Saturday, 28 February 2009

SCO v.s IBM

Summary

On March 6, 2003, the SCO Group (formerly known as Caldera Systems) filed a $1 billion lawsuit in the US against IBM for allegedly “devaluing” its version of the UNIX operating system. The amount of alleged damages was later increased to $3 billion, and then $5 billion. SCO claimed that IBM had, without authorization, contributed SCO's intellectual property to the codebase of the open source, Unix-like Linux operating system. In May 2003 SCO Group sent letters to members of the Fortune 1000 and Global 500 companies warning them of the possibility of liability if they use Linux.
The claims and counter-claims made by both sides then escalated, with both IBM and Linux distributor Red Hat starting legal action against SCO, SCO threatening Linux users who do not take out SCO UNIX licenses, and SCO suing Novell (see also SCO-Linux controversies), AutoZone and DaimlerChrysler.
On September 30, 2003, Judge Kimball (the presiding federal district judge) granted the SCO Group's request for a delay until February 4, 2004, “to file any amended pleadings or add parties to this action”. The schedule was amended again on July 1, 2005. In December 2006 the trial date was vacated pending the resolution of SCO's litigation with Novell, all parties agreeing that SCO v. Novell would resolve issues relating to SCO v. IBM.
In an “Order Granting in Part IBM's Motion to Limit SCO's Claims” dated June 28, 2006, Judge Brooke Wells (the federal magistrate judge presiding over discovery aspects of the case) barred SCO from asserting 187 of the 298 allegedly misused items that IBM had moved to exclude from the lawsuit for lack of specificity,[1] stating “many of SCO’s arguments and much of Mr. Rochkind’s declaration miss the mark”, and comparing SCO's tactics with those of an officer who accuses a citizen of theft, but will not disclose what the citizen is accused of stealing. “Certainly if an individual was stopped and accused of shoplifting after walking out of Neiman Marcus, they would expect to be eventually told what they allegedly stole. It would be absurd for an officer to tell the accused that ‘you know what you stole I'm not telling.’ Or, to simply hand the accused individual a catalog of Neiman Marcus' entire inventory and say ‘it's in there somewhere, you figure it out.’”[1][2]
On August 10, 2007 Judge Kimball, who also presides over the SCO v. Novell case, ruled that Novell, not the SCO Group, is the rightful owner of the copyrights covering the Unix operating system. The court also ruled that "SCO is obligated to recognize Novell's waiver of SCO's claims against IBM and Sequent". After the ruling Novell announced they have no interest in suing people over Unix and stated "We don't believe there is Unix in Linux".[3][4][5][6]
In a order entered on 21 September 2007, Judge Kimball administratively closed the case of SCO v. IBM due to SCO filing for bankruptcy on 14 September 2007. This means that all action in SCO v. IBM is stayed until SCO emerges from bankruptcy proceedings. If and when it does, the case SCO v. IBM will resume where it left off.[7]
 SCO's claims

SCO's lawsuit has been consistent only in its claim of breach of contract[8][9] (since the abandonment in early 2004 of its claim of misappropriation of trade secrets). SCO's initial claims were:[8]
Misappropriation of trade secrets
Unfair competition
Interference with contract
Breach of IBM Software Agreement
On July 22, 2003, SCO amended its complaint. It added two new claims:[10]
Breach of IBM Sublicensing Agreement
Breach of Sequent Software Agreement
On February 27, 2004 SCO amended the complaint again. It dropped the trade secrets claim, but added the following claims:[9]
Breach of Sequent Sublicensing Agreement
Copyright infringement
Interference with contract
Interference with business relationships
SCO's claims in press releases and interviews have changed repeatedly as the affair has progressed. SCO has also both claimed and denied that the alleged copyright violations involved the Linux kernel.[11] Computerworld reported Chris Sontag of SCO as saying:
It's very extensive. It is many different sections of code ranging from five to ten to fifteen lines of code in multiple places that are of issue, up to large blocks of code that have been inappropriately copied into Linux in violation of our source-code licensing contract. That's in the kernel itself, so it is significant. It is not a line or two here or there. It was quite a surprise for us.[12]
SCO refuses to allow access to the samples of code containing the alleged copyright violations except under a non-disclosure agreement (NDA). SCO's NDA would not only require that the signer keep confidential which lines of code SCO contested, but would also require that they hold confidential any information SCO told them, even if they already knew that information before being informed of it by SCO; all Linux kernel developers have considered this to be far too restrictive, so none of them have signed it. However, at SCO's annual reseller's convention in August 2003 they revealed two short sections of code they alleged were copyright violations, and images of Darl McBride's presentation of this code were soon after published on German computer magazine publisher Heinz Heise's website.[13]
On May 30, 2003, SCO Group's CEO Darl McBride was quoted as saying that the Linux kernel contained "hundreds of lines" of code[14] from SCO's version of UNIX, and that SCO would reveal the code to other companies under NDA in July.[15] To put this into context, David Wheeler's SLOCCount estimates the size of the Linux 2.4.2 kernel as 2,440,919 source lines of code out of over 30 million physical source lines of code for a typical GNU/Linux distribution. Therefore, as per SCO's own estimate, the allegedly infringing code would make up about 0.001% of the total code of a typical GNU/Linux installation.[16] SCO has since upwardly revised this figure to over a million lines of code, however.[17][18][19]
SCO's major claims have now been reported as relating to the following components of the Linux kernel:
symmetric multiprocessing (SMP),
non-uniform memory access (NUMA) multiprocessing,
the read-copy-update (RCU) locking strategy,
This technique is widely believed to have been developed at Sequent Computer Systems, who were then bought by IBM, who holds several patents (including patent 5,442,758 ) on this technique.
SGI's Extended File System (XFS),
IBM's JFS journaling file system
These claims flow from the accusation of breach of contract. The contract between IBM and AT&T (to which SCO claims to be successor in interest) allows IBM to use the SVR4 code, but the SVR4 code, plus any derivative works made from that code, must be held confidential by IBM. According to IBM's interpretation of the contract, and the interpretation published by AT&T in their "$ echo" newsletter in 1985, "derivative works" means any works containing SVR4 code. But according to SCO's interpretation, "derivative works" also includes any code built on top of SVR4, even if that does not contain, or even never contained, any SVR4 code. Thus, according to SCO, any AIX operating system code that IBM developed must be kept confidential, even if it contains nothing from SVR4.
On August 10, 2007 a federal district court judge in Utah ruled that Novell, not the SCO Group, is the rightful owner of the copyrights covering the Unix operating system.
 Free software and open source community reaction


