Patents by Inventor Abhishek Appu
Abhishek Appu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 12293431Abstract: 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 detect zero value elements within a vector or a set of packed data elements output by a processing resource and generate metadata to indicate a location of the zero value elements within the plurality of data elements.Type: GrantFiled: May 2, 2023Date of Patent: May 6, 2025Assignee: Intel CorporationInventors: Joydeep Ray, Scott Janus, Varghese George, Subramaniam Maiyuran, Altug Koker, Abhishek Appu, Prasoonkumar Surti, Vasanth Ranganathan, Valentin Andrei, Ashutosh Garg, Yoav Harel, Arthur Hunter, Jr., SungYe Kim, Mike Macpherson, Elmoustapha Ould-Ahmed-Vall, William Sadler, Lakshminarayanan Striramassarma, Vikranth Vemulapalli
-
Publication number: 20250103548Abstract: 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 coupled to the processing resources. The cache controller is configured to control cache priority by determining whether default settings or an instruction will control cache operations for the cache.Type: ApplicationFiled: November 14, 2024Publication date: March 27, 2025Applicant: Intel CorporationInventors: Altug Koker, Joydeep Ray, Ben Ashbaugh, Jonathan Pearce, Abhishek Appu, Vasanth Ranganathan, Lakshminarayanan Striramassarma, Elmoustapha Ould-Ahmed-Vall, Aravindh Anantaraman, Valentin Andrei, Nicolas Galoppo Von Borries, Varghese George, Yoav Harel, Arthur Hunter, JR., Brent Insko, Scott Janus, Pattabhiraman K, Mike Macpherson, Subramaniam Maiyuran, Marian Alin Petre, Murali Ramadoss, Shailesh Shah, Kamal Sinha, Prasoonkumar Surti, Vikranth Vemulapalli
-
Publication number: 20250103547Abstract: 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 techniques to optimize training and inference on a systolic array when using sparse data. One embodiment provides techniques to use decompression information when performing sparse compute operations. One embodiment enables the disaggregation of special function compute arrays via a shared reg file. One embodiment enables packed data compress and expand operations on a GPGPU. One embodiment provides techniques to exploit block sparsity within the cache hierarchy of a GPGPU.Type: ApplicationFiled: October 4, 2024Publication date: March 27, 2025Applicant: INTEL CORPORATIONInventors: Prasoonkumar Surti, Subramaniam Maiyuran, Valentin Andrei, Abhishek Appu, Varghese George, Altug Koker, Mike Macpherson, Elmoustapha Ould-Ahmed-Vall, Vasanth Ranganathan, Joydeep Ray, Lakshminarayanan Striramassarma, SungYe Kim
-
Publication number: 20250103511Abstract: 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.Type: ApplicationFiled: October 3, 2024Publication date: March 27, 2025Applicant: Intel CorporationInventors: 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
-
Publication number: 20250104180Abstract: 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.Type: ApplicationFiled: December 3, 2024Publication date: March 27, 2025Applicant: Intel CorporationInventors: Abhishek Appu, Subramaniam Maiyuran, Mike Macpherson, Fangwen Fu, Jiasheng Chen, Varghese George, Vasanth Ranganathan, Ashutosh Garg, Joydeep Ray
-
Patent number: 12210477Abstract: 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 coupled to the processing resources. The cache controller is configured to control cache priority by determining whether default settings or an instruction will control cache operations for the cache.Type: GrantFiled: March 14, 2020Date of Patent: January 28, 2025Assignee: Intel CorporationInventors: Altug Koker, Joydeep Ray, Ben Ashbaugh, Jonathan Pearce, Abhishek Appu, Vasanth Ranganathan, Lakshminarayanan Striramassarma, Elmoustapha Ould-Ahmed-Vall, Aravindh Anantaraman, Valentin Andrei, Nicolas Galoppo Von Borries, Varghese George, Yoav Harel, Arthur Hunter, Jr., Brent Insko, Scott Janus, Pattabhiraman K, Mike Macpherson, Subramaniam Maiyuran, Marian Alin Petre, Murali Ramadoss, Shailesh Shah, Kamal Sinha, Prasoonkumar Surti, Vikranth Vemulapalli
-
Publication number: 20250028675Abstract: Embodiments described herein include software, firmware, and hardware that provides techniques to enable deterministic scheduling across multiple general-purpose graphics processing units. One embodiment provides a multi-GPU architecture with uniform latency. One embodiment provides techniques to distribute memory output based on memory chip thermals. One embodiment provides techniques to enable thermally aware workload scheduling. One embodiment provides techniques to enable end to end contracts for workload scheduling on multiple GPUs.Type: ApplicationFiled: August 1, 2024Publication date: January 23, 2025Applicant: Intel CorporationInventors: JOYDEEP RAY, SELVAKUMAR PANNEER, SAURABH TANGRI, BEN ASHBAUGH, SCOTT JANUS, ABHISHEK APPU, VARGHESE GEORGE, RAVISHANKAR IYER, NILESH JAIN, PATTABHIRAMAN K, ALTUG KOKER, MIKE MACPHERSON, JOSH MASTRONARDE, ELMOUSTAPHA OULD-AHMED-VALL, JAYAKRISHNA P. S, ERIC SAMSON
-
Patent number: 12198222Abstract: 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.Type: GrantFiled: December 7, 2023Date of Patent: January 14, 2025Assignee: Intel CorporationInventors: Abhishek Appu, Subramaniam Maiyuran, Mike Macpherson, Fangwen Fu, Jiasheng Chen, Varghese George, Vasanth Ranganathan, Ashutosh Garg, Joydeep Ray
-
