Engineering:AMD PowerPlay

From HandWiki
Short description: Brand name by AMD
AMD PowerPlay
Design firmAdvanced Micro Devices
TypeDynamic frequency scaling

AMD PowerPlay is the brand name for a set of technologies for the reduction of the energy consumption implemented in several of AMD's graphics processing units and APUs supported by their proprietary graphics device driver "Catalyst". AMD PowerPlay is also implemented into ATI/AMD chipsets which integrated graphics and into AMD's Imageon handheld chipset, that was sold to Qualcomm in 2008.

Besides the desirable goal to reduce energy consumption, AMD PowerPlay helps to lower the noise levels created by the cooling in desktop computers and extend battery life in mobile devices. AMD PowerPlay has been succeeded by AMD PowerTune.[1]

History

The technology was first implemented in Mobility Radeon products for notebooks, to provide a set of features to lower the power consumption of the laptop computer. The technology consists of several technologies; examples include dynamic clock adjustments when the notebook is not plugged into a power socket and allowing different backlight brightness levels of the notebook LCD monitor. The technology was updated with the release of each generation of mobile GPUs. The latest release is ATI PowerPlay 7.0.[2]

Since the release of Radeon HD 3000 Series, PowerPlay was implemented to further reduce the power consumption of desktop GPUs.

Currently supported products

The official ATI support list[3] lists only the ATI Radeon 3800 series desktop cards, but PowerPlay is also a listed feature of all Radeon HD 3000/4000/5000 series products. Independent reviews indicated that the latter was already lower power compared to other 3D cards, so the addition of PowerPlay to that line was clearly intended to address an increasingly power, heat and noise conscious market. The ATI Radeon HD 2600 line – which does not support PowerPlay – was being phased out in favour of the 3000 series at the same price points that also support PCI Express 2.0, DirectX 10.1 and faster GDDR3 memory.

The entire ATI Radeon Xpress line is also supported for single board computers which tend to be power sensitive and used in large installations where configuration and boot image control are major concerns.

Support for "PowerPlay" was added to the Linux kernel driver "amdgpu" on November 11, 2015.[4]

Desktop versus laptop

The main difference between the desktop and laptop versions is that the desktop version cuts the features which are aimed at notebook usage, including variable LCD backlight brightness. The PowerPlay technology for Radeon desktop graphics features three usage scenarios: normal mode (2D mode), light gaming mode and intensive gaming mode (3D mode), replacing notebook scenarios (running on AC power or battery power). Tests indicated that the lowest core clock frequency of an RV670 GPU core can reach as low as 300 MHz with PowerPlay technology enabled.[5]

Feature overview for AMD APUs

The following table shows features of AMD's APUs (see also: List of AMD accelerated processing units).

[ VisualEditor ] [view · talk · edit]

