Tag Archives: GPGPU

NVIDIA Computex 2024 Keynote Live Coverage!

I managed to make it to the exclusive NVIDIA Keynote at Computex 2024! Join me as I cover it live at the NTU Sports Centre!

Please REFRESH the page for the live updates, in case they don’t show up.

 

NVIDIA Computex 2024 Keynote Live Coverage!

Despite a flight delay, I managed to make it to the exclusive NVIDIA Keynote at Computex 2024! Join me as I cover it live at the NTU (National Taiwan University) Sports Centre here in downtown Taipei!

5:35 PM : It’s a wet and gloomy day, but the NVIDIA keynote at Computex 2024 is fully booked!

Recommended : AMD Computex 2024 Q&A With Dr. Lisa Su!

5:55 PM : The holding area is packed with people! 😅

6:15 PM : I finally have the opportunity to catch up with old friends 😆

6:23 PM : Inside the NVIDIA Keynote hall, NTU Sports Centre

6:57 PM : The MC just announced that the NVIDIA keynote for Computex 2024 is about to start… Stay tuned!

7:10 PM : The NVIDIA keynote event just kicked off with an intro video!

7:12 PM : Jensen Huang appears on stage.

7:13 PM : Jensen Huang speaks about the importance of NVIDIA partners in Taiwan.

7:15 PM : Jensen Huang kicks off the Omniverse demo which he said is entirely created using computer graphics.

7:18 PM : Jensen Huang made a joke about the video, saying in Hokkien – It’s not too bad, right? Beh pai kuah hoh?

7:20 PM : Jensen Huang speaks of the dangers of computational inflation, due to slowing CPU [performance] scaling.

7:25 PM : Huang’s law? The more you buy, the more you save. 😆

7:35 : Jensen Huang – CUDA has achieved the virtuous cycle.

7:36 : Jensen Huang unveils the NVIDIA Earth-2 – a digital twin of planet Earth, built on its Corrdiff AI. Interestingly, the globe is centred on Malaysia!

7:40 : Jensen said that while he wrote the words, AI was used to make him appear to speak in Mandarin in that Earth-2 video.

7:50 PM : Tesla invented an AC generator, NVIDIA invented an AI generator.

7:51 PM : The $3 trillion IT industry will soon support $100 trillion of industry.

7:53 PM : The computer industry has been reinvented. In the past, computers retrieve existing data, while in the future, computers will generate data. Generative AI will drive a full stack reinvention.

7:54 PM : NVIDIA Inference Microservice (NIM) offer pre-trained AI models packaged and optimised to run across CUDA installed base.

8:02 PM : Jensen Huang showcases the ultra-realism of NVIDIA’s current “digital humans”.

8:14 PM : Jensen Huang shows off a production unit of the NVIDIA Blackwell DB200 super chip, which features two Blackwell GPUs and one Grace CPU.

8:16 PM : NVIDIA Blackwell reduced the energy required to train GPT4-1.8T by 350X in the past 8 years.

8:20 PM : NVIDIA DGX Blackwell GB200 super chip offers significantly more performance in a single GPU domain, than the previous DGX Hopper.

8:24 PM : Jensen Huang shows the massive NVLink spine used in the NVIDIA DGX Blackwell.

8:30 PM : NVIDIA Spectrum-X switches will scan from tens of thousands of GPUs (Spectrum-X800) to hundreds of thousands of GPUs in next year’s Spectrum-X800 Ultra, and the future Spectrum-X1600 will support millions of GPUs.

8:34 PM : NVIDIA continues its one-year rhythm for datacenter platforms, which are designed to be fully-integrated, but is offered to customers as desegregated options.

8:37 PM : NVIDIA will introduce the Blackwell Ultra GPU next year, with the Spectrum X-1600 switch.

8:38 PM : Jensen Huang reveals that Rubin is the codename for NVIDIA’s post-Blackwell platform!

8:47 PM : Video shows Foxconn’s new factory designed using NVIDIA Omniverse. The Omniverse Digital Twin is also used to train its robots.

8:54 PM : Jensen Huang shows off humanoid robot examples, as well as more “conventional” looking robots.

8:55 PM : Video shows Taiwan’s contribution to NVIDIA’s success story. The crowd rapturously applauds at the end of the video.

8:57 PM : The NVIDIA Keynote ends! Thanks for staying tuned!

 

Please Support My Work!

Support my work through a bank transfer /  PayPal / credit card!

Name : Adrian Wong
Bank Transfer : CIMB 7064555917 (Swift Code : CIBBMYKL)
Credit Card / Paypal : https://paypal.me/techarp

Dr. Adrian Wong has been writing about tech and science since 1997, even publishing a book with Prentice Hall called Breaking Through The BIOS Barrier (ISBN 978-0131455368) while in medical school.

