公开(公告)号：US11580361B2

公开(公告)日：2023-02-14

申请号：US15494826

申请日：2017-04-24

Applicant: Intel Corporation

Inventor： Gokcen Cilingir ,  Elmoustapha Ould-Ahmed-Vall ,  Rajkishore Barik ,  Kevin Nealis ,  Xiaoming Chen ,  Justin E. Gottschlich ,  Prasoonkumar Surti ,  Chandrasekaran Sakthivel ,  Abhishek Appu ,  John C. Weast ,  Sara S. Baghsorkhi ,  Barnan Das ,  Narayan Biswal ,  Stanley J. Baran ,  Nilesh V. Shah ,  Archie Sharma ,  Mayuresh M. Varerkar

IPC: G06N3/08 ,  G06N3/04 ,  G06F9/38 ,  G06N3/063 ,  G06F9/30 ,  G06T1/20 ,  G06N3/084

Abstract: An apparatus to facilitate neural network (NN) training is disclosed. The apparatus includes training logic to receive one or more network constraints and train the NN by automatically determining a best network layout and parameters based on the network constraints.

公开(公告)号：US20220350751A1

公开(公告)日：2022-11-03

申请号：US17862739

申请日：2022-07-12

Applicant: Intel Corporation

Inventor： Altug Koker ,  Joydeep Ray ,  Elmoustapha Ould-Ahmed-Vall ,  Abhishek Appu ,  Aravindh Anantaraman ,  Valentin Andrei ,  Durgaprasad Bilagi ,  Varghese George ,  Brent Insko ,  Sanjeev Jahagirdar ,  Scott Janus ,  Pattabhiraman K ,  SungYe Kim ,  Subramaniam Maiyuran ,  Vasanth Ranganathan ,  Lakshminarayanan Striramassarma ,  Xinmin Tian

IPC: G06F12/123 ,  G06F12/0875 ,  G06F12/0891 ,  G06T1/60

Abstract: Systems and methods for improving cache efficiency and utilization are disclosed. In one embodiment, a graphics processor includes processing resources to perform graphics operations and a cache controller of a cache memory that is coupled to the processing resources. The cache controller is configured to set an initial aging policy using an aging field based on age of cache lines within the cache memory and to determine whether a hint or an instruction to indicate a level of aging has been received. In one embodiment, the cache memory configured to be partitioned into multiple cache regions, wherein the multiple cache regions include a first cache region having a cache eviction policy with a configurable level of data persistence.

公开(公告)号：US20220114108A1

公开(公告)日：2022-04-14

申请号：US17428529

申请日：2020-03-14

Applicant: Intel Corporation

Inventor： Altug Koker ,  Joydeep Ray ,  Elmoustapha Ould-Ahmed-Vall ,  Abhishek Appu ,  Aravindh Anantaraman ,  Valentin Andrei ,  Durgaprasad Bilagi ,  Varghese George ,  Brent Insko ,  Sanjeev Jahagirdar ,  Scott Janus ,  Pattabhiraman K. ,  SungYe Kim ,  Subramaniam Maiyuran ,  Vasanth Ranganathan ,  Lakshminarayanan Striramassarma ,  Xinmin Tian

IPC: G06F12/123 ,  G06F12/0891 ,  G06F12/0875 ,  G06T1/60

Abstract: Systems and methods for improving cache efficiency and utilization are disclosed. In one embodiment, a graphics processor includes processing resources to perform graphics operations and a cache controller of a cache memory that is coupled to the processing resources. The cache controller is configured to set an initial aging policy using an aging field based on age of cache lines within the cache memory and to determine whether a hint or an instruction to indicate a level of aging has been received.

公开(公告)号：US20220114096A1

公开(公告)日：2022-04-14

申请号：US17428527

申请日：2020-03-14

Applicant: Intel Corporation

Inventor： Lakshminarayanan Striramassarma ,  Prasoonkumar Surti ,  Varghese George ,  Ben Ashbaugh ,  Aravindh Anantaraman ,  Valentin Andrei ,  Abhishek Appu ,  Nicolas Galoppo Von Borries ,  Altug Koker ,  Mike Macpherson ,  Subramaniam Maiyuran ,  Nilay Mistry ,  Elmoustapha Ould-Ahmed-Vall ,  Selvakumar Panneer ,  Vasanth Ranganathan ,  Joydeep Ray ,  Ankur Shah ,  Saurabh Tangri

IPC: G06F12/0802

Abstract: Multi-tile Memory Management for Detecting Cross Tile Access, Providing Multi-Tile Inference Scaling with multicasting of data via copy operation, and Providing Page Migration are disclosed herein. In one embodiment, a graphics processor for a multi-tile architecture includes a first graphics processing unit (GPU) having a memory and a memory controller, a second graphics processing unit (GPU) having a memory and a cross-GPU fabric to communicatively couple the first and second GPUs. The memory controller is configured to determine whether frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU in the multi-GPU configuration and to send a message to initiate a data transfer mechanism when frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU.

