公开(公告)号：US20180246762A1

公开(公告)日：2018-08-30

申请号：US15444390

申请日：2017-02-28

Applicant: Intel Corporation

Inventor： Stephen J. Tarsa ,  Gautham N. Chinya ,  Gokce Keskin ,  Hong Wang ,  Karthik Sankaranarayanan

IPC: G06F9/50

CPC classification number: G06F9/5083

Abstract: In one embodiment, a processor comprises a processor optimization unit. The processor optimization unit is to collect runtime information associated with a computing device, wherein the runtime information comprises information indicating a performance of the computing device during program execution. The processor optimization unit is further to receive runtime optimization information for the computing device, wherein the runtime optimization information comprises information associated with one or more runtime optimizations for the computing device, and wherein the runtime optimization information is determined based on an analysis of the collected runtime information. The processor optimization unit is further to perform the one or more runtime optimizations for the computing device based on the runtime optimization information.

公开(公告)号：US12056906B2

公开(公告)日：2024-08-06

申请号：US18466141

申请日：2023-09-13

Applicant: Intel Corporation

Inventor： Joydeep Ray ,  Ben Ashbaugh ,  Prasoonkumar Surti ,  Pradeep Ramani ,  Rama Harihara ,  Jerin C. Justin ,  Jing Huang ,  Xiaoming Cui ,  Timothy B. Costa ,  Ting Gong ,  Elmoustapha Ould-ahmed-vall ,  Kumar Balasubramanian ,  Anil Thomas ,  Oguz H. Elibol ,  Jayaram Bobba ,  Guozhong Zhuang ,  Bhavani Subramanian ,  Gokce Keskin ,  Chandrasekaran Sakthivel ,  Rajesh Poornachandran

IPC: G06F12/02 ,  G06T9/00 ,  G06T15/00

CPC classification number: G06T9/002 ,  G06F12/023 ,  G06T15/005 ,  G06F2212/302 ,  G06F2212/401

Abstract: Embodiments are generally directed to compression in machine learning and deep learning processing. An embodiment of an apparatus for compression of untyped data includes a graphical processing unit (GPU) including a data compression pipeline, the data compression pipeline including a data port coupled with one or more shader cores, wherein the data port is to allow transfer of untyped data without format conversion, and a 3D compression/decompression unit to provide for compression of untyped data to be stored to a memory subsystem and decompression of untyped data from the memory subsystem.

公开(公告)号：US11798198B2

公开(公告)日：2023-10-24

申请号：US18152643

申请日：2023-01-10

Applicant: Intel Corporation

Inventor： Joydeep Ray ,  Ben Ashbaugh ,  Prasoonkumar Surti ,  Pradeep Ramani ,  Rama Harihara ,  Jerin C. Justin ,  Jing Huang ,  Xiaoming Cui ,  Timothy B. Costa ,  Ting Gong ,  Elmoustapha Ould-ahmed-vall ,  Kumar Balasubramanian ,  Anil Thomas ,  Oguz H. Elibol ,  Jayaram Bobba ,  Guozhong Zhuang ,  Bhavani Subramanian ,  Gokce Keskin ,  Chandrasekaran Sakthivel ,  Rajesh Poornachandran

IPC: G06T9/00 ,  G06F12/02 ,  G06T15/00

CPC classification number: G06T9/002 ,  G06F12/023 ,  G06T15/005 ,  G06F2212/302 ,  G06F2212/401

Abstract: Embodiments are generally directed to compression in machine learning and deep learning processing. An embodiment of an apparatus for compression of untyped data includes a graphical processing unit (GPU) including a data compression pipeline, the data compression pipeline including a data port coupled with one or more shader cores, wherein the data port is to allow transfer of untyped data without format conversion, and a 3D compression/decompression unit to provide for compression of untyped data to be stored to a memory subsystem and decompression of untyped data from the memory subsystem.

公开(公告)号：US20190205736A1

公开(公告)日：2019-07-04

申请号：US15858014

申请日：2017-12-29

Applicant: Intel Corporation

Inventor： Amit Bleiweiss ,  Abhishek Venkatesh ,  Gokce Keskin ,  John Gierach ,  Oguz Elibol ,  Tomer Bar-On ,  Huma Abidi ,  Devan Burke ,  Jaikrishnan Menon ,  Eriko Nurvitadhi ,  Pruthvi Gowda Thorehosur Appajigowda ,  Travis T. Schluessler ,  Dhawal Srivastava ,  Nishant Patel ,  Anil Thomas

IPC: G06N3/063 ,  G06N5/04 ,  G06N3/04 ,  G06N99/00 ,  G06F9/38 ,  G06N3/08 ,  G06T1/20

CPC classification number: G06N3/063 ,  G06F9/3887 ,  G06N3/04 ,  G06N3/08 ,  G06N5/046 ,  G06N20/00 ,  G06T1/20

Abstract: An apparatus to facilitate compute optimization is disclosed. The apparatus includes a at least one processor to perform operations to implement a neural network and compute logic to accelerate neural network computations.

公开(公告)号：US20190042927A1

公开(公告)日：2019-02-07

申请号：US16108817

申请日：2018-08-22

Applicant: Intel Corporation

Inventor： Gokce Keskin ,  Anil Thomas ,  Oguz Elibol

IPC: G06N3/063 ,  G06N3/08 ,  G10L15/16 ,  G06N3/04 ,  G06F17/16

Abstract: An embodiment of a semiconductor package apparatus may include technology to process one or more vectors with a sum of squares operation with a layer of a multi-layer neural network, and determine a fixed-point approximation for the sum of squares operation. Other embodiments are disclosed and claimed.