This article needs additional citations for verification. Please help improve this article by adding reliable references. Unsourced material may be challenged and removed. (March 2008)
The lawsuit caused moral indignation and outrage in the free software and open source communities, who consider SCO's claims to be without merit and even cynically dishonest. Open source advocates' arguments include:
that SCO does not even own the code in question. SCO has often called themselves "The owner of the UNIX operating system." But that claim is dubious at best. SCO certainly has no clear claim to SVR4 code. This view is now upheld by summary judgment in the SCO vs Novell Slander of Title case.
that the Linux operating system was unlikely to contain UNIX code, as it had been written from scratch by hundreds of collaborators, with a well-documented provenance and revision history that was entirely in the public view;
that it made no technical sense to incorporate SCO UNIX code in Linux, as Linux had the technical features that are claimed to have been appropriated already implemented before SCO UNIX had them;
that even if Linux and SCO UNIX had some code in common, this did not necessarily mean that this code was copied to Linux from SCO UNIX -- perhaps the common pieces of code had been legitimately copied from another open source operating system, perhaps a BSD-derived one, or one of the historical UNIX versions previously released by SCO;
that Caldera Systems had begun as a Linux company before buying SCO's UNIX business and certain assets related to it, and has added many Linux-like features to SCO UNIX, and any common code may have in fact been copied from Linux into SCO UNIX:
and furthermore, that if such reverse copying from Linux itself had occurred, that the distribution of SCO UNIX binaries containing GPL'd contributions may therefore require SCO either to remove their product from the market until GPL'd code has been removed, or to release their source code under the GPL to their users;
that even if Linux did contain copied SCO UNIX code, the UNIX source code had already been made widely available without a non-disclosure agreement, and therefore had no trade secret status (as a judge found in USL v. BSDi);
that even if Linux did contain some UNIX code, the SCO Group had lost any right to sue IBM for trade secret or other intellectual property infringement by distributing Linux itself (their Caldera distribution) under the GNU General Public License (GPL), both before and after their announcement, which precludes them from pursuing any other user of Linux.[20][21]
SCO and its officers have been the subject of much criticism by the free software community, some of whom have stated that SCO's behavior may amount to illegal conduct.[22] SEC filings[where?] show that senior SCO executives dumped their personal holdings in SCO shortly after counter-suits were filed by IBM and Red Hat. SCO Group's CEO Darl McBride has been the subject of particular criticism, because of his extreme statements to the press.
On March 10, 2003, the Open Source Initiative (OSI) released a position paper on the SCO v. IBM complaint, written by Eric S. Raymond, president of the OSI and author of The Cathedral and the Bazaar.[23]
On May 16, 2003, Groklaw, a website founded by journalist/paralegal Pamela Jones began covering the SCO litigation on a daily basis, and became a voice for the community to express its views of SCO's claims, as well as being an experiment in applying Open Source principles to legal research. The SCO Group has singled the site out as a particular thorn in its side.[24]
On May 30, 2003, Linus Torvalds, developer of the Linux kernel, was quoted as saying, regarding the case:
Quite frankly, I found it mostly interesting in a Jerry Springer kind of way. White trash battling it out in public, throwing chairs at each other. SCO crying about IBM's other women. ... Fairly entertaining.
—,[25] paragraph 7
The Inquirer reported on June 15, 2003, that an unnamed Linux kernel programmer has written to SCO, threatening action based on their distribution of a Linux distribution that, according to their own claims, contains code not licensed under the GPL. According to the letter reproduced there, the programmer claimed that SCO's doing so was an infringement of his own copyright. SCO's response to this letter is not known.[26]
In an interview on June 23, 2003, Torvalds responded to SCO's allegation that Linux development had no process for vetting kernel contributions:[27]
I allege that SCO is full of it, and that the Linux process is already the most transparent process in the whole industry. Let's face it, nobody else even comes close to being as good at showing the evolution and source of every single line of code out there.
On June 27, 2003, Eben Moglen, the counsel for the Free Software Foundation, released a fuller statement regarding the SCO lawsuit. In this statement, he reiterates many of the points made above, and states that:[21]
As to its trade secret claims, which are the only claims actually made in the lawsuit against IBM, there remains the simple fact that SCO has for years distributed copies of the kernel, Linux, as part of GNU/Linux free software systems. [...] There is simply no legal basis on which SCO can claim trade secret liability in others for material it widely and commercially published itself under a license that specifically permitted unrestricted copying and distribution.
On July 31, 2003, the Open Source Development Labs released a position paper on the ongoing conflict,[28][29] written by the FSF's Eben Moglen.
 Accusations of creating fear, uncertainty and doubt
A number of Linux supporters have characterized SCO's actions as an attempt to create fear, uncertainty and doubt about Linux. Many believe that SCO's aim is to be bought out by IBM.[30] Others have pointed to Microsoft's subsequent licensing of the SCO source code as a possible quid pro quo for SCO's action.[31]
Univention GmbH, a Linux integrator, reported[32][33] on May 30, 2003 it was granted an injunction by a Bremen court under German competition law that prohibits the SCO Group's German division from claiming that Linux contains illegally obtained SCO intellectual property. If the SCO Group continued to express this position, they would have to pay a fine of €250,000. A similar injunction was sought around the same time in Poland.[34]
On July 23, Open Source Victoria announced that they had filed a complaint with the Australian Competition and Consumer Commission, "asking the ACCC to investigate the SCO Group's activities in light of their unsubstantiated claims and their extortive legal threats for money against possibly hundreds of thousands of Australians."[35]
SCO Group then filed subpoenas for Richard Stallman and Linus Torvalds on November 13, 2003.[36]
 The GPL issue

