Patents by Inventor Bret L. Toll
Bret L. Toll 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: 12282773Abstract: Embodiments detailed herein relate to matrix (tile) operations. For example, decode circuitry to decode an instruction having fields for an opcode and a memory address; and execution circuitry to execute the decoded instruction to set a tile configuration for the processor to utilize tiles in matrix operations based on a description retrieved from the memory address, wherein a tile a set of 2-dimensional registers are discussed.Type: GrantFiled: December 8, 2023Date of Patent: April 22, 2025Assignee: Intel CorporationInventors: Menachem Adelman, Robert Valentine, Zeev Sperber, Mark J. Charney, Bret L. Toll, Rinat Rappoport, Jesus Corbal, Dan Baum, Alexander F. Heinecke, Elmoustapha Ould-Ahmed-Vall, Yuri Gebil, Raanan Sade
-
Publication number: 20250117222Abstract: Embodiments detailed herein relate to matrix operations. In particular, matrix (tile) multiply accumulate and negated matrix (tile) multiply accumulate are discussed. For example, in some embodiments decode circuitry to decode an instruction having fields for an opcode, an identifier for a first source matrix operand, an identifier of a second source matrix operand, and an identifier for a source/destination matrix operand; and execution circuitry to execute the decoded instruction to multiply the identified first source matrix operand by the identified second source matrix operand, add a result of the multiplication to the identified source/destination matrix operand, and store a result of the addition in the identified source/destination matrix operand and zero unconfigured columns of identified source/destination matrix operand are detailed.Type: ApplicationFiled: October 29, 2024Publication date: April 10, 2025Inventors: Robert VALENTINE, Zeev SPERBER, Mark J. CHARNEY, Bret L. TOLL, Rinat RAPPOPORT, Stanislav SHWARTSMAN, Dan BAUM, Igor YANOVER, Elmoustapha OULD-AHMED-VALL, Menachem ADELMAN, Jesus CORBAL, Yuri GEBIL, Simon RUBANOVICH
-
Publication number: 20250117221Abstract: Embodiments detailed herein relate to matrix operations. In particular, support for a matrix transpose instruction is detailed. In some embodiments, decode circuitry to decode an instruction having fields for an opcode, a source matrix operand identifier, and a destination matrix operand identifier; and execution circuitry to execute the decoded instruction to transpose each row of elements of the identified source matrix operand into a corresponding column of the identified destination matrix operand are detailed.Type: ApplicationFiled: October 18, 2024Publication date: April 10, 2025Inventors: Robert VALENTINE, Dan BAUM, Zeev SPERBER, Jesus CORBAL, Elmoustapha OULD-AHMED-VALL, Bret L. TOLL, Mark J. CHARNEY, Barukh ZIV, Alexander HEINECKE, Milind GIRKAR, Menachem ADELMAN, Simon RUBANOVICH
-
Patent number: 12260213Abstract: Embodiments detailed herein relate to matrix operations. In particular, support for matrix (tile) addition, subtraction, and multiplication is described. For example, circuitry to support instructions for element-by-element matrix (tile) addition, subtraction, and multiplication are detailed. In some embodiments, for matrix (tile) addition, decode circuitry is to decode an instruction having fields for an opcode, a first source matrix operand identifier, a second source matrix operand identifier, and a destination matrix operand identifier; and execution circuitry is to execute the decoded instruction to, for each data element position of the identified first source matrix operand: add a first data value at that data element position to a second data value at a corresponding data element position of the identified second source matrix operand, and store a result of the addition into a corresponding data element position of the identified destination matrix operand.Type: GrantFiled: December 10, 2021Date of Patent: March 25, 2025Assignee: Intel CorporationInventors: Robert Valentine, Dan Baum, Zeev Sperber, Jesus Corbal, Elmoustapha Ould-Ahmed-Vall, Bret L. Toll, Mark J. Charney, Barukh Ziv, Alexander Heinecke, Milind Girkar, Simon Rubanovich
