AMD's CDNA 3 Compute Architecture – Chips and Cheese
AMD has a long history of vying for GPU compute market share. Ever since Nvidia got first dibs with their Tesla architecture, AMD has been playing catch up. Terascale 3 moved from VLIW5 to VLIW4 to improve execution unit utilization in compute workloads. GCN replaced Terascale and emphasized consistent performance for both GPGPU and graphics…
Source: chipsandcheese.com
