公开(公告)号：US12073310B2

公开(公告)日：2024-08-27

申请号：US16837171

申请日：2020-04-01

申请人： Microsoft Technology Licensing, LLC

发明人： Stephen Sangho Youn ,  Lok Chand Koppaka ,  Steven Karl Reinhardt

IPC分类号： G06N3/063 ,  G06F9/38 ,  G06F9/48 ,  G06F9/50 ,  G06F17/16

CPC分类号： G06N3/063 ,  G06F9/3836 ,  G06F9/3887 ,  G06F9/4843 ,  G06F9/5027 ,  G06F17/16

摘要： Deep neural network accelerators (DNNs) with independent datapaths for simultaneous processing of different classes of operations and related methods are described. An example DNN accelerator includes an instruction dispatcher for receiving chains of instructions having both instructions for performing a first class of operations and a second class of operations corresponding to a neural network model. The DNN accelerator further includes a first datapath and a second datapath, where each is configured to execute at least one instruction chain locally before outputting any results. The instruction dispatcher is configured to forward instructions for performing the first class of operations to the first datapath and forward instructions for performing the second class of operations to the second datapath to overlap in time a performance of at least a subset of the first class of operations with a performance of at least a subset of the second class of operations.

公开(公告)号：US12124391B2

公开(公告)日：2024-10-22

申请号：US18218426

申请日：2023-07-05

申请人： Microsoft Technology Licensing, LLC

发明人： Stephen Sangho Youn ,  Steven Karl Reinhardt ,  Jeremy Halden Fowers ,  Lok Chand Koppaka ,  Kalin Ovtcharov

IPC分类号： G06F13/40 ,  G06N3/04

CPC分类号： G06F13/4027 ,  G06N3/04

摘要： The present disclosure relates to devices for using a configurable stacked architecture for a fixed function datapath with an accelerator for accelerating an operation or a layer of a deep neural network (DNN). The stacked architecture may have a fixed function datapath that includes one or more configurable micro-execution units that execute a series of vector, scalar, reduction, broadcasting, and normalization operations for a DNN layer operation. The fixed function datapath may be customizable based on the DNN or the operation.

公开(公告)号：US11734214B2

公开(公告)日：2023-08-22

申请号：US17212751

申请日：2021-03-25

申请人： Microsoft Technology Licensing, LLC

发明人： Stephen Sangho Youn ,  Steven Karl Reinhardt ,  Jeremy Halden Fowers ,  Lok Chand Koppaka ,  Kalin Ovtcharov

IPC分类号： G06F13/40 ,  G06N3/04

CPC分类号： G06F13/4027 ,  G06N3/04

摘要： The present disclosure relates to devices for using a configurable stacked architecture for a fixed function datapath with an accelerator for accelerating an operation or a layer of a deep neural network (DNN). The stacked architecture may have a fixed function datapath that includes one or more configurable micro-execution units that execute a series of vector, scalar, reduction, broadcasting, and normalization operations for a DNN layer operation. The fixed function datapath may be customizable based on the DNN or the operation.