Nvidia's design flaw with Blackwell AI chips now fixed, CEO says
Technology
''It was functional, but the design flaw caused the yield to be low'
COPENHAGEN/STOCKHOLM (Reuters) - Nvidia (NVDA.O) CEO Jensen Huang said on Wednesday a design flaw with its latest Blackwell AI chips which impacted production has been fixed with the help of longtime Taiwanese manufacturing partner TSMC (2330.TW).
Nvidia unveiled Blackwell chips in March and had earlier said they would ship in the second quarter but were delayed, potentially affecting customers such as Meta Platforms (META.O), Alphabet's (GOOGL.O), Google and Microsoft (MSFT.O).
"We had a design flaw in Blackwell," Huang said. "It was functional, but the design flaw caused the yield to be low. It was 100% Nvidia's fault."
According to media reports the delay in production had caused tensions between Nvidia and TSMC but Huang dismissed that as "fake news".
"In order to make a Blackwell computer work, seven different types of chips were designed from scratch and had to be ramped into production at the same time," he said.
"What TSMC did, was to help us recover from that yield difficulty and resume the manufacturing of Blackwell at an incredible place."
Nvidia's Blackwell chips take two squares of silicon the size of the company's previous offering and binds them together into a single component that is 30 times speedier at tasks like serving up answers from chatbots.
At a recent Goldman Sachs conference the CEO said the chips will now ship in the fourth quarter.
Huang was in Denmark on Wednesday to launch a new supercomputer named Gefion, which boasts 1,528 graphic processing units (GPUs) and was built in partnership with Novo Nordisk Foundation, Denmark's Export and Investment Fund and Nvidia.
