RDNA 2

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.[1] Each Compute Unit contains 64 shader cores.[7] CUs are organized into groups of two named Work Group Processors with 32 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.[8] New low precision data types like INT4 and INT8 are new supported data types for RDNA 2 CUs.[8]

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.[9]

Real-time hardware accelerated ray tracing is a new feature for RDNA 2 which is handled by a dedicated ray accelerator inside each CU.[10] Ray tracing on RDNA 2 relies on the more open DirectX Raytracing protocol rather than the Nvidia RTX protocol.[11]

In February 2023, it was reported that driver updates had boosted ray tracing performance by up to 40% using DirectX Raytracing.[12]

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.[13]

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".[14] AMD claims that RDNA 2's 128 MB of on-die Infinity Cache "dramatically reduces latency and power consumption".[15] 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 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 controllers.[8] 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.[15] 21% of that 54% improvement is attributed to performance-per-clock enhancements, in part due to the addition of Infinity Cache.[16]

RDNA 2 uses the VCN 3.0, VCN 3.1, and VCN 3.1.2 video decoding blocks in its media engine.[17][18] It adds support for AV1 decoding at up to 8K resolution, though AV1 hardware encoding support would not come until RDNA 3 in 2022.[19][20] However, the low-end Navi 24 die does not contain any media encoders and cannot decode AV1 as a result.[17]