Difference between revisions of "Template:AMD GPU features"

From blackwiki
Jump to navigation Jump to search
(add vega VII column)
blackwiki>Wikiinger
(Undid revision 878155316 by 192.228.218.2 (talk) Please wait until this information is actually available.)
Line 18: Line 18:
 
! [[AMD Radeon 400 series|Arctic<br />Islands]]
 
! [[AMD Radeon 400 series|Arctic<br />Islands]]
 
! [[AMD RX Vega series|Vega]]
 
! [[AMD RX Vega series|Vega]]
−
!Vega VII
 
 
|-  
 
|-  
 
! {{rh}} | Released
 
! {{rh}} | Released
Line 36: Line 35:
 
| Jun 2016
 
| Jun 2016
 
| Jun 2017
 
| Jun 2017
−
|Feb 2019
 
 
|-  
 
|-  
 
! {{rh}} | AMD support
 
! {{rh}} | AMD support
 
| colspan=10 {{na|Ended}}  
 
| colspan=10 {{na|Ended}}  
 
| colspan=5 {{ya|Current}}
 
| colspan=5 {{ya|Current}}
−
|
 
 
|-
 
|-
 
! {{rh}} | [[Instruction set]]
 
! {{rh}} | [[Instruction set]]
Line 47: Line 44:
 
| colspan="5" | '''[[TeraScale (microarchitecture)|TeraScale]] instruction set'''
 
| colspan="5" | '''[[TeraScale (microarchitecture)|TeraScale]] instruction set'''
 
| colspan="5" | '''[[Graphics Core Next#Instruction set|GCN instruction set]]'''
 
| colspan="5" | '''[[Graphics Core Next#Instruction set|GCN instruction set]]'''
−
|
 
 
|-
 
|-
 
! {{rh}} | [[Microarchitecture]]
 
! {{rh}} | [[Microarchitecture]]
Line 58: Line 54:
 
| [[Graphics Core Next#fourth|GCN 4<sup>th</sup> gen]]
 
| [[Graphics Core Next#fourth|GCN 4<sup>th</sup> gen]]
 
| [[Graphics Core Next#fifth|GCN 5<sup>th</sup> gen]]
 
| [[Graphics Core Next#fifth|GCN 5<sup>th</sup> gen]]
−
|
 
 
|-
 
|-
 
! {{rh}} | Type
 
! {{rh}} | Type
Line 64: Line 59:
 
| colspan="4" | Programmable pixel & vertex pipelines
 
| colspan="4" | Programmable pixel & vertex pipelines
 
| colspan="10" | [[Unified shader model]]
 
| colspan="10" | [[Unified shader model]]
−
|
 
 
|- style="border-top:2px solid grey;"
 
|- style="border-top:2px solid grey;"
 
! {{rh}} | [[Direct3D]]
 
! {{rh}} | [[Direct3D]]
Line 78: Line 72:
 
| colspan="3" | 11 (12_0)<br/>12 (12_0)
 
| colspan="3" | 11 (12_0)<br/>12 (12_0)
 
| colspan="1" | 11 (12_1)<br/>12 (12_1)
 
| colspan="1" | 11 (12_1)<br/>12 (12_1)
−
|
 
 
|-
 
|-
 
! {{rh}} | [[High-Level Shading Language#Shader model comparison|Shader model]]
 
! {{rh}} | [[High-Level Shading Language#Shader model comparison|Shader model]]
Line 90: Line 83:
 
| colspan="2" | 5.0
 
| colspan="2" | 5.0
 
| colspan="5" | 5.1<br/>6.0
 
| colspan="5" | 5.1<br/>6.0
−
|
 
 
|-  
 
|-  
 
! {{rh}} | [[OpenGL]]
 
! {{rh}} | [[OpenGL]]
Line 98: Line 90:
 
| colspan="2" | 4.4{{efn|name="nofp64"}}
 
| colspan="2" | 4.4{{efn|name="nofp64"}}
 
| colspan="5" | 4.6 with GLSL 4.5 (Linux 4.5+)
 
| colspan="5" | 4.6 with GLSL 4.5 (Linux 4.5+)
−
|
 
 
|-
 
|-
 
! {{rh}} | [[Vulkan (API)|Vulkan]]
 
! {{rh}} | [[Vulkan (API)|Vulkan]]
Line 104: Line 95:
 
| colspan="1" {{not yet|Linux Mesa 17+<br />Win 7+: 1.0}}
 
| colspan="1" {{not yet|Linux Mesa 17+<br />Win 7+: 1.0}}
 
| colspan="4" | 1.1
 
| colspan="4" | 1.1
−
|
 
 
|-  
 
|-  
 
! {{rh}} | [[OpenCL]]
 