-
Patent number: 12197617Abstract: An apparatus is described that includes an execution unit to execute a first instruction and a second instruction. The execution unit includes input register space to store a first data structure to be replicated when executing the first instruction and to store a second data structure to be replicated when executing the second instruction. The first and second data structures are both packed data structures. Data values of the first packed data structure are twice as large as data values of the second packed data structure. The execution unit also includes replication logic circuitry to replicate the first data structure when executing the first instruction to create a first replication data structure, and, to replicate the second data structure when executing the second data instruction to create a second replication data structure.Type: GrantFiled: July 21, 2023Date of Patent: January 14, 2025Assignee: Intel CorporationInventors: Elmoustapha Ould-Ahmed-Vall, Robert Valentine, Jesus Corbal, Bret L Toll, Mark J. Charney
-
Publication number: 20250004716Abstract: Embodiments detailed herein relate to matrix operations. In particular, the loading of a matrix (tile) from memory. For example, support for a loading instruction is described in the form of decode circuitry to decode an instruction having fields for an opcode, a destination matrix operand identifier, and source memory information, and execution circuitry to execute the decoded instruction to load groups of strided data elements from memory into configured rows of the identified destination matrix operand to memory.Type: ApplicationFiled: May 3, 2024Publication date: January 2, 2025Inventors: Robert VALENTINE, Menachem ADELMAN, Milind B. GIRKAR, Zeev SPERBER, Mark J. CHARNEY, Bret L. TOLL, Rinat RAPPOPORT, Jesus Corbal, Stanislav SHWARTSMAN, Dan BAUM, Igor YANOVER, Alexander F. HEINECKE, Barukh ZIV, Elmoustapha OULD-AHMED-VALL, Yuri GEBIL, Raanan SADE
-
Patent number: 12182571Abstract: Embodiments detailed herein relate to matrix operations. In particular, the loading of a matrix (tile) from memory. For example, support for a loading instruction is described in the form of decode circuitry to decode an instruction having fields for an opcode, a destination matrix operand identifier, and source memory information, and execution circuitry to execute the decoded instruction to load groups of strided data elements from memory into configured rows of the identified destination matrix operand to memory.Type: GrantFiled: January 23, 2023Date of Patent: December 31, 2024Assignee: Intel CorporationInventors: Robert Valentine, Menachem Adelman, Milind B. Girkar, Zeev Sperber, Mark J. Charney, Bret L. Toll, Rinat Rappoport, Jesus Corbal, Stanislav Shwartsman, Dan Baum, Igor Yanover, Alexander F. Heinecke, Barukh Ziv, Elmoustapha Ould-Ahmed-Vall, Yuri Gebil, Raanan Sade
-
Publication number: 20240427600Abstract: A vector friendly instruction format and execution thereof. According to one embodiment of the invention, a processor is configured to execute an instruction set. The instruction set includes a vector friendly instruction format. The vector friendly instruction format has a plurality of fields including a base operation field, a modifier field, an augmentation operation field, and a data element width field, wherein the first instruction format supports different versions of base operations and different augmentation operations through placement of different values in the base operation field, the modifier field, the alpha field, the beta field, and the data element width field, and wherein only one of the different values may be placed in each of the base operation field, the modifier field, the alpha field, the beta field, and the data element width field on each occurrence of an instruction in the first instruction format in instruction streams.Type: ApplicationFiled: September 6, 2024Publication date: December 26, 2024Applicant: Intel CorporationInventors: Robert C. VALENTINE, Jesus Corbal SAN ADRIAN, Roger Espasa SANS, Robert D. CAVIN, Bret L. TOLL, Santiago Galan DURAN, Jeffrey G. WIEDEMEIER, Sridhar SAMUDRALA, Milind Baburao GIRKAR, Edward Thomas GROCHOWSKI, Jonathan Cannon HALL, Dennis R. BRADFORD, Elmoustapha OULD-AHMED-VALL, James C ABEL, Mark CHARNEY, Seth ABRAHAM, Suleyman SAIR, Andrew Thomas FORSYTH, Lisa WU, Charles YOUNT
