Patents by Inventor Linyang WU
Linyang WU 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: 11803404Abstract: The present disclosure relates to a deep learning algorithm compiling method and a device and a related product, the product comprising a controller unit, and the controller unit comprising: an instruction cache unit, an instruction processing unit, and a queue-storing unit. The instruction cache unit is configured to store computation instructions associated with artificial neural network operations. The instruction processing unit is configured to parse the computation instructions to obtain a plurality of operation instructions. The queue-storing unit is configured to store an instruction queue, which comprises: a plurality of operation instructions or computation instructions to be executed according to the front-to-rear sequence of the queue. By means of the described method, the present disclosure may improve the operation efficiency of the related product when carrying out neural network model operations.Type: GrantFiled: August 25, 2020Date of Patent: October 31, 2023Assignee: ANHUI CAMBRICON INFORMATION TECHNOLOGY CO., LTD.Inventors: Liming Chen, Linyang Wu, Ziyi Wang
-
Patent number: 11726754Abstract: Disclosed are a general machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201); performing classification processing on the task parameters to obtain task instructions and model parameters (S1202); aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203); and integrating the stack data and the heap data to obtain a general machine learning model (S1204). By means of the method, compiled results of a corresponding general model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: GrantFiled: June 26, 2022Date of Patent: August 15, 2023Assignee: SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTD.Inventors: Weijian Du, Linyang Wu, Xunyu Chen
-
Publication number: 20230196069Abstract: A neural network processing method, comprising the following steps: obtaining a model dataset and model structure parameters of an original network (S100); obtaining an operational attribute of each compute node in the original network; operating the original network according to the model dataset and the model structure parameters of the original network and the operational attribute of each compute node, to obtain an instruction corresponding to each compute node in the original network (S200); and if the operational attribute of the current compute node is a first operational attribute, storing a network weight and the instruction corresponding to the current compute node into a first non-volatile memory, so as to obtain a first offline model corresponding to the original network (S300). Further provided are a computer system and a storage medium.Type: ApplicationFiled: December 17, 2018Publication date: June 22, 2023Inventors: Xunyu Chen, Qi Guo, Jie Wei, Linyang Wu
-
Publication number: 20220326919Abstract: Disclosed are a general machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201); performing classification processing on the task parameters to obtain task instructions and model parameters (S1202); aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203); and integrating the stack data and the heap data to obtain a general machine learning model (S1204). By means of the method, compiled results of a corresponding general model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: ApplicationFiled: June 26, 2022Publication date: October 13, 2022Inventors: Weijian DU, Linyang WU, Xunyu CHEN
-
Patent number: 11403080Abstract: Disclosed are a general machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201); performing classification processing on the task parameters to obtain task instructions and model parameters (S1202); aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203); and integrating the stack data and the heap data to obtain a general machine learning model (S1204). By means of the method, compiled results of a corresponding general model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: GrantFiled: December 22, 2020Date of Patent: August 2, 2022Assignee: SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTD.Inventors: Weijian Du, Linyang Wu, Xunyu Chen
-
Patent number: 11379199Abstract: Disclosed are a general-purpose machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201), performing classification processing on the task parameters to obtain task instructions and model parameters (S1202), aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203), and integrating the stack data and the heap data to obtain a general-purpose machine learning model (S1204). By means of the method, compiled results of a corresponding general-purpose model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: GrantFiled: December 22, 2020Date of Patent: July 5, 2022Assignee: SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTD.Inventors: Weijian Du, Linyang Wu, Xunyu Chen
-
