Patents by Inventor Neta ZMORA
Neta ZMORA 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).
-
Publication number: 20250028650Abstract: In an example, an apparatus comprises a plurality of compute engines; and logic, at least partially including hardware logic, to detect a cache line conflict in a last-level cache (LLC) communicatively coupled to the plurality of compute engines; and implement context-based eviction policy to determine a cache way in the cache to evict in order to resolve the cache line conflict. Other embodiments are also disclosed and claimed.Type: ApplicationFiled: January 9, 2024Publication date: January 23, 2025Applicant: Intel CorporationInventors: Neta Zmora, Eran Ben-Avi
-
Publication number: 20240419956Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to traverse a solution space, score a plurality of solutions to a scheduling deep learning network execution, and select a preferred solution from the plurality of solutions to implement the deep learning network. Other embodiments are also disclosed and claimed.Type: ApplicationFiled: June 21, 2024Publication date: December 19, 2024Applicant: Intel CorporationInventors: Eran Ben-Avi, Neta Zmora, Guy Jacob, Lev Faivishevsky, Jeremie Dreyfuss, Tomer Bar-On, Jacob Subag, Yaniv Fais, Shira Hirsch, Orly Weisel, Zigi Walter, Yarden Oren
-
Patent number: 12033063Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to traverse a solution space, score a plurality of solutions to a scheduling deep learning network execution, and select a preferred solution from the plurality of solutions to implement the deep learning network. Other embodiments are also disclosed and claimed.Type: GrantFiled: February 24, 2023Date of Patent: July 9, 2024Assignee: Intel CorporationInventors: Eran Ben-Avi, Neta Zmora, Guy Jacob, Lev Faivishevsky, Jeremie Dreyfuss, Tomer Bar-On, Jacob Subag, Yaniv Fais, Shira Hirsch, Orly Weisel, Zigi Walter, Yarden Oren
-
Patent number: 11914525Abstract: In an example, an apparatus comprises a plurality of compute engines; and logic, at least partially including hardware logic, to detect a cache line conflict in a last-level cache (LLC) communicatively coupled to the plurality of compute engines; and implement context-based eviction policy to determine a cache way in the cache to evict in order to resolve the cache line conflict. Other embodiments are also disclosed and claimed.Type: GrantFiled: February 14, 2023Date of Patent: February 27, 2024Assignee: INTEL CORPORATIONInventors: Neta Zmora, Eran Ben-Avi
-
Publication number: 20230289299Abstract: In an example, an apparatus comprises a plurality of compute engines; and logic, at least partially including hardware logic, to detect a cache line conflict in a last-level cache (LLC) communicatively coupled to the plurality of compute engines; and implement context-based eviction policy to determine a cache way in the cache to evict in order to resolve the cache line conflict. Other embodiments are also disclosed and claimed.Type: ApplicationFiled: February 14, 2023Publication date: September 14, 2023Applicant: Intel CorporationInventors: Neta Zmora, Eran Ben-Avi
-
Publication number: 20230281435Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to traverse a solution space, score a plurality of solutions to a scheduling deep learning network execution, and select a preferred solution from the plurality of solutions to implement the deep learning network. Other embodiments are also disclosed and claimed.Type: ApplicationFiled: February 24, 2023Publication date: September 7, 2023Applicant: Intel CorporationInventors: Eran Ben-Avi, Neta Zmora, Guy Jacob, Lev Faivishevsky, Jeremie Dreyfuss, Tomer Bar-On, Jacob Subag, Yaniv Fais, Shira Hirsch, Orly Weisel, Zigi Walter, Yarden Oren
-
Patent number: 11669719Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to save one or more outputs of a deep learning neural network in a storage system of an autonomous vehicle and upload the one or more outputs to a remote server. Other embodiments are also disclosed and claimed.Type: GrantFiled: February 12, 2021Date of Patent: June 6, 2023Assignee: INTEL CORPORATIONInventors: Jeremie Dreyfuss, Amit Bleiweiss, Lev Faivishevsky, Tomer Bar-On, Yaniv Fais, Jacob Subag, Eran Ben-Avi, Neta Zmora, Tomer Schwartz
-
Patent number: 11599777Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to traverse a solution space, score a plurality of solutions to a scheduling deep learning network execution, and select a preferred solution from the plurality of solutions to implement the deep learning network. Other embodiments are also disclosed and claimed.Type: GrantFiled: April 28, 2017Date of Patent: March 7, 2023Assignee: Intel CorporationInventors: Eran Ben-Avi, Neta Zmora, Guy Jacob, Lev Faivishevsky, Jeremie Dreyfuss, Tomer Bar-On, Jacob Subag, Yaniv Fais, Shira Hirsch, Orly Weisel, Zigi Walter, Yarden Oren
-