-
Patent number: 12147804Abstract: Embodiments detailed herein relate to matrix operations. In particular, matrix (tile) multiply accumulate and negated matrix (tile) multiply accumulate are discussed. For example, in some embodiments decode circuitry to decode an instruction having fields for an opcode, an identifier for a first source matrix operand, an identifier of a second source matrix operand, and an identifier for a source/destination matrix operand; and execution circuitry to execute the decoded instruction to multiply the identified first source matrix operand by the identified second source matrix operand, add a result of the multiplication to the identified source/destination matrix operand, and store a result of the addition in the identified source/destination matrix operand and zero unconfigured columns of identified source/destination matrix operand are detailed.Type: GrantFiled: July 22, 2021Date of Patent: November 19, 2024Assignee: Intel CorporationInventors: Robert Valentine, Zeev Sperber, Mark J. Charney, Bret L. Toll, Rinat Rappoport, Stanislav Shwartsman, Dan Baum, Igor Yanover, Elmoustapha Ould-Ahmed-Vall, Menachem Adelman, Jesus Corbal, Yuri Gebil, Simon Rubanovich
-
Patent number: 12130740Abstract: Embodiments of an invention a processor architecture are disclosed. In an embodiment, a processor includes a decoder, an execution unit, a coherent cache, and an interconnect. The decoder is to decode an instruction to zero a cache line. The execution unit is to issue a write command to initiate a cache line sized write of zeros. The coherent cache is to receive the write command, to determine whether there is a hit in the coherent cache and whether a cache coherency protocol state of the hit cache line is a modified state or an exclusive state, to configure a cache line to indicate all zeros, and to issue the write command toward the interconnect. The interconnect is to, responsive to receipt of the write command, issue a snoop to each of a plurality of other coherent caches for which it must be determined if there is a hit.Type: GrantFiled: April 4, 2022Date of Patent: October 29, 2024Assignee: Intel CorporationInventors: Jason W. Brandt, Robert S. Chappell, Jesus Corbal, Edward T. Grochowski, Stephen H. Gunther, Buford M. Guy, Thomas R. Huff, Christopher J. Hughes, Elmoustapha Ould-Ahmed-Vall, Ronak Singhal, Seyed Yahya Sotoudeh, Bret L. Toll, Lihu Rappoport, David B. Papworth, James D. Allen
-
Patent number: 12124847Abstract: Embodiments detailed herein relate to matrix operations. In particular, support for a matrix transpose instruction is detailed. In some embodiments, decode circuitry to decode an instruction having fields for an opcode, a source matrix operand identifier, and a destination matrix operand identifier; and execution circuitry to execute the decoded instruction to transpose each row of elements of the identified source matrix operand into a corresponding column of the identified destination matrix operand are detailed.Type: GrantFiled: July 1, 2017Date of Patent: October 22, 2024Assignee: Intel CorporationInventors: Robert Valentine, Dan Baum, Zeev Sperber, Jesus Corbal, Elmoustapha Ould-Ahmed-Vall, Bret L Toll, Mark J. Charney, Barukh Ziv, Alexander Heinecke, Milind Girkar, Menachem Adelman, Simon Rubanovich
-
Patent number: 12106100Abstract: Embodiments detailed herein relate to matrix (tile) operations. For example, decode circuitry to decode an instruction having fields for an opcode and a memory address; and execution circuitry to execute the decoded instruction to set a tile configuration for the processor to utilize tiles in matrix operations based on a description retrieved from the memory address, wherein a tile a set of 2-dimensional registers are discussed.Type: GrantFiled: July 1, 2017Date of Patent: October 1, 2024Assignee: Intel CorporationInventors: Robert Valentine, Mark J. Charney, Elmoustapha Ould-Ahmed-Vall, Dan Baum, Zeev Sperber, Jesus Corbal, Bret L. Toll, Raanan Sade, Igor Yanover, Yuri Gebil, Rinat Rappoport, Stanislav Shwartsman, Menachem Adelman, Simon Rubanovich
