By Desire Athow

Copyright techradar

Skip to main content

Tech Radar Pro

Tech Radar Gaming

Close main menu

the business technology experts

België (Nederlands)

Deutschland

North America

US (English)

Australasia

New Zealand

View Profile

Search TechRadar

Expert Insights

Website builders

Web hosting

Best web hosting
Best office chairs
Best website builder
Best antivirus
Expert Insights

Don’t miss these

Huawei released an AI SSD which uses a secret sauce to reduce the need for large amounts of expensive HBM

Google’s most powerful supercomputer ever has a combined memory of 1.77PB – apparently a new world record for shared memory multi-CPU setups

AMD sheds more light on 128-GPU MI355X DLC rack that will deliver 2.4 Exaflop at FP4 precision – here’s how it compares with Nvidia’s flagship Vera Rubin

Could this be the next big step forward for AI? Huawei’s open source move will make it easier than ever to connect together, well, pretty much everything

Elon Musk says xAI will have 50 million ‘H100 equivalent’ Nvidia GPUs by 2030 — but at what cost?

Chaos at DeepSeek as R2 launch crashes into hardware problems – rivals gain huge advantage

OpenAI’s Sam Altman is dreaming of running 100 million GPUs in the future – 100x more than it plans to run by December 2025

Chinese vendor launches liquid-cooled mini PC powered by AMD’s most powerful AI processor, with a built-in 400W PSU

Nvidia is powering the UK’s fastest supercomputer yet – here’s what it can do

Acer joins Nvidia GB10 superchip fan club with $3,999 Veriton AI mini workstation PC – and yes, you can link two to get even more power

Meta unveils new plans for multi-gigawatt datacenter clusters the size of Manhattan

Pizza-sized chips are the future of AI accelerators, researchers concur – but heat remains a huge problem

Fujitsu is teaming with Nvidia to build probably the world’s fastest AI supercomputer ever at 600,000 FP8 Petaflops – so Feyman GPU could well feature

AMD gets ready for Nvidia Vera Rubin with 432GB MI400 GPU monster paired with 256-core EPYC Venice – I can’t wait to see the sparks fly

‘No asterisk generation’ : AMD promises its MI450 AI GPU will be faster than ANYTHING Nvidia has, yes, that includes even Rubin Ultra

Huawei throws massive 1-million NPU gauntlet at Nvidia and AMD as it positions itself an alternative to US AI giants

Desire Athow

18 September 2025

Who needs Instinct or Blackwell when we’ve got the Ascend family?

When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works.

(Image credit: Huawei)

Huawei has announced what it calls the, “world’s most powerful SuperPoDs and superclusters”.

In AI nomenclature, a SuperPOD is a group of racks that work as a single unit integrating compute, network, software, storage and management. A supercluster is a group of superPODs.
Given that Nvidia trademarked SuperPOD, the Chinese company was smart enough to call its product SuperPoD (AMD has its own version called MegaPOD). Its Atlas 950 SuperPoD comprises of 8,192 Ascend NPU (essentially AI accelerators) with a superior version, the 960, delivering almost twice that number at 15,488 (89% more).

You may like

Huawei released an AI SSD which uses a secret sauce to reduce the need for large amounts of expensive HBM

Google’s most powerful supercomputer ever has a combined memory of 1.77PB – apparently a new world record for shared memory multi-CPU setups

AMD sheds more light on 128-GPU MI355X DLC rack that will deliver 2.4 Exaflop at FP4 precision – here’s how it compares with Nvidia’s flagship Vera Rubin

A supercluster with 1-million NPUs
The Atlas 950 will use the newly announced Ascend 950 chips while the Ascend 960 series will fit in the Atlas 960. The 950 series will be available in Q1 26, while the 960 will come in Q4 27 and – you’ve guessed it – there’s an Ascend 970 planned for Q4 2028.

Huawei’s deputy chairman, Eric Xu, went on to claim that its SuperPoDs “are currently the most powerful SuperPoDs in the world, and will remain so for years to come”, based on publicly available roadmaps from Nvidia and AMD (although he didn’t name them).
Xu went on to announce superclusters based on the Atlas 950 and Atlas 960, with more than 520,000 (64 superPoDs) and more than one million NPUs, respectively (at least 66 superPoDs).
This, Xu posits, will outstrip xAI Colossus, currently the world’s largest computing cluster.