公开(公告)号：US09794089B2

公开(公告)日：2017-10-17

申请号：US15187382

申请日：2016-06-20

Applicant: Intel Corporation

Inventor： Tawfiq Musah ,  Gokce Keskin ,  Ganesh Balamurugan ,  James E. Jaussi ,  Bryan K. Casper

IPC: H04L25/03 ,  H04L7/00 ,  H04L25/14 ,  H04L7/033

CPC classification number: H04L25/03057 ,  H04L7/0058 ,  H04L7/0087 ,  H04L7/033 ,  H04L25/03146 ,  H04L25/14

Abstract: Some embodiments include apparatus and methods having an input to receive an input signal, additional inputs to receive clock signals having different phases to sample the input signal, and a decision feedback equalizer (DFE) having DFE slices. The DFE slices include a number of data comparators to provide data information based on the sampling of the input signal, and a number of phase error comparators to provide phase error information associated with the sampling of the input signal. The number of phase error comparators of the DFE slices is not greater than the number of data comparators of the DFE slices.

公开(公告)号：US20160301548A1

公开(公告)日：2016-10-13

申请号：US15187382

申请日：2016-06-20

Applicant: Intel Corporation

Inventor： Tawfiq Musah ,  Gokce Keskin ,  Ganesh Balamurugan ,  James E. Jaussi ,  Bryan K. Casper

IPC: H04L25/03 ,  H04L7/00

CPC classification number: H04L25/03057 ,  H04L7/0058 ,  H04L7/0087 ,  H04L7/033 ,  H04L25/03146 ,  H04L25/14

Abstract: Some embodiments include apparatus and methods having an input to receive an input signal, additional inputs to receive clock signals having different phases to sample the input signal, and a decision feedback equalizer (DFE) having DFE slices. The DFE slices include a number of data comparators to provide data information based on the sampling of the input signal, and a number of phase error comparators to provide phase error information associated with the sampling of the input signal. The number of phase error comparators of the DFE slices is not greater than the number of data comparators of the DFE slices.

公开(公告)号：US20250053797A1

公开(公告)日：2025-02-13

申请号：US18812822

申请日：2024-08-22

Applicant: Intel Corporation

Inventor： Amit Bleiweiss ,  Abhishek Venkatesh ,  Gokce Keskin ,  John Gierach ,  Oguz Elibol ,  Tomer Bar-On ,  Huma Abidi ,  Devan Burke ,  Jaikrishnan Menon ,  Eriko Nurvitadhi ,  Pruthvi Gowda Thorehosur Appajigowda ,  Travis T. Schluessler ,  Dhawal Srivastava ,  Nishant Patel ,  Anil Thomas

IPC: G06N3/063 ,  G06F9/38 ,  G06N3/04 ,  G06N3/08 ,  G06N5/046 ,  G06N20/00 ,  G06T1/20

Abstract: An apparatus to facilitate compute optimization is disclosed. The apparatus includes a at least one processor to perform operations to implement a neural network and compute logic to accelerate neural network computations.

公开(公告)号：US12086705B2

公开(公告)日：2024-09-10

申请号：US15858014

申请日：2017-12-29

Applicant: Intel Corporation

Inventor： Amit Bleiweiss ,  Abhishek Venkatesh ,  Gokce Keskin ,  John Gierach ,  Oguz Elibol ,  Tomer Bar-On ,  Huma Abidi ,  Devan Burke ,  Jaikrishnan Menon ,  Eriko Nurvitadhi ,  Pruthvi Gowda Thorehosur Appajigowda ,  Travis T. Schluessler ,  Dhawal Srivastava ,  Nishant Patel ,  Anil Thomas

IPC: G06N3/063 ,  G06F9/38 ,  G06N3/04 ,  G06N3/08 ,  G06N5/046 ,  G06N20/00 ,  G06T1/20

CPC classification number: G06N3/063 ,  G06F9/3887 ,  G06N3/04 ,  G06N3/08 ,  G06N5/046 ,  G06N20/00 ,  G06T1/20

Abstract: An apparatus to facilitate compute optimization is disclosed. The apparatus includes a at least one processor to perform operations to implement a neural network and compute logic to accelerate neural network computations.

公开(公告)号：US10546393B2

公开(公告)日：2020-01-28

申请号：US15859408

申请日：2017-12-30

Applicant: Intel Corporation

Inventor： Joydeep Ray ,  Ben Ashbaugh ,  Prasoonkumar Surti ,  Pradeep Ramani ,  Rama Harihara ,  Jerin C. Justin ,  Jing Huang ,  Xiaoming Cui ,  Timothy B. Costa ,  Ting Gong ,  Elmoustapha Ould-Ahmed-Vall ,  Kumar Balasubramanian ,  Anil Thomas ,  Oguz H. Elibol ,  Jayaram Bobba ,  Guozhong Zhuang ,  Bhavani Subramanian ,  Gokce Keskin ,  Chandrasekaran Sakthivel ,  Rajesh Poornachandran

IPC: G06T9/00 ,  G06T15/00

Abstract: Embodiments are generally directed to compression in machine learning and deep learning processing. An embodiment of an apparatus for compression of untyped data includes a graphical processing unit (GPU) including a data compression pipeline, the data compression pipeline including a data port coupled with one or more shader cores, wherein the data port is to allow transfer of untyped data without format conversion, and a 3D compression/decompression unit to provide for compression of untyped data to be stored to a memory subsystem and decompression of untyped data from the memory subsystem.