Qualcomm announced its return to the data center central processing unit (CPU) market, developing custom CPUs compatible with Nvidia’s artificial intelligence (AI) chips. Nvidia dominates the AI market, traditionally pairing its chips with CPUs from Intel and Advanced Micro Devices. Nvidia itself has entered the CPU market, designing its own ‘Grace’ CPU using Arm Holdings technology.
In the 2010s, Qualcomm developed an Arm-based CPU tested with Meta Platforms but later curtailed these efforts due to cost cuts and legal challenges. However, after acquiring a team of ex-Apple chip designers in 2021, Qualcomm has revived its efforts, discussing data center CPUs with Meta and confirming a letter of understanding with Saudi Arabian AI firm Humain to develop custom data center CPUs.
Qualcomm’s future chips will use Nvidia’s technology to communicate quickly with its graphics processors (GPUs), central to its AI chip portfolio. Cristiano Amon stated, “With the ability to connect our custom processors to Nvidia’s rack-scale architecture, we’re advancing a shared vision of high-performance, energy-efficient computing to the data center.”
— new from Reuters