RDNA 2

On July 7, 2019, AMD released the first iteration of the RDNA microarchitecture, a new graphics architecture designed specifically for gaming that replaced the aging Graphics Core Next (GCN) microarchitecture. With RDNA, AMD sought to reduce latency and improve power efficiency over their previous Vega series based on GCN 5th gen and Nvidia's competing Turing microarchitecture.{{cite web |last1=James |first1=Dave |date=October 31, 2019 |title=AMD Navi RDNA architecture – a GPU designed purely for PC gamers |url=https://www.pcgamesn.com/amd/navi-rdna-architecture-release-date-specs-performance |website=PCGamesN |language=en-US |access-date=April 10, 2023}}

RDNA 2 was first publicly announced in January 2020 with AMD initially calling RDNA 2 a "refresh" of the original RDNA architecture from the previous year.{{cite web |last1=Alcorn |first1=Paul |date=January 29, 2020 |title=AMD to Introduce New Next-Gen RDNA GPUs in 2020, Not a Typical 'Refresh' of Navi |url=https://www.tomshardware.com/news/amds-navi-to-be-refreshed-with-next-gen-rdna-architecture-in-2020 |website=Tom's Hardware |language=en-US |access-date=April 10, 2023}} At AMD's Financial Analysts Day held on March 5, 2020, AMD showed a client GPU roadmap that gave details on RDNA's successor, RDNA 2, that it would again be built using TSMC's 7 nm process and would be coming in 2020.{{cite web |last1=Smith |first1=Ryan |date=March 5, 2020 |title=AMD's 2020-2022 Client GPU Roadmap: RDNA 3 & Navi 3X On the Horizon With More Perf & Efficiency |url=https://www.anandtech.com/show/15592/amds-2020-client-gpu-roadmap-rdna-3-on-the-horizon |website=AnandTech |language=en-US |access-date=April 10, 2023}} AMD told their investors that they were targeting a 50% uplift in performance-per-watt and increased IPC with the RDNA 2 microarchitecture.{{cite web |last1=Smith |first1=Ryan |date=March 5, 2020 |title=AMD's RDNA 2 Gets A Codename: "Navi 2X" Comes This Year With 50% Improved Perf-Per-Watt |url=https://www.anandtech.com/show/15591/amds-rdna-2-gets-a-codename-navi-2x-comes-this-year-with-50-improved-perfperwatt |website=AnandTech |language=en-US |access-date=April 10, 2023}}

On October 28, 2020, AMD held an online unveiling event for the RDNA 2 architecture and Radeon RX 6000 series.{{cite web |last1=Thubron |first1=Rob |date=September 9, 2020 |title=AMD confirms Radeon 6000 reveal and Zen 3 launch for October |url=https://www.techspot.com/news/86683-big-radeon-6000-reveal-could-arrive-tomorrow.html |website=TechSpot |language=en-AU |access-date=April 10, 2023}}{{cite web |last1=Lyles |first1=Taylor |date=September 9, 2020 |title=AMD's next-generation Zen 3 CPUs and Radeon RX 6000 'Big Navi' GPU will be revealed next month |url=https://www.theverge.com/2020/9/9/21429127/amd-zen-3-cpu-big-navi-gpu-events-october |work=The Verge |language=en-US |access-date=April 10, 2023}} The event came 20 days after AMD's unveiling event for Ryzen 5000 series processors built on the Zen 3 microarchitecture.

RDNA 2 contains a significant increase in the number of Compute Units (CUs) with a maximum of 80, a doubling from the maximum of 40 in the Radeon RX 5700 XT. Each Compute Unit contains 64 shader cores.{{cite web |last1=Walton |first1=Jarred |date=November 3, 2020 |title=AMD Unveils Big Navi: RX 6900 XT, RX 6800 XT and RX 6800 Take On Ampere |url=https://www.tomshardware.com/news/amd-rx-6000-rdna-2-big-navi-gpus-revealed |website=Tom's Hardware |language=en-US |access-date=April 10, 2023}} CUs are organized into groups of two named Work Group Processors with 32{{nbsp}}KB of shared L0 cache per WGP. Each CU contains two sets of an SIMD32 vector unit, an SISD scalar unit, textures units, and a stack of various caches.{{cite web |last1=Evanson |first1=Nick |date=December 6, 2020 |title=Nvidia Ampere vs. AMD RDNA 2: Battle of the Architectures |url=https://www.techspot.com/article/2151-nvidia-ampere-vs-amd-rdna2/ |website=TechSpot |language=en-AU |access-date=April 10, 2023}} New low precision data types like INT4 and INT8 are new supported data types for RDNA 2 CUs.

