Technical discussion of memory bus widths, Radeon VII's 1TB/s throughput, comparison to modern RTX 5080/5090, regression in performance per dollar over years
← Back to The RAM shortage could last years
Technical enthusiasts highlight a perceived regression in GPU memory bandwidth value, noting that the 2019 Radeon VII’s 1TB/s throughput remains superior to modern high-end offerings like the RTX 5080. While flagship cards like the RTX 5090 eventually surpassed this milestone, commenters argue that manufacturers are now using faster GDDR7 memory to mask narrower bus widths, effectively cutting production costs while raising consumer prices. This architectural shift prioritizes gaming-focused compute power over the raw bandwidth and FP64 performance required for AI inference and scientific tasks, leading some users to cling to "ancient" AMD hardware or budget Intel alternatives for specialized workloads. Ultimately, the discussion suggests that while modern cards are faster for general users, the "golden era" of affordable, high-bandwidth HBM technology has been restricted to the expensive professional market.
20 comments tagged with this topic