-
Publication number: 20240320001Abstract: Detailed herein are embodiment systems, processors, and methods for matrix move. For example, a processor comprising decode circuitry to decode an instruction having fields for an opcode, a source matrix operand identifier, and a destination matrix operand identifier; and execution circuitry to execute the decoded instruction to move each data element of the identified source matrix operand to corresponding data element position of the identified destination matrix operand is described.Type: ApplicationFiled: May 14, 2024Publication date: September 26, 2024Inventors: Robert VALENTINE, Zeev SPERBER, Mark J. CHARNEY, Bret L. TOLL, Jesus CORBAL, Dan BAUM, Alexander HEINECKE, Elmoustapha OULD-AHMED-VALL
-
Patent number: 12086594Abstract: A vector friendly instruction format and execution thereof. According to one embodiment of the invention, a processor is configured to execute an instruction set. The instruction set includes a vector friendly instruction format. The vector friendly instruction format has a plurality of fields including a base operation field, a modifier field, an augmentation operation field, and a data element width field, wherein the first instruction format supports different versions of base operations and different augmentation operations through placement of different values in the base operation field, the modifier field, the alpha field, the beta field, and the data element width field, and wherein only one of the different values may be placed in each of the base operation field, the modifier field, the alpha field, the beta field, and the data element width field on each occurrence of an instruction in the first instruction format in instruction streams.Type: GrantFiled: August 28, 2023Date of Patent: September 10, 2024Assignee: Intel CorporationInventors: Robert C. Valentine, Jesus Corbal San Adrian, Roger Espasa Sans, Robert D. Cavin, Bret L. Toll, Santiago Galan Duran, Jeffrey G. Wiedemeier, Sridhar Samudrala, Milind Baburao Girkar, Edward Thomas Grochowski, Jonathan Cannon Hall, Dennis R. Bradford, Elmoustapha Ould-Ahmed-Vall, James C Abel, Mark Charney, Seth Abraham, Suleyman Sair, Andrew Thomas Forsyth, Lisa Wu, Charles Yount
-
Publication number: 20240256276Abstract: Embodiments detailed herein relate to matrix operations. In particular, the loading of a matrix (tile) from memory. For example, support for a loading instruction is described in at least a form of decode circuitry to decode an instruction having fields for an opcode, a source matrix operand identifier, and destination memory information, and execution circuitry to execute the decoded instruction to store each data element of configured rows of the identified source matrix operand to memory based on the destination memory information.Type: ApplicationFiled: February 5, 2024Publication date: August 1, 2024Inventors: Robert VALENTINE, Menachem ADELMAN, Elmoustapha OULD-AHMED-VALL, Bret L. TOLL, Milind B. GIRKAR, Zeev SPERBER, Mark J. CHARNEY, Rinat RAPPOPORT, Jesus CORBAL, Stanislav SHWARTSMAN, Igor YANOVER, Alexander F. HEINECKE, Barukh ZIV, Dan BAUM, Yuri GEBIL, Raanan SADE
-
Patent number: 12039332Abstract: Detailed herein are embodiment systems, processors, and methods for matrix move. For example, a processor comprising decode circuitry to decode an instruction having fields for an opcode, a source matrix operand identifier, and a destination matrix operand identifier; and execution circuitry to execute the decoded instruction to move each data element of the identified source matrix operand to corresponding data element position of the identified destination matrix operand is described.Type: GrantFiled: January 28, 2022Date of Patent: July 16, 2024Assignee: Intel CorporationInventors: Robert Valentine, Zeev Sperber, Mark J. Charney, Bret L. Toll, Jesus Corbal, Dan Baum, Alexander Heinecke, Elmoustapha Ould-Ahmed-Vall
