- 专利标题: Reconfigurable neural network processing based on subgraph recognition
-
申请号: US18231024申请日: 2023-08-07
-
公开(公告)号: US12045611B1公开(公告)日: 2024-07-23
- 发明人: Ron Diamant , Hongbin Zheng , Drazen Borkovic , Haichen Li
- 申请人: Amazon Technologies, Inc.
- 申请人地址: US WA Seattle
- 专利权人: Amazon Technologies, Inc.
- 当前专利权人: Amazon Technologies, Inc.
- 当前专利权人地址: US WA Seattle
- 代理机构: Kilpatrick Townsend & Stockton LLP
- 分案原申请号: US17361992 2021.06.29
- 主分类号: G06F9/30
- IPC分类号: G06F9/30 ; G06F7/548 ; G06F8/41 ; G06N3/04 ; G06N3/063
摘要:
In one example, a method comprises: receiving input codes, wherein the input codes represent a computational dataflow graph; traversing the computational dataflow graph to identify single-entry-single-exit (SESE) subgraphs of the computational dataflow graph, wherein each SESE subgraph has a sequence of nodes comprising a root node and a child node and representing a sequence of element-wise operators, wherein the root node receives a single input tensor, and wherein the child node outputs a single output tensor; determining a merged operator for each SESE subgraph; and generating executable instructions for the computational dataflow graph to be executed by a hardware accelerator having a first execution unit and a second execution unit, wherein the executable instructions comprise first executable instructions for the merged operators targeted at the first execution unit, and second executable instructions for other operators of the computational dataflow graph targeted at the second execution unit.
信息查询