Within a few months of the filing of the lawsuit, Eben Moglen, the Free Software Foundation's legal counsel, stated that SCO's suit should not concern Linux users other than IBM. In an interview with internetnews.com, he was reported as saying:[20]
There is absolute difficulty with this line of argument which ought to make everybody in the world aware that the letters that SCO has put out can be safely put in the wastebasket... From the moment that SCO distributed that code under the GNU General Public License, they would have given everybody in the world the right to copy, modify and distribute that code freely... From the moment SCO distributed the Linux kernel under GPL, they licensed the use. Always. That's what our license says.
Apparently noticing the incongruity of their selling a Linux distribution while suing IBM for stealing their intellectual property and giving it to the developers of that operating system, the SCO Group then announced on May 14, 2003 that they would no longer distribute Linux. According to their press release,[37] "SCO will continue to support existing SCO Linux and Caldera OpenLinux customers and hold them harmless from any SCO intellectual property issues regarding SCO Linux and Caldera OpenLinux products."
SCO currently claims:[38][39]
Any code belonging to SCO that might have been GPL'd was done by SCO employees without proper legal authorization, and thus is not legally GPL'd.
That for code to be GPL'd, the code's copyright owner must put a GPL notice before the code, but since SCO itself was not the one to add the notices, the code was never GPL'd.
 GPL and the US Constitution
During a certain period of its litigation against IBM, SCO alleged that the GPL violates the United States Constitution. This allegation was dropped however from SCO's claims in April 2004 in "SCO's Answer to IBM's Second Amended Counterclaims".[40]
SCO originally based its views on the following considerations:
Section 8 of Article One of the United States Constitution states that
[Congress shall have power] to promote the progress of science and useful arts, by securing for limited times to authors and inventors the exclusive right to their respective writings and discoveries.
Since the GNU General Public License for the most part disclaims exclusive rights, SCO claimed that its use violates this clause. SCO's argument asks the court to limit both Congress's discretion in implementing the copyright clause, which the Supreme Court refused to do in Eldred v. Ashcroft, and copyright holders' discretion over the enjoyment of their exclusive rights. The GPL specifically prohibits, in section 7, distribution of software in jurisdictions where the laws are incompatible with the GPL, so a ruling that upheld SCO's constitutional argument would prevent distribution of Linux (and other copylefted software) in the United States.
Other commentators disagree however. One such commentator, Tom Carey, partner and chairman of a Boston intellectual property law firm, even went so far as to say "Attacks on the GPL are far-fetched and a little bit desperate."[41] Stacey Quandt, principal analyst at Quandt Analytics, remarked, "SCO's prior claim that the GPL was unconstitutional was equivalent to Microsoft's claims about open source being un-American — totally ridiculous.".[41]
Professor Eben Moglen, on leave from the Columbia University law faculty for the year 2006-2007, speaking as counsel to the Free Software Foundation (FSF) who is responsible for drafting the GPL, also takes this view. He says, "I believe the constitutionality attack on the GPL is not a tenable legal argument but is rather a public relations argument." In a talk at Harvard in February, he addressed the issue of constitutionality by referring to Congress' recent extension of copyright term limits. "It turns out that there's no such thing as an unconstitutional copyright rule," he said, "if Congress passes it, and if it observes the distinction between expression and idea."[42]
 Novell enters the controversy

Main article: SCO v. Novell
Novell entered the controversy by publishing on May 28, 2003, a press release concerning the SCO Group's ownership of UNIX. "To Novell's knowledge, the 1995 agreement governing SCO's purchase of UNIX from Novell does not convey to SCO the associated copyrights," a letter to the SCO Group's CEO Darl McBride said in part. "We believe it unlikely that SCO can demonstrate that it has any ownership interest whatsoever in those copyrights. Apparently you share this view, since over the last few months you have repeatedly asked Novell to transfer the copyrights to SCO, requests that Novell has rejected."
SCO later claimed to have discovered an amendment to their contract with Novell transferring partial ownership to SCO. Novell stated that the amendment "appears to bear a valid Novell signature, and the language, though convoluted, seems to support SCO's claim that ownership of some copyrights for Unix did transfer to SCO"; Novell also said that it could not find its own copy of the amendment.
But in subsequent letters to SCO that Novell released as part of a press release on December 22, 2003, Joseph LaSala Jr., Novell's general counsel, argued that the amendment provided for a copyright transfer only under certain conditions that SCO has allegedly failed to meet.
SCO was quick to dismiss Novell's claims. The same day, during a conference call to discuss SCO's quarterly financial results, SCO CEO Darl McBride said "We see this as a fraudulent filing of copyright notices ... and we'll take the appropriate measures as necessary with our legal team." SCO made good on this threat on January 20, 2004, when it filed SCO v. Novell. On August 10, 2007, Judge Kimball issued a ruling which says in part "the court concludes that Novell is the owner of the UNIX and UnixWare copyrights." This decision is expected to impact the SCO v. IBM since the ruling states that Novell "is entitled, at its sole discretion, to direct SCO to waive its claims against IBM and Sequent".[43][5]
 IBM's AIX license

Reuters reported that the SCO Group intended to revoke IBM's license to use UNIX code in their AIX operating system on Friday, June 13, 2003 if no resolution is reached before then. IBM responded that they believe that SCO has no power to do so, as their license is "irrevocable". On the following Monday, June 16, 2003, CNET News.com reported that SCO had announced it had terminated IBM's license. IBM continues to distribute and support AIX, and the SCO Group now states that they will be seeking an injunction to force IBM not only to stop selling and supporting AIX, but also to return to the SCO Group or destroy all copies of the AIX operating system. IBM's continued distribution of AIX is the basis of SCO's copyright claim.
On June 9, however, Novell privately conversed with SCO expressing their belief that SCO did not have rights to terminate the license. Three days later, Novell cited Section 4.16(b) of their Asset Purchase Agreement (APA) with SCO that gave Novell the ability to intercede in the dispute between SCO and IBM and waived SCO's rights to terminate the license.[44]
On August 10, 2007, Judge Kimball ruled that Novell was the owner of UNIX and thus could waive SCO's termination of IBM's license.[45]
 IBM counterclaims against SCO

On August 6, 2003, IBM filed its counterclaims against SCO.[46][47] It made 10 counterclaims:
breach of contract
Lanham Act violation
Unfair competition
Intentional interference with prospective economic relations
Unfair and deceptive trade practices
Breach of the GNU General Public License
and four counts of patent infringement
In response to these counterclaims, SCO asserted that the GPL is unenforceable, void, and violates the United States Constitution, but later dropped that claim. If these claims are true, then the GPL'd applications that SCO continues to distribute (like Samba) are being distributed without the permission of the copyright owners of those applications (since the permission was the GPL itself), which would be illegal. Thus some speculate that, in order to remain legally consistent, SCO will claim that software that has been GPL'd is actually in the public domain.
On September 25, 2003 IBM amended its counterclaims bringing the total number of counterclaims to 13. The new counterclaims are:
Copyright infringement
This counterclaim involves an alleged copyright infringement by SCO of GPL-licensed IBM code in the Linux kernel. Some commentators have pointed out that if SCO manages to invalidate the GPL, they are highly likely to be caught by this counterclaim, as it is of the same form as their claim against IBM.[48]
Promissory estoppel
Declaratory judgment
On March 29, 2004 IBM amended its counterclaims again. It dropped one of the patent infringement claims, but added 2 new Declaratory judgments of Noninfringement of Copyrights. One of these seeks a declaration that IBM's AIX-related activities do not infringe any of SCO's copyrights. The other one seeks a similar declaration about IBM's Linux-related activities.
 Discovery