-
Patent number: 12039336Abstract: A processor includes a first mode where the processor is not to use packed data operation masking, and a second mode where the processor is to use packed data operation masking. A decode unit to decode an unmasked packed data instruction for a given packed data operation in the first mode, and to decode a masked packed data instruction for a masked version of the given packed data operation in the second mode. The instructions have a same instruction length. The masked instruction has bit(s) to specify a mask. Execution unit(s) are coupled with the decode unit. The execution unit(s), in response to the decode unit decoding the unmasked instruction in the first mode, to perform the given packed data operation. The execution unit(s), in response to the decode unit decoding the masked instruction in the second mode, to perform the masked version of the given packed data operation.Type: GrantFiled: August 29, 2022Date of Patent: July 16, 2024Assignee: Intel CorporationInventors: Bret L. Toll, Buford M. Guy, Ronak Singhal, Mishali Naik
-
Publication number: 20240192954Abstract: Embodiments detailed herein relate to matrix (tile) operations. For example, decode circuitry to decode an instruction having fields for an opcode and a memory address; and execution circuitry to execute the decoded instruction to set a tile configuration for the processor to utilize tiles in matrix operations based on a description retrieved from the memory address, wherein a tile a set of 2-dimensional registers are discussed.Type: ApplicationFiled: February 16, 2024Publication date: June 13, 2024Applicant: Intel CorporationInventors: Robert VALENTINE, Mark J. CHARNEY, Elmoustapha OULD-AHMED-VALL, Dan BAUM, Zeev SPERBER, Jesus CORBAL, Bret L. TOLL, Raanan SADE, Igor YANOVER, Yuri GEBIL, Rinat RAPPOPORT, Stanislav SHWARTSMAN, Menachem ADELMAN, Simon RUBANOVICH
-
Patent number: 11977886Abstract: Embodiments detailed herein relate to matrix operations. In particular, the loading of a matrix (tile) from memory. For example, support for a loading instruction is described in at least a form of decode circuitry to decode an instruction having fields for an opcode, a source matrix operand identifier, and destination memory information, and execution circuitry to execute the decoded instruction to store each data element of configured rows of the identified source matrix operand to memory based on the destination memory information.Type: GrantFiled: March 28, 2022Date of Patent: May 7, 2024Assignee: Intel CorporationInventors: Robert Valentine, Menachem Adelman, Elmoustapha Ould-Ahmed-Vall, Bret L. Toll, Milind B. Girkar, Zeev Sperber, Mark J. Charney, Rinat Rappoport, Jesus Corbal, Stanislav Shwartsman, Igor Yanover, Alexander F. Heinecke, Barukh Ziv, Dan Baum, Yuri Gebil, Raanan Sade
-
Publication number: 20240134644Abstract: Embodiments detailed herein relate to matrix operations. In particular, support for matrix (tile) addition, subtraction, and multiplication is described. For example, circuitry to support instructions for element-by-element matrix (tile) addition, subtraction, and multiplication are detailed. In some embodiments, for matrix (tile) addition, decode circuitry is to decode an instruction having fields for an opcode, a first source matrix operand identifier, a second source matrix operand identifier, and a destination matrix operand identifier; and execution circuitry is to execute the decoded instruction to, for each data element position of the identified first source matrix operand: add a first data value at that data element position to a second data value at a corresponding data element position of the identified second source matrix operand, and store a result of the addition into a corresponding data element position of the identified destination matrix operand.Type: ApplicationFiled: December 29, 2023Publication date: April 25, 2024Applicant: Intel CorporationInventors: Robert VALENTINE, Dan BAUM, Zeev SPERBER, Jesus CORBAL, Elmoustapha OULD-AHMED-VALL, Bret L. TOLL, Mark J. CHARNEY, Barukh ZIV, Alexander HEINECKE, Milind GIRKAR, Simon RUBANOVICH