Jump to content

AMD 10h

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by Metageek (talk | contribs) at 21:30, 4 March 2008 (Grammary fix: splitting a run-on sentence.). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Template:Future chip

The AMD K10 is AMD's latest microprocessor architecture. Though there were once reports that the K10 had been cancelled by tech tabloid The Inquirer [1], the first third-generation Opteron products for servers were launched on September 10, 2007 and the Phenom processors for desktop followed and launched on November 11, 2007 as the immediate successors to the AMD K8 series of processors (Athlon 64, Opteron, Sempron 64).

Nomenclatures

It is commonly perceived that from the time after the use of the codename K8 for the AMD K8 or Athlon 64 processor family, AMD no longer uses K-nomenclatures (originally stood for Kryptonite [2]) since no K-nomenclature naming convention beyond K8 has appeared in official AMD documents and press releases after the beginning of 2005.

The name "K8L" was first coined by Charlie Demerjian, one of the writers of The Inquirer back in 2005 [3], and was used by the wider IT community as a convenient shorthand [4] along with Stars, as the codenames for desktop line of processors was named under stars or constellations, while according to AMD official documents, the processor family was termed "AMD Next Generation Processor Technology" [5].

In a video interview [6], Giuseppe Amato confirmed that the codename is K10.

It was revealed, by The Inquirer itself, that the codename "K8L" referred to a low-power version of the K8 family, later named Turion 64, and that K10 was the official codename for the microarchitecture [4].

AMD refers to it as Family 10h Processors, as it is the successor of the K8 Family 0Fh Processors. 10h and 0Fh refer to the main result of the CPUID x86 processor instruction. In hexadecimal numbering, 0Fh (h represents hexadecimal numbering) equals the decimal number 15, and 10h equals decimal 16.

Schedule of launch and delivery

Timeline

Historical information

In 2003, AMD outlined the features for upcoming generations of microprocessors after K8 family of processors in various events and analyst meetings, including the Microprocessor Forum 2003 [7]. The outlined features to be deployed by the next-generation microprocessors are as follows:

On April 13, 2006, Henri Richard, AMD executive vice president and chief officer for marketing and sales, acknowledged[8] the existence of the new microarchitecture in an interview.

In June 2006, AMD executive vice president Henri Richard had another interview with DigiTimes commented on the upcoming processor developments:

Q: What is your broad perspective on the development of AMD processor technology over the next three to four years?

A: Well, as Dirk Meyer commented at our analysts meeting, we're not standing still. We've talked about the refresh of the current K8 architecture that will come in '07, with significant improvements in many different areas of the processor, including integer performance, floating point performance, memory bandwidth, interconnections and so on. You know that platform still has a lot of legs under it, but of course we're not standing still, and there's a next-generation core that's being worked on. I can't give you more details right now, but I think that what's important is that we're establishing clearly that this is a two-horse race. And as you would expect in a race, sometimes, when one horse is a little bit in front of the other, it reverses the situation. But what's important is that it is a race.

— AMD Executive Vice President, Henri Richard, Source: DigiTimes Interview with Henri Richard[9]

Confirmation of time frames

File:AMD Barcelona die.jpg
"Barcelona" die shot

On July 21 2006, AMD President and Chief operating officer (COO) Dirk Meyer and Senior VP Marty Seyer confirmed that the launch date of new microprocessors of Revision H under the new microarchitecture is slated for the middle of 2007; and that it will contain a quad core version for servers, workstations, and high-end desktops, as well as a dual core version for consumer Desktops. Some of the Revision H Opterons shipped in 2007 will have a thermal design power of 68 W.