The discovery portion of the lawsuit has been dragging on for several years. The basis for SCO's suit is that any code developed on top of SVRX is a derivative work of SVRX (which would include AIX), and that IBM has publicly admitted to contributing AIX code to the Linux kernel. Since SCO has never seen the AIX code, it has, as part of the discovery process, deposed IBM for the AIX code, so that it can compare AIX code to Linux kernel code. IBM, rejecting SCO's concept of derivative work, has deposed SCO for which lines of code it claims are infringing. SCO has responded that it can't determine which code is infringing until it has had the chance to look at the AIX code.
On December 5, 2003, in the first oral arguments relating to the discovery process, a judge granted IBM's two motions to compel against SCO, and deferred consideration of SCO's motions until later. This gave SCO a 30 day deadline to provide "with specificity" which lines of code in Linux they claim form the basis of their case. This was widely regarded as a first-round victory for IBM.[49][50]
On June 28, 2006 Judge Brooke Wells granted IBM's motion to strike most of SCO's evidence, citing in part SCO's inability to provide the specificity required by the court:
In December 2003, near the beginning of this case, the court ordered SCO to, "identify and state with specificity the source code(s) that SCO is claiming form the basis of their action against IBM." Even if SCO lacked the code behind methods and concepts at this early stage, SCO could have and should have, at least articulated which methods and concepts formed "the basis of their action against IBM." At a minimum, SCO should have identified the code behind their method and concepts in the final submission pursuant to this original order entered in December 2003 and Judge Kimball’s order entered in July 2005.
—[1] (paragraph 30)
SCO appealed to Judge Kimball and asked for a de novo review of Judge Wells' order.[51] On November 29, 2006, Judge Dale Kimball affirmed Judge Wells' order in its entirety.[52]
 Controversial code

At a reseller show in August 2003, SCO revealed a sample of alleged copied code. This was later shown to be originally released under a BSD License.[53]
The code (atealloc) has been in the IA64 version of Linux for a short period of time. It is no longer in Linux after having been removed on July 4, 2003, since much better alternatives existed.[54][55]
UNIX creator Dennis Ritchie confirms that either he or Ken Thompson wrote the atealloc code, which is released under the BSD licence.[56][57] It is claimed that SCO removed the original license text from UNIX source, allegedly violating the BSD licence.[58]
 Copyright claims and DMCA notices

In late December 2003, new developments involving copyright claims emerged.
Novell registered their claim to the copyright of original UNIX source code, effectively challenging SCO's registration of the same code.[59][60]
SCO Group claimed in a press release to have sent DMCA notification letters alleging copyright infringement.[61][62] Alleged copies of these letters were posted online.[63][64] The letters give the names of 65 files in the Linux source code tree which supposedly incorporate "copyrighted binary interfaces". Linus Torvalds then posted a rebuttal on Groklaw.

Friday, 20 February 2009

Redirected from AMD Virtualization- x86 virtualization

This article may require copy-editing for grammar, style, cohesion, tone or spelling. You can assist by editing it now. A how-to guide is available. (August 2008)


Ubuntu running on Windows Vista, an example of virtualization
x86 virtualization is the method by which x86-based "guest" operating systems are run under another "host" x86 operating system, with little or no modification of the guest OS. The x86 processor architecture did not originally meet the Popek and Goldberg virtualization requirements. As a result, it was very difficult to implement a general virtual machine on an x86 processor. In 2005 and 2006, extensions to their respective x86 architectures by Intel and AMD resolved this and other virtualization difficulties.
Contents [hide]
1 Software techniques
2 Hardware support
2.1 AMD virtualization (AMD-V)
2.2 Intel Virtualization Technology for x86 (Intel VT-x)
2.3 IOMMU
2.4 A note on 64-bits Guests
2.5 Virtualization features activation
2.6 Software using AMD-V and/or Intel VT
2.6.1 Open source
2.6.2 Closed source
3 See also
4 References
 Software techniques

On February 8, 1999, VMware introduced the first x86 virtualization product, "VMware Virtual Platform", based on earlier research by its founders at Stanford University. VMware filed for a patent on their techniques in October 1998, which was granted as U.S. Patent 6,397,242  on May 28, 2002. VMware and similar virtualization software for the x86 must employ binary translation techniques to trap and virtualize the execution of certain instructions. These techniques incur some performance overhead as compared to a VM running on a natively virtualizable architecture such as the IBM System/370 or Motorola MC68020.
Kevin Lawton started the Plex86 project (originally called "freemware") to create Free software for x86 virtualization. The focus of this project has since changed to support only Linux as a guest operating system, but prior to that, Lawton published the paper Running multiple operating systems concurrently on an IA32 PC using virtualization techniques, which gives an analysis of what aspects of the x86 architecture are hard to virtualize and some techniques to overcome these difficulties.
Microsoft offers three Windows-based x86 virtualization products: Microsoft Virtual PC and Microsoft Virtual Server, based on technology they acquired from Connectix, as well as Hyper-V.
Open source alternatives include QEMU and VirtualBox.
The research systems Denali, L4, and Xen explored ways to provide high performance virtualization of x86 by implementing a virtual machine that differs from the raw hardware. Operating systems are ported to run on the resulting virtual machine, which does not implement the hard-to-virtualize parts of the actual x86 instruction set. This technique is known as paravirtualization. As of 3.0 Xen also now supports full virtualization with an unmodified guest OS provided hardware-assisted virtualization support (i.e., Intel VT or AMD-V) is available.
 Hardware support


