Radeon RX Vega
AMD graphics processors using the fifth generation GCN architecture
The Radeon RX Vega series comprises graphics processing units developed by AMD. Launched in August 2017, these chips utilise the fifth generation Graphics Core Next architecture. They power desktop cards, mobile APUs and embedded systems, featuring high bandwidth memory support.
- Uses fifth generation Graphics Core Next architecture
- Manufactured on 14 nm and 7 nm FinFET processes
- Supports HBM2 memory with high bandwidth
- Launched for desktops in August 2017
- Integrated into Ryzen and Athlon APUs
What it is
The Radeon RX Vega series represents a line of graphics processors created by AMD. These units rely on the fifth generation of the Graphics Core Next architecture, known internally as Vega. The initial models arrived in August 2017 for desktop computers. The family expanded to include integrated graphics for mobile devices and embedded systems. Manufacturing involved both 14 nanometre and 7 nanometre processes. This series bridges the gap between discrete gaming cards and system-on-chip solutions for laptops.
How it came about
AMD first revealed partial details of the Vega architecture in December 2016 with the Radeon Instinct MI25. The full consumer lineup was announced at CES in January 2017 alongside Zen central processors. The first desktop cards launched later that year in August. Mobile variants followed in October 2017 within Ryzen processors. Desktop APUs appeared in early 2018. The architecture succeeded the R9 300 series and Fury products, aiming to improve performance per clock cycle.
Inside the chip
Vega introduces the Next-Gen Compute Unit, which handles various data precisions efficiently. It supports eight, sixteen, thirty-two or sixty-four bit operations in a single cycle. Rapid Packed Math allows two half-precision calculations in the time of one standard operation. A new memory hierarchy includes a high-bandwidth cache controller. The primitive shader replaces older geometry stages for better load balancing. Draw Stream Binning Rasterizer improves efficiency by culling invisible pixels early. Support extends to HBM2 memory and large virtual address spaces.
How it was made
The initial Vega 10 chips used a 14 nanometre FinFET process. Samsung Electronics developed this technology and licensed it to GlobalFoundries for production. These dies contained approximately 12.5 billion transistors. Later, the Vega 20 design moved to a seven nanometre node manufactured by TSMC. This smaller process increased the transistor count to 13.2 billion. The shift allowed for higher frequencies and better power efficiency in subsequent products like the Radeon VII.
Where it went
Desktop users employed the RX Vega 56 and 64 for gaming and content creation. Mobile APUs such as the Ryzen 2500U and 2700U brought Vega graphics to laptops. Desktop APUs like the Ryzen 3 2200G integrated these cores for budget builds. Embedded applications utilised the Ryzen Embedded V1000 line. Athlon processors also adopted Vega graphics in 2018. The architecture supported OpenGL 4.6, Vulkan 1.3 and Direct3D feature level 12_1.
Versions and family
The series includes discrete cards like the RX Vega 56 and 64. A liquid-cooled version of the Vega 64 was also released. The enthusiast-grade Radeon VII used the newer seven nanometre process. Integrated variants appeared in Raven Ridge, Picasso, Renoir and Cezanne APUs. These covered desktop, mobile and embedded segments. Each APU generation updated the underlying CPU core while retaining the Vega graphics design. The RX Vega 10 and 11 served as entry-level integrated options.
Why it matters
Vega marked AMD's return to the high-end graphics market after the Fury era. It introduced hardware features like conservative rasterisation and rasterizer ordered views. The architecture enabled double the bandwidth per pin compared to previous HBM standards. This allowed for compact memory footprints with high capacity. The transition to seven nanometres demonstrated AMD's ability to scale the design. It paved the way for the subsequent RDNA architecture found in the RX 5000 series.
Questions people ask about Radeon RX Vega
What architecture does the Radeon RX Vega use?
The series uses the fifth generation of AMD's Graphics Core Next architecture. This design is codenamed Vega and introduces new compute units and memory controllers.
Which companies manufactured these chips?
Samsung Electronics and GlobalFoundries produced the initial 14 nanometre versions. TSMC later manufactured the seven nanometre variants used in high-end models like the Radeon VII.
What type of memory does Vega support?
Vega supports High Bandwidth Memory 2 (HBM2). This technology offers double the bandwidth per pin compared to the previous generation and uses less physical space than GDDR5.
Are there mobile versions of Vega graphics?
Yes, Vega graphics are integrated into many AMD mobile APUs. These include the Ryzen 2000, 3000, 4000 and 5000 series for laptops, as well as embedded processors.
Good reading and sources
- Radeon Vega Frontier Edition: First AMD Vega GPU is for the prosArs Technica, Article
- AMD's Radeon RX Vega graphics cards revealed: Specs, price, featuresPCWorld, Article
- Checking your browserAnandTech, Article
- Radeon RX Vega series on WikipediaEncyclopedia
- More photos on Wikimedia CommonsPhotos
- Wikidata recordOpen data
The facts on this page come from the Wikipedia article "Radeon RX Vega series", written by its contributors and used under the CC BY-SA 4.0 licence, and from its Wikidata record (CC0). EveryChip rewrote the text in its own words, with AI assistance, and compares every page with the article to make sure no passage is copied. It may be reused under the same CC BY-SA 4.0 licence with a link back.
It may contain mistakes, and figures change over time. Nothing here is investment or buying advice. If something is wrong, tell us. Last refreshed 2026-11-14.