On August 15 2006, at the launch of the first Socket F dual-core Opterons, AMD announced that the firm had reached the final design stage (tape-out) of quad-core Opteron parts. The next stages are testing and validation, with sampling to follow after several months.[10]

On June 29 2007, AMD stated that server processors codenamed Barcelona will ship in August 2007, and corresponding server systems from partners will ship in September of the same year.[11]

On August 13, the reported ship dates for the first Barcelona processors were set for September 10, 2007. They announced the Opteron 2348 and 2350 will have core frequencies of 1.9 GHz and 2.0 GHz. [12]

Internal codenames

As of November 2006, reports leaked the upcoming desktop part codenames Agena, Agena FX, and the core speeds of the parts range from 2.4 GHz - 2.9 GHz respectively, 512 KiB L2 cache each core, 2 MiB L3 cache, using HyperTransport 3.0, with a TDP of 125 W.[13] In recent reports, single core variants (codenamed Spica) and dual core with or without L3 cache (codenamed Kuma and Rana respectively) are available under the same microarchitecture [14].

During the AMD Analyst Day 2006 on December 14, 2006, AMD announced their official timeline for server, desktop and mobile processors.[15] For the servers segment, AMD will unveil two new processors based on the architecture codenamed "Barcelona" and "Budapest" for more than 1-way and 1-way servers respectively [15]. Desktops will see an overhaul of the entire processor lineup. Single-core "Lima" built on 65 nm fabrication process node the single-core processors will arrive in Q1 2007 while Sparta, the Sempron 65 nm process update, will come in Q2 2007. For the second half of 2007, HyperTransport 3.0 and Socket AM2+ will be unveiled, which are designed for the specific implementation of the aforementioned consumer quad core desktop chip series, with naming convention changes from city names (up to middle of 2007) to stars or constellations after that, such as Agena; in addition, the AMD Quad FX platform and its immediate successor will support the high end enthusiast dual-processor versions of the chip, codenamed as Agena FX, updates the processors line for AMD Quad FX platform. As with the server chips codenamed Barcelona, the new desktop quad core series will feature a shared L3 cache, 128-bit floating point (FP) units and an enhanced microarchitecture. Agena will be the native quad-core processor for the desktop. Kuma, a dual-core variant will follow on in Q3 while Rana, the dual-core version with no shared L3 cache is expected at the end of the year.

Subsequent product launches

More information about the upcoming chip codenamed "Montreal" on the server roadmap [16] using MCM technique of two "Shanghai" cores with a total of 12 MiB L3-cache [17] codenamed AMD K10.5 [18]. The desktop variant for Shanghai is codenamed Ridgeback [19]. Afterwards is the release of products based on the Bulldozer cores, which is optimized with integrated graphics core (AMD Fusion) or native octal-core (8 core) server architecture (codenamed Sandtiger), and the Bobcat core, optimized for low-power operations.

Change of model nomenclatures

During Computex 2007 in early June, new information regarding the naming schemes of upcoming AMD microprocessors emerged. Additional letters indicating both performance and power envelope will precede the 4 digit model number [20].

The model numbers of the new line of processors were apprently changed from the PR ratings used by its predecessors, the Athlon 64 series processors (except Phenom FX series, being suggested to follow the nomenclature of Athlon 64 FX series). As reported by DailyTech [21], the model numbers are in alpha-numeric format as AA-@### where AA are alphabetical letters, the first letter indicating the processor class and the second indicating the typical TDP power envelope. The character @ is the series indicator, which varies by branding (see below table), and the last three characters (###) are the model number, with higher numbers indicating greater performance.

Not much information was known about the details of the model numbers, but the processors will be divided into three segments: Premium, Intermediate, and Value. Premium segment model numbers have processor class "G", Intermediate segment "B", and Value level "L", as discovered on the web from the AsRock website [22]. Similarly, three levels of TDP, "more than 65W", "65W", and "less than 65W", are indicated by the letters "P", "S", and "E" respectively [21].

