AMD Accelerated Processing Unit

From Wikipedia, the free encyclopedia
  (Redirected from AMD Fusion)
Jump to: navigation, search
This article may require copy editing for tense and grammar. You can assist by editing it. (February 2013)
AMD Accelerated Processing Unit
AMD A-series logo.jpg
Release date 2011
Codename(s) Fusion
Desna
Ontario
Zacate
Llano
Hondo
Trinity
Weatherford
Richland
Kaveri
Kabini
Temash
IGP
Wrestler
WinterPark
BeaverCreek
Model(s) Desktop E2 Series
Cores 2 to 4
Transistors
Fabrication		 1,178M 32 nm (Llano)
  • 1,303M 32 nm (Trinity)
Direct3D support Direct3D 11
OpenCL support 1.1
OpenGL support 4.0
Predecessor Radeon HD 5xxx series[citation needed]

The AMD Accelerated Processing Unit, formerly known as Fusion, is a marketing brand of AMD for a system on a chip solution for the consumer market. The technology is aimed at adding Heterogeneous System Architecture features with the goal of making it easier to program, optimize, and load balance, while providing higher performance and lower power consumption.[1] The technology has been in development by AMD since 2006 and the current design is the product of the merger between AMD and ATI, combining general processor execution as well as 3D geometry processing and other functions of modern GPUs (like GPGPU computation) into a single die.[2] The first generation, "Llano", was unveiled in January 2011;[3] the second-generation, "Trinity", was released in June 2012;[4][5] and the third-generation, "Kaveri", is expected to be released in late 2013.[6] The new game console PlayStation 4 from Sony uses a custom-designed chip, which was modified in cooperation with AMD.[citation needed] Microsoft announced in May 2013 that the XBox One game console also uses a custom-designed APU built on a 28 nm process.[7][8]

Contents

History [edit]

The AMD Fusion project started in 2006 with the aim of developing a system on a chip that combined a CPU with a GPU on a single die. The acquisition of graphics chipset manufacturer ATI by AMD was a key step toward realising such a vision.[9] The project reportedly required three internal iterations of the Fusion concept to create a product deemed worthy of release.[9] Reasons contributing to the delay of the project include the technical difficulties of combining a CPU and GPU on the same die at a 45 nm process, and conflicting views on what the role of the CPU and GPU should be within the project.[10] The name of the project was eventually changed to AMD Accelerated Processing Unit (APU) due a trademark dispute.

The first generation desktop and laptop APU, codenamed Llano, was announced on January 4, 2011 at the 2011 CES show in Las Vegas and released shortly after.[3][11] It featured K10 CPU cores and a Radeon HD 6000-series GPU on the same die on the FM1 socket. An APU for low-power devices was announced as the Brazos platform, based on the Bobcat processor and a Radeon HD 6000-series GPU on the same die.

The second generation desktop and laptop APU, codenamed Trinity was announced at AMD's Financial Analyst Day 2010.[12] It featured Piledriver CPU cores and Radeon HD 7000-series GPU cores on the FM2 socket.[13] AMD is expected to release a new APU based on the Piledriver microarchitecture in June 2013 under the codename Richland.[14] The second generation APU for low-power devices, Brazos 2.0, remained on the Bobcat processor but integrated a Radeon HD 7000-series GPU core onto the die.

A third generation of the technology is expected to be released in late 2013, featuring greater integration between the CPU and GPU. The desktop and laptop variant is codenamed Kaveri, based on the Steamroller (microarchitecture), while the low-power variants, codenamed Kabini and Tamesh, are based on the Jaguar (microarchitecture).

