Aurora Supercomputer Sets AI Tragedy Speed Record!
One of the world's largest GPU clusters, the Aurora supercomputer features 166 racks, 10,624 compute blades, 21,248 Intel Xeon CPU Max Series processors, and 63,744 Intel Data Centre GPU Max Series units.
The Intel Data Centre GPU Max Series is the brains behind the Aurora supercomputer
Neural network AI computation requires complicated matrix-vector operations, which the X design excels at
Deep learning models use matrix operations, which these compute cores speed up
The Intel oneAPI DPC++/C++ Compiler and X architecture offer an open developer environment that adapts and scales across devices and form factors
Intel Tiber Developer Cloud is integrating cutting-edge hardware platforms and service features to increase computational capacity
Intel Kubernetes Service for multiuser accounts and cloud-native AI training and inference workloads is one of the new features