As of November 2007, AMD has removed the letters from the model names and X2/X3/X4 monikers for depicting the number of cores of the processor, leaving just a four digit model number with the first character being the sole identification of the processor family [23], while Sempron remained using the LE prefix, as follows:

Series number [24]
Processor series Indicator
Phenom quad-core (Agena) 9
Phenom triple-core (Toliman) 7
Athlon dual-core (Kuma) 6
Athlon single-core (Lima) 1
Sempron LE single-core (Sparta) 1

Live demonstrations

On November 30, 2006, AMD live demoed the native quad core chip known as "Barcelona" for the first time in public,[25] while running Windows Server 2003 64-bit Edition. AMD claims 70% scaling of performance in real world loads, and better performance than Intel Xeon 5355 processor codenamed Clovertown [26]. More details regarding this first revision of the next generation AMD microprocessor architecture have surfaced on the web recently including their clock speeds.[27][28]

On January 24, 2007, AMD Executive Vice President Randy Allen claimed that in live tests, in regard to a wide variety of workloads, "Barcelona" was able to demonstrate 40% performance advantage over the comparable Intel Xeon codenamed Clovertown dual-processor (2P) quad-core processors [29]. The expected performance of floating point per core would be approximately 1.8 times that of the K8 family, at the same clock speed [30].

On May 10 2007, AMD held a private event demonstrating the upcoming processors codenamed Agena FX and chipsets, with one demonstrated system being AMD Quad FX platform with one Radeon HD 2900 XT graphics card on the upcoming RD790 chipset, the system was also demonstrated real-time converting a 720p video clip into another undisclosed format while all 8 cores were maxed at 100% by other tasks. [31]

Sister microarchitecture

Also due in a similar timeframe will be a sister microarchitecture, which will focus on lower power consumption chips in mobile platforms as well as small form factor features. This microarchitecture will contain specialized features such as mobile optimized crossbar switch and memory controller and other on-die components; link power management for HyperTransport 3.0; and others. At that time, AMD simply dubbed it "New Mobile Core", without giving a specific codename.

On the December 2006 analyst day, Executive vice president Marty Seyer announced the new mobile core codenamed Griffin to be launched in 2008 with inherited power optimizations technologies from the K10 architecture, but based on a K8 design [32].

Iterations of the release

In late 2007 to second quarter of 2008, there will be a modification to the core to be fabricated at 45 nm process node [33], with enhancements such as FB-DIMM support, Direct Connect Architecture 2.0, enhanced Reliability, Availability and Serviceability (RAS), and probably more for the processor die. The platform will also add support for I/O Virtualization, PCI Express 2.0, 10 Gigabit NIC, larger caches, and more.

However, reports have suggested that FB-DIMM support had been dropped from future roadmaps of the majority of AMD products since popularity is low [34][35]. Also, FB-DIMM's future as an industry standard had been called into question.

An article published by The Inquirer corroborates the earlier reports of the timeline (as cited in this article). According to the report, there will be three iterations of the server processor core: one named Barcelona, due in Q2 of 2007, with new CPU core components as well as the microarchitecture, but built on the old HyperTransport 2.0 infrastructure; the second is Budapest for single socket systems using socket AM2+ or socket AM3, with HyperTransport 3.0; and the third, codenamed Shanghai is an update of the server chip, based on 45 nm process [36], probably also with HyperTransport 3.0 and DDR3 implementation, due in Q1-Q2 2008.[37]

AMD, on September 17, 2007, announced [38] that a three core (triple-core) processor will also be released under the Phenom brand lineup, codenamed Toliman. AMD official replied in an interview that this product is benefitted from ATI technologies to add fuses to the quad-core processor and shutting down one of the four cores [39] to become a triple-core processor, which the technique has been popular for making one or more mainstream GPU cores from a single high-end GPU core by blowing out parts of the circuit to save R&D costs while targeting more markets some time ago. The triple-core processor still see the same specifications for quad-core variants, the naming of the processor lineup, according to the AMD branding scheme, will be named as Phenom triple-core 7000 series, the processor line will be focused on what AMD called the fourth market segment or the "High-end Mainstream" segment beside Value, Mainstream and Performance segments in an interview with BetaNews, which the targeted customers of the processors are "those who are willing to pay more for more performance but not required for too much processing power as required by gamers and system builders [40][41], while there are single core (Sempron) variants for low-end market, and dual-core (Athlon) variants for mid-range market, and quad-core (Phenom quad-core 9000 series and Phenom FX) variants should be seen in the high-end market at the same timeframe.

