In the realm of supercomputers, there are efforts to develop a high-performing machine that would be 30x more powerful than the current fastest supercomputer, Frontier.
Only a few thousand GPUs connected via high-speed interconnect across several local servers make current training clusters. Notably, Frontier has 37,888 Radeon GPUs.For the advanced AI training cluster, the client has approached AMD, which supplied only 2% of the data center GPU shipments in 2023. The market leader, Nvidia, supplied the other 98%.
This shouldn’t come as a shock, as the past few years in the tech world have been defined by the explosion in AI advancements. It seems that companies are ready to invest significant sums in AI and machine learning to remain competitive, reportedis claimed to be the fastest ramping product of AMD.