AMD Accelerated Processing Unit

From Wikipedia, the free encyclopedia
  (Redirected from AMD Fusion)
Jump to: navigation, search
AMD Accelerated Processing Unit
AMD A-series logo.jpg
Release date 2011
Codename(s) Fusion
Model(s) Desktop E2 Series
Cores 2 to 4
1,178M 32 nm (Llano)
  • 1,303M 32 nm (Trinity)
  • 1,3M 32 nm (Richland)
  • 2,41M 28 nm (Kaveri)
Direct3D support Direct3D 11
OpenCL support 1.2
OpenGL support 4.1+

The AMD Accelerated Processing Unit series, formerly known as Fusion, is a marketing name for a series of microprocessors from AMD designed to act as a CPU and graphics accelerator (GPU) on a single chip.

AMD announced the first generation APUs, Llano for high-performance and Brazos for low-power devices in January 2011. The second-generation Trinity for high-performance and Brazos-2 for low-power devices were announced in June 2012. The third-generation Kaveri for high performance devices was launched in January 2014, while Kabini and Temash for low-power devices were announced in summer 2013.

The Sony PlayStation 4 and Microsoft Xbox One eighth generation video game consoles both use semi-custom third-generation low-power APUs.


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.[1] The project reportedly required three internal iterations of the Fusion concept to create a product deemed worthy of release.[1] 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.[2]

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][4] 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 microarchitecture and a Radeon HD 6000-series GPU on the same die.

At a conference in January 2012, corporate fellow Phil Rogers announced that AMD would re-brand the Fusion platform as the Heterogeneous Systems Architecture (HSA), stating that "it's only fitting that the name of this evolving architecture and platform be representative of the entire, technical community that is leading the way in this very important area of technology and programming development."[5] However, it was later revealed that AMD had been the subject of a trademark infringement lawsuit by the Swiss company Arctic, who used the name "Fusion" for a line of power supplies.[6]

The second generation desktop and laptop APU, codenamed Trinity was announced at AMD's Financial Analyst Day 2010[7][8] and released in October 2012.[9] It featured Piledriver CPU cores and Radeon HD 7000 Series GPU cores on the FM2 socket.[10] AMD released a new APU based on the Piledriver microarchitecture on March 12, 2013 for Laptops/Mobile and on June 4, 2013 for desktops under the codename Richland.[11] The second generation APU for low-power devices, Brazos 2.0, remained on the Bobcat microarchitecture but integrated a Radeon HD 7000-series GPU core onto the die.

Semi-custom chips were introduced in the Microsoft Xbox One and Sony PlayStation 4 video games consoles.[12][13]

A third generation of the technology was released on 14 January 2014, featuring greater integration between the CPU and GPU. The desktop and laptop variant is codenamed Kaveri, based on Steamroller architecture, while the low-power variants, codenamed Kabini and Temash, are based on Jaguar architecture.[14]

Heterogeneous System Architecture[edit]

Heterogeneous System Architecture (HSA), maintained by the HSA Foundation, is a system architecture that allows accelerators, for instance, graphics processor, to operate at the processing level as the system's CPU. To ease various aspects of programming heterogeneous applications, and to be HSA-compliant, accelerators must meet certain requirements, including:

  • Be ISA agnostic for both CPUs and accelerators.
  • Support high-level programming languages.
  • Provide the ability to access pageable system memory.
  • zero-copy
  • Maintain 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 utilize 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 APUs
Support OpenCL C++ directions and Microsoft’s C++ AMP language extension. This eases programming of both CPU and GPU working together to process support parallel workloads.
HSA-aware MMU GPU can access the entire system memory through the translation services and page fault management of the HSA MMU.
Shared Power Management CPU and GPU now share the power budget. Priority goes to the processor most suited to the current tasks.
Architectural Integration Unified Address Space for CPU and GPU[18][19] 2014
Kaveri APUs
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 2015
Carrizo APU
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 so processes have low latency access to the GPU.
Quality of Service[18] 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 a 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.[20] 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.[21]