! {{rh}} | [[OpenCL]]
Line 112: Line 102:
 
| colspan="3" | 1.2
 
| colspan="3" | 1.2
 
| colspan="4" | 2.0 Windows 7+ Adrenalin (1.2 in Linux, 2.0 and 2.1 WIP mostly in Linux ROCm)
 
| colspan="4" | 2.0 Windows 7+ Adrenalin (1.2 in Linux, 2.0 and 2.1 WIP mostly in Linux ROCm)
−
|
 
 
|-  
 
|-  
 
! {{rh}} | [[Heterogeneous System Architecture|HSA]]
 
! {{rh}} | [[Heterogeneous System Architecture|HSA]]
 
| colspan=10 {{n/a}}  
 
| colspan=10 {{n/a}}  
 
| colspan=5 {{ya}}
 
| colspan=5 {{ya}}
−
|
 
 
|- style="border-top:2px solid grey;"
 
|- style="border-top:2px solid grey;"
 
! {{rh}} | Power saving
 
! {{rh}} | Power saving
Line 124: Line 112:
 
| [[AMD PowerTune|PowerTune]]
 
| [[AMD PowerTune|PowerTune]]
 
| colspan="5" | [[AMD PowerTune|PowerTune]] & [[AMD ZeroCore Power|ZeroCore Power]]
 
| colspan="5" | [[AMD PowerTune|PowerTune]] & [[AMD ZeroCore Power|ZeroCore Power]]
−
|
 
 
|-
 
|-
 
! {{rh}} | Video decoder [[ASIC]]
 
! {{rh}} | Video decoder [[ASIC]]
Line 138: Line 125:
 
| [[Unified Video Decoder#UVD 6|UVD 6.3]]
 
| [[Unified Video Decoder#UVD 6|UVD 6.3]]
 
| [[Unified Video Decoder#UVD 7|UVD 7]]<ref name='TR_vega'>{{cite news|last1=Killian|first1=Zak|title=AMD publishes patches for Vega support on Linux|url=https://techreport.com/news/31627/amd-publishes-patches-for-vega-support-on-linux|accessdate=23 March 2017|publisher=Tech Report|date=22 March 2017}}</ref>{{efn|name="vcn"}}
 
| [[Unified Video Decoder#UVD 7|UVD 7]]<ref name='TR_vega'>{{cite news|last1=Killian|first1=Zak|title=AMD publishes patches for Vega support on Linux|url=https://techreport.com/news/31627/amd-publishes-patches-for-vega-support-on-linux|accessdate=23 March 2017|publisher=Tech Report|date=22 March 2017}}</ref>{{efn|name="vcn"}}
−
|
 
 
|-
 
|-
 
! {{rh}} | Video encoding [[ASIC]]
 
! {{rh}} | Video encoding [[ASIC]]
Line 147: Line 133:
 
| [[Video Coding Engine#VCE 3.4|VCE 3.4]]
 
| [[Video Coding Engine#VCE 3.4|VCE 3.4]]
 
| [[Video Coding Engine#VCE 4.0|VCE 4.0]]<ref name='TR_vega' />{{efn|name="vcn"}}
 
| [[Video Coding Engine#VCE 4.0|VCE 4.0]]<ref name='TR_vega' />{{efn|name="vcn"}}
−
|
 
 
|-
 
|-
 
! {{rh}} | [[AMD TrueAudio|TrueAudio]]
 
! {{rh}} | [[AMD TrueAudio|TrueAudio]]
Line 153: Line 138:
 
| colspan="2" style="background:#DFD;" | Via dedicated DSP
 
| colspan="2" style="background:#DFD;" | Via dedicated DSP
 
| colspan="2" style="background:#DFD;" | Via shaders
 
| colspan="2" style="background:#DFD;" | Via shaders
−
|
 
 
|-
 
|-
 
! {{rh}} | [[FreeSync]]
 
