From WikiChip
Difference between revisions of "amd/microarchitectures/vega"
(23 intermediate revisions by 13 users not shown) | |||
Line 1: | Line 1: | ||
− | {{amd title| | + | {{amd title|Vega|arch}} |
{{microarchitecture | {{microarchitecture | ||
− | | atype | + | |atype=GPU |
− | | name | + | |name=Vega |
− | | designer | + | |designer=AMD |
− | | manufacturer | + | |manufacturer=GlobalFoundries |
− | | | + | |introduction=2017 |
− | | | + | |process=12 nm |
− | | | + | |predecessor=Polaris |
− | | | + | |predecessor link=amd/microarchitectures/polaris |
+ | |successor=Navi | ||
+ | |successor link=amd/microarchitectures/navi | ||
+ | |succession=yes | ||
+ | }} | ||
+ | '''Vega''' (also known as '''Graphics core next 5th generation''') is both a [[microarchitecture]] and GPU family developed by [[AMD]] as a successor to the {{\\|GCN4}} [[microarchitecture]] and the {{\\|arctic islands}} family. | ||
+ | |||
+ | == Codenames == | ||
+ | [[File:amd ryzen radeon.svg|right|400px]] | ||
+ | {| class="wikitable" | ||
+ | |- | ||
+ | ! Codename !! Description | ||
+ | |- | ||
+ | | {{amd|Raven Ridge|l=core}} || Mobile processors based on {{\\|Zen}} CPUs and a Vega GPU | ||
+ | |} | ||
+ | |||
+ | == Models == | ||
+ | {| class="wikitable tc2 tc3" | ||
+ | |- | ||
+ | ! colspan="3" | Vega [[IGP]] Models !! colspan="10" | Standards | ||
+ | |- | ||
+ | ! rowspan="2" | Name !! rowspan="2" | Compute Units !! rowspan="2" | Shaders!! colspan="2" | [[Vulkan]] !! colspan="3" | [[Direct3D]] !! colspan="2" | [[OpenGL]] !! colspan="2" | [[OpenCL]] | ||
+ | |- | ||
+ | | Windows || Linux || Windows || Linux || [[High Level Shading Language|HLSL]] || Windows || Linux || Windows || Linux | ||
+ | |- | ||
+ | | Vega 8 || 8|| 512 || rowspan="3" colspan="2" style="text-align: center;" | '''1.1''' || rowspan="3" style="text-align: center;" | '''12''' || rowspan="3" style="text-align: center;" | '''N/A''' || rowspan="3" style="text-align: center;" | '''-''' || rowspan="3" style="text-align: center;" | '''4.6''' || rowspan="3" style="text-align: center;" | '''4.6''' || rowspan="3" style="text-align: center;" colspan="2" | '''2.2''' | ||
+ | |- | ||
+ | | Vega 10 || 10|| 640 | ||
+ | |- | ||
+ | | Vega 11 || 11|| 704 | ||
+ | |} | ||
+ | |||
+ | {| class="wikitable tc2 tc3" | ||
+ | |- | ||
+ | ! colspan="3" | Vega Dedicated Models !! colspan="10" | Standards | ||
+ | |- | ||
+ | ! rowspan="2" | Name !! rowspan="2" | Compute Units !! rowspan="2" | Shaders!! colspan="2" | [[Vulkan]] !! colspan="3" | [[Direct3D]] !! colspan="2" | [[OpenGL]] !! colspan="2" | [[OpenCL]] | ||
+ | |- | ||
+ | | Windows || Linux || Windows || Linux || [[High Level Shading Language|HLSL]] || Windows || Linux || Windows || Linux | ||
+ | |- | ||
+ | | Vega 56 || 56|| 3584 || rowspan="2" colspan="2" style="text-align: center;" | '''1.1''' || rowspan="2" style="text-align: center;" | '''12''' || rowspan="2" style="text-align: center;" | '''N/A''' || rowspan="2" style="text-align: center;" | '''-''' || rowspan="2" style="text-align: center;" | '''4.6''' || rowspan="2" style="text-align: center;" | '''4.6''' || rowspan="2" style="text-align: center;" colspan="2" | '''2.2''' | ||