Heterogeneous System Architecture [edit]

[icon] This section requires expansion. (February 2013)

Heterogeneous System Architecture (HSA), maintained by HSA Foundation, is a system architecture that allows accelerators, for instance, graphics processor, to be as first-class of a component as the CPU in the system. HSA-compliant accelerators ease various aspects of the programming of heterogeneous applications, by being ISA agnostic for both CPUs and accelerators, supporting high-level programming languages, having the ability to access pageable system memory, maintaining cache coherency for system memory with CPUs, and so on.[15] HSA is widely used in System-on-Chip devices, such as tablets, smartphones, and other mobile devices.[16] HSA allows programs to use the graphics processor for floating point calculations without separate memory or scheduling.[17]

AMD HSA Implementation [edit]

Type HSA Feature First Implemented Notes
Optimized
Platform		 GPU Compute C++ Support 2012
Trinity APU		 Support OpenCL C++ directions and Microsoft’s upcoming C++ AMP language. This eases programming of both CPU and GPU working together to process support parallel workloads.
HSA MMU GPU can access the entire system memory through the translation services and page fault management of the HSA MMU.
Shared Power Management Power budget is now shared by CPU and GPU, while priority of having more power budget depends on which is more suited to the current tasks.
Architectural
Integration		 Unified Address Space for CPU and GPU[1][18] 2013
Kaveri APU		 CPU and GPU now access the memory with the same address space. Pointers can now be freely passed between CPU and GPU.
Fully coherent memory between CPU & GPU GPU can now access and cache data from coherent memory regions in the system memory, and also reference the data from CPU's cache. Cache coherency is maintained.
GPU uses pageable system memory via CPU pointers GPU can take advantage of the shared virtual memory between CPU and GPU, and pageable system memory can now be referenced directly by the GPU, instead of being copied or pinned before accessing.
System
Integration		 GPU compute context switch 2014 Compute tasks on GPU can be context switched, allowing a multi-tasking environment and also faster interpretation between applications, compute and graphics.
GPU graphics pre-emption Long-running graphics tasks can be pre-empted in order to allow processes having low latency access to the GPU.
Quality of Service[1] In addition to context switch and pre-emption, hardware resources can be either equalized or prioritized among multiple users and applications.


APU-branded platforms [edit]

AMD APUs have unique architecture: they have AMD CPU modules, cache, and a discrete-class graphics processor all on the same die, using the same bus. This architecture allows for the use of graphics accelerators, such as OpenCL, with the integrated graphics processor.[19] The goal is to create a "fully integrated" APU, which, according to AMD will eventually feature 'heterogeneous cores' capable of processing both CPU and GPU work automatically, depending on the workload requirement.[20]

K10 architecture (Llano) [edit]

The first generation APU, released in June 2011, was used in both desktops and laptops. It was based on the K10 architecture and built on a 32 nm process featuring 2 to 4 CPU cores on a TDP of 65-100 W, and integrated graphics based on the Radeon HD6000 Series with support for DirectX 11, OpenGL 4.2 and OpenCL 1.2. It was criticised for its poor CPU performance compared to the similarly priced Intel Core i3-2105[22] and for AMD's decision to abandon Socket FM1 after the first generation.[23] However, it was praised for providing better GPU performance compared to the Intel Core i3-2105.[24][25]

Piledriver architecture (Trinity and Richland) [edit]

  • Piledriver CPU cores
  • On-die Radeon HD 7000 Series (not Graphics Core Next) graphics processor
  • Unified Northbridge includes AMD Turbo Core 3.0 which enables automatic bi-directional power management between CPU modules and GPU. Power to the CPU and GPU is controlled automatically by changing the clock rate depending on the load. For example, for a non-overclocked A10-5800K APU the CPU frequency can change from 1.4 GHz to 4.2 Ghz, and the GPU frequency can change from 304 MHz to 800 MHz. In addition, CC6 mode is capable of powering down individual CPU cores, while PC6 mode is able to lower the power on the entire rail."[26]
  • AMD HD Media Accelerator.[27] Includes AMD Perfect Picture HD, AMD Quick Stream technology, and AMD Steady Video technology[27]
  • HDMI, DisplayPort 1.2, DVI Controllers

Trinity

The first iteration of the second generation platform, released in October 2012, brought improvements to CPU and GPU performance to both the desktop and laptop. The platform features 2 to 4 Piledriver CPU cores built on a 32 nm process with a TDP between 65-100 W, and a GPU based on the Radeon HD6000 Series with support for Direct X 11, OpenGL 4.2, and OpenCL 1.2. The Trinity APU was praised for the improvements to CPU performance compared to the Llano APU.[28]

