[Workshop] Hot Chips 2020 Alibabas Hanguang 800 NPU
Hot Chips 2020 Alibabas Hanguang 800 NPU1
The four cores are connected with ring bus, and the memory is shared via this bus.
Data is pre-processed in Memory Engine.
And the tasks are controlled and mapped by software to make it more fixable.
08:01PM EDT - 4 cores with ring bus
08:01PM EDT - 192 MB local memory, distributed shared, no DDR
08:01PM EDT - Command processor above all four cores
08:01PM EDT - PCIe 4.0 x16
08:02PM EDT - Each core has three engines: Tensor, Pooling, Memory
-
Anandtech. https://www.anandtech.com/show/16009/hot-chips-2020-live-blog-alibabas-hanguang-800-npu-500pm-pt ↩