This section needs additional citations for verification.
Please help improve this article by adding reliable references. Unsourced material may be challenged and removed. (January 2009)
Intel and AMD have independently developed virtualization extensions to the x86 architecture. They are not directly compatible with each other, but serve largely the same functions. Either will allow a virtual machine hypervisor to run an unmodified guest operating system without incurring significant emulation performance penalties.
 AMD virtualization (AMD-V)
AMD's virtualization extensions to the 64-bit x86 architecture is named AMD Virtualization, abbreviated AMD-V. It is still referred to as "Pacifica", the AMD internal project code name.
AMD-V is present in AMD Athlon 64 and Athlon 64 X2 with family "F" or "G" on socket AM2 (not 939), Turion 64 X2, Opteron 2nd generation[1] and 3rd generation[2], Phenom, and all newer processors. Sempron processors do not include support for AMD-V.
On May 23, 2006, AMD released the Athlon 64 ("Orleans"), the Athlon 64 X2 ("Windsor") and the Athlon 64 FX ("Windsor") as the first AMD processors to support AMD-V. Prior processors do not have AMD-V.
AMD has published a specification for a technology named IO Memory Management Unit (IOMMU) to AMD-V. This provides a way of configuring interrupt delivery to individual virtual machines and an IO memory translation unit for preventing a virtual machine from using DMA to break isolation. The IOMMU also plays an important role in advanced operating systems (absent virtualization) and the AMD Torrenza architecture.
 Intel Virtualization Technology for x86 (Intel VT-x)
Previously codenamed "Vanderpool", VT-x is Intel's technology for virtualization on the x86 platform. Intel plans to add Extended Page Tables (EPT),[3] a technology for page table virtualization,[4] in the upcoming Nehalem architecture.[5]
The following modern Intel processors include support for VT-x,[6]:
Pentium 4 662 and 672
Pentium Extreme Edition 955 and 965 (not Pentium 4 Extreme Edition with HT)
Pentium D 920-960 except 945, 935, 925, 915
some models of the Core processors family
some models of the Core 2 processors family
Xeon 3000 series
Xeon 5000 series
Xeon 7000 series
Neither Intel Celeron, Pentium Dual-Core, Atom nor Pentium M processors have VT technology.
 IOMMU
Main article: IOMMU
A input/output memory management unit (IOMMU) enables guest virtual machines to directly use peripheral devices, such as Ethernet and accelerated graphics cards, through DMA and interrupt remapping. Both AMD and Intel have released specifications. AMD calls it by what it is ("IOMMU") and Intel calls their implementation "Intel's Virtualization Technology for Directed I/O (VT-d)".
 A note on 64-bits Guests
It is possible to run a 64-bit guest on a 32-bit host OS, if the underlying processor is 64-bit and supports virtualization extensions, however not all platforms support this. It should be noted, however, that a 32-bit host OS's memory addressing limits can become problematic, and users should generally install 64-bit operating systems on 64-bit capable processors.
 Virtualization features activation
Intel's VT-x feature need to be activated by the BIOS in order to be available to applications. Most computer and motherboard/BIOS/Chipset manufacturers disable this support by default but make an option available to activate it, some do not. AMD CPUs that support AMD-V always have this feature enabled, and therefore are not affected by this problem.
 Software using AMD-V and/or Intel VT
The following software is known to conditionally make use of virtualization technology features:
 Open source
Kernel-based Virtual Machine (KVM) - a Linux kernel module and hypervisor. It supports both architectures (AMD-V and VT-x) and requires one of them. Supports real-time guests.
VirtualBox runs on Windows, Linux, OSX and Solaris. It supports both architectures. [7]
Xen — Xen is a separate and independent operating system that virtualizes everything else on the machine. It supports both architectures, but does not require them for supported guest OS's.
Blue Pill (proof of concept malware)
 Closed source
Hyper-V - Microsoft's Windows Server 2008 hosted platform. Require hardware virtualization support [8]
LynxSecure - Secure MILS Hypervisor from LynuxWorks Supports Intel VT-x and VT-d.
Microsoft Virtual Server — Virtual Server 2005 R2 SP1 supports hardware assisted virtualization.[clarification needed][9][10]
Microsoft Virtual PC
Oracle VM - Oracle VM Server (GPL license) uses the Xen hypervisor; while Oracle VM Manager is closed source. [11]
Parallels Workstation and Parallels Desktop for Mac — lightweight hypervisor with Intel VT-x and AMD-V support.
Parallels Server (Beta) — Enterprise version of Parallels Workstation and Desktop for Mac. It will support Intel's IOMMU, VT-d.
Padded Cell - virtual machine technology from Green Hills Software hosted on INTEGRITY real-time operating system. Supports both architectures.
Real-Time Systems RTS Real-Time Hypervisor for x86
Sun xVM - xVM Server is based on Xen on x64
Virtual Iron - Supports both architectures.
VirtualLogix - Supports both architectures.
VMware Workstation, VMware Fusion, VMware Server — Recent versions support both architectures.[12]
VMware ESX Server - Requires hardware support to run 64 bit virtual machines.
VMware Server - Requires hardware support to run 64 bit virtual machines.

Sockets- AMD

Socket 754: The Athlon 64 value/budget line, 64-bit memory interface (Single-Channel)
Socket 939: Athlon 64 performance line, Athlon 64 X2s, and newer Athlon 64 FXs, Opteron, 128-bit memory interface (Dual-channel)
Socket 940: Opteron and old Athlon 64 FX, 128-bit memory interface - requires registered DDR memory
Socket AM2: Athlon 64/Athlon 64 FX/Athlon 64 X2/Sempron, 940 Pins (Not compatible with Socket 940); the first AMD socket to use DDR2 SDRAM.
Socket F: Opteron, 1207 Pins
Socket F (1207 FX): Athlon 64 FX on AMD Quad FX platform, also compatible for dual-processor Opteron 2200 series[59]
At the introduction of Athlon 64 in September 2003, only Socket 754 and Socket 940 (Opteron) were ready and available. The onboard memory controller was not capable of running unbuffered (non-registered) memory in dual-channel mode at the time of release; as a stopgap measure, they introduced the Athlon 64 on Socket 754, and brought out a non-multiprocessor version of the Opteron called the Athlon 64 FX, as a multiplier unlocked enthusiast part for Socket 940, comparable to Intel's Pentium 4 Extreme Edition for the high end market.
In June 2004, AMD released Socket 939 as the mainstream Athlon 64 with dual-channel memory interface, leaving Socket 940 solely for the server market (Opterons), and relegating Socket 754 as a value/budget line, for Semprons and slower versions of the Athlon 64. Eventually Socket 754 replaced Socket A for Semprons.
In May 2006, AMD released Socket AM2, which provided support for the DDR2 memory interface. Also, this marked the release of AMD-V.
In August 2006, AMD released Socket F for Opteron server CPU which uses the LGA chip form factor.
In November 2006, AMD released a specialized version of Socket F, called 1207 FX, for dual-socket, dual-core Athlon FX processors on the Quad FX platform. While Socket F Opterons already allowed for four processor cores, Quad FX allowed unbuffered RAM and expanded CPU/chipset configuration in the BIOS. Consequentially, Socket F and F 1207 FX are incompatible and require different processors, chipsets, and motherboards.
 Athlon 64 FX models