! {{rh}} | [[FreeSync]]
 
| colspan="11" {{N/A}}
 
| colspan="11" {{N/A}}
 
| colspan="4" style="background:#DFD;" | 1<br />2
 
| colspan="4" style="background:#DFD;" | 1<br />2
−
|
 
 
|-
 
|-
 
! {{rh}} | [[HDCP]]{{efn|name="DRM"}}
 
! {{rh}} | [[HDCP]]{{efn|name="DRM"}}
Line 164: Line 147:
 
| colspan="2" | 1.4
 
| colspan="2" | 1.4
 
| colspan="2" | 1.4<br />2.2
 
| colspan="2" | 1.4<br />2.2
−
|
 
 
|-
 
|-
 
! {{rh}} | [[PlayReady]]{{efn|name="DRM"}}
 
! {{rh}} | [[PlayReady]]{{efn|name="DRM"}}
 
| colspan="13" {{N/A}}
 
| colspan="13" {{N/A}}
 
| colspan="2" style="background:#DFD;" | 3.0
 
| colspan="2" style="background:#DFD;" | 3.0
−
|
 
 
|-
 
|-
 
! {{rh}} | Max. [[AMD Eyefinity|displays]]{{efn|name="max display"}}
 
! {{rh}} | Max. [[AMD Eyefinity|displays]]{{efn|name="max display"}}
Line 175: Line 156:
 
| colspan="7" | 2
 
| colspan="7" | 2
 
| colspan="7" | 2–6
 
| colspan="7" | 2–6
−
|
 
 
|-
 
|-
 
! {{rh}} | Max. [[display resolution|resolution]]
 
! {{rh}} | Max. [[display resolution|resolution]]
Line 183: Line 163:
 
| 2–6 × 5120×2880 @ 60&nbsp;Hz
 
| 2–6 × 5120×2880 @ 60&nbsp;Hz
 
| 3 × 7680×4320 @ 60&nbsp;Hz<ref>{{cite web|url=http://radeon.com/_downloads/vega-whitepaper-11.6.17.pdf |title=Radeon’s next-generation Vega architecture |date=13 June 2017 |publisher=Radeon Technologies Group (AMD) |website=radeon.com}}</ref>
 
| 3 × 7680×4320 @ 60&nbsp;Hz<ref>{{cite web|url=http://radeon.com/_downloads/vega-whitepaper-11.6.17.pdf |title=Radeon’s next-generation Vega architecture |date=13 June 2017 |publisher=Radeon Technologies Group (AMD) |website=radeon.com}}</ref>
−
|
 
 
|- style="border-top:2px solid grey;"  
 
|- style="border-top:2px solid grey;"  
 
! {{rh}} | <code>/drm/radeon</code>{{efn|name="drm"}}
 
! {{rh}} | <code>/drm/radeon</code>{{efn|name="drm"}}
 
| colspan="12" {{ya}}
 
| colspan="12" {{ya}}
 
| colspan="3" {{N/A}}
 
| colspan="3" {{N/A}}
−
|
 
 
|-  
 
|-  
 
! {{rh}} | <code>/drm/amdgpu</code>{{efn|name="drm"}}
 
! {{rh}} | <code>/drm/amdgpu</code>{{efn|name="drm"}}
Line 194: Line 172:
 
| colspan="2" {{not yet|Experimental}}<ref>{{cite web |url=http://phoronix.com/scan.php?page=news_item&px=Linux-4.9-Kernel-Highlights |title=The Best Features Of The Linux 4.9 Kernel |last=Larabel |first=Michael |date=7 December 2016 |publisher=[[Phoronix]] |accessdate=7 December 2016}}</ref>
 
| colspan="2" {{not yet|Experimental}}<ref>{{cite web |url=http://phoronix.com/scan.php?page=news_item&px=Linux-4.9-Kernel-Highlights |title=The Best Features Of The Linux 4.9 Kernel |last=Larabel |first=Michael |date=7 December 2016 |publisher=[[Phoronix]] |accessdate=7 December 2016}}</ref>
 
| colspan="3" {{ya}}
 
| colspan="3" {{ya}}
−
|
 
 
|}
 
|}
  

Revision as of 12:29, 13 January 2019

The following table shows features of Radeon-branded GPU microarchitectures.

