AI Data Centers Look Beyond Just GPUs

Key Takeaways: AI data centers are becoming increasingly heterogeneous, with each processing type targeted for what they do best. Inference is being segmented into different stages to make it more efficient. Interconnects and orchestration are now critical bottlenecks. Experts At The Table : Semiconductor Engineering sat down to discuss changes in AI data center architectures with Satadal Bhattacharjee, global head of cloud and AI infrastructure silicon at Arm ; Ashish Darbari, CEO of Axiomise ;