It has been suggested that this article or section be merged into List of AMD Athlon 64 microprocessors. (Discuss)
 Sledgehammer (130 nm SOI)
CPU-Stepping: C0, CG
L1-Cache: 64 + 64 KB (Data + Instructions)
L2-Cache: 1024 KB, fullspeed
MMX, Extended 3DNow!, SSE, SSE2, AMD64
Socket 940, 800 MHz HyperTransport (HT800)
Registered DDR-SDRAM required
VCore: 1.50/1.55 V
Power Consumption (TDP): 89 Watt max
First Release: September 23, 2003
Clockrate: 2200 MHz (FX-51, C0), 2400 MHz (FX-53, C0 and CG)
 Clawhammer (130 nm SOI)
CPU-Stepping: CG
L1-Cache: 64 + 64 KB (Data + Instructions)
L2-Cache: 1024 KB, fullspeed
MMX, Extended 3DNow!, SSE, SSE2, AMD64
Socket 939, 1000 MHz HyperTransport (HT1000)
VCore: 1.50 V
Power Consumption (TDP): 89 Watt (FX-55:104 Watt)
First Release: June 1, 2004
Clockrate: 2400 MHz (FX-53), 2600 MHz (FX-55)
 San Diego (90 nm SOI)
CPU-Stepping: E4, E6
L1-Cache: 64 + 64 KB (Data + Instructions)
L2-Cache: 1024 KB, fullspeed
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool'n'Quiet, NX Bit
Socket 939, 1000 MHz HyperTransport (HT1000)
VCore: 1.35 V or 1.40 V
Power Consumption (TDP): 104 Watt max
First Release: April 15, 2005
Clockrate: 2600 MHz (FX-55), 2800 MHz (FX-57)
 Toledo (90 nm SOI)
Dual-core CPU
CPU-Stepping: E6
L1-Cache: 64 + 64 KB (Data + Instructions), per core
L2-Cache: 1024 KB fullspeed, per core
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool'n'Quiet, NX Bit
Socket 939, 1000 MHz HyperTransport (HT1000)
VCore: 1.30 V - 1.35 V
Power Consumption (TDP): 110 Watt max
First Release: January 10, 2006
Clockrate: 2600 MHz (FX-60)
 Windsor (90 nm SOI)
Dual-core CPU
CPU-Stepping: F2, F3
L1-Cache: 64 + 64 KB (Data + Instructions), per core
L2-Cache: 512 - 1024 KB fullspeed, per core
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool'n'Quiet, NX Bit, AMD-V
Socket AM2, 1000 MHz HyperTransport (HT1000)
VCore: 1.30 V - 1.40 V
Power Consumption (TDP): 125 Watt max
First Release: May 23, 2006
Clockrate: 2000 - 3200 MHz (6400+)
 Windsor (90 nm SOI) - Quad FX platform
Main article: AMD Quad FX platform
Dual-core, dual CPUs (four cores total)
CPU-Stepping: F3
L1-Cache: 64 + 64 KB (Data + Instructions), per core
L2-Cache: 1024 KB fullspeed, per core
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool'n'Quiet, NX Bit, AMD-V
Socket F (1207 FX), 2000 MHz HyperTransport (HT2000)
VCore: 1.35 V - 1.40 V
Power Consumption (TDP): 125 Watt max per CPU
First Release: November 30, 2006
Clockrate: 2600 MHz (FX-70), 2800 MHz (FX-72), 3000 MHz (FX-74)
 Athlon 64 models


It has been suggested that this article or section be merged into List of AMD Athlon 64 microprocessors. (Discuss)
 Clawhammer (130 nm SOI)
CPU-Stepping: C0, CG
L1-Cache: 64 + 64 KB (Data + Instructions)
L2-Cache: 1024 KB, fullspeed
MMX, Extended 3DNow!, SSE, SSE2, AMD64, Cool'n'Quiet, NX Bit (only CG)
Socket 754, 800 MHz HyperTransport (HT800)
Socket 939, 1000 MHz HyperTransport (HT1000)
VCore: 1.50 V
Power Consumption (TDP): 89 Watt max
First Release: September 23, 2003
Clockrate: 2000–2600 MHz
 Newcastle (130 nm SOI)
Also possible: ClawHammer-512 (Clawhammer with partially disabled L2-Cache)
CPU-Stepping: CG
L1-Cache: 64 + 64 KB (Data + Instructions)
L2-Cache: 512 KB, fullspeed
MMX, Extended 3DNow!, SSE, SSE2, AMD64, Cool'n'Quiet, NX Bit
Socket 754, 800 MHz HyperTransport (HT800)
Socket 939, 1000 MHz HyperTransport (HT1000)
VCore: 1.50 V
Power Consumption (TDP): 89 Watt max
First Release: 2004
Clockrate: 1800–2400 MHz
 Winchester (90 nm SOI)
CPU-Stepping: D0
L1-Cache: 64 + 64 KB (Data + Instructions)
L2-Cache: 512 KB, fullspeed
MMX, Extended 3DNow!, SSE, SSE2, AMD64, Cool'n'Quiet, NX Bit
Socket 939, 1000 MHz HyperTransport (HT1000)
VCore: 1.40 V
Power Consumption (TDP): 67 Watt max
First Release: 2004
Clockrate: 1800–2200 MHz
 Venice (90 nm SOI)
CPU-Stepping: E3, E6
L1-Cache: 64 + 64 KB (Data + Instructions)
L2-Cache: 512 KB, fullspeed
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool'n'Quiet, NX Bit
Socket 754, 800 MHz HyperTransport (HT800)
Socket 939, 1000 MHz HyperTransport (HT1000)
VCore: 1.35 V or 1.40 V
Power Consumption (TDP): 89 Watt max
First Release: April 4, 2005
Clockrate: 1800–2400 MHz
 San Diego (90 nm SOI)
CPU-Stepping: E4, E6
L1-Cache: 64 + 64 KB (Data + Instructions)
L2-Cache: 1024 KB, fullspeed
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool'n'Quiet, NX Bit
Socket 939, 1000 MHz HyperTransport (HT1000)
VCore: 1.35 V or 1.40 V
Power Consumption (TDP): 89 Watt max
First Release: April 15, 2005
Clockrate: 2200–2600 MHz
 Orleans (90 nm SOI)
CPU-Stepping: F2, F3
L1-Cache: 64 + 64 KB (Data + Instructions)
L2-Cache: 512 KB, fullspeed
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool'n'Quiet, NX Bit, AMD-V
Socket AM2, 1000 MHz HyperTransport (HT1000)
VCore: 1.25 V or 1.40 V
Power Consumption (TDP): 62 Watt max
First Release: May 23, 2006
Clockrate: 1800–2600 MHz
 Lima (65 nm SOI)
CPU-Stepping: G1
L1-Cache: 64 + 64 KB (Data + Instructions)
L2-Cache: 512 KB, fullspeed
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool'n'Quiet, NX Bit, AMD-V
Socket AM2, 1000 MHz HyperTransport (HT1000)
VCore: 1.25/1.35/1.40V
Power Consumption (TDP): 45 Watt max
First Release: February 20, 2007
Clockrate: 2000–2800 MHz
 Athlon Neo

 Huron (65 nm SOI)
CPU-Stepping: ?
L1-Cache: 64 + 64 KB (Data + Instructions)
L2-Cache: 512 KB, fullspeed
MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool'n'Quiet, NX Bit, AMD-V
ASB1 package (BGA), 800 MHz HyperTransport (HT800)
VCore: ?
Power Consumption (TDP): 15 Watt max
First Release: January 8, 2009
Clockrate: 1600 MHz
 Successors

Main article: AMD K10
The Athlon 64 line is expected to continue to evolve. In particular, new models scheduled to be launched starting from the third quarter of 2007 are to be based on the "K10" microarchitecture. The initial offerings are expected to be based on the Agena (quad-core, 2 MB L3 cache), and Kuma (dual-core, 2 MB L3 cache) cores. These processors will be packaged in Socket AM2+ form factors, but are expected to function in Socket AM2 motherboards as well, with the loss of HyperTransport 3.0 enhancements, which will only be available with Socket AM2+ motherboards.
 

