Nvidia’s AD102 Lovelace GPU reportedly offers gamers up to 18432 CUDA cores

Nvidia’s next-generation GPU architecture will reportedly be called Lovelace after Ada Lovelace. This next-generation graphics architecture is also rumoured to use 5nm lithography and make up Nvidia’s RTX 40 series of products. 

If the specifications from kopite7kimi are accurate, Nvidia’s AD102 GPU will feature 71.4% more CUDA cores than Nvidia’s GA102 (Ampere) GPU. This factor alone should make Lovelace a huge generational leap over Ampere, assuming that Nvidia can offer the same (or higher) performance levels from each Lovelace FP32 unit. 

At this time, it is unknown when Nvidia will release a post-Ampere graphics architecture. Right now, Nvidia hasn’t released their entire Ampere lineup, and mobile Ampere products have not been released onto the consumer market. Even if we discount the possibility of an Ampere-based RTX 30 Super series refresh, Nvidia is unlikely to release a next-generation graphics architecture until mid-to-late 2021 at the earliest.

Rumour has it that Nvidia is working on RTX 3070 Ti and RTX 3080 Ti products, which are both due to release in early 2021. These products would negate the need for an Ampere RTX Super refresh, making it likely that Nvidia plans to release RTX 40 series products and a new GPU architecture sooner than expected.

Reports of Nvidia’s accelerated product launches could be due to AMD’s recent RDNA 2 products, which have proven to be very competitive with Nvidia’s RTX 30 series offerings. Have AMD forced Nvidia to accelerate their roadmap?