Patents by Inventor Kevin Nealis
Kevin Nealis 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: 11308574Abstract: 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 precisions.Type: GrantFiled: August 3, 2020Date of Patent: April 19, 2022Assignee: Intel CorporationInventors: 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
-
Publication number: 20220114430Abstract: 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.Type: ApplicationFiled: December 21, 2021Publication date: April 14, 2022Applicant: Intel CorporationInventors: 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
-
Patent number: 11210760Abstract: 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.Type: GrantFiled: July 14, 2020Date of Patent: December 28, 2021Assignee: Intel CorporationInventors: 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
-
Publication number: 20210397925Abstract: A library of machine learning primitives is provided to optimize a machine learning model to improve the efficiency of inference operations. In one embodiment a trained convolutional neural network (CNN) model is processed into a trained CNN model via pruning, convolution window optimization, and quantization.Type: ApplicationFiled: August 26, 2021Publication date: December 23, 2021Applicant: Intel CorporationInventors: 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
-
Publication number: 20210373886Abstract: 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.Type: ApplicationFiled: July 26, 2021Publication date: December 2, 2021Applicant: Intel CorporationInventors: 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
-
Patent number: 11138686Abstract: 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 precisions.Type: GrantFiled: June 19, 2019Date of Patent: October 5, 2021Assignee: Intel CorporationInventors: 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
-
Patent number: 11074072Abstract: 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 bipolar binary 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 bipolar binary 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.Type: GrantFiled: July 8, 2019Date of Patent: July 27, 2021Assignee: Intel CorporationInventors: 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
-
Publication number: 20210081774Abstract: 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.Type: ApplicationFiled: October 28, 2020Publication date: March 18, 2021Applicant: Intel CorporationInventors: 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
-
Publication number: 20210035255Abstract: 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.Type: ApplicationFiled: July 14, 2020Publication date: February 4, 2021Applicant: Intel CorporationInventors: 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
-
Patent number: 10853906Abstract: 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 is to cause at least a portion of the GPU to perform a floating point operation on input having differing precisions. The floating point operation is a two-dimensional matrix multiply and accumulate operation.Type: GrantFiled: November 21, 2018Date of Patent: December 1, 2020Assignee: Intel CorporationInventors: 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
-
Publication number: 20200364823Abstract: 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 precisions.Type: ApplicationFiled: August 3, 2020Publication date: November 19, 2020Applicant: Intel CorporationInventors: 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
-
Patent number: 10824938Abstract: One embodiment provides for a compute apparatus to perform machine learning operations, the apparatus comprising a decode unit to decode a single instruction into a decoded instruction, the decoded instruction to perform one or more machine learning operations, wherein the decode unit, based on parameters of the one or more machine learning operations, is to request a scheduler to schedule the one or more machine learning operations to one of an array of programmable compute units and a fixed function compute unit.Type: GrantFiled: April 24, 2017Date of Patent: November 3, 2020Assignee: Intel CorporationInventors: 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
-
Patent number: 10769748Abstract: 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.Type: GrantFiled: November 21, 2018Date of Patent: September 8, 2020Assignee: Intel CorporationInventors: 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
-
Patent number: 10726514Abstract: 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.Type: GrantFiled: April 28, 2017Date of Patent: July 28, 2020Assignee: Intel CorporationInventors: 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
-
Publication number: 20190332903Abstract: 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 bipolar binary 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 bipolar binary 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.Type: ApplicationFiled: July 8, 2019Publication date: October 31, 2019Applicant: Intel CorporationInventors: 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
-
Publication number: 20190304053Abstract: 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 precisions.Type: ApplicationFiled: June 19, 2019Publication date: October 3, 2019Applicant: Intel CorporationInventors: 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
-
Patent number: 10410098Abstract: One embodiment provides for a compute apparatus to perform machine learning operations, the apparatus comprising a decode unit to decode a single instruction into a decoded instruction that specifies multiple operands including an input value and a quantized weight value associated with a neural network and an arithmetic logic unit including a barrel shifter, an adder, and an accumulator register, wherein to execute the decoded instruction, the barrel shifter is to shift the input value by the quantized weight value to generate a shifted input value and the adder is to add the shifted input value to a value stored in the accumulator register and update the value stored in the accumulator register.Type: GrantFiled: April 24, 2017Date of Patent: September 10, 2019Assignee: Intel CorporationInventors: 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
-
Patent number: 10394990Abstract: Devices and methods for initializing one or more registers of a programmable integrated circuit (IC) to store an initial condition value are provided. A first bitstream that programs the region of the IC to supply the initial condition value to the one or more registers is first programmed on the IC. Then, once the registers are initialized with the initial condition value, a second bitstream is subsequently programmed to the region of the IC to supply values associated with a function of the design to the one or more registers.Type: GrantFiled: September 27, 2016Date of Patent: August 27, 2019Assignee: Altera CorporationInventors: Kalen Brunham, Kevin Nealis, Yi Peng, Scott Weber
-
Publication number: 20190206020Abstract: 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 is to cause at least a portion of the GPU to perform a floating point operation on input having differing precisions. The floating point operation is a two-dimensional matrix multiply and accumulate operation.Type: ApplicationFiled: November 21, 2018Publication date: July 4, 2019Applicant: Intel CorporationInventors: 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
-
Publication number: 20190188554Abstract: 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.Type: ApplicationFiled: February 22, 2019Publication date: June 20, 2019Applicant: Intel CorporationInventors: 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