Richland

[icon] This section requires expansion. (April 2013)

The second iteration of this generation is expected to be released in June 2013.[14]

Steamroller architecture (Kaveri) [edit]

The third generation of the platform, codenamed Kaveri, is expected to be released in the second half of 2013. It is reported to contain Steamroller CPU cores,[32] a Graphics Core Next GPU,[33] and on-chip ARM Cortex-A5 MPCore.[34]

Bobcat architecture (Ontario, Zacate, Desna, Hondo) [edit]

The AMD Brazos platform was introduced on January 4, 2011 targeting the subnotebook, netbook and low power small form factor markets.[35] It features the 9-watt AMD C-Series APU (codename: Ontario) for netbooks and low power devices as well as the 18-watt AMD E-Series APU (codename: Zacate) for mainstream and value notebooks, all-in-ones and small form factor desktops. Both APUs feature one or two Bobcat x86 cores and a Radeon Evergreen Series GPU wth full DirectX11, DirectCompute and OpenCL support including UVD3 video acceleration for HD video including 1080p.[35]

AMD expanded the Brazos platform on June 5, 2011 with the announcement of the 5.9-watt AMD Z-Series APU (codename: Desna) designed for the Tablet market.[36] The Desna APU is based on the 9-watt Ontario APU, energy savings were achieved by lowering the CPU, GPU and north bridge voltages, reducing the idle clocks of the CPU and GPU as well as introducing a hardware thermal control mode.[36] A bidirectional turbo core mode was also introduced.

AMD announced the Brazos-T platform on October 9, 2012. It comprises the 4.5-watt AMD Z-Series APU (codename: Hondo) and the A55T Fusion Controller Hub (FCH), designed for the tablet computer market.[37][38] The Hondo APU is re-architected variant of the Desna APU, the energy savings were achieved by optimizing the APU and FCH for tablet computers.[39][40]

The Deccan platform including Krishna and Witchita APUs of were canceled in 2011. They were planned to be released in the second half 2012.[41]

Jaguar architecture (Kabini and Temash) [edit]

In January 2013 the Jaguar-based Kabini and Temash APUs were unveiled as the successors of the Bobcat-based Ontario, Zacate and Hondo APUs.[42][43][44] The Kabini APU is aimed at the low-power, subnotebook, netbook, ultra-thin and small form factor markets, the Temash APU is aimed at the tablet, ultra-low power and small form factor markets.[44] The 2 to 4 Jaguar cores of the Kabini and Temash APUs will feature numerous architectural improvements regarding power requirement and performance, such as support for newer x86-instructions, a higher IPC, a CC6 power state mode and clock gating.[45][46][47] Kabini and Temash will be AMD's first, and also the first ever quad-core x86 based SoCs.[48] The integrated Fusion Controller Hubs (FCH) for Kabini and Temash are codenamed "Yangtze" and "Salton" respectively.[49] The Yangtze FCH features support for two USB 3.0 ports, two SATA 6 Gbit/s ports, as well as the xHCI 1.0 and SD/SDIO 3.0 protocols for SD-card support.[49] Both chips will feature DirectX 11.1-compliant GCN-based graphics as well as numerous heterogeneous system architecture (HSA) improvements.[42][43] Both chips will be manufactured in 28 nm with a FT2 BGA package at TSMC and are released on May, 23th.[45][50][51]

The PlayStation 4 and Xbox One, were revealed to both be powered by an 8-core APU (semi-custom). This leaves room in AMD's future for a novel 8-core, lower-power APU to be placed in it's portfolio.

