounts, etc, is unfair is exactly the sort of issue that anti-trust law (and the courts) was set up to address. As Intels profit margins are by far the highest in the industry (40%; the rest don't meet double figures AFAIK), it'd be impossible for other manufacturers to compete with like-for-like discounts. If the other allegations are true - Intel locking out AMD from discussions with memory manfacturers over new standards for the next generation, Intel developing compilers that create code designed to run poorly on AMD processors - IMO you'd have to want AMD to win just to keep the market competitive and thus more fairly priced.
-
Originally posted by aldo_14
Intel developing compilers that create code designed to run poorly on AMD processors
That's quite debatable...
There a *chough* very mainstream *chough* software developer that has been developing opteron optimized (32bit and 64bit is coming) software since it came out... But you didn't hear that from me ;)
Add that to the fact that not many professional projects rely on Intel compilers but rather uses those made by the mainstream developer previously cited, much of the arguement looks moot to me...
-
Originally posted by Zarax
That's quite debatable...
There a *chough* very mainstream *chough* software developer that has been developing opteron optimized (32bit and 64bit is coming) software since it came out... But you didn't hear that from me ;)
Add that to the fact that not many professional projects rely on Intel compilers but rather uses those made by the mainstream developer previously cited, much of the arguement looks moot to me...
If it is true, though, then it's a major issue. It's one thing to have a compiler that optimizes for one type of hardware - it's another to have one that 'de-optimizes' against a rival. More importantly it's indicative of a policy to harm a rival un-competitively.
-
Zarax, that must be one hell of a NDA.
-
Sounds pretty much standard to me. I ****ing hate NDAs.... I can't actually say what i used to work on when I got for interviews, and it annoys the hell out of me.
-
Originally posted by Bobboau
Zarax, that must be one hell of a NDA.
Yeah, but it's a price I happily pay for all the great stuff I've got access to ;)
-
Well, whatever AMD is after, you can bet your arse it isn't hyperthreading. HT isn't so much a feature as it is a way of addressing weaknesses in the P4 architecture, and it even then it's fairly hit or miss whether it helps or hurts performance. In a core not designed for it, it just wouldn't help.
-
HT can help in certain situations as recent tests of a side by side comparison of the new duel core chips. With alot of applications running, Intel clearly wins.
-
Originally posted by redmenace
HT can help in certain situations as recent tests of a side by side comparison of the new duel core chips. With alot of applications running, Intel clearly wins.
http://news.com.com/AMD+edges+Intel+in+early+dual-core+benchmarks/2100-1006_3-5726935.html?tag=nefd.top
http://news.cnet.co.uk/desktops/0,39029662,39189666,00.htm
http://www.theinquirer.net/?article=22711
http://reviews.zdnet.co.uk/hardware/processorsmemory/0,39024015,39197754,00.htm
http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=2397&p=10
All beg to differ.
-
I'm definately rooting for the underdogs. My current system is AMD...their chips are top notch, I sell them to people whenever I can (I recommend them - people choose) and they are well priced. But I'm annoyed that you can't goto Dell (or HP/Compaq it seems either) and buy a AMD chip because even tho I don't like Dell I'd rather see people buy a AMD chip than Intel unless the Intel offers something they want.
HT is ok...I haven't used it, I hear its got some benefit but its sort of a interesting but ultimately not necessary sort of thing. The Athlon64 is very impressive on the other hand and I've read that the new 64X2 is quite a bit better than Intel's dual core attempt. I've also read that in single threaded applications, AMD's FX-57 is a winner take all in terms of performance.
So you know...I'd like to see the playing field leveled a bit. Intel makes good stuff often but its sometimes overly expensive compared to the AMD offering and I'd like to see the competition.
nVidia and ATI are having a wicked round of competition right now. Keeps the prices low...its good.
-
HT is kickass for things like Lightwave and 3dsMax that are SMP capable.
Btw, I'm not sure if its been mentioned but the debate isn't about discounts, etc. The case is about Intel forcing major OEMs to use Intel chips ONLY, in much the same way as Microsoft uses its market position to prevent major OEMs from selling naked (no OS) machines and/or selling machines preinstalled with competing OSes (Linux, BSD, BeOS, etc). AMD is just feeling rather bouncy and giddy since they just won this exact case in Japan, so they figure they'll go for a repeat in their biggest market.
-
All I will say is
AMD > Intel
-
I use one of each, a 1.7Ghz (1.4 Overclocked) for games, and a 3Ghz Intel system for my Lightwave stuff. The Intel performs awesomely on Lightwave, but I seem to have a lot more problems with keeping it cool (though, in it's defence, it is running at over twice the speed of the AMD).
