Radeon RX Vega series: Difference between revisions
mNo edit summary |
→Chipset table: add pro cards |
||
Line 29: | Line 29: | ||
===Desktop=== |
===Desktop=== |
||
{{AMD Radeon RX Vega}} |
{{AMD Radeon RX Vega}} |
||
===Professional=== |
|||
{{AMD Radeon Vega Frontier Edition}} |
|||
== See also == |
== See also == |
Revision as of 21:09, 1 August 2017
Release date | TBA |
---|---|
Codename |
|
Architecture | GCN 5th gen |
History | |
Predecessor | Radeon 500 Series |
Successor | Navi Architecture |
The AMD RX Vega series is a series of graphics processors produced by AMD. These cards are to use the Vega architecture, are to feature HBM2 high-speed memory[1] and will continue to use the 14nm FinFET architecture.[2] Vega will be the first to use the new Graphics Core Next 5th generation and will be succeeded by the Navi architecture in 2018.[3]
Microarchitecture
The Vega microarchitecture is set to be AMD's upcoming flagship graphics cards,[4] and is to be the successors to the RX 300 series enthusiast Fury products and is set to launch in 2017.
Partial specifications of the architecture and Vega 10 GPU were announced with the Radeon Instinct MI25 in December 2016.[5] The GPU is expected to have 12.5 TFLOPS of single precision performance. AMD later teased details of the Vega architecture which is to target increased instructions per clock, higher clock speeds, and support HBM2.[6][7][8] Pre-release performance comparisons of the RX Vega series to Nvidia's Geforce 10 series have also been inferred based on the professionally targeted Radeon Vega Frontier Edition.[9]
Announcement
Vega was originally announced at AMD's CES 2017 presentation on January 5, 2017[10] alongside the Zen line of CPUs.[11] Raja Koduri, Senior Vice President and Chief Architect of the Radeon Technologies Group,[12] stated "It is incredible to see GPUs being used to solve gigabyte-scale data problems in gaming to exabyte-scale data problems in machine intelligence. We designed the Vega architecture to build on this ability".[10]
Chipset table
Desktop
Model (Code name) |
Release Date & Price |
Architecture & fab |
Transistors & die size |
Core | Fillrate[a][b][c] | Processing power[a][d] (GFLOPS) |
Memory | TBP | Bus interface | |||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Config[e] | Clock[a] (MHz) |
Texture (GT/s) |
Pixel (GP/s) |
Half | Single | Double | Size (GB) |
Bandwidth (GB/s) |
Bus type & width |
Clock (MT/s) | ||||||
Radeon RX Vega 56 (Vega 10)[13][14][15] |
Aug 28, 2017 $399 USD |
GCN 5 GloFo 14LPP[f][16][17] |
12.5×109 486 mm2 |
3584:224:64 56 CU |
1156 1471 |
258.9 329.5 |
73.98 94.14 |
16,572 21,088 |
8,286 10,544 |
517.9 659.0 |
8 | 409.6 | HBM2 2048-bit |
1600 | 210 W | PCIe 3.0 ×16 |
Radeon RX Vega 64 (Vega 10)[18][14][15] |
Aug 14, 2017 $499 USD |
4096:256:64 64 CU |
1247 1546 |
319.2 395.8 |
79.81 98.94 |
20,431 25,330 |
10,215 12,665 |
638.5 791.6 |
483.8 | 1890 | 295 W | |||||
Radeon RX Vega 64 Liquid (Vega 10)[18][14][15] |
Aug 14, 2017 $699 USD |
1406 1677 |
359.9 429.3 |
89.98 107.3 |
23,036 27,476 |
11,518 13,738 |
719.9 858.6 |
345 W |
- ^ a b c Boost values (if available) are stated below the base value in italic.
- ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
- ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
- ^ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
- ^ Unified shaders : Texture mapping units : Render output units and Compute units (CU)
- ^ GlobalFoundries' 14 nm 14LPP FinFET process is second-sourced from Samsung Electronics.