+ | |- | ||
+ | | Vega 64 || 64|| 4096 | ||
+ | |} | ||
+ | |||
+ | == Performance == | ||
+ | The original target of the RX Vega series was to compete with Nvidia's latest Pascal architecture. | ||
+ | RX Vega 64 -> GTX 1080 | ||
+ | RX Vega 56 -> GTX 1070 | ||
+ | |||
+ | The performance is generally good, but when it comes to performance per watt, or PPW, Vega is outperformed by Pascal. | ||
+ | |||
+ | == Hardware Accelerated Video == | ||
+ | {{zen with vega hardware accelerated video table|col=1}} | ||
− | + | == Process Technology == | |
− | + | {{see also|14 nm process}} | |
− | + | Vega is manufactured on [[GlobalFoundries]]' [[14 nm process]]. | |
− | |||
− | | | ||
− | }} | ||
− | |||
== Architecture == | == Architecture == | ||
[[File:amd gpu roadmap.png|400px|right]] | [[File:amd gpu roadmap.png|400px|right]] | ||
− | === Key changes from {{ | + | {{future information}} |
− | * High | + | |
− | + | === Key changes from {{amd|Arctic Islands|l=arch}} === | |
+ | *New programmable geometry pipeline | ||
+ | **Up to 2x throughput | ||
+ | **Primitive shaders | ||
+ | **Improved workload balancing | ||
+ | *Tile based rendering | ||
+ | *New low precision instructions | ||
+ | **Half precision floating point with 2x performance | ||
+ | **8 bit integer with 4x performance | ||
+ | *15% higher clock speeds | ||
+ | *HBM 2 | ||
+ | **2x bandwidth | ||
+ | **4x memory capacity | ||
+ | *New memory controller | ||
+ | *Render back-end is now a client of the L2 cache | ||
+ | *The instruction buffer has been enlarged | ||
+ | |||
+ | |||
+ | ====HBM 2==== | ||
+ | Vega makes use of 2 stacks of HBM 2 ([[High bandwidth memory]]). | ||
+ | |||
+ | {| class="wikitable" | ||
+ | |- | ||
+ | ! single stack !! HBM 1 !! HBM 2 | ||
+ | |- | ||
+ | | dies || 4 + 1<info>4 dram die, 1 control die</info> || 2-8 + 1<info>2,4 or 8 dram die, 1 control die</info> | ||
+ | |- | ||
+ | | Gb/die || 2Gb || 8Gb | ||
+ | |- | ||
+ | | total Gb || 8Gb || 16-64Gb | ||
+ | |- | ||
+ | | bus width || 1024 || 1024 | ||
+ | |- | ||
+ | | clock speed || 500 MHz || 945 MHz | ||
+ | |- | ||
+ | | bandwidth || 128 GB/s || 238 GB/s | ||
+ | |} | ||
== References == | == References == | ||
* AMD 2017 Financial Analyst Day, May 16, 2017 | * AMD 2017 Financial Analyst Day, May 16, 2017 | ||
+ | |||
+ | == Documents == | ||
+ | * [[:File:vega-whitepaper.pdf|White Paper: Radeon’s next-generation Vega architecture]] | ||
== See Also == | == See Also == | ||
* [[list of microarchitectures]] | * [[list of microarchitectures]] | ||
+ | * [[intel/microarchitectures|gen9]] | ||
+ | * {{amd|Raven Ridge|l=core}} |
Latest revision as of 11:42, 16 June 2020
Edit Values | |
Vega µarch | |
General Info | |
Arch Type | GPU |
Designer | AMD |
Manufacturer | GlobalFoundries |
Introduction | 2017 |
Process | 12 nm |
Succession | |
Vega (also known as Graphics core next 5th generation) is both a microarchitecture and GPU family developed by AMD as a successor to the GCN4 microarchitecture and the arctic islands family.
