The Radeon RX 7000-series from AMD, which has a significant performance gap between the enthusiast-class RX 7900 series and the consumer RX 7600, will benefit greatly from the inclusion of the Radeon RX 7800 XT. The astounding claim made in a report by “Moore’s Law is Dead” is that it is built on a brand-new ASIC that is neither the “Navi 31” powering the RX 7900 series nor the “Navi 32” planned for lower performance tiers, but rather something in between. It will be AMD’s response to the “AD103.” The GPU reportedly has a smaller packaging matching the “Navi 32” and the exact same 350 mm2 graphics compute die (GCD) as the “Navi 31.” Four MCDs (memory cache dies), totaling a 256-bit wide GDDR6 memory interface and 64 MB of 2nd Gen Infinity Cache memory, surround this enormous GCD.

However, AMD’s product managers can now provide the RX 7800 XT a far larger CU count than that of the “Navi 32,” while being lower than that of the RX 7900 XT (which is configured with 84). The GCD physically has 96 RDNA3 compute units. The smaller “Navi 32” GCD is said to have a maximum CU count of 60 (3,840 stream processors), hence the RX 7800 XT will be able to have a CU count of anywhere between 60 and 84 thanks to the new ASIC. Even if the final RX 7800 XT ends up performing within 10% of the RX 7900 XT (and matching the GeForce RTX 4070 Ti in the process), it would do so with better pricing headroom than a theoretical Navi 31 with two disabled MCDs (>60 mm2 of wasted 6 nm dies). The mobile RX 7900 series could even be powered by the same ASIC because of the smaller packaging and more condensed memory bus, which will save valuable PCB space.