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 two to four 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. In performance comparisons against the similarly priced Intel Core i3-2105, the Llano APU was criticised for its poor CPU performance[24] and praised for its better GPU performance.[25][26] AMD was also criticised for abandoning Socket FM1 after one generation.[27]

Piledriver architecture (Trinity and Richland)[edit]

  • Piledriver CPU cores
  • On-die Northern Islands/VLIW4-based GPU (branded Radeon HD 7000 and 8000 Series)
  • 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."[28]
  • AMD HD Media Accelerator[29] - includes AMD Perfect Picture HD, AMD Quick Stream technology, and AMD Steady Video technology.
  • HDMI, DisplayPort 1.2, DVI Controllers


The first iteration of the second generation platform, released in October 2012, brought improvements to CPU and GPU performance to both desktops and laptops. The platform features 2 to 4 Piledriver CPU cores built on a 32 nm process with a TDP between 65 W and 100 W, and a GPU based on the Radeon HD7000 Series with support for DirectX 11, OpenGL 4.2, and OpenCL 1.2. The Trinity APU was praised for the improvements to CPU performance compared to the Llano APU.[30]


  • "Enhanced Piledriver" CPU cores[31]
  • Temperature Smart Turbo Core technology. An advancement of the existing Turbo Core technology, which allows internal software to adjust the CPU and GPU clock speed to maximise performance within the constrains of the Thermal design power of the APU.[32]
  • New low-power consumption CPUs with only 45 W TDP[33]

The release of this second iteration of this generation was 12 March 2013 for mobile parts and 5 June 2013 for desktop parts.

Steamroller architecture (Kaveri)[edit]

  • Steamroller CPU cores
  • AMD Radeon R7 graphics
  • FM2+ socket support

The third generation of the platform, codenamed Kaveri, was partly released on January 14, 2014.[34] Kaveri contains up to four Steamroller CPU cores clocked to 3.7 GHz with a turbo mode of 4 GHz, up to a 512-core Graphics Core Next GPU, two decode units per module instead of one (which allows each core to decode four instructions per cycle instead of two), AMD TrueAudio,[35] Mantle,[36] an on-chip ARM Cortex-A5 MPCore,[37] and will release with a new socket, FM2+.[38]

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.[3] 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 with full DirectX11, DirectCompute and OpenCL support including UVD3 video acceleration for HD video including 1080p.[3]

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.[39] 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.[39] 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.[40][41] The Hondo APU is a redesign of the Desna APU. AMD lowered energy use by optimizing the APU and FCH for tablet computers.[42][43]

The Deccan platform including Krishna and Wichita APUs were cancelled in 2011. AMD originally planned to release them in the second half 2012.[44]

Jaguar architecture (Kabini and Temash)[edit]

  • Jaguar CPU cores
  • AMD Radeon R3 graphics
  • AM1 socket support

In January 2013 the Jaguar-based Kabini and Temash APUs were unveiled as the successors of the Bobcat-based Ontario, Zacate and Hondo APUs.[45][46][47] 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.[47] The two to four Jaguar cores of the Kabini and Temash APUs feature numerous architectural improvements regarding power requirement and performance, such as support for newer x86-instructions, a higher IPC count, a CC6 power state mode and clock gating.[48][49][50] Kabini and Temash are AMD's first, and also the first ever quad-core x86 based SoCs.[51] The integrated Fusion Controller Hubs (FCH) for Kabini and Temash are codenamed "Yangtze" and "Salton" respectively.[52] 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.[52] Both chips feature DirectX 11.1-compliant GCN-based graphics as well as numerous heterogeneous system architecture (HSA) improvements.[45][46] They were fabricated at a 28 nm process in an FT3 BGA package by TSMC, and were released on May 23, 2013.[48][53][54]

The PlayStation 4 and Xbox One, were revealed to both be powered by 8-core semi-custom Jaguar-derived APUs.

ARM server SoCs (Seattle architecture)[edit]

The ARM Cortex-A57 64-bit server solution SoC will be launched in the second half of 2014 and codenamed "Seattle".[55] They will feature 8 or 16 core variants, with an expected clockspeed over 2 GHz, and will reportedly deliver up to four times the performance of current Opteron X processors.[56] These ARM processors will incorporate SeaMicro freedom fabric on die, offering up to 10 Gbit/s bandwidth, for server usage; additionally, each ARM processor will support up to 64 GB DRAM.[57]

See also[edit]


  1. ^ a b "The rise and fall of AMD: A company on the ropes". 23 April 2013. Retrieved 20 December 2013. 
  2. ^ William Van Winkle (13 August 2012). "AMD Fusion: How It Started, Where It’s Going, And What It Means". Retrieved 20 December 2013. 
  3. ^ a b c AMD (4 January 2011). "AMD Fusion APU Era Begins". Retrieved 24 August 2013. 
  4. ^ 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. 
  5. ^ "AMD ditches Fusion branding". Bit-tech. Retrieved 24 July 2013. 
  6. ^ "AMD targeted by Arctic over Fusion brand". Bit-tech. Retrieved 24 July 2013. 
  7. ^ Cyril Kowaliski (9 November 2010). "AMD begins shipping Brazos, announces Bulldozer-based APUs". The Tech Report. Retrieved 7 January 2014. 
  8. ^ Rick Bergman (9 November 2010). "AMD 2010 Financial Analyst Day" (PDF). Advanced Micro Devices, Inc. Retrieved 7 January 2014. 
  9. ^ "AMD reveals its 2012-2013 roadmap, promises 28 nm chips across the board by 2013". Engadget. 2012-02-02. Retrieved 2012-08-22. 
  10. ^ Building an AMD 'Trinity' desktop PC
  11. ^ AMD launches "Richland" A-Series APUs: slight speed bump, better power management
  12. ^ Taylor, John (2013-02-21). "AMD and The Sony PS4. Allow Me To Elaborate.". Retrieved 2013-08-30. 
  13. ^ "XBox One Revealed". Wired. 2013-05-21. Retrieved 2013-05-23. 
  14. ^ Darren Murph. "AMD announces Temash, Kabini, Richland, and Kaveri APUs at CES 2013 (video)". Retrieved 20 December 2013. 
  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 j "The programmer's guide to the APU galaxy". 
  19. ^ a b c d e f g h i "AMD Outlines HSA Roadmap: Unified Memory for CPU/GPU in 2013, HSA GPUs in 2014". 
  20. ^ 2011.pdf[dead link]
  21. ^ AnandTech - AMD Outlines HSA Roadmap: Unified Memory for CPU/GPU in 2013, HSA GPUs in 2014
  22. ^ "AMD Llano core". 2014-03-17. Retrieved 2014-03-24. 
  23. ^ a b c d "AMD Fusion Architecture and Llano". 
  24. ^ Anand Lal Shimpi (30 June 2011). "The AMD A8-3850 Review: Llano on the Desktop". Anandtech, Inc. Retrieved 12 January 2014. 
  25. ^ Conclusion : AMD A8-3850 Review: Llano Rocks Entry-Level Desktops
  26. ^ AnandTech | The AMD A8-3850 Review: Llano on the Desktop
  27. ^ AnandTech | AMD A10-5800K & A8-5600K Review: Trinity on the Desktop, Part 1
  28. ^ "CPU + GPU = APU: East Meets West". Retrieved 1 September 2013. 
  29. ^ "AMD’s 2nd Generation APU, Codenamed "Trinity," Will Enable Superior Multimedia Experience for Our "Connected" Generation". 
  30. ^ AnandTech | The AMD A8-3850 Review: Llano on the Desktop
  31. ^ AMD Officially Announces Third Generation Richland A-Series Mobile APUs - 50% Faster GPU Than Intel Core i7 Mobile
  32. ^ New Details Revealed on AMD's Upcoming Richland Chips
  33. ^ "AMD A10-Series A10-6700T — AD670TYHA44HL / AD670TYHHLBOX". Retrieved 2013-11-10. 
  34. ^ "AnandTech Portal | AMD Kaveri APU Launch Details: Desktop, January 14th". Retrieved 2014-01-13. 
  35. ^ By ChrisFiebelkorn on Dec 3, 2013. "AMD A10 Kaveri APU Details Leaked". HotHardware. Retrieved 2014-01-13. 
  36. ^ By Dave_HH on Nov 14, 2013. "How AMD's Mantle Will Redefine Gaming, AMD Hardware Not Required". HotHardware. Retrieved 2014-01-13. 
  37. ^ AMD and ARM Fusion redefine beyond x86
  38. ^ AMD’s Next-Gen “Kaveri” APUs Will Require New Mainboards - X-bit labs
  39. ^ a b Nita, Sorin (1 June 2011). "AMD Releases More Details Regarding the Desna Tablet APU". Retrieved 20 March 2013. 
  40. ^ AMD (9 October 2013). "New AMD Z-Series APU for Tablets Enables Immersive Experience for Upcoming Microsoft Windows 8 Platforms". Retrieved 20 March 2013. 
  41. ^ Shvets, Anthony (10 October 2012). "AMD announces Z-60 APU for tablets". 
  42. ^ 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. 
  43. ^ Shilov, Anton (9 October 2012). "AMD Introduces Its First Accelerated Processing Unit for Media Tablets". Retrieved 20 March 2013. 
  44. ^ Demerjian, Charlie. "Exclusive: AMD kills Wichita and Krishna". SemiAccurate. Retrieved 2012-08-22. 
  45. ^ a b SKYMTL (9 January 2013). "Richland, Kaveri, Kabini & Temash; AMD’s 2013 APU Lineup Examined". Hardwarecanucks. Retrieved 23 March 2013. 
  46. ^ a b Halfacree, Gareth (January 8, 2013). "AMD unveils new APUs, SoCs and Radeon HD 8000 Series". Bit-Tech. Retrieved 23 March 2013. 
  47. ^ a b Lal Shimpi, Anand (2 February 2012). "AMD's 2012 - 2013 Client CPU/GPU/APU Roadmap Revealed". AnandTech. Retrieved August 8, 2012. 
  48. ^ 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. 
  49. ^ 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. 
  50. ^ Paul, Donald (21 October 2012). "Leaked details of the future some Kabini APU AMD". Technewspedia. Retrieved 21 March 2013. 
  51. ^ Paine, Steve Chippy (9 January 2013). "AMD Shares SoC Line-Up for 2013. Kabini is for Ultrathins". Ultrabooknews. Retrieved 21 March 2013. 
  52. ^ a b Abazovic, Fuad (24 January 2013). "Kabini chipset is Yangtze". Fudzilla. Retrieved 21 March 2013. 
  53. ^ Hruska, Paul (14 January 2013). "AMD quietly confirms 28 nm Kabini, Temash chips are being built at TSMC". Extremetech. Retrieved 21 March 2013. 
  54. ^ "AMDs sparsame Mobilprozessoren Kabini und Temash legen los". 23 May 2013. Retrieved 31 August 2013. 
  55. ^ "AMD Server Roadmap 2013". AMD. 2013-06-18. Retrieved 2013-07-05. 
  56. ^ "AMD details first ARM-based server chip: up to 16 helpings of Cortex-A57 clocked at 2 GHz". engadget. 2013-06-18. Retrieved 2013-07-05. 
  57. ^ "AMD bets ARM, server chip experience means market gains". zdnet. 2013-06-18. Retrieved 2013-07-05. 

External links[edit]