Trademark dispute [edit]

The “AMD Fusion” branding entered into a trademark dispute between Advanced Micro Devices (“AMD”), the EU trademark owner Boost Up International Limited and Arctic Switzerland AG, who claimed to be the first to use “Fusion” for its range of computer power supply products since 2006.[52] In early 2012, AMD has laid out plans to cease the Fusion branding for its APUs in favor of the “Heterogeneous System Architecture” (“HSA”) branding.[53] However, the parties failed to reach a compromise regarding the compensations for licensing fees and legal expenses incurred to bring the matter to the discussion table. On 23 January 2013, Arctic announced that the company and AMD had finally arrived at an agreement to settle the issue in private.[54] To put the dispute to an end, distributors and resellers are asked to terminate the use of “Fusion” and “AMD Fusion” latest by 31 January 2013 in the sale of any AMD computer hardware or its OEMs products.[55]

See also [edit]

References [edit]

  1. ^ a b c d e f g h i j k "The programmer's guide to the APU galaxy". 
  2. ^ ATI chipsets already include GPU
  3. ^ a b AMD Fusion APU Era Begins
  4. ^ "AMD Trinity Desktop APU Specs Revealed". Cpu-world.com. Retrieved 2012-08-22. 
  5. ^ "AMD reveals its 2012-2013 roadmap, promises 28 nm chips across the board by 2013". Engadget. 2012-02-02. Retrieved 2012-08-22. 
  6. ^ AMD announces Temash, Kabini, Richland, and Kaveri APUs at CES 2013 (video)
  7. ^ "Xbox One packs a Blu-ray drive, 8 GB of RAM, and lots of buzzwords". arstechnica.com. 2013-05-21. Retrieved 2013-05-22. 
  8. ^ "XBox One Revealed". Wired. 2013-05-21. Retrieved 2013-05-23. 
  9. ^ a b The rise and fall of AMD: A company on the ropes | Ars Technica
  10. ^ Scaling The Brick Wall : AMD Fusion: How It Started, Where It’s Going, And What It Means
  11. ^ Stokes, Jon (February 8, 2010). "AMD reveals Fusion CPU+GPU, to challege Intel in laptops". Ars Technica. Archived from the original on 10 February 2010. Retrieved February 9, 2010. 
  12. ^ AMD begins shipping Brazos, announces Bulldozer-based APUs, [1] pdf
  13. ^ Building an AMD 'Trinity' desktop PC
  14. ^ a b AMD Richland APU Prices Leaked – Scheduled For Launch on 4th June
  15. ^ What is Heterogeneous System Architecture (HSA)? | AMD
  16. ^ Heterogeneous System Architecture: Purpose and Outlook - GPU Science
  17. ^ Heterogeneous system architecture: Multicore image processing using a mix of CPU and GPU elements - Embedded Computing Design
  18. ^ a b c d e f g h i "AMD Outlines HSA Roadmap: Unified Memory for CPU/GPU in 2013, HSA GPUs in 2014". 
  19. ^ [2][dead link]
  20. ^ AnandTech - AMD Outlines HSA Roadmap: Unified Memory for CPU/GPU in 2013, HSA GPUs in 2014
  21. ^ a b c d "AMD Fusion Architecture and Llano". 
  22. ^ AnandTech | The AMD A8-3850 Review: Llano on the Desktop
  23. ^ AnandTech | AMD A10-5800K & A8-5600K Review: Trinity on the Desktop, Part 1
  24. ^ Conclusion : AMD A8-3850 Review: Llano Rocks Entry-Level Desktops
  25. ^ AnandTech | The AMD A8-3850 Review: Llano on the Desktop
  26. ^ "CPU + GPU = APU: East Meets West". 
  27. ^ a b "AMD’s 2nd Generation APU, Codenamed "Trinity," Will Enable Superior Multimedia Experience for Our "Connected" Generation". 
  28. ^ AnandTech | The AMD A8-3850 Review: Llano on the Desktop
  29. ^ AMD Officially Announces Third Generation Richland A-Series Mobile APUs - 50% Faster GPU Than Intel Core i7 Mobile