Patent number: 11360811Abstract: Computer systems, data processing methods, and computer-readable media are provided to run original networks. An exemplary computer system includes first and second processors a memory storing offline models and corresponding input data of a plurality of original networks, and a runtime system configured to run on the first processor. The runtime system, when runs on the first processor, causes the first processor to implement a plurality of virtual devices comprising a data processing device configured to obtain an offline model and corresponding input data of an original network from the memory, an equipment management device configured to control turning on or off of the second processor, and a task execution device configured to control the second processor to run the offline model of the original network.Type: GrantFiled: December 3, 2019Date of Patent: June 14, 2022Assignee: SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTDInventors: Linyang Wu, Qi Guo, Xunyu Chen, Kangyu Wang
-
Patent number: 11334330Abstract: Disclosed are a general machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201); performing classification processing on the task parameters to obtain task instructions and model parameters (S1202); aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203); and integrating the stack data and the heap data to obtain a general machine learning model (S1204). By means of the method, compiled results of a corresponding general model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: GrantFiled: December 22, 2020Date of Patent: May 17, 2022Assignee: SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTD.Inventors: Weijian Du, Linyang Wu, Xunyu Chen
-
Patent number: 11334329Abstract: Disclosed are a general machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201); performing classification processing on the task parameters to obtain task instructions and model parameters (S1202); aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203); and integrating the stack data and the heap data to obtain a general machine learning model (S1204). By means of the method, compiled results of a corresponding general model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: GrantFiled: May 7, 2019Date of Patent: May 17, 2022Assignee: SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTD.Inventors: Weijian Du, Linyang Wu, Xunyu Chen
-
Publication number: 20220129289Abstract: The present disclosure relates to a deep learning algorithm compiling method and a device and a related product, the product comprising a controller unit, and the controller unit comprising: an instruction cache unit, an instruction processing unit, and a queue-storing unit. The instruction cache unit is configured to store computation instructions associated with artificial neural network operations. The instruction processing unit is configured to parse the computation instructions to obtain a plurality of operation instructions. The queue-storing unit is configured to store an instruction queue, which comprises: a plurality of operation instructions or computation instructions to be executed according to the front-to-rear sequence of the queue. By means of the described method, the present disclosure may improve the operation efficiency of the related product when carrying out neural network model operations.Type: ApplicationFiled: August 25, 2020Publication date: April 28, 2022Inventors: Liming CHEN, Linyang WU, Ziyi WANG
-
Patent number: 11307836Abstract: Disclosed are a general machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201); performing classification processing on the task parameters to obtain task instructions and model parameters (S1202); aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203); and integrating the stack data and the heap data to obtain a general machine learning model (S1204). By means of the method, compiled results of a corresponding general model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: GrantFiled: December 22, 2020Date of Patent: April 19, 2022Assignee: SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTD.Inventors: Weijian Du, Linyang Wu, Xunyu Chen
-
Publication number: 20220114429Abstract: The present disclosure relates to a method and a device for generation operation data and a related product, the product comprising a controller unit, and the controller unit comprising: an instruction caching unit, an instruction processing unit and a queue-storing unit. The instruction caching unit is used to store computing instructions associated with artificial neural network operations. The instruction processing unit is used to resolve the computing instructions to obtain a plurality of operation instructions. The queue-storing unit is used to store an instruction queue, which comprises: a plurality of operation instructions or computing instructions to be executed according to the front-to-rear sequence of the queue. Through the above method, the present disclosure may improve the operation efficiency of the related product when carrying out neural network model operations.Type: ApplicationFiled: August 25, 2020Publication date: April 14, 2022Inventors: Liming CHEN, Linyang WU, Ziyi WANG
-
Publication number: 20220092386Abstract: The present disclosure provides a neural network model splitting method and related products. The scheme provided by the present disclosure splits an operator into a plurality of smaller-scale sub-operators, so that a compute library under a single-core architecture can be called directly, which helps to avoid the extra work caused by re-implementation.Type: ApplicationFiled: April 13, 2020Publication date: March 24, 2022Applicant: Shanghai Cambricon Information Technology Co., LtdInventors: Yusong ZHOU, Xiao ZHANG, Linyang WU, Yehao YU, Yunlong XU
-
Patent number: 11221877Abstract: The present disclosure provides a task parallel processing method, a device, a system, a storage medium and computer equipment, which are capable of distributing and regulating tasks to be executed according to a task directed acyclic graph, and may thereby realize task parallelism of a multi-core processor and improve the efficiency of data processing.Type: GrantFiled: September 18, 2019Date of Patent: January 11, 2022Assignee: Shanghai Cambricon Information Technology Co., LtdInventors: Linyang Wu, Xiaofu Meng
-
Patent number: 11113104Abstract: Computer systems, data processing methods, and computer-readable media are provided to run original networks. An exemplary computer system includes first and second processors and first and second memories. The first memory stores offline models and corresponding input data of a plurality of original networks, and a runtime system configured to run on the first processor. The second memory stores an operating system configured to run on the first processor or the second processor. When the runtime system runs on the first processor, the runtime system obtains an offline model and corresponding input data of an original network from the first memory and controls the second processor to run the offline model of the original network. The offline model of the original network includes model parameters, instructions, and interface data of respective computation nodes of the original network.Type: GrantFiled: December 5, 2019Date of Patent: September 7, 2021Assignee: Shanghai Cambricon Information Technology Co., LtdInventors: Linyang Wu, Qi Guo, Xunyu Chen, Kangyu Wang
-
Patent number: 11036480Abstract: Disclosed are a general machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201); performing classification processing on the task parameters to obtain task instructions and model parameters (S1202); aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203); and integrating the stack data and the heap data to obtain a general machine learning model (S1204). By means of the method, compiled results of a corresponding general model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: GrantFiled: December 22, 2020Date of Patent: June 15, 2021Assignee: Shanghai Cambricon Information Technology Co., Ltd.Inventors: Weijian Du, Linyang Wu, Xunyu Chen
-
Publication number: 20210109725Abstract: Disclosed are a general-purpose machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201), performing classification processing on the task parameters to obtain task instructions and model parameters (S1202), aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203), and integrating the stack data and the heap data to obtain a general-purpose machine learning model (S1204). By means of the method, compiled results of a corresponding general-purpose model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: ApplicationFiled: December 22, 2020Publication date: April 15, 2021Inventors: Weijian DU, Linyang WU, Xunyu CHEN
-
Publication number: 20210109726Abstract: Disclosed are a general machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201); performing classification processing on the task parameters to obtain task instructions and model parameters (S1202); aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203); and integrating the stack data and the heap data to obtain a general machine learning model (S1204). By means of the method, compiled results of a corresponding general model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: ApplicationFiled: December 22, 2020Publication date: April 15, 2021Inventors: Weijian DU, Linyang WU, Xunyu CHEN
-
Publication number: 20210109729Abstract: Disclosed are a general machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201); performing classification processing on the task parameters to obtain task instructions and model parameters (S1202); aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203); and integrating the stack data and the heap data to obtain a general machine learning model (S1204). By means of the method, compiled results of a corresponding general model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: ApplicationFiled: December 22, 2020Publication date: April 15, 2021Inventors: Weijian DU, Linyang WU, Xunyu CHEN
-
Publication number: 20210109728Abstract: Disclosed are a general machine learning model generation method and apparatus, and a computer device and a storage medium. The method comprises: acquiring task parameters of a machine learning task (S1201); performing classification processing on the task parameters to obtain task instructions and model parameters (S1202); aggregating the task instructions and the model parameters according to a data type to obtain stack data and heap data (S1203); and integrating the stack data and the heap data to obtain a general machine learning model (S1204). By means of the method, compiled results of a corresponding general model in the running of an algorithm can be directly executed, which avoids repetitive compilation, thus greatly improving the efficiency of machine learning algorithm implementation and shortening the time from compilation to obtaining execution results.Type: ApplicationFiled: December 22, 2020Publication date: April 15, 2021Inventors: Weijian DU, Linyang WU, Xunyu CHEN