NVIDIA ADA LOVELACE GPU Gets First Rumored Specs: Absolute Monster At 18432 CUDA Cores And 64 TFLOPs Of Graphics Horsepower


We have a very very delicious rumor making the rounds today and it comes from a highly credible source. @kopite7kimi, the Twitter leaker responsible for pretty much all of the Ampere leaks, revealed a tidbit about the upcoming NVIDIA Ada Lovelace architecture (likely called NVIDIA ADA). Our colleagues over at 3DCenter extrapolated a lot of information from the die size, which Kopite appears to have more or less confirmed. While the source is highly reliable, we are still marking this post as a rumor because of the magnitude of the leak.

NVIDIA ADA GPU Leaked: Monster 64 TFLOPs GPU with 18432 CUDA Cores and 5nm process architecture

The Ada Lovelace architecture - which will likely only be referred to as NVIDIA ADA by the way - was recently leaked by Kopite (and confirmed by Videocardz) and we already seem to have the preliminary specifications of NVIDIA's upcoming GPU. As we mentioned in the original Ada article, Hopper appears to have been delayed for now (and along with it, NVIDIA's MCM ambitions). Thankfully, it seems that NVIDIA has kept its pedal to the metal and its Ada architecture, championed by the AD102 GPU will be an absolute beast. Given below is the original die size leak:

The folks over at 3DCenter quickly extrapolated a ton of details (we have revised their TFLOP numbers to be a bit more conservative with a clock of 1.75 GHz) which Kopite confirmed:

For those that want all the information in one place, here is a table summarizing everything:


Flagship SKURTX 2080 TiRTX 3090 TiRTX 4090?
ArchitectureTuringAmpereAda Lovelace
ProcessTSMC 12nm NFFSamsung 8nmTSMC 4N?
Die Size754mm2628mm2~600mm2
Graphics Processing Clusters (GPC)6712
Texture Processing Clusters (TPC)364272
Streaming Multiprocessors (SM)7284144
CUDA Cores46081075218432
L2 Cache6 MB6 MB96 MB
Theoretical TFLOPs 16 TFLOPs40 TFLOPs~90 TFLOPs?
Memory Capacity11 GB (2080 Ti)24 GB (3090 Ti)24 GB (4090?)
Memory Speed14 Gbps21 Gbps24 Gbps?
Memory Bandwidth616 GB/s1.008 GB/s1152 GB/s?
Memory Bus384-bit384-bit384-bit
PCIe InterfacePCIe Gen 3.0PCIe Gen 4.0PCIe Gen 4.0
ReleaseSep. 2018Sept. 202H 2022 (TBC)

The NVIDIA AD102 "ADA GPU" appears to have 18432 CUDA Cores based on the information provided by Kopite. This is almost twice the cores present in Ampere which was already a massive step up from Turing. The only way this is even possible is because NVIDIA is apparently building this on the 5nm process which has significant die area and power reduction. Interestingly, if you assume a clock speed of 1.75 GHz you can also get the peak single-precision performance of the ADA 102 GPU: 64 TFLOPs.

According to Kopite the ADA architecture will feature a much bigger L2 Cache (both Turing and Ampere have 6 MB of cache) which means this might be a major architectural revision (as Turing was to Pascal and Pascal was to Fermi/Kepler) instead of just the usual process shrink. It is also unclear at this time whether NVIDIA will be using Samsung's 5nm process or TSMC. While the company has previously experienced bad yields over at Samsung, the fact that TSMC is all choked up and won't have access fab capacity for quite some time now means NVIDIA might be more willing to tap Samsung and have a shot at "unconstrained" production.

Recap on NVIDIA ADA GPU architecture

In many ways, Ada Lovelace can be thought of as the world's first computer enthusiast. She is the first person to have realized that the Analytical Engine proposed by Charles Babbage had applications beyond pure calculation and also published what is thought to be the first algorithm (becoming the first computer programmer) intended to be carried by such a machine. This was almost half a century before Alan Turing would finish their work and invent the general-purpose computer during the world war.

NVIDIA has been known to base its architectures on prominent physicists, mathematicians, and scientists and Ada Lovelace is no different. Videocardz actually managed to find a major hint in NVIDIA's own merchandise store that appears to confirm this rumor about Lovelace architecture being the next generation of GPUs from the company. If you look at the heroes showcased during GTC's 2018 keynote you find not only Ada Lovelace but what are potentially all future architectural codenames from NVIDIA. Jensen might have sneakily left the entire future roadmap (as far as codenames go) in the GTC'18 keynote.

There are now multiple rumors which seem to suggest that Lovelace architecture will be based on a 5nm process. Since NVIDIA has transitioned to Samsung's foundry, it is unclear whether 5nm refers to a TSMC process or Samsung's. Keep in mind, however, that a recent report out of Korea had also confirmed an order on 6nm from NVIDIA - which means that either there is another generation from NVIDIA before Lovelace or that the 6nm process was for the refresh lineup.