  30. ^ AMD’s new Richland APU boosts clocks and adds features, but is ultimately just a minor Trinity refresh | ExtremeTech
  31. ^ New Details Revealed on AMD's Upcoming Richland Chips
  32. ^ AMD Launching 28 nm Kaveri APU with Steamroller Cores in 2H 2013
  33. ^ "AMD Kaveri Unveiled: PC Architecture Gets GDDR5". brightsideofnews.com. 2013-03-05. Retrieved 2013-04-20. 
  34. ^ "AMD and ARM Fusion redefine beyond x86". Tech News Pedia. 2012-06-13. Retrieved 2012-08-22. 
  35. ^ a b AMD (4 January 2011). "AMD Fusion APU Era Begins". Retrieved 20 March 2013. 
  36. ^ a b Nita, Sorin (1 June 2011). "AMD Releases More Details Regarding the Desna Tablet APU". Retrieved 20 March 2013. 
  37. ^ AMD (9 October 2013). "New AMD Z-Series APU for Tablets Enables Immersive Experience for Upcoming Microsoft Windows 8 Platforms". Retrieved 20 March 2013. 
  38. ^ Shvets, Anthony (10 October 2012). "AMD announces Z-60 APU for tablets". 
  39. ^ Hruska, Joel (9 October 2012). "AMD's Hondo Z-Series APU To Challenge Intel's Atom In Windows 8 Tablet Market". Retrieved 20 March 2013. 
  40. ^ Shilov, Anton (9 October 2012). "AMD Introduces Its First Accelerated Processing Unit for Media Tablets". Retrieved 20 March 2013. 
  41. ^ Demerjian, Charlie. "Exclusive: AMD kills Wichita and Krishna". SemiAccurate. Retrieved 2012-08-22. 
  42. ^ a b SKYMTL (9 January 2013). "Richland, Kaveri, Kabini & Temash; AMD’s 2013 APU Lineup Examined". Hardwarecanucks. Retrieved 23 March 2013. 
  43. ^ a b Halfacree, Gareth (January 8, 2013). "AMD unveils new APUs, SoCs and Radeon HD 8000 Series". Bit-Tech. Retrieved 23 March 2013. 
  44. ^ a b Lal Shimpi, Anand (2 February 2012). "AMD's 2012 - 2013 Client CPU/GPU/APU Roadmap Revealed". AnandTech. Retrieved August 8, 2012. 
  45. ^ a b Shilov, Anton (2 January 2013). "AMD to Officially Roll-Out "Kabini" and "Temash" Low-Power APUs This Quarter". X-bit labs. Retrieved 21 March 2013. 
  46. ^ Shilov, Anton (24 July 2013). "AMD's New Low-Power Micro-Architecture to Support AVX, BMI Other New Instructions". X-bit labs. Retrieved 21 March 2013. 
  47. ^ Paul, Donald (21 October 2012). "Leaked details of the future some Kabini APU AMD". Technewspedia. Retrieved 21 March 2013. 
  48. ^ Paine, Steve Chippy (9 January 2013). "AMD Shares SoC Line-Up for 2013. Kabini is for Ultrathins". Ultrabooknews. Retrieved 21 March 2013. 
  49. ^ a b Abazovic, Fuad (24 January 2013). "Kabini chipset is Yangtze". Fudzilla. Retrieved 21 March 2013. 
  50. ^ Hruska, Paul (14 January 2013). "AMD quietly confirms 28 nm Kabini, Temash chips are being built at TSMC". Extremetech. Retrieved 21 March 2013. 
  51. ^ http://www.heise.de/newsticker/meldung/AMDs-sparsame-Mobilprozessoren-Kabini-und-Temash-legen-los-1867778.html
  52. ^ "AMD targeted by Arctic over Fusion bran", bit-tech, 23 January 2012. Retrieved 28 January 2013
  53. ^ "AMD ditches Fusion branding", bit-tech, 19 January 2012. Retrieved 28 January 2013
  54. ^ "ARCTIC and Boost Up Announce Negotiated Solution with AMD Regarding "FUSION" Trademark in European Union", www.arctic.ac, 23 January 2013. Retrieved 28 January 2013
  55. ^ "Use of the terms "AMD" and "AMD Fusion"", 18 December 2012. Retrieved 28 January 2013.

External links [edit]

Wikimedia Commons has media related to: AMD Fusion

AMD [edit]

Media [edit]
Discontinued
pre-x86
x86-16 (16-bit)
x86-32/IA-32 (32-bit)
x86-64/AMD64 (64-bit)
RISC
Current
x86-32
x86-64
Lists
Microarchitectures
Related
Retrieved from "http://en.wikipedia.org/w/index.php?title=AMD_Accelerated_Processing_Unit&oldid=556468671"