The RDNA 2 graphics pipeline has been reconfigured and reordered for greater performance-per-watt and more efficient rendering by moving the caches closer to the shader engines. A new mesh shaders model allows shader rendering to be done in parallel using smaller batches of primitives called "meshlets". As a result, the mesh shaders feature enables greater control of the GPU geometry pipeline.{{cite web |last1=Riley |first1=Colin |year=2020 |title=Sampler Feedback & Mesh Shaders |url=https://gpuopen.com/wp-content/uploads/slides/AMD_RDNA2_DirectX12_Ultimate_SamplerFeedbackMeshShaders.pdf |website=GPUOpen |language=en-US |access-date=April 10, 2023}}

Real-time hardware accelerated ray tracing is a new feature for RDNA 2 which is handled by a dedicated ray accelerator inside each CU.{{cite web |last1=Evenden |first1=Ian |date=November 17, 2020 |title=AMD teases 'mind-blowing' RDNA 2 ray tracing in its new tech demo |url=https://www.pcgamer.com/amd-has-all-the-shinies/ |website=Tom's Hardware |language=en-US |access-date=April 10, 2023}} Ray tracing on RDNA 2 relies on the more open DirectX Raytracing protocol rather than the Nvidia RTX protocol.{{cite web |last1=Salter |first1=Jim |date=October 28, 2020 |title=AMD's newest graphics cards: RDNA2 power from $579 to $999 |url=https://arstechnica.com/gaming/2020/10/amds-newest-graphics-cards-rdna2-power-from-579-999/ |website=Ars Technica |language=en-US |access-date=April 10, 2023}}

In February 2023, it was reported that driver updates had boosted ray tracing performance by up to 40% using DirectX Raytracing.{{cite web |last1=Mujtaba |first1=Hassan |date=February 16, 2023 |title=AMD Radeon RX 6000 "RDNA 2" GPUs Get Up To 40% Ray Tracing Performance Boost In 3DMark DXR With Latest Drivers |url=https://wccftech.com/amd-radeon-rx-6000-rdna-2-gpus-40-percent-ray-tracing-performance-boost-3dmark-dxr-latest-drivers/ |website=Wccftech |language=en-US |access-date=April 10, 2023}}

With RDNA 2 using the same 7 nm node as RDNA, AMD claims that RDNA 2 achieves a 30% frequency increase over its predecessor while using the same power.{{cite web |last1=Altavilla |first1=Dave |last2=Chiapetta |first2=Marco |date=October 28, 2020 |title=AMD Unveils Three Powerful Radeon RX 6000 Series Big Navi Cards To Topple NVIDIA's Best |url=https://hothardware.com/news/amd-unveils-radeon-rx-6800-radeon-rx-6800-xt-and-radeon-rx-6900-xt |website=HotHardware |language=en-US |access-date=April 10, 2023}}

In addition to the traditional L1 and L2 caches that GPUs possess, RDNA 2 adds a new global L3 cache that AMD calls "Infinity Cache".{{cite web |last1=Chacos |first1=Brad |date=November 18, 2020 |title=RDNA 2 deep-dive: What's inside AMD's Radeon RX 6000 graphics cards |url=https://www.pcworld.com/article/393733/rdna-2-deep-dive-inside-amd-radeon-rx-6000-graphics-cards.html |website=PCWorld |language=en-US |access-date=April 10, 2023}} This was done to avoid the use of a wider memory bus while still being able to maintain the same data bandwidth. Product technology architect Sam Naffziger said that, without Infinity Cache, "We were looking at the daunting prospect of having to put a 512-bit interface and all the power, area and expense associated with that".{{cite web |last=Ridley |first=Jacob |date=November 21, 2020 |title=AMD's Infinity Cache is the MVP of the RX 6000-series, and it's only going to get better |url=https://www.pcgamer.com/amd-infinity-cache-rx-6800-xt-rx-6800-rdna-2/ |website=PC Gamer |language=en-US |access-date=April 14, 2024}} Using a wider memory bus requires more power which is in conflict with AMD's increased performance-per-watt goals for RDNA 2. AMD engineers ran tests comparing RDNA 2 silicon featuring a large on-die cache and with wider memory buses. They discovered that having such a cache would aid in the re-use of temporal and spatial data when the GPU is rendering a complex image. It is beneficial for the GPU's compute units to have fast access to a physically close cache rather than searching for data in video memory. AMD claims that RDNA 2's 128{{nbsp}}MB of on-die Infinity Cache "dramatically reduces latency and power consumption".{{cite press release |title=AMD Unveils Next-Generation PC Gaming with AMD Radeon™ RX 6000 Series – Bringing Leadership 4K Resolution Performance to AAA Gaming |url=https://www.amd.com/en/press-releases/2020-10-28-amd-unveils-next-generation-pc-gaming-amd-radeon-rx-6000-series-bringing |location=Santa Clara, CA |website=AMD |language=en-US |date=October 28, 2020 |access-date=April 10, 2023}} The GPU having access to a large L2 or L3 cache allows it to more quickly access necessary data compared to accessing VRAM or system RAM. The Infinity Cache is made up of two sets of 64{{nbsp}}MB cache that can run on its own clock rate independent from the GPU cores. The Infinity Cache has a peak internal transfer bandwidth of 1986.6 GB/s and results in less reliance being placed on the GPU's GDDR6 memory controllers. Each Shader Engine now has two sets of L1 caches. The large cache of RDNA 2 GPUs give them a higher overall memory bandwidth compared to Nvidia's GeForce RTX 30 series GPUs.

