NVIDIA Ada Lovelace AD102 GPU Rumored To Clock As High As 2.2 GHz & Feature 384-bit GDDR6X Bus, Over 80 TFLOPs

According to the latest rumor by Greymon55, NVIDIA’s Ada Lovelace AD102 GPU could feature a clock speed as high as 2.2 GHz.

NVIDIA’s Next-Gen Ada Lovelace ‘AD102’ GPU Featured on Flagship GeForce RTX 40 Graphics Card To Clock As High As 2.2 GHz

There have been quite a few rumors already regarding the NVIDIA Ada Lovelace GPUs, especially the AD102 SKU. The AD102 GPU will power the flagship lineup of graphics cards whether they be for gamers or workstation users. It will be the successor to the existing GA102 GPU & as such, we can definitely expect some killer specifications.

NVIDIA GeForce RTX 3060 Graphics Cards With Ampere GA104 GPUs Spotted

Based upon previous rumors, there have been whispers that NVIDIA would utilize TSMC’s N5 (5nm) process node for its Ada Lovelace GPUs. This includes the AD102  SKU too which will be an entirely monolithic design. In his latest tweet which talks about the specific GPU configurations, the AD102 GPU is said to feature a clock speed as high as 2.2 GHz. The specific tweet states that the GPU clock for Ada Lovelace ‘AD102’ could be 2.2 GHz or greater so let’s take that as a baseline and previously leaked specifications to figure out where the performance should land.

ad102 frequency：≥2.2ghz

— Greymon55 (@greymon55) September 19, 2021

The NVIDIA AD102 “ADA GPU” appears to have 18432 CUDA Cores based on the preliminary specs (which can change) provided by Kopite. This is almost twice the cores present in Ampere which was already a massive step up from Turing. A 2.2 GHz clock speed would give us 81 TFLOPs of compute performance (FP32). This is more than twice the performance of the existing RTX 3090 which packs 36 TFLOPs of FP32 compute power.

The 125% performance jump looks huge but one should remember that NVIDIA already gave a big jump in FP32 numbers this generation with Ampere. The Ampere GA102 GPU (RTX 3090) offers 36 TFLOPs while the Turing TU102 GPU (RTX 2080 Ti) offered 13 TFLOPs. That’s over a 150% increase in FP32 Flops but the real world gaming performance increase for the RTX 3090 averaged at around 50-60% faster over the RTX 2080 Ti. So one thing we shouldn’t forget is that Flops don’t equal GPU gaming performance these days. Furthermore, we don’t know if 2.2 GHz is the average boost or the peak boost with the former meaning that there could be even higher compute potential for AD102.

NVIDIA GeForce RTX 2060 12 GB Graphics Card Reportedly Launches In Q1 2022 To Tackle GPU Availability Issues

Aside from that, the leaker also states that the NVIDIA GeForce RTX 40 flagship would retain a 384-bit bus interface, similar to the RTX 3090. What’s interesting is though that the leaker mentions G6X which means that NVIDIA won’t be moving to a new memory standard until after Ada Lovelace and utilize the higher pin-speeds of G6X (20 Gbps+) for its next-generation cards before we see a newer standard (e.g. GDDR7).

NVIDIA CUDA GPU (RUMORED) Preliminary:

The NVIDIA Ada Lovelace GPUs will power the next-generation GeForce RTX 40 graphics cards that will go head-on with AMD’s RDNA 3 based Radeon RX 7000 series graphics cards. There’s still some speculation regarding the use of MCM by NVIDIA. The Hopper GPU, which is primarily aimed at the Datacenter & AI segment, is allegedly taping out soon and will feature an MCM architecture. NVIDIA won’t be using an MCM design on its Ada Lovelace GPUs so they will keep the traditional monolithic design.

AMD on the other hand is going on board with offering both MCM and Monolithic chips in its RDNA 3 and CDNA 2 families. The CDNA 2 GPUs will be MCM only while RDNA 3 will feature a mix of MCM and monolithic design as detailed here. It isn’t confirmed which process node each company will be relying on but based on speculation, AMD’s RDNA 3 & CDNA 2 family is going to be a mix of 6nm & 5nm nodes featuring new and refreshed GPUs while NVIDIA is expected to utilize TSMC’s 5nm process node for its Ada Lovelace GPUs though it is not confirmed if those will be fabricated on the N5 or N5P node. Intel, on the other hand, may also rely on TSMC’s 6nm process node for its own ARC Alchemist lineup of GPUs which enter mass production later this year and launch in Q1 2022.

News Source: 3DCenter