Features

There are four variants: Athlon 64, Athlon 64 FX, Mobile Athlon 64 (later renamed "Turion 64") and the dual-core Athlon 64 X2.[39] Common among the Athlon 64 line are a variety of instruction sets including MMX, 3DNow!, SSE, SSE2, and SSE3.[40] All Athlon 64s also support the NX bit, a security feature named "Enhanced Virus Protection" by AMD.[41] And as implementations of the AMD64 architecture, all Athlon 64 variants are able to run 16 bit, 32 bit x86, and AMD64 code, through two different modes the processor can run in: "Legacy mode" and "long mode". Legacy mode runs 16-bit and 32-bit programs natively, and long mode runs 64-bit programs natively, but also allows for 32-bit programs running inside a 64-bit operating system.[42] All Athlon 64 processors feature 128 Kilobytes of level 1 cache, and at least 512 KB of level 2 cache.[40]
The Athlon 64 features an on-die memory controller,[5] a feature not previously seen on x86 CPUs. Not only does this mean the controller runs at the same clock rate as the CPU itself, it also means the electrical signals have a shorter physical distance to travel compared to the old northbridge interfaces.[43] The result is a significant reduction in latency (response time) for access requests to main memory.[44] The lower latency is often cited as one of the advantages of the Athlon 64's architecture over those of its competitors.[45]
Translation Lookaside Buffers (TLBs) have also been enlarged (40 4k/2M/4M entries in L1 cache, 512 4k entries),[46] with reduced latencies and improved branch prediction, with four times the number of bimodal counters in the global history counter.[42] This and other architectural enhancements, especially as regards SSE implementation, improve instruction per cycle (IPC) performance over the previous Athlon XP generation.[42] To make this easier for consumers to understand, AMD has chosen to market the Athlon 64 using a PR (Performance Rating) system, where the numbers roughly map to Pentium 4 performance equivalents, rather than actual clock speed.[47]
Athlon 64 also features CPU speed throttling technology branded Cool'n'Quiet, a feature similar to Intel's SpeedStep that can throttle the processor's clock speed back to facilitate lower power consumption and heat production.[48] When the user is running undemanding applications and the load on the processor is light, the processor's clock speed and voltage are reduced. This in turn reduces its peak power consumption (max TDP set at 89 W by AMD) to as low as 32 W (stepping C0, clock speed reduced to 800 MHz) or 22W (stepping CG, clock speed reduced to 1 GHz). The Athlon 64 also has an Integrated Heat Spreader (IHS) which prevents the CPU die from accidentally being damaged when mounting and unmounting cooling solutions. With prior AMD CPUs a CPU shim could be used by people worried about damaging the die.
The No Execute bit (NX bit) supported by Windows Vista, Windows XP Service Pack 2,[49] Windows XP Professional x64 Edition, Windows Server 2003 x64 Edition, and Linux 2.6.8 and higher is also included, for improved protection from malicious buffer overflow security threats. Hardware-set permission levels make it much more difficult for malicious code to take control of the system. It is intended to make 64-bit computing a more secure environment.
The Athlon 64 CPUs have been produced with 130 nm and 90 nm SOI process technologies.[50] All of the latest chips (Winchester, Venice and San Diego models) are on 90 nm. The Venice and San Diego models also incorporate dual stress liner technology[51] (an amalgam of strained silicon and 'squeezed silicon', the latter of which is not actually a technology) co-developed with IBM.[52]
As the memory controller is integrated onto the CPU die, there is no FSB for the system memory to base its speed upon.[53] Instead, system memory speed is obtained by using the following formula (using the ceiling function):[54]

In simpler terms, the memory is always running at a set fraction of the CPU speed, with the divisor being a whole number. A 'FSB' figure is still used to determine the CPU speed, but the RAM speed is no longer directly related to this 'FSB' figure (known otherwise as the LDT).
To summarize, the Athlon 64 architecture features two buses from the CPU. One is the HT bus to the northbridge connecting the CPU to the chipset and device attachment bus (PCIe, AGP, PCI) and the other is the memory bus which connects the on-board memory controller to the bank of either DDR or DDR2 DRAM.
 Athlon 64 FX
The Athlon 64 FX is positioned as a hardware enthusiast product, marketed by AMD especially toward gamers.[55] Unlike the standard Athlon 64, all of the Athlon 64 FX processors have their multipliers completely unlocked.[56] The FX line is now dual-core, starting with the FX-60.[57] The FX always has the highest clock speed of all Athlons at its release.[58] From FX-70 onwards, the line of processors will also support dual-processor setup with NUMA, named AMD Quad FX platform.
 Athlon 64 X2
Main article: Athlon 64 X2
The Athlon 64 X2 is the first dual-core desktop CPU manufactured by AMD. In 2007, AMD released two final Athlon 64 X2 versions: the AMD Athlon 64 X2 6400+ and 5000+ Black Editions. Both processors feature an unlocked multiplier, which allows for a large range of overclocked settings. The 6400+ is based on a 90nm Windsor core (3.2GHz, 2x1MB L2, 125W TDP) while the 5000+ is based on a 65nm Brisbane core (2.6GHz, 2x512KB L2, 65W TDP). These Black Edition processors are available at retail, but AMD does not include heatsinks in the retail package.
 Turion 64 (formerly Mobile Athlon 64)


