-
公开(公告)号:US20210174177A1
公开(公告)日:2021-06-10
申请号:US16893560
申请日:2020-06-05
Applicant: Samsung Electronics Co., Ltd. , UNIST(ULSAN NATIONAL INSTITUTE OF SCIENCE AND TECHNOLOGY)
Inventor: Hyeongseok YU , Hyeonuk SIM , Jongeun LEE
Abstract: A neural network device includes: an on-chip buffer memory that stores an input feature map of a first layer of a neural network, a computational circuit that receives the input feature map of the first layer through a single port of the on-chip buffer memory and performs a neural network operation on the input feature map of the first layer to output an output feature map of the first layer corresponding to the input feature map of the first layer, and a controller that transmits the output feature map of the first layer to the on-chip buffer memory through the single port to store the output feature map of the first layer and the input feature map of the first layer together in the on-chip buffer memory.
-
公开(公告)号:US20220253692A1
公开(公告)日:2022-08-11
申请号:US17400353
申请日:2021-08-12
Applicant: Samsung Electronics Co., Ltd.
Inventor: Hyeongseok YU , Yoojin KIM , Seongwook PARK , Hyun Sun PARK , Sehwan LEE , Jun-Woo JANG , Deokjin JOO
Abstract: Disclosed is a method and apparatus of operating a neural network. The neural network operation method includes receiving data for the neural network operation, verifying whether competition occurs between a first data traversal path corresponding to a first operation device and a second data traversal path corresponding to a second operation device, determining first operand data and second operand data from among the data using a result of the verifying and a priority between the first data traversal path and the second data traversal path, and performing the neural network operation based on the first operand data and the second operand data.
-
公开(公告)号:US20200380360A1
公开(公告)日:2020-12-03
申请号:US16890045
申请日:2020-06-02
Applicant: Samsung Electronics Co., Ltd. , UNIST(ULSAN NATIONAL INSTITUTE OF SCIENCE AND TECHNOLOGY)
Inventor: Hyeongseok YU , Hyeonuk SIM , Jongeun LEE
Abstract: A processor-implemented method includes determining a first quantization value by performing log quantization on a parameter from one of input activation values and weight values in a layer of a neural network, comparing a threshold value with an error between a first dequantization value obtained by dequantization of the first quantization value and the parameter, determining a second quantization value by performing log quantization on the error in response to the error being greater than the threshold value as a result of the comparing; and quantizing the parameter to a value in which the first quantization value and the second quantization value are grouped.
-
公开(公告)号:US20240046082A1
公开(公告)日:2024-02-08
申请号:US18489209
申请日:2023-10-18
Applicant: Samsung Electronics Co., Ltd. , UNIST(ULSAN NATIONAL INSTITUTE OF SCIENCE AND TECHNOLOGY)
Inventor: Hyeongseok YU , Hyeonuk SIM , Jongeun LEE
Abstract: A neural network device including an on-chip buffer memory that stores an input feature map of a first layer of a neural network, a computational circuit that receives the input feature map of the first layer through a single port of the on-chip buffer memory and performs a neural network operation on the input feature map of the first layer to output an output feature map of the first layer corresponding to the input feature map of the first layer, and a controller that transmits the output feature map of the first layer to the on-chip buffer memory through the single port to store the output feature map of the first layer and the input feature map of the first layer together in the on-chip buffer memory.
-
公开(公告)号:US20210064992A1
公开(公告)日:2021-03-04
申请号:US16803342
申请日:2020-02-27
Applicant: Samsung Electronics Co., Ltd.
Inventor: Hyunsun PARK , Yoojin KIM , Hyeongseok YU , Sehwan LEE , Junwoo JANG
Abstract: A method of processing data includes identifying a sparsity of input data, based on valid information included in the input data, rearranging the input data, based on a form of the sparsity, and generating output data by processing the rearranged input data.
-
公开(公告)号:US20240235575A1
公开(公告)日:2024-07-11
申请号:US18406521
申请日:2024-01-08
Applicant: Samsung Electronics Co., Ltd.
Inventor: Hyeongseok YU , Deok Jae OH , Seong Wook PARK
CPC classification number: H03M7/405 , H03M7/3064
Abstract: A processor-implemented method including generating k sub-compressed data streams based on a compressed data stream for a plurality of symbols divided into a plurality of k blocks and count information for each of the plurality of k blocks, generating k sub-symbols by processing each of the k sub-compressed data streams using k decoding engines, metadata about the compressed data stream, and generating an output data stream corresponding to the plurality of symbols based on the k sub-symbols.
-
公开(公告)号:US20230065528A1
公开(公告)日:2023-03-02
申请号:US17883987
申请日:2022-08-09
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Hyeongseok YU , Donghyuk KWON , Channoh KIM , Seongwook PARK , Yeongon CHO
Abstract: An apparatus with multi-format data support includes: a receiver configured to receive a plurality of data corresponding to a plurality of data formats; one or more processors configured to: multiply the plurality of data using one or more multipliers; perform a first alignment on a result of the multiplication based on an exponent value of the plurality of data; add a result of the first alignment; and perform a second alignment on a result of the addition based on the exponent value and an operation result of a previous cycle.
-
公开(公告)号:US20170083287A1
公开(公告)日:2017-03-23
申请号:US15076084
申请日:2016-03-21
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Hyeongseok YU
Abstract: A method of performing an arithmetic operation by a processing apparatus includes determining a polynomial expression approximating an arithmetic operation to be performed on a variable; adaptively determining upper bits for addressing a look-up table (LUT) according to a variable section to which the variable belongs; obtaining coefficients of the polynomial expression from the LUT by addressing the LUT using a value of the upper bits; and performing the arithmetic operation by calculating a result value of the polynomial expression using the coefficients.
-
公开(公告)号:US20240095532A1
公开(公告)日:2024-03-21
申请号:US18522982
申请日:2023-11-29
Applicant: Samsung Electronics Co., Ltd.
Inventor: Hyunsun PARK , Yoojin KIM , Hyeongseok YU , Sehwan LEE , Junwoo JANG
Abstract: A method of processing data includes identifying a sparsity among information, included in input data, based on valid information or invalid information included in the input data, rearranging the input data based on the sparsity among the information indicating a distribution of the invalid values included in the input data, and generating, by performing an operation on the rearranged input data in the neural network, an output data.
-
公开(公告)号:US20230085442A1
公开(公告)日:2023-03-16
申请号:US17987079
申请日:2022-11-15
Applicant: SAMSUNG ELECTRONICS CO., LTD. , UNIST(ULSAN NATIONAL INSTITUTE OF SCIENCE AND TECHNOLOGY)
Inventor: Hyeongseok YU , Hyeonuk SIM , Jongeun LEE
Abstract: A processor-implemented method includes determining a first quantization value by performing log quantization on a parameter from one of input activation values and weight values in a layer of a neural network, comparing a threshold value with an error between a first dequantization value obtained by dequantization of the first quantization value and the parameter, determining a second quantization value by performing log quantization on the error in response to the error being greater than the threshold value as a result of the comparing; and quantizing the parameter to a value in which the first quantization value and the second quantization value are grouped.
-
-
-
-
-
-
-
-
-