He continues to devote countless hours every day writing about tech, medicine and science, in his pursuit of facts in a post-truth world.

 

Recommended Reading

Go Back To > Computer | Business | Tech ARP

 

Support Tech ARP!

Please support us by visiting our sponsors, participating in the Tech ARP Forums, or donating to our fund. Thank you!

How Biren Got Its Own AI Chips Banned At TSMC!

TSMC stopped making artificial intelligence chips for China’s Biren Technology, and it was all Biren’s own fault!

 

TSMC Stops Making Biren AI Chips Over US Sanctions

TSMC – Taiwan Semiconductor Manufacturing Company – has suspended production of advanced artificial intelligence (AI) chips for China’s Biren Technology.

TSMC was forced to make this decision after public domain information revealed that the Biren BR100 and BR104 chips outperformed the NVIDIA A100 chip, which was used as the baseline of US sanctions.

While TSMC has not reached a conclusion on whether the top-of-the-line Biren BR100 or the slower BR104 meet or exceed US government threshold on advanced AI chip technology restrictions, it decided to stop production and supply of the Biren chips for now.

For TSMC to continue producing BR100 or BR104 chips, Biren must now prove that their chips do not offer “peak performance and chip-to-chip I/O performance equal to or greater than thresholds that are roughly equivalent to the [NVIDIA] A100“, or get an export licence from the US Department of Commerce.

And believe it or not – it was Biren Technology that created this mess for itself!

 

How Biren Screwed Up Its Own BR100 AI Chips

Biren, which is one of China’s most promising semiconductor design firms, earlier claimed that its AI chips that were being produced by TSMC are not covered by the latest US export restrictions.

However, its own website touts that the BR100 family of chips offers “world-class performance“, and has “improved by more than 3X” compared to mainstream rivals.

On top of that, Biren actually released a press statement on September 9, 2022, declaring that the slower BR104 was proven by the MLPerf to beat the NVIDIA A100!

Releasing such a statement less than 2 weeks after the US government ordered both AMD and NVIDIA to stop exporting their MI250 and A100 and faster AI chips to China is either amazing chutzpah, or a combination of hubris and idiocy.

Either way, the US government took notice, and TSMC came under pressure to comply with American export restrictions. Awesome PR, but stupid move, Biren…

Take a look at the benchmark results that Biren itself released into public domain, showing that the slower BR104 chip was between 27% and 58% faster than the NVIDIA A100.

With such results, the BR104 would certainly fall under the latest US tech export restrictions. No wonder TSMC quickly stopped making and supplying Biren BR100 series chips.

As powerful as the BR100 and BR104 GPGPU chips may be, they are now dead in the water as TSMC will not manufacture them anymore, and Biren Technology has no plausible alternatives for 7nm fabrication.

Read more : US Targets Chinese Military With New Chip Export Ban!

 

Biren BR100 AI Chips That TSMC Stopped Producing

The Biren BR100 and slower BR104 are General Purpose GPU (GPGPU) chips, which are targeted at artificial intelligence applications.

They are both fabricated on the TSMC 7nm process technology, and use chipset and 2.5D Chip-on-Wafer-on-Substrate (CoWoS) packaging technologies to achieve high yield, and high performance.

The Biren BR100 family of GPGPU chips supports up to eight independent virtual instances (SVI) – each physically isolated with their own hardware resources, for improved security.

Their chips are designed with a proprietary Blink high-speed GPU interconnect bus offering bandwidth of up to 448 GB/s, with the ability to connect up to 8 cards in a single node, using state-of-the-art PCI Express 5.0.

Biren Technology offers two BR100-based products – the Bili 100P OCP Accelerator Module (OAM), and the Bill 104P PCI Express accelerator card.

 

Please Support My Work!

Support my work through a bank transfer /  PayPal / credit card!

Name : Adrian Wong
Bank Transfer : CIMB 7064555917 (Swift Code : CIBBMYKL)
Credit Card / Paypal : https://paypal.me/techarp

Dr. Adrian Wong has been writing about tech and science since 1997, even publishing a book with Prentice Hall called Breaking Through The BIOS Barrier (ISBN 978-0131455368) while in medical school.

He continues to devote countless hours every day writing about tech, medicine and science, in his pursuit of facts in a post-truth world.

 

Recommended Reading

Go Back To > Computer | BusinessTech ARP

 

Support Tech ARP!

Please support us by visiting our sponsors, participating in the Tech ARP Forums, or donating to our fund. Thank you!