Model MT-34
Main article: Turion 64


MT-34 (bottom)
Previously introduced as "Mobile Athlon 64", Turion 64 is now the brand name AMD applies to its 64-bit low-power consumption (mobile) processors. The Turion 64 and Turion 64 X2 processors compete with Intel's mobile processors, initially the Pentium M and currently the Intel Core and Intel Core 2 processors.
Earlier Turion 64 processors are compatible with AMD's Socket 754. The newer "Richmond" models are designed for AMD's Socket S1. They are equipped with 512 or 1024 KB of L2 cache, a 64-bit single channel on-die memory controller, and an 800 MHz HyperTransport bus. Battery saving features, like PowerNow!, are central to the marketing and usefulness of these CPUs.
 Model naming methodology
The model naming scheme does not make it obvious how to compare one Turion with another, or even an Athlon 64. The model name is two letters, a dash, and a two digit number (for example, ML-34). The two letters together designate a processor class, while the number represents a PR rating. The first letter is M for single core processors and T for dual core Turion 64 X2 processors. The later in the alphabet that the second letter appears, the more the model has been designed for mobility (frugal power consumption). Take for instance, an MT-30 and an ML-34. Since the T in the MT-30 is later in the alphabet than the L in ML-34, the MT-30 consumes less power than the ML-34. But since 34 is greater than 30, the ML-34 is faster than the MT-30.
 Athlon Neo
With 27 mm × 27 mm in size and 2.5 mm in thickness, the Athlon Neo processors utilize a new package called "ASB1", essentially a BGA package, for smaller footprint to allow smaller designs for notebooks and lowering the cost. The clock of the processors are signficantly lower than desktop and other mobile counterparts to reach a low TDP, at 15W maximum for a single core x86 CPU. The Athlon Neo processors are equipped with 512 KB of L2 cache and HyperTransport 1.0 running at 800 MHz frequency.
On June 1, 2004, AMD released new versions of both the ClawHammer and Newcastle core revisions for the newly-introduced Socket 939, an altered Socket 940 without the need for buffered memory.[13] Socket 939 offered two main improvements over Socket 754: the memory controller was altered with dual-channel architecture,[14] doubling peak memory bandwidth, and the HyperTransport bus was increased in speed from 800 MHz to 1000 MHz.[15] Socket 939 also was introduced in the FX series in the form of the FX-55.[16] At the same time, AMD also began to ship the "Winchester" core, based on a 90 nanometer process.
Core revisions "Venice" and "San Diego" succeeded all previous revisions on April 15, 2005. Venice, the lower-end part, was produced for both Sockets 754 and 939, and included 512 KB of L2 cache.[17] San Diego, the higher-end chip, was produced only for Socket 939 and doubled Venice's L2 cache to one MB.[18] Both were produced on the 90 nm fabrication process.[19] Both also included support for the SSE3 instruction set,[20] a new feature that had been included in the rival Pentium 4 since the release of the Prescott core in February 2004.[21] In addition, AMD overhauled the memory controller for this revision, resulting in performance improvements as well as support for newer DDR RAM.[22]
 Dual-core Athlon 64
Main article: Athlon 64 X2
On April 21, 2005, less than a week after the release of Venice and San Diego, AMD announced its next addition to the Athlon 64 line, the Athlon 64 X2.[23] Released on May 31, 2005,[24] it also initially had two different core revisions available to the public, Manchester and Toledo, the only appreciable difference between them being the amount of L2 cache.[25] Both were released only for Socket 939.[26] A response to Intel's dual core Pentium D, the Athlon 64 X2 was received very well by reviewers and the general public, with a general consensus emerging that AMD's implementation of multi-core was superior to that of the Pentium D.[27][28] Some felt initially that the X2 would cause market confusion with regard to price points since the new processor was targeted at the same "enthusiast," US$350 and above market[29] already occupied by AMD's existing socket 939 Athlon 64s.[30] AMD's official breakdown of the chips placed the Athlon X2 aimed at a segment they called the "prosumer", along with digital media fans.[24] The Athlon 64 was targeted at the mainstream consumer, and the Athlon FX at gamers. The Sempron budget processor was targeted at value-conscious consumers.[31]
 DDR2
See also: AMD#Athlon 64 (K8)
The Athlon 64 had been maligned by some critics for some time because of its lack of support for DDR2 SDRAM, an emerging technology that had been adopted much earlier by Intel.[32] AMD's official position was that the CAS latency on DDR2 had not progressed to a point where it would be advantageous for the consumer to adopt it.[33] AMD finally remedied this gap with the "Orleans" core revision, the first Athlon 64 to fit Socket AM2, released on May 23, 2006.[34] "Windsor", an Athlon 64 X2 revision for Socket AM2, was released concurrently. Both Orleans and Windsor have either 512KB or 1MB of L2 cache per core.[35] The Athlon 64 FX-62 was also released concurrently on the Socket AM2 platform.[36] Socket AM2 also consumes less power than previous platforms, and supports AMD-V.[37]
The memory controller used in all DDR2 SDRAM capable processors (Socket AM2), has extended column address range of 11 columns instead of conventional 10 columns, and the support of 16 KB page size, with at most 2048 individual entries supported. An OCZ unbuffered DDR2 kit, optimized for 64-bit operating systems, was released to exploit the functionality provided by the memory controller in socket AM2 processors, allowing the memory controller to stay longer on the same page, thus benefitting graphics intensive applications.[38]
 Moving to the subnotebook space
The Athlon architecture was further extended with the release of Athlon Neo processors on January 9, 2009. Based on the same architecture as the other Athlon 64 variants, the new processor features a small package footprint targeting Ultra-portable notebook market.

History

The Athlon 64 was originally codenamed ClawHammer by AMD,[3] and was referred to as such internally and in press releases. The first Athlon 64 FX was based on the first Opteron core, SledgeHammer. Both cores, produced on a 130 nanometer process, were first introduced on September 23, 2003. The models first available were the FX-51, fitting Socket 940, and the 3200+, fitting Socket 754.[6] Like the Opteron, on which it was based, the Athlon FX-51 required buffered RAM, increasing the final cost of an upgrade.[7] The week of the Athlon 64's launch, Intel released the Pentium 4 Extreme Edition, a CPU designed to compete with the Athlon 64 FX.[8] The Extreme Edition was widely considered a marketing ploy to draw publicity away from AMD, and was quickly nicknamed among some circles the "Emergency Edition".[9] Despite a very strong demand for the chip, AMD experienced early manufacturing difficulties that made it difficult to deliver Athlon 64s in quantity. In the early months of the Athlon 64 lifespan, AMD could only produce one hundred thousand chips per month.[10] However, it was very competitive in terms of performance to the Pentium 4, with magazine PC World calling it the "fastest yet".[11] "Newcastle" was released soon after ClawHammer, with half the Level 2 cache.[12]
All of the 64-bit processors sold by AMD so far have their genesis in the K8 or Hammer project.

Athlon 64

Athlon 64
Athlon 64 3400+ "Newcastle" in Socket 754
Produced From 2004 to present
Common manufacturer(s) AMD
Max. CPU clock 1.0 GHz to 3.2 GHz
FSB speeds 800 MT/s to 1000 MT/s
Min. feature size 0.13µm to 65nm
Instruction set MMX, SSE, SSE2, SSE3, SSSE3, x86-64, 3DNow!
Microarchitecture K8 Microarchitecture
Cores 1
Socket(s) Socket 754, Socket 939, Socket 940, Socket AM2
The Athlon 64 is an eighth-generation, AMD64-architecture microprocessor produced by AMD, released on September 23, 2003.[1] It is the third processor to bear the name Athlon, and the immediate successor to the Athlon XP.[2] The second processor (after the Opteron) to implement AMD64 architecture and the first 64-bit processor targeted at the average consumer,[3] it was AMD's primary consumer microprocessor, and competes primarily with Intel's Pentium 4, especially the "Prescott" and "Cedar Mill" core revisions. It is AMD's first K8, eighth-generation processor core for desktop and mobile computers.[4] Despite being natively 64-bit, the AMD64 architecture is backward-compatible with 32-bit x86 instructions.[5] Athlon 64s have been produced for Socket 754, Socket 939, Socket 940, and Socket AM2.