公开(公告)号：US11948224B2

公开(公告)日：2024-04-02

申请号：US17978573

申请日：2022-11-01

申请人： Intel Corporation

发明人： Elmoustapha Ould-Ahmed-Vall ,  Sara S. Baghsorkhi ,  Anbang Yao ,  Kevin Nealis ,  Xiaoming Chen ,  Altug Koker ,  Abhishek R. Appu ,  John C. Weast ,  Mike B. Macpherson ,  Dukhwan Kim ,  Linda L. Hurd ,  Ben J. Ashbaugh ,  Barath Lakshmanan ,  Liwei Ma ,  Joydeep Ray ,  Ping T. Tang ,  Michael S. Strickland

IPC分类号： G06T1/20 ,  G06F3/14 ,  G06F7/483 ,  G06F9/30 ,  G06F9/38 ,  G06F9/50 ,  G06N3/044 ,  G06N3/045 ,  G06N3/063 ,  G06N3/08 ,  G06N3/084 ,  G06N20/00 ,  G06T1/60 ,  G06T15/00

CPC分类号： G06T1/20 ,  G06F7/483 ,  G06F9/30014 ,  G06F9/30185 ,  G06F9/3863 ,  G06F9/5044 ,  G06N3/044 ,  G06N3/045 ,  G06N3/063 ,  G06N3/084 ,  G06N20/00 ,  G06F3/14 ,  G06T1/60 ,  G06T15/005

摘要： One embodiment provides an apparatus comprising a memory stack including multiple memory dies and a parallel processor including a plurality of multiprocessors. Each multiprocessor has a single instruction, multiple thread (SIMT) architecture, the parallel processor coupled to the memory stack via one or more memory interfaces. At least one multiprocessor comprises a multiply-accumulate circuit to perform multiply-accumulate operations on matrix data in a stage of a neural network implementation to produce a result matrix comprising a plurality of matrix data elements at a first precision, precision tracking logic to evaluate metrics associated with the matrix data elements and indicate if an optimization is to be performed for representing data at a second stage of the neural network implementation, and a numerical transform unit to dynamically perform a numerical transform operation on the matrix data elements based on the indication to produce transformed matrix data elements at a second precision.

公开(公告)号：US20240013337A1

公开(公告)日：2024-01-11

申请号：US18351898

申请日：2023-07-13

申请人： Intel Corporation

发明人： Abhishek R. Appu ,  Altug Koker ,  John C. Weast ,  Mike B. Macpherson ,  Linda L. Hurd ,  Sara S. Baghsorkhi ,  Justin E. Gottschlich ,  Prasoonkumar Surti ,  Chandrasekaran Sakthivel ,  Liwei Ma ,  Elmoustapha Ould-Ahmed-Vall ,  Kamal Sinha ,  Joydeep Ray ,  Balaji Vembu ,  Sanjeev Jahagirdar ,  Vasanth Ranganathan ,  Dukhwan Kim

IPC分类号： G06T1/20 ,  G06F9/46 ,  G06N3/063 ,  G06N3/045 ,  G06N3/08

CPC分类号： G06T1/20 ,  G06F9/46 ,  G06N3/063 ,  G06N3/045 ,  G06N3/08 ,  G06N3/084

摘要： A mechanism is described for detecting, at training time, information related to one or more tasks to be performed by the one or more processors according to a training dataset for a neural network, analyzing the information to determine one or more portions of hardware of a processor of the one or more processors that is configurable to support the one or more tasks, configuring the hardware to pre-select the one or more portions to perform the one or more tasks, while other portions of the hardware remain available for other tasks, and monitoring utilization of the hardware via a hardware unit of the graphics processor and, via a scheduler of the graphics processor, adjusting allocation of the one or more tasks to the one or more portions of the hardware based on the utilization.

公开(公告)号：US20230359461A1

公开(公告)日：2023-11-09

申请号：US18315625

申请日：2023-05-11

申请人： Intel Corporation

发明人： Kevin Nealis ,  Anbang Yao ,  Xiaoming Chen ,  Elmoustapha Ould-Ahmed-Vall ,  Sara S. Baghsorkhi ,  Eriko Nurvitadhi ,  Balaji Vembu ,  Nicolas C. Galoppo Von Borries ,  Rajkishore Barik ,  Tsung-Han Lin ,  Kamal Sinha

IPC分类号： G06F9/30 ,  G06F9/38 ,  G06N3/063 ,  G06N3/084 ,  G06T1/20 ,  G06N3/044 ,  G06N3/045

CPC分类号： G06F9/3001 ,  G06F9/3851 ,  G06F9/3887 ,  G06F9/3893 ,  G06N3/063 ,  G06N3/084 ,  G06T1/20 ,  G06N3/044 ,  G06N3/045 ,  G06F2207/4824

摘要： One embodiment provides for a compute apparatus comprising a decode unit to decode a single instruction into a decoded instruction that specifies multiple operands including a multi-bit input value and a one-bit weight associated with a neural network, as well as an arithmetic logic unit including a multiplier, an adder, and an accumulator register. To execute the decoded instruction, the multiplier is to perform a fused operation including an exclusive not OR (XNOR) operation and a population count operation. The adder is configured to add the intermediate product to a value stored in the accumulator register and update the value stored in the accumulator register.

