Nvidia May Move to Yearly GPU Architecture Releases
Nvidia's Blackwell set to arrive in 2024, its successor to hit the market in 2025.

In a bid to maintain its leadership in artificial intelligence (AI) and high-performance computing (HPC) hardware, Nvidia plans to speed up development of new GPU architectures and essentially get back to its one-year cadence for product introductions, according to its roadmap published for investors and further explained by SemiAnalysis. As a result, Nvidia's Blackwell will come in 2024 and will be succeeded by a new architecture in 2025.
But before Blackwell arrives next year (presumably in the second half of next year), Nvidia is set to roll out multiple new products based on its Hopper architecture. This includes the H200 product, which might be a re-spin of the H100 made for enhanced yields, or just higher performance, as well as GH200NVL, which will address training and inference on large language models with an Arm-based CPU and Hopper-based GPU. These are set to come rather sooner than later.
As for the Blackwell family due in 2024, Nvidia seems to prep the B100 product for AI and HPC compute on x86 platforms, which will succeed H100. In addition, the company preps GB200, which is presumably Grace Hopper module featuring an Arm CPU and a Hopper GPU, targeting inference as well as GB200NVL, an Arm-based solution for LLM training and inference. Also, the company is planning B40 product, presumably a client GPU-based solution for AI inference.
In 2025, Blackwell will be succeeded with an architecture designated with the letter X, which is probably a placeholder for now. Anyhow, Nvidia preps X100 for x86 AI training and inference as well as HPC, GX200 for Arm inference (Grace CPU + X GPU), and GX200NVL for Arm-based LLM training and inference. In addition, there will be X40 product — presumably based on a client GPU-based solution — for lower cost inference.
For now, Nvidia leads the market of AI GPUs, but AWS, Google, Microsoft as well as traditional AI and HPC players like AMD and Nvidia are all prepping their new-generation processors for training and inference, which is why Nvidia reportedly accelerated its plans for B100 and X100-based products.
To further solidify its positions further, Nvidia has reportedly pre-purchased TSMC capacity and HBM memory from all three makers. In addition, the company is pushing its HGX and MGX servers in a bid to commoditize these machines and make them popular among end users, particularly in the enterprise AI segment.
Stay On the Cutting Edge: Get the Tom's Hardware Newsletter
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Anton Shilov is a contributing writer at Tom’s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends.
-
Order 66 Nvidia gets more chances to learn from their mistakes and release reasonably priced GPUs for consumers, All right! If they go with Intel's strategy and try to undercut AMD then maybe people will buy their GPUs again.Reply -
helper800
In my opinion, thats never going to happen. Nvidia will do what best for Nvidia and that's producing non-consumer GPUs for extreme profit. If we do get any graphics cards, you best believe we are paying an arm and a leg for them.Order 66 said:Nvidia gets more chances to learn from their mistakes and release reasonably priced GPUs for consumers, All right! If they go with Intel's strategy and try to undercut AMD then maybe people will buy their GPUs again. -
Cliff3.141592653589793238 Nvidia is sure making better GPU's than me =0 Cant wait for the next gen to come out.Reply -
renz496
what mistake? did you see nvidia "gaming" revenue for the last 3 quarters? there is no such thing "people will buy their GPU again". right now their gaming GPU are selling extremely well.Order 66 said:Nvidia gets more chances to learn from their mistakes and release reasonably priced GPUs for consumers, All right! If they go with Intel's strategy and try to undercut AMD then maybe people will buy their GPUs again. -
btmedic04
yeah, but how many of those are 4090s that are just ending up in AI-lite applications? Nvidia doesn't drop prices on their products unless they've launched their next product.renz496 said:what mistake? did you see nvidia "gaming" revenue for the last 3 quarters? there is no such thing "people will buy their GPU again". right now their gaming GPU are selling extremely well. -
renz496
that's the future of gaming GPU sales going forward. 60% to 70% of gaming GPU sales will have nothing to do with gaming at allbtmedic04 said:yeah, but how many of those are 4090s that are just ending up in AI-lite applications? Nvidia doesn't drop prices on their products unless they've launched their next product. -
Order 66
Their mistake was ticking off consumers. Their GPUs are selling well because of all the fanboys who keep buying them. The 4090 is selling well but the 4080 is not.renz496 said:what mistake? did you see nvidia "gaming" revenue for the last 3 quarters? there is no such thing "people will buy their GPU again". right now their gaming GPU are selling extremely well. -
renz496
fanboys did not make up the sales. even if you combined AMD and nvidia fanboys together it will not going to make to 1% of total sales.Order 66 said:Their mistake was ticking off consumers. Their GPUs are selling well because of all the fanboys who keep buying them. The 4090 is selling well but the 4080 is not. -
Order 66
The 4090 has sold very well but the 4080 has not because it is in an awkward position since most people who are looking at a 4080 will just get a 4090 or they will step down and get a 4070.renz496 said:fanboys did not make up the sales. even if you combined AMD and nvidia fanboys together it will not going to make to 1% of total sales. -
jp7189 They may be aiming for faster cadence on the datacenter side, but I bet they won't sink nearly as much effort into the consumer gaming side going forward. I would expect them to chase the highest margin products, and when those are also now high volume...Reply