Codename Server Basic Toronto
Micro Kyoto
Desktop Mainstream Carrizo Bristol Ridge Raven Ridge Picasso
Entry Llano Trinity Richland Kaveri
Basic Kabini
Mobile Performance Renoir
Mainstream Llano Trinity Richland Kaveri Carrizo Bristol Ridge Raven Ridge Picasso
Entry Dalí
Basic Desna, Ontario, Zacate Kabini, Temash Beema, Mullins Carrizo-L Stoney Ridge
Embedded Trinity Bald Eagle Merlin Falcon,
Brown Falcon
Great Horned Owl Ontario, Zacate Kabini Steppe Eagle, Crowned Eagle,
LX-Family
Prairie Falcon Banded Kestrel
Platform High, standard and low power Low and ultra-low power
Released Aug 2011 Oct 2012 Jun 2013 Jan 2014 Jun 2015 Jun 2016 Oct 2017 Jan 2019 Mar 2020 Jan 2011 May 2013 Apr 2014 May 2015 Feb 2016 Apr 2019
CPU microarchitecture K10 Piledriver Steamroller Excavator "Excavator+"[6] Zen Zen+ Zen 2 Bobcat Jaguar Puma Puma+[7] "Excavator+" Zen
ISA x86-64 x86-64
Socket Desktop High-end N/A N/A
Mainstream N/A AM4
Entry FM1 FM2 FM2+[lower-alpha 1] N/A
Basic N/A N/A AM1 N/A
Other FS1 FS1+, FP2 FP3 FP4 FP5 FP6 FT1 FT3 FT3b FP4 FP5
PCI Express version 2.0 3.0 2.0 3.0
[[Engineering:Semiconductor device fabricatFab. (Nanometre|nm]]) GF 32SHP
(HKMG SOI)
GF 28SHP
(HKMG bulk)
GF 14LPP
(FinFET bulk)
GF 12LP
(FinFET bulk)
TSMC N7
(FinFET bulk)
TSMC N40
(bulk)
TSMC N28
(HKMG bulk)
GF 28SHP
(HKMG bulk)
GF 14LPP
(FinFET bulk)
Die area (mm2) 228 246 245 245 250 210[8] 156 75 (+ 28 FCH) 107 ? 125
Min TDP (W) 35 17 12 10 4.5 4 3.95 10 6
Max APU TDP (W) 100 95 65 54 18 25
Max stock APU base clock (GHz) 3 3.8 4.1 3.7 3.8 3.6 3.7 3.3 1.75 2.2 2 2.2 3.2 3.3
Max APUs per node[lower-alpha 2] 1 1
Max CPU[lower-alpha 3] cores per APU 4 8 2 4 2
Max threads per CPU core 1 2 1 2
Integer structure 3+3 2+2 4+2 4+2+1 1+1+1+1 2+2 4+2
i386, i486, i586, CMOV, NOPL, i686, PAE, NX bit, CMPXCHG16B, AMD-V, RVI, ABM, and 64-bit LAHF/SAHF Yes Yes
IOMMU[lower-alpha 4] N/A Yes
BMI1, AES-NI, CLMUL, and F16C N/A Yes
MOVBE N/A Yes
AVIC, BMI2 and RDRAND N/A Yes
ADX, SHA, RDSEED, SMAP, SMEP, XSAVEC, XSAVES, XRSTORS, CLFLUSHOPT, and CLZERO N/A Yes N/A Yes
WBNOINVD, CLWB, RDPID, RDPRU, and MCOMMIT N/A Yes N/A
FPUs per core 1 0.5 1 1 0.5 1
Pipes per FPU 2 2
FPU pipe width 128-bit 256-bit 80-bit 128-bit
CPU instruction set SIMD level SSE4a[lower-alpha 5] AVX AVX2 SSSE3 AVX AVX2
3DNow! 3DNow!+ N/A N/A
PREFETCH/PREFETCHW Yes Yes
FMA4, LWP, TBM, and XOP N/A Yes N/A N/A Yes N/A
FMA3 Yes Yes
L1 data cache per core (KiB) 64 16 32 32
L1 data cache associativity (ways) 2 4 8 8
L1 instruction caches per core 1 0.5 1 1 0.5 1
Max APU total L1 instruction cache (KiB) 256 128 192 256 64 128 96 128
L1 instruction cache associativity (ways) 2 3 4 8 2 3 4
L2 caches per core 1 0.5 1 1 0.5 1
Max APU total L2 cache (MiB) 4 2 4 1 2 1
L2 cache associativity (ways) 16 8 16 8
APU total L3 cache (MiB) N/A 4 8 N/A 4
APU L3 cache associativity (ways) 16 16
L3 cache scheme Victim N/A Victim Victim
Max stock DRAM support DDR3-1866 DDR3-2133 DDR3-2133, DDR4-2400 DDR4-2400 DDR4-2933 DDR4-3200, LPDDR4-4266 DDR3L-1333 DDR3L-1600 DDR3L-1866 DDR3-1866, DDR4-2400 DDR4-2400
Max DRAM channels per APU 2 1 2
Max stock DRAM bandwidth (GB/s) per APU 29.866 34.132 38.400 46.932 68.256 10.666 12.800 14.933 19.200 38.400
GPU microarchitecture TeraScale 2 (VLIW5) TeraScale 3 (VLIW4) GCN 2nd gen GCN 3rd gen GCN 5th gen[9] TeraScale 2 (VLIW5) GCN 2nd gen GCN 3rd gen[9] GCN 5th gen
GPU instruction set TeraScale instruction set GCN instruction set TeraScale instruction set GCN instruction set
Max stock GPU base clock (MHz) 600 800 844 866 1108 1250 1400 1750 538 600 ? 847 900 1200
Max stock GPU base GFLOPS[lower-alpha 6] 480 614.4 648.1 886.7 1134.5 1760 1971.2 1792 86 ? ? ? 345.6 460.8
3D engine[lower-alpha 7] Up to 400:20:8 Up to 384:24:6 Up to 512:32:8 Up to 704:44:16[10] Up to 512:?:? 80:8:4 128:8:4 Up to 192:?:? Up to 192:?:?
IOMMUv1 IOMMUv2 IOMMUv1 ? IOMMUv2
Video decoder UVD 3.0 UVD 4.2 UVD 6.0 VCN 1.0[11] UVD 3.0 UVD 4.0 UVD 4.2 UVD 6.0 UVD 6.3 VCN 1.0
Video encoder N/A VCE 1.0 VCE 2.0 VCE 3.1 N/A VCE 2.0 VCE 3.1
GPU power saving PowerPlay PowerTune PowerPlay PowerTune[12]
TrueAudio N/A Yes[13] N/A Yes
FreeSync 1
2
1
2
HDCP[lower-alpha 8] ? 1.4 1.4
2.2
? 1.4 1.4
2.2
PlayReady[lower-alpha 8] N/A 3.0 not yet N/A 3.0 not yet
Supported displays[lower-alpha 9] 2–3 2–4 3 3 (desktop)
4 (mobile, embedded)
4 2 3 4
/drm/radeon[lower-alpha 10][15][16] Yes N/A Yes N/A
/drm/amdgpu[lower-alpha 10][17] N/A Yes[18] Yes N/A Yes[18] Yes
  1. APU models: A8-7680, A6-7480. CPU only: Athlon X4 845.
  2. A PC would be one node.
  3. An APU combines a CPU and a GPU. Both have cores.
  4. Requires firmware support.
  5. No SSE4. No SSSE3.
  6. Single-precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
  7. Unified shaders : texture mapping units : render output units
  8. 8.0 8.1 To play protected video content, it also requires card, operating system, driver, and application support. A compatible HDCP display is also needed for this. HDCP is mandatory for the output of certain audio formats, placing additional constraints on the multimedia setup.
  9. To feed more than two displays, the additional panels must have native DisplayPort support.[14] Alternatively active DisplayPort-to-DVI/HDMI/VGA adapters can be employed.
  10. 10.0 10.1 DRM (Direct Rendering Manager) is a component of the Linux kernel. Support in this table refers to the most current version.