公开(公告)号：US20210374897A1

公开(公告)日：2021-12-02

申请号：US17303654

申请日：2021-06-03

Applicant: Intel Corporation

Inventor： Joydeep Ray ,  Scott Janus ,  Varghese George ,  Subramaniam Maiyuran ,  Altug Koker ,  Abhishek Appu ,  Prasoonkumar Surti ,  Vasanth Ranganathan ,  Andrei Valentin ,  Ashutosh Garg ,  Yoav Harel ,  Arthur Hunter, JR. ,  SungYe Kim ,  Mike Macpherson ,  Elmoustapha Ould-Ahmed-Vall ,  William Sadler ,  Lakshminarayanan Striramassarma ,  Vikranth Vemulapalli

IPC: G06T1/20 ,  G06F9/50 ,  G06F12/0806 ,  G06F15/80 ,  G06F17/16 ,  G06N3/04 ,  G06N3/08 ,  G06F7/544

Abstract: Embodiments described herein include, software, firmware, and hardware logic that provides techniques to perform arithmetic on sparse data via a systolic processing unit. Embodiment described herein provided techniques to skip computational operations for zero filled matrices and sub-matrices. Embodiments additionally provide techniques to maintain data compression through to a processing unit. Embodiments additionally provide an architecture for a sparse aware logic unit.

公开(公告)号：US10402224B2

公开(公告)日：2019-09-03

申请号：US15860708

申请日：2018-01-03

Applicant: Intel Corporation

Inventor： Kiran C. Veernapu ,  Kamlesh Pillai ,  James Valerio ,  Joydeep Ray ,  Abhishek Appu

IPC: G06F9/48 ,  G06F9/54 ,  G06T1/20 ,  G06F9/22 ,  G06T15/00

Abstract: A mechanism is described to facilitate microcontroller-based flexible thread scheduling launching in computing environments. An apparatus of embodiments, as described herein, includes facilitating a graphics processor hosting a microcontroller having a thread scheduling unit, and detection and observation logic to detect a scheduling algorithm associated with an application at the apparatus. The apparatus may further include reading and dispatching logic to facilitate the microcontroller to prepare a flexible dispatch routine based on the scheduling algorithm. The apparatus may further include scheduling and launching logic to facilitate the thread scheduling unit to dynamically schedule and launch threads based on the flexible dispatch routine, where the threads are hosted by the graphics processor.

公开(公告)号：US20250166114A1

公开(公告)日：2025-05-22

申请号：US18967123

申请日：2024-12-03

Applicant: Intel Corporation

Inventor： Abhishek Appu ,  Subramaniam Maiyuran ,  Mike Macpherson ,  Fangwen Fu ,  Jiasheng Chen ,  Varghese George ,  Vasanth Ranganathan ,  Ashutosh Garg ,  Joydeep Ray

IPC: G06T1/20 ,  G06F7/544 ,  G06F9/30 ,  G06F9/38 ,  G06F9/50 ,  G06F12/0806 ,  G06F15/80 ,  G06F17/16 ,  G06N3/048 ,  G06N3/08 ,  G06N3/084

Abstract: Embodiments described herein include software, firmware, and hardware logic that provides techniques to perform arithmetic on sparse data via a systolic processing unit. One embodiment provides for data aware sparsity via compressed bitstreams. One embodiment provides for block sparse dot product instructions. One embodiment provides for a depth-wise adapter for a systolic array.

公开(公告)号：US12056059B2

公开(公告)日：2024-08-06

申请号：US17590362

申请日：2022-02-01

Applicant: Intel Corporation

Inventor： Altug Koker ,  Joydeep Ray ,  Elmoustapha Ould-Ahmed-Vall ,  Abhishek Appu ,  Aravindh Anantaraman ,  Valentin Andrei ,  Durgaprasad Bilagi ,  Varghese George ,  Brent Insko ,  Sanjeev Jahagirdar ,  Scott Janus ,  Pattabhiraman K ,  SungYe Kim ,  Subramaniam Maiyuran ,  Vasanth Ranganathan ,  Lakshminarayanan Striramassarma ,  Xinmin Tian

IPC: G06F12/00 ,  G06F12/0875 ,  G06F12/0891 ,  G06F12/123 ,  G06T1/60

CPC classification number: G06F12/123 ,  G06F12/0875 ,  G06F12/0891 ,  G06T1/60 ,  G06F2212/302

Abstract: Systems and methods for cache utilization are disclosed. In one embodiment, a graphics processor includes processing resources to perform graphics operations and a cache controller of a cache memory that is coupled to the processing resources. The cache controller is configured to set an initial aging policy using an aging field based on age of cache lines within the cache memory and to determine whether a hint or an instruction to indicate a level of aging has been received. In one embodiment, the cache memory configured to be partitioned into multiple cache regions, wherein the multiple cache regions include a first cache region having a cache eviction policy with a configurable level of data persistence.