Contents
Codenames[edit]
Codename | Description |
---|---|
Raven Ridge | Mobile processors based on Zen CPUs and a Vega GPU |
Models[edit]
Vega IGP Models | Standards | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Name | Compute Units | Shaders | Vulkan | Direct3D | OpenGL | OpenCL | ||||||
Windows | Linux | Windows | Linux | HLSL | Windows | Linux | Windows | Linux | ||||
Vega 8 | 8 | 512 | 1.1 | 12 | N/A | - | 4.6 | 4.6 | 2.2 | |||
Vega 10 | 10 | 640 | ||||||||||
Vega 11 | 11 | 704 |
Vega Dedicated Models | Standards | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Name | Compute Units | Shaders | Vulkan | Direct3D | OpenGL | OpenCL | ||||||
Windows | Linux | Windows | Linux | HLSL | Windows | Linux | Windows | Linux | ||||
Vega 56 | 56 | 3584 | 1.1 | 12 | N/A | - | 4.6 | 4.6 | 2.2 | |||
Vega 64 | 64 | 4096 |
Performance[edit]
The original target of the RX Vega series was to compete with Nvidia's latest Pascal architecture. RX Vega 64 -> GTX 1080 RX Vega 56 -> GTX 1070
The performance is generally good, but when it comes to performance per watt, or PPW, Vega is outperformed by Pascal.
Hardware Accelerated Video[edit]
[Edit] Zen with Radeon Vega Hardware Accelerated Video Capabilities | |||||
---|---|---|---|---|---|
Codec | Encode | Decode | |||
Max FPS | @1080p | @1440p | @2160p | @1080p 4:2:0 | @2160p 4:2:0 |
MPEG-2 (H.262) | 60 FPS | N/A | |||
VC-1 | |||||
VP9 8bpc | 240 FPS | 60 FPS | |||
VP9 10bpc | |||||
MPEG-4 AVC (H.264) 8bpc | 120 FPS | 60 FPS | 30 FPS | ||
MPEG-4 AVC (H.264) 10bpc | |||||
HEVC (H.265) 8bpc | 120 FPS | 60 FPS | 30 FPS | ||
HEVC (H.265) 10bpc | |||||
JPEG/MJPEG 8bpc |
Process Technology[edit]
- See also: 14 nm process
Vega is manufactured on GlobalFoundries' 14 nm process.
Architecture[edit]
Key changes from Arctic Islands[edit]
- New programmable geometry pipeline
- Up to 2x throughput
- Primitive shaders
- Improved workload balancing
- Tile based rendering
- New low precision instructions
- Half precision floating point with 2x performance
- 8 bit integer with 4x performance
- 15% higher clock speeds
- HBM 2
- 2x bandwidth
- 4x memory capacity
- New memory controller
- Render back-end is now a client of the L2 cache
- The instruction buffer has been enlarged
HBM 2[edit]
Vega makes use of 2 stacks of HBM 2 (High bandwidth memory).
single stack | HBM 1 | HBM 2 |
---|---|---|
dies | 4 + 1 4 dram die, 1 control die |
2-8 + 1 2,4 or 8 dram die, 1 control die
|
Gb/die | 2Gb | 8Gb |
total Gb | 8Gb | 16-64Gb |
bus width | 1024 | 1024 |
clock speed | 500 MHz | 945 MHz |
bandwidth | 128 GB/s | 238 GB/s |
References[edit]
- AMD 2017 Financial Analyst Day, May 16, 2017
Documents[edit]
See Also[edit]
Facts about "Vega - Microarchitectures - AMD"
codename | Vega + |
designer | AMD + |
first launched | 2017 + |
full page name | amd/microarchitectures/vega + |
instance of | microarchitecture + |
manufacturer | GlobalFoundries + |
microarchitecture type | GPU + |
name | Vega + |
process | 12 nm (0.012 μm, 1.2e-5 mm) + |