Further in 2008, AMD will introduce Deneb FX for the replacement for the AMD Quad FX platform, as well as Deneb for the mainstream. Propos and Regor will also replace Kuma and Rana in the lower market segments. Socket AM2+ being named in the late 2006 might actually have been the original AM3 socket, but as naming conventions changed, so that the next generation of consumer desktop socket capable of DDR3 will be socket AM3. [42]

Features

Fabrication technology

File:Amd cpu die compare.jpg
Visual scale comparison of K10 die against multitude of K8-based products. The K10 die size is estimated.

AMD will introduce the microprocessors manufactured at 65 nm feature width using Silicon-on-insulator (SOI) technology, since the release of K10 coincides with the volume ramp of this manufacturing process [43]. The servers will be produced for Socket F(1207) or later 1207-pin socket infrastructure, the only server socket on AMD's near-term roadmap; the desktop parts will come on Socket AM2 or Socket AM2+.

AMD announced during the Technology Analyst Day [44] that the use of Continuous Transistor Improvement (CTI) and Shared Transistor Technology (STT) would finally lead to the implementation of Silicon-Germanium-On-Insulator (SGoI) on 65 nm process CPUs [45].

Supported DRAM standards

The K8 family was known to be particularly sensitive to memory latency since its design gains performance by minimizing this through the use of an on-die memory controller (integrated into the CPU); increased latency in the external modules negates the usefulness of the feature. DDR2 RAM introduces some additional latency over traditional DDR RAM since the DRAM is internally driven by a clock at one quarter of the external data frequency, as opposed to one half that of DDR. However, since the command clock rate in DDR2 is doubled relative to DDR and other latency-reducing features (e.g. additive latency) have been introduced, common comparisons based on CAS Latency alone are not sufficient. For example, Socket AM2 processors are known to demonstrate similar performance using DDR2 SDRAM as Socket 939 processors that utilize DDR-400 SDRAM. K10 processors support DDR2 SDRAM rated up to DDR2-1066 (1066 MHz) [46].

Higher computational throughput

It was also reported by several sources (such as AnandTech, The Inquirer and Geek.com) that the microprocessors implementing the microarchitecture will feature a doubling in the width of SSE execution units in the cores. With the help of major improvements in the memory subsystem (such as load re-ordering and improved prefetch mechanisms) as well as the doubled instruction fetch and load, it is expected to increase the suitability of the processor to scientific and high-performance computing tasks and potentially improve its competitiveness with Intel's Xeon, Core 2, Itanium 2 and other contemporary microprocessors.

Many of the improvements in computational throughput of each core are listed below.

Characteristics of the microarchitecture

K10 architecture.
K10 single core with overlay description, excluding the L2 cache array.

[47]

  • Instruction set additions and extensions
    • New bit-manipulation instructions: Leading Zero Count (LZCNT) and Population Count (POPCNT)
    • New SSE instructions named as SSE4a: combined mask-shift instructions (EXTRQ/INSERTQ) and scalar streaming store instructions (MOVNTSD/MOVNTSS). These instructions are not found in Intel's SSE4
    • Support for unaligned SSE load-operation instructions (which formerly required 16-byte alignment)[49]
  • Execution pipeline enhancements
    • 128-bit wide SSE units
    • Wider L1 data cache interface allowing for two 128-bit loads per cycle (as opposed to two 64-bit loads per cycle with K8)
    • Lower integer divide latency
    • 512-entry indirect branch predictor and a larger return stack (size doubled from K8) and branch target buffer
    • Side-Band Stack Optimizer, dedicated to perform increment/decrement of register stack pointer
    • Fastpathed CALL and RET-Imm instructions (formerly microcoded) as well as MOVs from SIMD registers to general purpose registers
  • Integration of new technologies onto CPU die:
    • Four processor cores (Quad-core)
    • Split power planes for CPU core and memory controller/northbridge for more effective power management, first dubbed Dynamic Independent Core Engagement or D. I. C. E. by AMD and now known as Enhanced PowerNow!, allowing the cores and northbridge (integrated memory controller) to scale power consumption up or down independently [50].
    • Shutting down portions of the circuits in core when not in load, named "CoolCore" Technology.
  • Improvements in the memory subsystem:
    • Improvements in access latency:
      • Support for re-ordering loads ahead of other loads and stores
      • More aggressive instruction prefetching, 32 bytes instruction prefetch as opposed to 16 bytes in K8
      • DRAM prefetcher for buffering reads
      • Buffered burst writeback to RAM in order to reduce contention
    • Changes in memory hierarchy:
      • Prefetch directly into L1 cache as opposed to L2 cache with K8 family
      • 32-way set associative L3 victim cache sized at least 2 MiB, shared between processing cores on a single die (each with 512 KiB of independent exclusive L2 cache), with a sharing-aware replacement policy.
      • Extensible L3 cache design, with 6 MiB planned for 45 nm process node, with the chips codenamed Shanghai.
    • Changes in address space management:
      • Two 64-bit independent memory controllers, each with its own physical address space; this provides an opportunity to better utilize the available bandwidth in case of random memory accesses occurring in heavily multi-threaded environments. This approach is in contrast to the previous "interleaved" design, where the two 64-bit data channels were bounded to a single common address space.
      • Larger Tagged Lookaside Buffers; support for 1 GiB page entries and a new 128-entry 2 MiB page TLB
      • 48-bit memory addressing to allow for 256 TiB memory subsystems
      • Memory mirroring, data poisoning support and Enhanced RAS
      • Nested page tables for AMD-V virtualization technology, claimed to have decreasing world switch time by 25%.
  • Improvements in system interconnect:
    • HyperTransport retry support
    • Support for HyperTransport 3.0, with HyperTransport Link unganging which creates 8 point-to-point links per socket.
  • Platform-level enhancements with additional functionality:
    • Five p-states allowing for automatic clock rate modulation
    • Increased clock gating
    • Official support for coprocessors via HTX slots and vacant CPU sockets through HyperTransport: Torrenza initiative.

Successor

Codenamed "Fusion" is a CPU technology furthering the trend of continued system component integration onto CPU die (which was initiated by K8 with integrated System Request Queue (SRQ), cross-bar switch, memory controller as well as HyperTransport links), planned beyond these two aforementioned families of products, and will be due in late 2008 or sometime in 2009, the Fusion products will see new processor cores, codenamed "Bulldozer" and "Bobcat" incorporated into the die.

Media discussions

Note: These media discussions are listed in ascending date of publication.