公开(公告)号：US12032496B2

公开(公告)日：2024-07-09

申请号：US18358550

申请日：2023-07-25

Applicant: Intel Corporation

Inventor： Joydeep Ray ,  Altug Koker ,  Elmoustapha Ould-Ahmed-Vall ,  Michael Macpherson ,  Aravindh V. Anantaraman ,  Vasanth Ranganathan ,  Lakshminarayanan Striramassarma ,  Varghese George ,  Abhishek Appu ,  Prasoonkumar Surti

IPC: G06F13/16 ,  G06F9/30 ,  G06F9/38 ,  G06F9/50 ,  G06T1/20 ,  G06T1/60

CPC classification number: G06F13/1605 ,  G06F9/3004 ,  G06F9/3887 ,  G06F9/5016 ,  G06T1/20 ,  G06T1/60

Abstract: An apparatus to facilitate efficient data sharing for graphics data processing operations is disclosed. The apparatus includes a processing resource to generate a stream of instructions, an L1 cache communicably coupled to the processing resource and comprising an on-page detector circuit to determine that a set of memory requests in the stream of instructions access a same memory page; and set a marker in a first request of the set of memory requests; and arbitration circuitry communicably coupled to the L1 cache, the arbitration circuitry to route the set of memory requests to memory comprising the memory page and to, in response to receiving the first request with the marker set, remain with the processing resource to process the set of memory requests.

公开(公告)号：US11995029B2

公开(公告)日：2024-05-28

申请号：US17428527

申请日：2020-03-14

Applicant: Intel Corporation

Inventor： Lakshminarayanan Striramassarma ,  Prasoonkumar Surti ,  Varghese George ,  Ben Ashbaugh ,  Aravindh Anantaraman ,  Valentin Andrei ,  Abhishek Appu ,  Nicolas Galoppo Von Borries ,  Altug Koker ,  Mike Macpherson ,  Subramaniam Maiyuran ,  Nilay Mistry ,  Elmoustapha Ould-Ahmed-Vall ,  Selvakumar Panneer ,  Vasanth Ranganathan ,  Joydeep Ray ,  Ankur Shah ,  Saurabh Tangri

IPC: G06F12/00 ,  G06F7/544 ,  G06F7/575 ,  G06F7/58 ,  G06F9/30 ,  G06F9/38 ,  G06F9/50 ,  G06F12/02 ,  G06F12/06 ,  G06F12/0802 ,  G06F12/0804 ,  G06F12/0811 ,  G06F12/0862 ,  G06F12/0866 ,  G06F12/0871 ,  G06F12/0875 ,  G06F12/0882 ,  G06F12/0888 ,  G06F12/0891 ,  G06F12/0893 ,  G06F12/0895 ,  G06F12/0897 ,  G06F12/1009 ,  G06F12/128 ,  G06F15/78 ,  G06F15/80 ,  G06F17/16 ,  G06F17/18 ,  G06T1/20 ,  G06T1/60 ,  H03M7/46 ,  G06N3/08 ,  G06T15/06

CPC classification number: G06F15/7839 ,  G06F7/5443 ,  G06F7/575 ,  G06F7/588 ,  G06F9/3001 ,  G06F9/30014 ,  G06F9/30036 ,  G06F9/3004 ,  G06F9/30043 ,  G06F9/30047 ,  G06F9/30065 ,  G06F9/30079 ,  G06F9/3887 ,  G06F9/5011 ,  G06F9/5077 ,  G06F12/0215 ,  G06F12/0238 ,  G06F12/0246 ,  G06F12/0607 ,  G06F12/0802 ,  G06F12/0804 ,  G06F12/0811 ,  G06F12/0862 ,  G06F12/0866 ,  G06F12/0871 ,  G06F12/0875 ,  G06F12/0882 ,  G06F12/0888 ,  G06F12/0891 ,  G06F12/0893 ,  G06F12/0895 ,  G06F12/0897 ,  G06F12/1009 ,  G06F12/128 ,  G06F15/8046 ,  G06F17/16 ,  G06F17/18 ,  G06T1/20 ,  G06T1/60 ,  H03M7/46 ,  G06F9/3802 ,  G06F9/3818 ,  G06F9/3867 ,  G06F2212/1008 ,  G06F2212/1021 ,  G06F2212/1044 ,  G06F2212/302 ,  G06F2212/401 ,  G06F2212/455 ,  G06F2212/60 ,  G06N3/08 ,  G06T15/06

Abstract: Multi-tile Memory Management for Detecting Cross Tile Access, Providing Multi-Tile Inference Scaling with multicasting of data via copy operation, and Providing Page Migration are disclosed herein. In one embodiment, a graphics processor for a multi-tile architecture includes a first graphics processing unit (GPU) having a memory and a memory controller, a second graphics processing unit (GPU) having a memory and a cross-GPU fabric to communicatively couple the first and second GPUs. The memory controller is configured to determine whether frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU in the multi-GPU configuration and to send a message to initiate a data transfer mechanism when frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU.