Nvidia's newBlackwellAI chips, which have already faced delays, have encountered problems with accompanying servers thatoverheat, causing some customers to worry they will not have enough time to get new data centres up and running, the Information reported on Sun.
The Blackwell graphics processing unitsoverheatwhen connected together inserver racksdesigned to hold up to 72 chips, the report said, citing sources familiar with the issue.
The chipmaker has asked its suppliers tochange the design of the racksseveral times to resolve overheating problems, according to Nvidia employees who have been working on the issue, as well as customers and suppliers with knowledge of the issue, the report said without naming the suppliers.
"Nvidia is working with leading cloud service providers as an integral part of our engineering team and process. The engineering iterations are normal and expected," a company spokesperson said in a statement to Reuters.
In Mar, Nvidia unveiled Blackwell chips and had earlier said they would ship in the second quarter before encountering delays, potentially affecting customers such as Meta Platforms, Alphabet's Google and Microsoft.
Nvidia's Blackwell chip takes two squares of silicon the size of the company's previous offering and binds them into a single component that is 30 times speedier at tasks like providing responses from chatbots.
Lnova
:
It makes me wonder if any connection with $Super Micro Computer (SMCI.US)$ having issues and Nvidia directing orders to other companies than SMCI. It would be interesting to know if the overheating happened regardless of which company’s cooling racks were used. wonder if it’s an issue with the chips, with other companies’ cooling systems that Nvidia used, or both.
Lnova
bullrider_21
OP
:
It makes me wonder if there is a connection to that and to the overheating. Or, I wonder if the overheating still happened when Nvidia was using SMCI cooling racks too
103428530
:
You should get your facts straight it’s not the chips, it’s the racks that hold the servers that the chips are installed in. Not a major issue for those who don’t understand what a rack is? It’s a metal box not rocket science!!
Lnova : Super Micro Computer (SMCI) Reportedly Drops The Ball On A "Huge" Order For NVIDIA's NVL72 GB200 Chips, Prompting A Taiwanese Company To Pick Up The Tab
bullrider_21 OP Lnova : Customers are abandoning SMCI for other more stable suppliers.
Lnova : It makes me wonder if any connection with $Super Micro Computer (SMCI.US)$ having issues and Nvidia directing orders to other companies than SMCI. It would be interesting to know if the overheating happened regardless of which company’s cooling racks were used. wonder if it’s an issue with the chips, with other companies’ cooling systems that Nvidia used, or both.
Lnova bullrider_21 OP : It makes me wonder if there is a connection to that and to the overheating. Or, I wonder if the overheating still happened when Nvidia was using SMCI cooling racks too
Lnova : tyvm for posting
bullrider_21 OP Lnova : yw. Glad you enjoyed it.
103428530 : You should get your facts straight it’s not the chips, it’s the racks that hold the servers that the chips are installed in. Not a major issue for those who don’t understand what a rack is? It’s a metal box not rocket science!!
103428530 : overnight open up
Small issue only
Dun worry