公开(公告)号：US20230061331A1

公开(公告)日：2023-03-02

申请号：US17960611

申请日：2022-10-05

申请人： Intel Corporation

发明人： Elmoustapha Ould-Ahmed-Vall ,  Sara S. Baghsorkhi ,  Anbang Yao ,  Kevin Nealis ,  Xiaoming Chen ,  Altug Koker ,  Abhishek R. Appu ,  John C. Weast ,  Mike B. Macpherson ,  Dukhwan Kim ,  Linda L. Hurd ,  Ben J. Ashbaugh ,  Barath Lakshmanan ,  Liwei Ma ,  Joydeep Ray ,  Ping T. Tang ,  Michael S. Strickland

IPC分类号： G06T1/20 ,  G06F7/483 ,  G06N3/08 ,  G06F9/30 ,  G06N3/04 ,  G06N3/063 ,  G06F9/50 ,  G06F9/38 ,  G06N20/00

摘要： One embodiment provides a multi-chip module accelerator usable to execute tensor data processing operations a multi-chip module. The multi-chip module may include a memory stack including multiple memory dies and parallel processor circuitry communicatively coupled to the memory stack. The parallel processor circuitry may include multiprocessor cores to execute matrix multiplication and accumulate operations. The matrix multiplication and accumulate operations may include floating-point operations that are configurable to include two-dimensional matrix multiply and accumulate operations involving inputs that have differing floating-point precisions. The floating-point operations may include a first operation at a first precision and a second operation at a second precision. The first operation may include a multiply having at least one 16-bit floating-point input and the second operation may include an accumulate having a 32-bit floating-point input.

公开(公告)号：US11348198B2

公开(公告)日：2022-05-31

申请号：US17145885

申请日：2021-01-11

申请人： Intel Corporation

发明人： Prasoonkumar Surti ,  Narayan Srinivasa ,  Feng Chen ,  Joydeep Ray ,  Ben J. Ashbaugh ,  Nicolas C. Galoppo Von Borries ,  Eriko Nurvitadhi ,  Balaji Vembu ,  Tsung-Han Lin ,  Kamal Sinha ,  Rajkishore Barik ,  Sara S. Baghsorkhi ,  Justin E. Gottschlich ,  Altug Koker ,  Nadathur Rajagopalan Satish ,  Farshad Akhbari ,  Dukhwan Kim ,  Wenyin Fu ,  Travis T. Schluessler ,  Josh B. Mastronarde ,  Linda L. Hurd ,  John H. Feit ,  Jeffery S. Boles ,  Adam T. Lake ,  Karthik Vaidyanathan ,  Devan Burke ,  Subramaniam Maiyuran ,  Abhishek R. Appu

IPC分类号： G06T1/20 ,  G06F9/455 ,  G06F9/50 ,  G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06F8/41

摘要： An apparatus to facilitate compute optimization is disclosed. The apparatus includes a plurality of processing units each comprising a plurality of execution units (EUs), wherein the plurality of EUs comprise a first EU type and a second EU type.

公开(公告)号：US20220114430A1

公开(公告)日：2022-04-14

申请号：US17558285

申请日：2021-12-21

申请人： Intel Corporation

发明人： Rajkishore Barik ,  Elmoustapha Ould-Ahmed-Vall ,  Xiaoming Chen ,  Dhawal Srivastava ,  Anbang Yao ,  Kevin Nealis ,  Eriko Nurvitadhi ,  Sara S. Baghsorkhi ,  Balaji Vembu ,  Tatiana Shpeisman ,  Ping T. Tang

IPC分类号： G06N3/063 ,  G06N3/04 ,  G06F9/30 ,  G06F9/38 ,  G06T1/20 ,  G06N3/08 ,  G06F16/17

摘要： One embodiment provides an apparatus comprising an instruction cache to store a plurality of instructions, a scheduler unit coupled to the instruction cache, the scheduler unit to schedule the plurality of instructions for execution, an instruction fetch and decode unit to decode the plurality of instructions to determine a set of operations to perform in response, one or more compute blocks to perform parallel multiply-accumulate operations based on the instruction fetch and decode unit decoding a first instruction of the plurality of instructions, and matrix multiplication logic to perform matrix multiplication operations based on the instruction fetch and decode unit decoding a second instruction of the plurality of instructions.