Patent number: 11586558Abstract: In an example, an apparatus comprises a plurality of compute engines; and logic, at least partially including hardware logic, to detect a cache line conflict in a last-level cache (LLC) communicatively coupled to the plurality of compute engines; and implement context-based eviction policy to determine a cache way in the cache to evict in order to resolve the cache line conflict. Other embodiments are also disclosed and claimed.Type: GrantFiled: May 4, 2021Date of Patent: February 21, 2023Assignee: Intel CorporationInventors: Neta Zmora, Eran Ben-Avi
-
Publication number: 20210349835Abstract: In an example, an apparatus comprises a plurality of compute engines; and logic, at least partially including hardware logic, to detect a cache line conflict in a last-level cache (LLC) communicatively coupled to the plurality of compute engines; and implement context-based eviction policy to determine a cache way in the cache to evict in order to resolve the cache line conflict. Other embodiments are also disclosed and claimed.Type: ApplicationFiled: May 4, 2021Publication date: November 11, 2021Applicant: Intel CorporationInventors: Neta Zmora, Eran Ben-Avi
-
Publication number: 20210256272Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to save one or more outputs of a deep learning neural network in a storage system of an autonomous vehicle and upload the one or more outputs to a remote server. Other embodiments are also disclosed and claimed.Type: ApplicationFiled: February 12, 2021Publication date: August 19, 2021Applicant: Intel CorporationInventors: Jeremie Dreyfuss, Amit Bleiweiss, Lev Faivishevsky, Tomer Bar-On, Yaniv Fais, Jacob Subag, Eran Ben-Avi, Neta Zmora, Tomer Schwartz
-
Patent number: 11003592Abstract: In an example, an apparatus comprises a plurality of compute engines; and logic, at least partially including hardware logic, to detect a cache line conflict in a last-level cache (LLC) communicatively coupled to the plurality of compute engines; and implement context-based eviction policy to determine a cache way in the cache to evict in order to resolve the cache line conflict. Other embodiments are also disclosed and claimed.Type: GrantFiled: April 24, 2017Date of Patent: May 11, 2021Assignee: INTEL CORPORATIONInventors: Neta Zmora, Eran Ben-Avi
-
Patent number: 10922556Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to save one or more outputs of a deep learning neural network in a storage system of an autonomous vehicle and upload the one or more outputs to a remote server. Other embodiments are also disclosed and claimed.Type: GrantFiled: April 28, 2017Date of Patent: February 16, 2021Assignee: INTEL CORPORATIONInventors: Jeremie Dreyfuss, Amit Bleiweiss, Lev Faivishevsky, Tomer Bar-On, Yaniv Fais, Jacob Subag, Eran Ben-Avi, Neta Zmora, Tomer Schwartz
-
Publication number: 20180314899Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to save one or more outputs of a deep learning neural network in a storage system of an autonomous vehicle and upload the one or more outputs to a remote server. Other embodiments are also disclosed and claimed.Type: ApplicationFiled: April 28, 2017Publication date: November 1, 2018Applicant: Intel CorporationInventors: Jeremie Dreyfuss, Amit Bleiweiss, Lev Faivishevsky, Tomer Bar-On, Yaniv Fais, Jacob Subag, Eran Ben-Avi, Neta Zmora, Tomer Schwartz
-
Publication number: 20180314934Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to traverse a solution space, score a plurality of solutions to a scheduling deep learning network execution, and select a preferred solution from the plurality of solutions to implement the deep learning network. Other embodiments are also disclosed and claimed.Type: ApplicationFiled: April 28, 2017Publication date: November 1, 2018Applicant: Intel CorporationInventors: Eran Ben-Avi, Neta Zmora, Guy Jacob, Lev Faivishevsky, Jeremie Dreyfuss, Tomer Bar-On, Jacob Subag, Yaniv Fais, Shira Hirsh, Orly Weisel, Zigi Walter, Yarden Oren
-
Publication number: 20180307624Abstract: In an example, an apparatus comprises a plurality of compute engines; and logic, at least partially including hardware logic, to detect a cache line conflict in a last-level cache (LLC) communicatively coupled to the plurality of compute engines; and implement context-based eviction policy to determine a cache way in the cache to evict in order to resolve the cache line conflict. Other embodiments are also disclosed and claimed.Type: ApplicationFiled: April 24, 2017Publication date: October 25, 2018Applicant: Intel CorporationInventors: Neta Zmora, Eran Ben-Avi
-
Publication number: 20070253418Abstract: Methods and systems for optimized routing of real time media session data between session initiation protocol SIP endpoints. In one embodiment of the invention, first and second SIP endpoints each provide notification of network address translation NAT topology thereof and based on the NAT topologies of the two endpoints an SIP server decides whether to route media between the two endpoints via a direct path or via a media relay.Type: ApplicationFiled: April 26, 2007Publication date: November 1, 2007Applicant: D.S.P. Group Ltd.Inventors: Effi SHIRI, Neta ZMORA
