公开(公告)号：US11727527B2

公开(公告)日：2023-08-15

申请号：US17541413

申请日：2021-12-03

Applicant: Intel Corporation

Inventor： 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: G06T1/20 ,  G06N3/063 ,  G06F9/38 ,  G06F9/30 ,  G06N3/084 ,  G06N3/044 ,  G06N3/045 ,  G06N3/04 ,  G06N3/08

CPC classification number: G06T1/20 ,  G06F9/3001 ,  G06F9/3017 ,  G06F9/3851 ,  G06F9/3887 ,  G06F9/3895 ,  G06N3/04 ,  G06N3/044 ,  G06N3/045 ,  G06N3/063 ,  G06N3/08 ,  G06N3/084

Abstract: 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 compute operation.

公开(公告)号：US11693658B2

公开(公告)日：2023-07-04

申请号：US17443376

申请日：2021-07-26

Applicant: Intel Corporation

Inventor： 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: G06F9/30 ,  G06F9/38 ,  G06N3/063 ,  G06N3/084 ,  G06T1/20 ,  G06N3/044 ,  G06N3/045

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

Abstract: 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 ternary weight associated with a neural network and an arithmetic logic unit including a multiplier, an adder, and an accumulator register. To execute the decoded instruction, the multiplier is to perform a multiplication operation on the multi-bit input based on the ternary weight to generate an intermediate product and the adder is 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：US20230061670A1

公开(公告)日：2023-03-02

申请号：US17978573

申请日：2022-11-01

Applicant: Intel Corporation

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

Abstract: 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：US11468541B2

公开(公告)日：2022-10-11

申请号：US17720804

申请日：2022-04-14

Applicant: Intel Corporation

Inventor： Elmoustapha Ould-Ahmed-Vall ,  Sara S. Baghsorkhi ,  Anhang 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: G06T1/20 ,  G06F7/483 ,  G06N20/00 ,  G06F3/14 ,  G06T1/60 ,  G06N3/08 ,  G06F9/30 ,  G06N3/04 ,  G06N3/063 ,  G06F9/50 ,  G06F9/38 ,  G06T15/00

Abstract: Embodiments described herein provide a graphics processor that can perform a variety of mixed and multiple precision instructions and operations. One embodiment provides a streaming multiprocessor that can concurrently execute multiple thread groups, wherein the streaming multiprocessor includes a single instruction, multiple thread (SIMT) architecture and the streaming multiprocessor is to execute multiple threads for each of multiple instructions. The streaming multiprocessor can perform concurrent integer and floating-point operations and includes a mixed precision core to perform operations at multiple or mixed precisions and dynamic ranges.

公开(公告)号：US20210035255A1

公开(公告)日：2021-02-04

申请号：US16928353

申请日：2020-07-14

Applicant: Intel Corporation

Inventor： 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: G06T1/20 ,  G06N3/04 ,  G06N3/063 ,  G06F9/38 ,  G06F9/30 ,  G06N3/08

Abstract: 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：US10726514B2

公开(公告)日：2020-07-28

申请号：US15581167

申请日：2017-04-28

Applicant: Intel Corporation

Inventor： 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: G06T1/20 ,  G06F7/483 ,  G06N3/08 ,  G06F9/30 ,  G06N3/04 ,  G06N3/063 ,  G06F9/50 ,  G06F9/38 ,  G06N20/00 ,  G06F3/14 ,  G06T1/60 ,  G06T15/00

Abstract: One embodiment provides a general-purpose graphics processing unit comprising a dynamic precision floating-point unit including a control unit having precision tracking hardware logic to track an available number of bits of precision for computed data relative to a target precision, wherein the dynamic precision floating-point unit includes computational logic to output data at multiple precisions.

公开(公告)号：US20190188554A1

公开(公告)日：2019-06-20

申请号：US16283021

申请日：2019-02-22

Applicant: Intel Corporation

Inventor： Liwei Ma ,  Elmoustapha Ould-Ahmed-Vall ,  Barath Lakshmanan ,  Ben J. Ashbaugh ,  Jingyi Jin ,  Jeremy Bottleson ,  Mike B. Macpherson ,  Kevin Nealis ,  Dhawal Srivastava ,  Joydeep Ray ,  Ping T. Tang ,  Michael S. Strickland ,  Xiaoming Chen ,  Anbang Yao ,  Tatiana Shpeisman ,  Altug Koker ,  Abhishek R. Appu

IPC: G06N3/04 ,  G06N3/08 ,  G06T1/20 ,  G06N3/063

CPC classification number: G06N3/04 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/063 ,  G06N3/082 ,  G06T1/20

Abstract: Embodiments provide systems and methods which facilitate optimization of a convolutional neural network (CNN). One embodiment provides for a non-transitory machine-readable medium storing instructions that cause one or more processors to perform operations comprising processing a trained convolutional neural network (CNN) to generate a processed CNN, the trained CNN having weights in a floating-point format. Processing the trained CNN includes quantizing the weights in the floating-point format to generate weights in an integer format. Quantizing the weights includes generating a quantization table to enable non-uniform quantization of the weights and quantizing the weights from the floating-point format to the integer format using the quantization table. The operations additionally comprise performing an inference operation utilizing the processed CNN with the integer format weights.

公开(公告)号：US20180315159A1

公开(公告)日：2018-11-01

申请号：US15789565

申请日：2017-10-20

Applicant: Intel Corporation

Inventor： 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: G06T1/20 ,  G06N99/00 ,  G06F7/483

CPC classification number: G06T1/20 ,  G06F3/14 ,  G06F7/483 ,  G06F9/30014 ,  G06F9/30185 ,  G06F9/3863 ,  G06F9/5044 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/063 ,  G06N3/084 ,  G06T1/60 ,  G06T15/005

Abstract: One embodiment provides an accelerator module comprising a memory stack including multiple memory dies; a graphics processing unit (GPU) coupled with the memory stack via one or more memory controllers, the GPU including a plurality of multiprocessors having a single instruction, multiple thread (SIMT) architecture, the multiprocessors to execute at least one single instruction; the at least one single instruction to cause at least a portion of the GPU to perform a floating-point operation on input having differing precisions; and the floating-point operation is a two-dimensional matrix multiply and accumulate operation.

公开(公告)号：US11948224B2

公开(公告)日：2024-04-02

申请号：US17978573

申请日：2022-11-01

Applicant: Intel Corporation

Inventor： 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: 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 classification number: 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

Abstract: 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：US20230359461A1

公开(公告)日：2023-11-09

申请号：US18315625

申请日：2023-05-11

Applicant: Intel Corporation

Inventor： 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: G06F9/30 ,  G06F9/38 ,  G06N3/063 ,  G06N3/084 ,  G06T1/20 ,  G06N3/044 ,  G06N3/045

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

Abstract: 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.