The AMD is a good, solid little workhorse, which just keeps on ticking, even when it had to run 24/7 as the Internet server.
In total, I'd say that I've had less problems with the AMD system, however, a lot of the problems I've had with the Intel system couldn't really be blamed on the processor itself, so I really wouldn't like to say which is better, as such.
As far as the lawsuit is concerned, I think this really boils down more to busniess practice than the performance of the chips themselves ;)
-
True.
For what its worth, my AMD 2600+ is probably the most amazing chip I've ever used. Not because it performs so well in an application or whatever. Its done something far more amazing, in my opinion.
It routinely handles temps that are ridiculous: it ran at 101C for over a month before the fan bearing froze up, causing the system to shut down. One of my buddies (an engineer at AMD in Austin, Texas) said that its probably should have blown out spectacularly ("that chip should be glowing red slag", in his words).
-
In regaurds to HT and its performance, And take note I mentioned one specific situation and definatly not in general.
http://www.tomshardware.com/cpu/20050603/index.html
-
More news
http://www.theinquirer.net/?article=24350
-
My understanding RE: HT is that it requires software optimisation. Certainly it did for single-core; IIRC programmes which weren't optimised to load balance on HT chips would actually run slower than on a non-HT chip.
-
More news
http://www.tomshardware.com/business/20050712/index.html
http://www.tomshardware.com/hardnews/20050712_171125.html
-
Originally posted by aldo_14
My understanding RE: HT is that it requires software optimisation. Certainly it did for single-core; IIRC programmes which weren't optimised to load balance on HT chips would actually run slower than on a non-HT chip.
No.
Software that is not SMP capable will run on one core of a HT CPU. No loss. Programs like Lightwave and Max, etc, which are SMP aware, will split threads to as many cores (be they on the same die or seperate dies) as they can find.
-
I have only to add that I hope AMD stays in the chip making business. My Athlon XP 2700+ is the best chip I ever bought. Its damn fast...damn fast. Makes me want to say it twice.
Even when its two and a half years old now, its one of the best systems. I'm also partially biased because I built this machine myself. But I'm just so very impressed.
In a year or two time, I think another AMD offering will be seriously considered.
-
Originally posted by mikhael
No.
Software that is not SMP capable will run on one core of a HT CPU. No loss. Programs like Lightwave and Max, etc, which are SMP aware, will split threads to as many cores (be they on the same die or seperate dies) as they can find.
Actually, the hyperthreading setup is across logical, not physical processing 'cores'. Resources are shared across both logical processors, so you need to balance - optimize - executional threads to prevent deadlock or conflict, same as for software threads. Offhand, the dynamic scheduler used on the chip assigns tasks to aribtrary logical PUs; it's not a case of sending to a single logical PU, as the scheduler has no knowledge of which instruction belongs to which excecution thread (expressly that way; it's purpose it load balancing instructions across the logical PUs).
Within the Xeon specifically, the cache is - for example - shared between the logical threads. This is a specific bad point; there's no intelligent cache control to prevent one (excution) thread monopolizing it. Which of course can lead to thrashing and/or deadlock between threads. Benchmarks on HT processors shown performance degredation with non-optimized programs, likely as a result of aforementioned cache thrashing during memory intensive sections.
Hence, you need to optimise for HT processors to overcome the deficiencies within the architecture and take advantage of potential performance improvements. (same as any architecture; difference is that Ht was operating within the general x86 architecture shared with multiple other chips)
-
http://www.tomshardware.com/hardnews/20050901_200055.html
-
ATM I don't feel a need to go pointing fingers at people for AMD's market position. I'm more than happy with my AMD64 processor, hyperthreading is pretty much what drove me away from Intel, because under Windows 2000 it seemed to make the CPU appear as two separate ones with half the processor power.
-
Originally posted by WMCoolmon
ATM I don't feel a need to go pointing fingers at people for AMD's market position. I'm more than happy with my AMD64 processor, hyperthreading is pretty much what drove me away from Intel, because under Windows 2000 it seemed to make the CPU appear as two separate ones with half the processor power.
Which is precisely why I have it turned off. A largely useless feature, I'll admit, but harmless when disabled.
-
So wait a sec AMD claim that Intel are artificially inflating CPU prices and instead of selling their processors at a reduced, more realistic price and making a killing that way they instead simply sell their own processors at the same artificially inflated price and then ***** about it in an anti-trust case?
:wtf:
Someone really needs to explain simple economics to these guys.