Patent number: 12182035Abstract: 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.Type: GrantFiled: March 14, 2020Date of Patent: December 31, 2024Assignee: Intel CorporationInventors: 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
-
Publication number: 20240385975Abstract: 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.Type: ApplicationFiled: May 22, 2024Publication date: November 21, 2024Applicant: Intel CorporationInventors: Joydeep Ray, Altug Koker, Elmoustapha Ould-Ahmed-Vall, Michael Macpherson, Aravindh V. Anantaraman, Vasanth Ranganathan, Lakshminarayanan Striramassarma, Varghese George, Abhishek Appu, Prasoonkumar Surti
-
Patent number: 12141094Abstract: 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 techniques to optimize training and inference on a systolic array when using sparse data. One embodiment provides techniques to use decompression information when performing sparse compute operations. One embodiment enables the disaggregation of special function compute arrays via a shared reg file. One embodiment enables packed data compress and expand operations on a GPGPU. One embodiment provides techniques to exploit block sparsity within the cache hierarchy of a GPGPU.Type: GrantFiled: March 14, 2020Date of Patent: November 12, 2024Assignee: Intel CorporationInventors: Prasoonkumar Surti, Subramaniam Maiyuran, Valentin Andrei, Abhishek Appu, Varghese George, Altug Koker, Mike Macpherson, Elmoustapha Ould-Ahmed-Vall, Vasanth Ranganathan, Joydeep Ray, Lakshminarayanan Striramassarma, SungYe Kim
-
Patent number: 12124383Abstract: 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.Type: GrantFiled: July 12, 2022Date of Patent: October 22, 2024Assignee: Intel CorporationInventors: 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
-
Publication number: 20240345990Abstract: 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.Type: ApplicationFiled: April 4, 2024Publication date: October 17, 2024Applicant: Intel CorporationInventors: 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
-
Patent number: 12079155Abstract: Embodiments described herein include software, firmware, and hardware that provides techniques to enable deterministic scheduling across multiple general-purpose graphics processing units. One embodiment provides a multi-GPU architecture with uniform latency. One embodiment provides techniques to distribute memory output based on memory chip thermals. One embodiment provides techniques to enable thermally aware workload scheduling. One embodiment provides techniques to enable end to end contracts for workload scheduling on multiple GPUs.Type: GrantFiled: March 14, 2020Date of Patent: September 3, 2024Assignee: Intel CorporationInventors: Joydeep Ray, Selvakumar Panneer, Saurabh Tangri, Ben Ashbaugh, Scott Janus, Abhishek Appu, Varghese George, Ravishankar Iyer, Nilesh Jain, Pattabhiraman K, Altug Koker, Mike MacPherson, Josh Mastronarde, Elmoustapha Ould-Ahmed-Vall, Jayakrishna P. S, Eric Samson
-
Publication number: 20240282042Abstract: Apparatus and method for stack throttling.Type: ApplicationFiled: February 26, 2024Publication date: August 22, 2024Inventors: Karthik Vaidyanathan, Abhishek Appu, Vasanth Ranganathan, Joydeep Ray, Prasoonkumar Surti
-
Patent number: 12056059Abstract: 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.Type: GrantFiled: February 1, 2022Date of Patent: August 6, 2024Assignee: Intel CorporationInventors: 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
-
Patent number: 12032496Abstract: 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.Type: GrantFiled: July 25, 2023Date of Patent: July 9, 2024Assignee: INTEL CORPORATIONInventors: Joydeep Ray, Altug Koker, Elmoustapha Ould-Ahmed-Vall, Michael Macpherson, Aravindh V. Anantaraman, Vasanth Ranganathan, Lakshminarayanan Striramassarma, Varghese George, Abhishek Appu, Prasoonkumar Surti
-
Publication number: 20240184739Abstract: Embodiments described herein provide techniques to enable the dynamic reconfiguration of memory on a general-purpose graphics processing unit. One embodiment described herein enables dynamic reconfiguration of cache memory bank assignments based on hardware statistics. One embodiment enables for virtual memory address translation using mixed four kilobyte and sixty-four kilobyte pages within the same page table hierarchy and under the same page directory. One embodiment provides for a graphics processor and associated heterogenous processing system having near and far regions of the same level of a cache hierarchy.Type: ApplicationFiled: February 5, 2024Publication date: June 6, 2024Applicant: INTEL CORPORATIONInventors: Joydeep RAY, Niranjan COORAY, Subramaniam MAIYURAN, Altug KOKER, Prasoonkumar SURTI, Varghese GEORGE, Valentin ANDREI, Abhishek APPU, Guadalupe GARCIA, Pattabhiraman K, Sungye KIM, Sanjay KUMAR, Pratik MAROLIA, Elmoustapha OULD-AHMED-VALL, Vasanth RANGANATHAN, William SADLER, Lakshminarayanan STRIRAMASSARMA
-
Patent number: 11995029Abstract: 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.Type: GrantFiled: March 14, 2020Date of Patent: May 28, 2024Assignee: Intel CorporationInventors: 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
-
Publication number: 20240161227Abstract: 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.Type: ApplicationFiled: December 7, 2023Publication date: May 16, 2024Applicant: Intel CorporationInventors: Abhishek Appu, Subramaniam Maiyuran, Mike Macpherson, Fangwen Fu, Jiasheng Chen, Varghese George, Vasanth Ranganathan, Ashutosh Garg, Joydeep Ray