Feature overview for AMD graphics cards

See also

References

  1. "AMD PowerTune vs PowerPlay". AMD. December 1, 2010. https://www.amd.com/Documents/amd_powertune_whitepaper.pdf. 
  2. Marco Chiappetta (September 10, 2009). "ATI Radeon HD 4670, Redefining The Mainstream". https://hothardware.com/reviews/ati-radeon-hd-4670-redefining-the-mainstream. Retrieved December 10, 2018. 
  3. "AMD PowerPlay Technology". https://www.amd.com/us/products/technologies/ati-power-play/Pages/ati-power-play.aspx. 
  4. "Add amdgpu powerplay support". November 11, 2015. http://lists.freedesktop.org/archives/dri-devel/2015-November/094230.html. 
  5. PC Watch image. Retrieved December 3, 2007. Notice the core speed in current clock settings section in gray.
  6. "AMD Announces the 7th Generation APU: Excavator mk2 in Bristol Ridge and Stoney Ridge for Notebooks". 31 May 2016. https://www.anandtech.com/show/10362/amd-7th-generation-apu-bristol-ridge-stoney-ridge-for-notebooks. Retrieved 3 January 2020. 
  7. "AMD Mobile "Carrizo" Family of APUs Designed to Deliver Significant Leap in Performance, Energy Efficiency in 2015" (Press release). 20 November 2014. Retrieved 16 February 2015.
  8. "The Mobile CPU Comparison Guide Rev. 13.0 Page 5 : AMD Mobile CPU Full List". TechARP.com. https://www.techarp.com/guides/mobile-cpu-comparison-guide/5/. Retrieved 13 December 2017. 
  9. 9.0 9.1 "AMD VEGA10 and VEGA11 GPUs spotted in OpenCL driver". VideoCardz.com. http://videocardz.com/62250/amd-vega10-and-vega11-gpus-spotted-in-opencl-driver/. Retrieved 6 June 2017. 
  10. Cutress, Ian (1 February 2018). "Zen Cores and Vega: Ryzen APUs for AM4 – AMD Tech Day at CES: 2018 Roadmap Revealed, with Ryzen APUs, Zen+ on 12nm, Vega on 7nm". Anandtech. https://www.anandtech.com/show/12233/amd-tech-day-at-ces-2018-roadmap-revealed-with-ryzen-apus-zen-on-12nm-vega-on-7nm/3. Retrieved 7 February 2018. 
  11. Larabel, Michael (17 November 2017). "Radeon VCN Encode Support Lands in Mesa 17.4 Git". Phoronix. https://www.phoronix.com/scan.php?page=news_item&px=Radeon-VCN-Encode-Lands. Retrieved 20 November 2017. 
  12. Tony Chen; Jason Greaves, "AMD's Graphics Core Next (GCN) Architecture", AMD, http://meseec.ce.rit.edu/551-projects/fall2014/3-4.pdf, retrieved 13 August 2016 
  13. "A technical look at AMD's Kaveri architecture". Semi Accurate. http://semiaccurate.com/2014/01/15/technical-look-amds-kaveri-architecture/. Retrieved 6 July 2014. 
  14. "How do I connect three or More Monitors to an AMD Radeon™ HD 5000, HD 6000, and HD 7000 Series Graphics Card?". AMD. http://support.amd.com/en-us/search/faq/154. Retrieved 8 December 2014. 
  15. Airlie, David (26 November 2009). "DisplayPort supported by KMS driver mainlined into Linux kernel 2.6.33". http://airlied.livejournal.com/68805.html. Retrieved 16 January 2016. 
  16. "Radeon feature matrix". freedesktop.org. http://xorg.freedesktop.org/wiki/RadeonFeature/. Retrieved 10 January 2016. 
  17. Deucher, Alexander (16 September 2015). "XDC2015: AMDGPU". http://www.x.org/wiki/Events/XDC2015/Program/deucher_zhou_amdgpu.pdf. Retrieved 16 January 2016. 
  18. 18.0 18.1 Michel Dänzer (17 November 2016). "[ANNOUNCE xf86-video-amdgpu 1.2.0"]. lists.x.org. https://lists.x.org/archives/xorg-announce/2016-November/002741.html. 

External links