A HyperTransport-Enabled Global Memory Model for Improved Memory Efficiency
Modern and emerging data centers are presenting unprecedented demands in terms of cost and energy consumption, far outpacing architectural advances related to economies of scale. Consequently, blade designs exhibit significant cost and power inefficiencies, particularly in the memory system. For example, the authors observe that modern blades are often over-provisioned to accommodate peak memory demand which rarely occurs concurrently across blades. With memory often accounting for 20% to 40% of the total system power, this approach is not sustainable.