R100 R200 R300 R400 R500 R600 RV670 R700 Evergreen Northern
Islands
Southern
Islands
Sea
Islands
Volcanic
Islands
Arctic
Islands
Vega
Template:Rh | Released Apr 2000 Aug 2001 Sep 2002 May 2004 Oct 2005 May 2007 Nov 2007 Jun 2008 Sep 2009 Oct 2010 Jan 2012 Sep 2013 Jun 2015 Jun 2016 Jun 2017
Template:Rh | AMD support colspan=10 Template:Na colspan=5 Template:Ya
Template:Rh | Instruction set Not publicly known TeraScale instruction set GCN instruction set
Template:Rh | Microarchitecture TeraScale 1 (VLIW5) TeraScale 2 (VLIW5) TeraScale 3 (VLIW4) GCN 1st gen GCN 2nd gen GCN 3rd gen GCN 4th gen GCN 5th gen
Template:Rh | Type Fixed pipeline[lower-alpha 1] Programmable pixel & vertex pipelines Unified shader model
Template:Rh | Direct3D 7.0 8.1 9.0
11 (9_2)
9.0b
11 (9_2)
9.0c
11 (9_3)
10.0
11 (10_0)
10.1
11 (10_1)
11 (11_0) 11 (11_1)
12 (11_1)
11 (12_0)
12 (12_0)
11 (12_1)
12 (12_1)
Template:Rh | Shader model Template:N/A 1.4 2.0+ 2.0b 3.0 4.0 4.1 5.0 5.1
6.0
Template:Rh | OpenGL 1.3 2.0[lower-alpha 2] 3.3 4.4[lower-alpha 3] 4.6 with GLSL 4.5 (Linux 4.5+)
Template:Rh | Vulkan colspan="10" Template:N/A colspan="1" Template:Not yet 1.1
Template:Rh | OpenCL N/A Close to Metal 1.1 1.2 2.0 Windows 7+ Adrenalin (1.2 in Linux, 2.0 and 2.1 WIP mostly in Linux ROCm)
Template:Rh | HSA N/A colspan=5 Template:Ya
Template:Rh | Power saving colspan="5" Template:Unknown PowerPlay PowerTune PowerTune & ZeroCore Power
Template:Rh | Video decoder ASIC colspan="5" Template:N/A Avivo/UVD UVD+ UVD 2 UVD 2.2 UVD 3 UVD 4 UVD 4.2 UVD 5.0 or 6.0 UVD 6.3 UVD 7[1][lower-alpha 4]
Template:Rh | Video encoding ASIC colspan="10" Template:N/A VCE 1.0 VCE 2.0 VCE 3.0 or 3.1 VCE 3.4 VCE 4.0[1][lower-alpha 4]
Template:Rh | TrueAudio colspan="11" Template:N/A Via dedicated DSP Via shaders
Template:Rh | FreeSync colspan="11" Template:N/A 1
2
Template:Rh | HDCP[lower-alpha 5] colspan="11" Template:Unknown 1.4 1.4
2.2
Template:Rh | PlayReady[lower-alpha 5] colspan="13" Template:N/A 3.0
Template:Rh | Max. displays[lower-alpha 6] 1–2 2 2–6
Template:Rh | Max. resolution colspan="8" Template:Unknown 2–6 × 2560×1600 2–6 × 4096×2160 @ 60 Hz 2–6 × 5120×2880 @ 60 Hz 3 × 7680×4320 @ 60 Hz[2]
Template:Rh | /drm/radeon[lower-alpha 7] colspan="12" Template:Ya colspan="3" Template:N/A
Template:Rh | /drm/amdgpu[lower-alpha 7] colspan="10" Template:N/A colspan="2" Template:Not yet[3] colspan="3" Template:Ya
  1. ↑ The Radeon 100 Series has programmable pixel shaders, but do not fully comply with DirectX 8 or Pixel Shader 1.0. See article on R100's pixel shaders.
  2. ↑ These series do not fully comply with OpenGL 2+ as the hardware does not support all types of non power of two (NPOT) textures.
  3. ↑ OpenGL 4+ compliance requires supporting FP64 shaders and these are emulated on some TeraScale chips using 32-bit hardware.
  4. ↑ 4.0 4.1 The UVD and VCE were replaced by the Video Core Next (VCN) ASIC in the Raven Ridge APU implementation of Vega.
  5. ↑ 5.0 5.1 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.
  6. ↑ More displays may be supported with native DisplayPort connections, or splitting the maximum resolution between multiple monitors with active converters.
  7. ↑ 7.0 7.1 DRM (Direct Rendering Manager) is a component of the Linux kernel. Support in this table refers to the most current version.

References

  1. ↑ 1.0 1.1 Killian, Zak (22 March 2017). "AMD publishes patches for Vega support on Linux". Tech Report. Retrieved 23 March 2017.
  2. ↑ "Radeon's next-generation Vega architecture" (PDF). radeon.com. Radeon Technologies Group (AMD). 13 June 2017.
  3. ↑ Larabel, Michael (7 December 2016). "The Best Features Of The Linux 4.9 Kernel". Phoronix. Retrieved 7 December 2016.

See also