公开(公告)号：US11210760B2

公开(公告)日：2021-12-28

申请号：US16928353

申请日：2020-07-14

申请人： Intel Corporation

发明人： Eriko Nurvitadhi ,  Balaji Vembu ,  Nicolas C. Galoppo Von Borries ,  Rajkishore Barik ,  Tsung-Han Lin ,  Kamal Sinha ,  Nadathur Rajagopalan Satish ,  Jeremy Bottleson ,  Farshad Akhbari ,  Altug Koker ,  Narayan Srinivasa ,  Dukhwan Kim ,  Sara S. Baghsorkhi ,  Justin E. Gottschlich ,  Feng Chen ,  Elmoustapha Ould-Ahmed-Vall ,  Kevin Nealis ,  Xiaoming Chen ,  Anbang Yao

IPC分类号： G06T1/20 ,  G06N3/04 ,  G06N3/063 ,  G06F9/38 ,  G06F9/30 ,  G06N3/08

摘要： One embodiment provides for a compute apparatus to perform machine learning operations, the compute apparatus comprising a decode unit to decode a single instruction into a decoded instruction, the decoded instruction to cause the compute apparatus to perform a complex machine learning compute operation.

公开(公告)号：US10956330B2

公开(公告)日：2021-03-23

申请号：US16727127

申请日：2019-12-26

申请人： Intel Corporation

发明人： Chandrasekaran Sakthivel ,  Prasoonkumar Surti ,  John C. Weast ,  Sara S. Baghsorkhi ,  Justin E. Gottschlich ,  Abhishek R. Appu ,  Nicolas C. Galoppo Von Borries ,  Joydeep Ray ,  Narayan Srinivasa ,  Feng Chen ,  Ben J. Ashbaugh ,  Rajkishore Barik ,  Tsung-Han Lin ,  Kamal Sinha ,  Eriko Nurvitadhi ,  Balaji Vembu ,  Altug Koker

IPC分类号： G06F12/0837 ,  G06N3/08 ,  G06N20/00 ,  G06T1/20 ,  G06F12/0815 ,  G06N3/063 ,  G06N3/04

摘要： In an example, an apparatus comprises a plurality of processing unit cores, a plurality of cache memory modules associated with the plurality of processing unit cores, and a machine learning model communicatively coupled to the plurality of processing unit cores, wherein the plurality of cache memory modules share cache coherency data with the machine learning model. Other embodiments are also disclosed and claimed.

公开(公告)号：US20210081774A1

公开(公告)日：2021-03-18

申请号：US17083080

申请日：2020-10-28

申请人： Intel Corporation

发明人： Rajkishore Barik ,  Elmoustapha Ould-Ahmed-Vall ,  Xiaoming Chen ,  Dhawal Srivastava ,  Anbang Yao ,  Kevin Nealis ,  Eriko Nurvitadhi ,  Sara S. Baghsorkhi ,  Balaji Vembu ,  Tatiana Shpeisman ,  Ping T. Tang

IPC分类号： G06N3/063 ,  G06N3/04 ,  G06F9/30 ,  G06F9/38 ,  G06T1/20 ,  G06N3/08

摘要： One embodiment provides for a general-purpose graphics processing unit including a scheduler to schedule multiple matrix operations for execution by a general-purpose graphics processing unit. The multiple matrix operations are determined based on a single machine learning compute instruction. The single machine learning compute instruction is a convolution instruction and the multiple matrix operations are associated with a convolution operation.

公开(公告)号：US10929749B2

公开(公告)日：2021-02-23

申请号：US15494948

申请日：2017-04-24

申请人： Intel Corporation

发明人： Narayan Srinivasa ,  Joydeep Ray ,  Nicolas C. Galoppo Von Borries ,  Ben Ashbaugh ,  Prasoonkumar Surti ,  Feng Chen ,  Barath Lakshmanan ,  Elmoustapha Ould-Ahmed-Vall ,  Liwei Ma ,  Linda L. Hurd ,  Abhishek R. Appu ,  John C. Weast ,  Sara S. Baghsorkhi ,  Justin E. Gottschlich ,  Chandrasekaran Sakthivel ,  Farshad Akhbari ,  Dukhwan Kim ,  Altug Koker ,  Nadathur Rajagopalan Satish

IPC分类号： G06F9/30 ,  G06F9/38 ,  G06F9/28 ,  G06F9/302 ,  G06F15/00 ,  G06N3/08 ,  G06N3/04 ,  G06N3/063

摘要： An apparatus to facilitate optimization of a neural network (NN) is disclosed. The apparatus includes optimization logic to define a NN topology having one or more macro layers, adjust the one or more macro layers to adapt to input and output components of the NN and train the NN based on the one or more macro layers.