Are you a pro? Subscribe to our newsletter
Sign up to the TechRadar Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!
Contact me with news and offers from other Future brandsReceive email from us on behalf of our trusted partners or sponsorsBy submitting your information you agree to the Terms & Conditions and Privacy Policy and are aged 16 or over.
The caveat is that xAI is already working on Colossus 2, one of a number of Gigawatt-class clusters that will almost certainly surpass 950-based and 960-based superclusters. Oracle/OpenAI, Meta and AWS/Anthropic are also building such (hyper)clusters as well.
A third surprise announcement was the launch of UnifiedBus, which is Huawei’s alternative to Nvidia’s Infiniband. The company is keen to create an open UnifiedBus ecosystem, but its press release doesn’t mention whether this interconnect protocol will be open-sourced.
Huawei’s claims – if true – are impressive: 100x improved reliability for optical interconnect, with maximum range extended to more than 200 meters (almost 700 feet) and NPU-NPU latency reduced to 2.1ms, a 30% improvement over current technologies.
Chinese companies and China’s central government are most certainly going to be the main customers of Huawei’s SuperPoDs and superclusters for now.
Pricing, performance and power consumption are yet to be detailed.
You might also like

Ever wondered which AI tools the CEO of Nvidia uses? We have the answer – straight from Jensen Huang himself
Ryzen AI Max+ 395 CPU could be AMD’s sleeper hit against Nvidia’s AI dominance
Here are the best mobile workstations around today

Desire Athow

Social Links Navigation
Managing Editor, TechRadar Pro

Désiré has been musing and writing about technology during a career spanning four decades. He dabbled in website builders and web hosting when DHTML and frames were in vogue and started narrating about the impact of technology on society just before the start of the Y2K hysteria at the turn of the last millennium.

You must confirm your public display name before commenting

Please logout and then login again, you will then be prompted to enter your display name.

Huawei released an AI SSD which uses a secret sauce to reduce the need for large amounts of expensive HBM

Google’s most powerful supercomputer ever has a combined memory of 1.77PB – apparently a new world record for shared memory multi-CPU setups

AMD sheds more light on 128-GPU MI355X DLC rack that will deliver 2.4 Exaflop at FP4 precision – here’s how it compares with Nvidia’s flagship Vera Rubin

Could this be the next big step forward for AI? Huawei’s open source move will make it easier than ever to connect together, well, pretty much everything

Elon Musk says xAI will have 50 million ‘H100 equivalent’ Nvidia GPUs by 2030 — but at what cost?

Chaos at DeepSeek as R2 launch crashes into hardware problems – rivals gain huge advantage

Latest in Pro

“Our business in China has been a bit of a rollercoaster” – Nvidia CEO “disappointed” in further Chinese ban on buying its AI chips

1Password and Perplexity partner on Comet AI browser – a full time personal assistant with security by default

SMBs are turning to AI to solve their problems – but many are still cautious to go all-in

Repatriation games: the mid-market reevaluates its public cloud consumption

I’ve hand-picked my favorite discount standing desk and office chair deals for the perfect home office set-up

UK startup puts physical disconnect ‘switch’ in its cloud storage it claims can mitigate ransomware attacks – but will that be enough?

Latest in News

A US retailer may have leaked the Xbox ROG Ally’s price – and it’s better than we thought

You can now buy Hisense’s mid-range 116-inch mini-LED 4K TV, because that’s a thing in today’s TV world

“A wider campaign against human rights” – Experts condemn Russia’s escalation against VPNs and encrypted apps

TEAC’s new CD transport will treat your discs with the audiophile care that makes elite turntables so beloved – unless your discs are SACD

Huawei throws massive 1-million NPU gauntlet at Nvidia and AMD as it positions itself an alternative to US AI giants

The Summer I Turned Pretty season 4 isn’t happening, but Belly’s story is far from over

LATEST ARTICLES

We just got our first glimpse of the Xbox full-screen experience on an original Asus ROG Ally – and it has me pumped to see it on desktop PCs

A US retailer may have leaked the Xbox ROG Ally’s price – and it’s better than we thought

You can now buy Hisense’s mid-range 116-inch mini-LED 4K TV, because that’s a thing in today’s TV world

I tested Dyson’s most expensive vacuums side-by-side and there was a clear winner – and it wasn’t the one I expected

TEAC’s new CD transport will treat your discs with the audiophile care that makes elite turntables so beloved – unless your discs are SACD

TechRadar is part of Future US Inc, an international media group and leading digital publisher. Visit our corporate site.

Contact Future’s experts

Terms and conditions

Privacy policy

Cookies policy

Advertise with us

Web notifications

Accessibility Statement

Future US, Inc. Full 7th Floor, 130 West 42nd Street,

Please login or signup to comment

Please wait…