See also

References

  1. ^ AMD's K10 is delayed or dead
  2. ^ News.com report, retrieved August 22, 2007
  3. ^ The Inquirer report
  4. ^ a b Valich, Theo. "AMD explains K8L misnomer". The Inquirer. Retrieved 2007-03-16.
  5. ^ Official Announcement of "AMD Next Generation Processor Technology"
  6. ^ Video interview of Giuseppe Amato (AMD's Technical Director, Sales and Marketing EMEA) in February 2007]
  7. ^ Microprocessor Forum 2003 presentation slide
  8. ^ Hall, Chris. "Re-defining microprocessors: Q&A with AMD's Henri Richard". DigiTimes.com. Retrieved 2007-03-18.
  9. ^ AMD's vision for next few years - an interview with Henri Richard
  10. ^ "Next-Generation AMD Opteron Paves The Way For Quad-Core". crn.com. 15 August 2006.
  11. ^ "AMD to Ship Industry's First Native x86 Quad-Core Processors In August". amd.com. 29 June 2007.
  12. ^ "AMD to launch two Barcelona-based processors in September". tgdaily.com. 13 August 2007.
  13. ^ "AMD Quad-Core Altair upcoming in 2007 Q3". HKEPC. 3 October 2006.
  14. ^ "AMD to enter K10 era in 2H 2007". HKEPC. 4 October 2006.
  15. ^ a b 06A-DayMartySeyer.pdf "2006 Analyst Day Slides (Roadmaps for server and mobile" (PDF). AMD. {{cite news}}: Check |url= value (help)
  16. ^ The Inquirer report
  17. ^ FudZilla report
  18. ^ FudZilla report
  19. ^ Fudzilla report, retrieved August 1, 2007
  20. ^ "How to decipher AMD's new CPU naming code". Gadget Lab. 2007-06-04.
  21. ^ a b DailyTech report
  22. ^ XTReview image: AsRock BIOS 1.40 support Athlon X2 BE-xxxx and Sempron LE-xxxx processors
  23. ^ "AMD Revised Desktop Model Number Structure". VR-Zone. October 9, 2007.
  24. ^ VR-Zone report, retrieved October 9, 2007
  25. ^ "AMD Demonstrates Its Quad Core Server Chips". CNET.com. 30 November 2006.
  26. ^ "AMD Demonstrates Barcelona; The First True, Native Quad Core Opteron". legitreviews.com. 30 November 2006.
  27. ^ "Quick Look at AMD Quad Core Barcelona". arstechnica.com. {{cite news}}: Unknown parameter |dat= ignored (help)
  28. ^ The Inquirer article
  29. ^ "AMD Expects Quad Core Barcelona to Outperform Clovertown by 40%". dailytech.com. 25 January 2007.
  30. ^ "Go to 'Barcelona' over 'Cloverton'". CNET.com. 23 January 2007.
  31. ^ TGDaily report
  32. ^ "AMD updates Opteron, Turion roadmaps". informationweek.com. 14 December 2006.
  33. ^ "AMD Outlines Quad Core Computing". www.pcpro.co.uk. 19 September 2006.
  34. ^ "Intel Pulls Back from FB-DIMM". inquirer.net. 7 September 2006.
  35. ^ "No Shocker Here". legitreviews.com. 15 September 2006.
  36. ^ DailyTech report
  37. ^ "AMD Quad Cores: The Whole Story Unfolded". inquirer.net. 16 September 2006.
  38. ^ AMD announcement, retrieved September 17, 2007
  39. ^ ComputerWorld report, retrieved October 9, 2007
  40. ^ BetaNews report, retrieved September 17, 2007
  41. ^ BetaNews interview, retrieved September 17, 2007
  42. ^ "AMD: 45nm, DDR3, and AM3 in 2008". dailytech.com. 2 May 2007.
  43. ^ "An AMD Update: Fab 36 Begins Shipments, Planning for 65 nm process and AM2 Performance". AnandTech. April 4, 2006.
  44. ^ 2006 AMD Analyst Day 2006 page
  45. ^ Ostrander, Daryl. "2006 Technology Analyst Day Slides" (PDF). Advanced Micro Devices. Retrieved 2007-03-19.
  46. ^ "AMD's next-generation Star supports DDR2-1066 & SSE4a". HKEPC Hardware. Retrieved 2007-03-19.
  47. ^ Shimpi, Anand. "Barcelona Architecture: AMD on the Counterattack". AnandTech. Retrieved 2007-03-18. {{cite news}}: Unknown parameter |middle= ignored (help)
  48. ^ "AMD Quad-Core Altair upcoming in 2007 Q3". HKEPC. 3 October 2006.
  49. ^ Case, Loyd. "AMD Unveils Barcelona Quad-Core Details". Ziff Davis. Retrieved 2007-03-18.
  50. ^ "AMD Next Generation Processor Technology Slides". HardOCP. 22 August 2006.
Retrieved from "https://en.wikipedia.org/w/index.php?title=AMD_10h&oldid=195887629"