-
公开(公告)号：EP3869325A1
公开(公告)日：2021-08-25
申请号：EP21152465.7
申请日：2021-01-20
申请人： Facebook, Inc.
摘要： A floating-point number in a first format representation is received. Based on an identification of a floating-point format type of the floating-point number, different components of the first format representation are identified. The different components of the first format representation are placed in corresponding components of a second format representation of the floating-point number, wherein a total number of bits of the second format representation is larger than a total number of bits of the first format representation. At least one of the components of the second format representation is padded with one or more zero bits. The floating-point number in the second format representation is stored in a register. A multiplication using the second format representation of the floating-point number is performed.
-
公开(公告)号：EP3835949A1
公开(公告)日：2021-06-16
申请号：EP20207032.2
申请日：2020-11-11
申请人： Facebook, Inc.
发明人： ULRICH, Thomas , NAIR, Krishnakumar , HAO, Yuchen
摘要： A processor system (100) comprises a shared memory (101) and a processing element (161). The processing element (161) includes a matrix processor unit (107) and is in communication with the shared memory (101). The processing element (161) is configured to receive a processor instruction specifying a data matrix and a matrix manipulation operation. A manipulation matrix based on the processor instruction is identified. The data matrix and the manipulation matrix are loaded into the matrix processor unit (107) and a matrix operation is performed to determine a result matrix. The result matrix is outputted to a destination location.
-
3.发明公开
公开(公告)号：EP3816824A1
公开(公告)日：2021-05-05
申请号：EP20199591.7
申请日：2020-10-01
申请人： Facebook, Inc.
发明人： NAIR, Krishnakumar , WU, Olivia , ZADEH, Ehsan , DIRIL, Abdulkadir , ULRICH, Thomas , HAO, Yuchen , KOMURAVELLI, Rakesh , KALAIAH, Aravind
摘要： A system comprises a data input vector unit, a weight input vector unit, and a plurality of calculation units of a matrix processor unit. The data input vector unit is configured to concurrently receive elements of different rows of a first and second data matrix. The weight input vector unit is configured to receive a combined weight vector and at least in part concurrently provide obtained weight elements of a first and second weight matrix to a corresponding first and second group of calculation units. Each calculation unit of the first and second group of calculation units is configured to multiply elements from the data input vector unit with elements of the corresponding weight matrix from the weight input vector unit and sum together multiplication results of the corresponding calculation unit to at least in part determine a corresponding element in a first or second convolution result matrix.
-
4.发明公开
公开(公告)号：EP3816790A1
公开(公告)日：2021-05-05
申请号：EP20203634.9
申请日：2020-10-23
申请人： Facebook, Inc.
发明人： HAO, Yuchen , NAIR, Krishnakumar , ZADEH, Ehsan , KOMURAVELLI, Rakesh , DIRIL, Abdulkadir , ULRICH, Thomas
摘要： A first group of elements is element-wise multiplied with a second group of elements using a plurality of multipliers belonging to a matrix multiplication hardware unit. Results of the plurality of multipliers are added together using a hierarchical tree of adders belonging to the matrix multiplication hardware unit and a final result of the hierarchical tree of adders or any of a plurality of intermediate results of the hierarchical tree of adders is selectively provided for use in determining an output result matrix. A control unit is used to instruct the matrix multiplication hardware unit to perform a plurality of different matrix multiplications in parallel by using a combined matrix that includes elements of a plurality of different operand matrices and utilize one or more selected ones of the intermediate results of the hierarchical tree of adders for use in determining the output result matrix that includes different groups of elements representing different multiplication results corresponding to different ones of the different operand matrices.
-
-
-
搜索结果
4 条记录 (耗时 0.01 秒)