Professional
Model (Code name) |
Release date & price |
Architecture & fab |
Transistors & die size |
Core | Fillrate[a][b][c] | Processing power[a][d] (GFLOPS) |
Memory | TBP | Bus interface |
Graphic output ports | |||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Config[e] | Clock[a] (MHz) |
Texture (GT/s) |
Pixel (GP/s) |
Half | Single | Double | Size (GB) |
Bandwidth (GB/s) |
Bus type & width |
Clock (MT/s) | |||||||
Radeon Vega Frontier Edition (Air-cooled) (Vega 10)[19][20][21] |
Jun 27, 2017 $999 USD |
GCN 5 GloFo 14 nm |
12.5×109 494 mm2 |
4096:256:64 64 CU |
1382 1600 |
353.8 409.6 |
88.4 102.4 |
22,643 26,214 |
11,321 13,107 |
707.6 819.2 |
16 | 484 | HBM2 2048-bit |
1890 | 300 W | PCIe 3.0 ×16 |
3× DP 1.4a 1× HDMI 2.0b |
Radeon Vega Frontier Edition (Liquid-cooled) (Vega 10)[19][22][23] |
Jun 27, 2017 $1,499 USD |
375 W |
- ^ a b c Boost values (if available) are stated below the base value in italic.
- ^ Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
- ^ Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
- ^ Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
- ^ Unified shaders : Texture mapping units : Render output units and Compute units (CU)
See also
References
- ^ "AMD Radeon Vega Frontier Edition Unveiled: 13 TFLOPs, 16GB HBM2, Ships In June". Retrieved 2017-05-17.
- ^ "Radeon Vega Frontier Edition: First AMD Vega GPU is for the pros". Ars Technica. Retrieved 2017-05-17.
- ^ Smith, Ryan. "AMD Updates GPU Architecture Roadmap: After Navi Comes "Next Gen"". Retrieved 2017-05-17.
- ^ Smith, Ryan (5 January 2017). "The AMD Vega GPU Architecture Teaser". Anandtech.com. Retrieved 30 June 2017.
- ^ Shrout, Ryan (12 December 2016). "Radeon Instinct Machine Learning GPUs include Vega, Preview Performance". PC Per. Retrieved 12 December 2016.
- ^ Kampman, Jeff (5 January 2017). "The curtain comes up on AMD's Vega architecture". TechReport.com. Retrieved 10 January 2017.
- ^ Shrout, Ryan (5 January 2017). "AMD Vega GPU Architecture Preview: Redesigned Memory Architecture". PC Perspective. Retrieved 10 January 2017.
- ^ Smith, Ryan (5 January 2017). "The AMD Vega Architecture Teaser: Higher IPC, Tiling, & More, coming in H1'2017". Anandtech.com. Retrieved 10 January 2017.
- ^ Shrout, Ryan (30 June 2017). "The Radeon Vega Frontier Edition 16GB Air Cooled Review". PC Perspective. Retrieved 30 June 2017.
- ^ a b "Vega: AMD's New Graphics Architecture for Virtually Unlimited Workloads". www.amd.com. Retrieved 2017-05-17.
- ^ "AMD Ryzen CPUs: 7 all-new details revealed at CES 2017". PCWorld. Retrieved 2017-05-17.
- ^ "Executive Biography - Raja Koduri". www.amd.com. Retrieved 2017-05-17.
- ^ "Radeon RX Vega 56 Graphics". AMD. Retrieved July 31, 2017.
- ^ a b c Smith, Ryan (July 30, 2017). "Radeon RX Vega Unveiled". AnandTech. Retrieved July 31, 2017.
- ^ a b c Angelini, Chris (July 30, 2017). "AMD Radeon RX Vega 64: Bundles, Specs, And Aug. 14 Availability". Tom's Hardware. Retrieved July 31, 2017.
- ^ "14LPP 14nm FinFET Technology". GlobalFoundries.
- ^ Schor, David (July 22, 2018). "VLSI 2018: GlobalFoundries 12nm Leading-Performance, 12LP". WikiChip Fuse. Retrieved May 31, 2019.
- ^ a b "Radeon RX Vega 64 Graphics". AMD. Archived from the original on August 6, 2017. Retrieved May 18, 2022.
- ^ a b Shrout, Ryan (July 17, 2017). "The AMD Radeon Vega Frontier Edition 16GB Liquid-Cooled Review". PC Perspective. Retrieved July 26, 2017.
- ^ "Radeon Vega Frontier Edition (Air-cooled)". AMD. Retrieved April 21, 2022.
- ^ "AMD Radeon Vega Frontier Edition Specs". TechPowerUp. Retrieved April 21, 2022.
- ^ "Radeon Vega Frontier Edition (Liquid-cooled)". AMD. Retrieved April 21, 2022.
- ^ "AMD Radeon Vega Frontier Edition Watercooled Specs". TechPowerUp. Retrieved April 21, 2022.