AMD claims that RDNA 2 achieves up to a 54% increase in performance-per-watt over the first RDNA microarchitecture. 21% of that 54% improvement is attributed to performance-per-clock enhancements, in part due to the addition of Infinity Cache.{{cite web |last1=Frausto-Robledo |first1=Anthony |date=October 18, 2021 |title=AMD's RDNA 2 Architecture—Behind the Radeon Pro W6600’s Stellar Performance |url=https://architosh.com/2021/10/amds-rdna-2-architecture-behind-the-radeon-pro-w6600s-stellar-performance/ |website=Architosh |language=en-US |access-date=April 10, 2023}}

RDNA 2 uses the VCN 3.0, VCN 3.1, and VCN 3.1.2 video decoding blocks in its media engine.{{cite web |last1=Shilov |first1=Anton |date=May 4, 2022 |title=First Details About AMD's Next Generation Video Engine Revealed |url=https://www.tomshardware.com/news/next-amd-video-engine-may-lack-av1 |website=Tom's Hardware |language=en-US |access-date=April 10, 2023}}{{cite web |last1=Larabel |first1=Michael |date=September 15, 2020 |title=AMD Radeon Navi 2 / VCN 3.0 Supports AV1 Video Decoding |url=https://www.phoronix.com/news/AV1-Decode-For-AMD-VCN-3.0 |website=Phoronix |language=en-US |access-date=April 10, 2023}} It adds support for AV1 decoding at up to 8K resolution, though AV1 hardware encoding support would not come until RDNA 3 in 2022.{{cite web |title=AMD Navi 2X GPUs (RDNA2) to support AV1 decoding |url=https://videocardz.com/newz/amd-navi-2x-gpus-rdna2-to-support-av1-decoding |website=VideoCardz |language=en-US |date=September 15, 2020 |access-date=April 10, 2023}}{{cite web |title=AMD RDNA2 Graphics Architecture Features AV1 Decode Hardware-Acceleration |url=https://www.techpowerup.com/273243/amd-rdna2-graphics-architecture-features-av1-decode-hardware-acceleration |website=TechPowerUp |language=en-US |date=October 12, 2020 |access-date=April 10, 2023}} However, the low-end Navi 24 die and iGPUs based on RDNA 2.0 do not contain any media encoders and cannot decode AV1 as a result.

{{AMD Radeon RX 6000}}

{{AMD Radeon RX 6000M}}

{{AMD Radeon Pro W6000}}

{{AMD Radeon Pro W6000X}}

{{AMD Radeon Pro W6000M}}

{{notelist|refs=

{{efn|name="Boost"|Boost values (if available) are stated below the base value in italic.}}

{{efn|name="Texture fill"|Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.}}

{{efn|name="Pixel fill"|Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.}}

{{efn|name="FLOPS"|Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.}}

{{efn|name="Core config"|Unified shaders : Texture mapping units : Render output units : Ray accelerators and Compute units (CU)}}

}}

{{notelist|refs=

{{efn|name="Boost"|Boost values (if available) are stated below the base value in italic.}}

{{efn|name="Texture fill"|Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.}}

{{efn|name="Pixel fill"|Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.}}

{{efn|name="FLOPS"|Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.}}

{{efn|name="Core config"|Unified shaders : Texture mapping units : Render output units : Ray accelerators and Compute units (CU)}}

}}

• Ampere - competing Nvidia microarchitecture released in a similar time-frame with the competing GeForce RTX 30 series

{{reflist}}

{{AMD graphics}}

Category:AMD microarchitectures

Category:Computer-related introductions in 2020

Category:Graphics microarchitectures