Samsung has established a new dream team of engineers to secure HBM memory chip deals for AI GPUs from NVIDIA.
The news is coming from South Korean outlet KED Global, which reports Samsung's new task force features about 100 "excellent engineers" who have been working on improving manufacturing yields and quality with the first objective being passing NVIDIA's tests.
NVIDIA CEO Jensen Huang asked Samsung to raise the yields and quality of its 8-layer and 12-layer HBM3E memory chips for supply according to industry insiders on Monday. HBM3E memory is the cornerstone of NVIDIA's next-gen Blackwell B200 AI GPUs, as well as the new beefed-up Hopper H200 AI GPU, each with HBM3E memory mostly from Samsung's South Korean HBM rival: SK hynix.
Samsung has been working on the world's first 36-gigabyte (GB) 12-layer HBM3E that it developed in February, hoping to pass quality tests from NVIDIA this month. Samsung has also reportedly secured production lines ahead of time to increase output to meet NVIDIA's continuously growing demand.
- Read more: Samsung begins emergency mode: all Samsung execs to now work 6 days a week
- Read more: Samsung co-CEO visits Taiwan in 'low-key manner' to promote HBM, meets with TSMC
- Read more: Samsung wins advanced chip packaging order from NVIDIA for AI GPUs, TSMC isn't enough
- Read more: Samsung forms dedicated 'HBM team' to boost HBM production to beat SK hynix
One of the sources told KED Global: "Samsung aims to log a high market share by quickly increasing supply to NVIDIA. It is expected to speed up the supply from the third quarter".
Samsung President and CEO Kyung Kye Hyun, who manages Samsung's chip business, said: "We lost the first battle but we have to win the second".
SK hynix has been selling 8-layer HBM3E memory chips to NVIDIA for its new H200 and B200 AI GPUs, while also providing 12-layer HBM3E samples for performance evaluation for supply in Q3 2024. SK hynix CEO Kwak Noh-jung said: "It is impossible to secure a competitive edge in an instant, but we won't be complacent".