A digital signal processor includes K first electronic circuits. The first inputs receive K groups of G successive coefficients of a polynomial. The polynomial are of degree N with N+1 coefficients, where K is a sub-multiple of N+1 greater than or equal to two and G is equal to (N+1)/K. The first electronic circuits are configured to simultaneously implement K respective Homer methods and deliver K output results. A second electronic circuit includes a first input configured to successively receive the output results of the first electronic circuits starting with the output result of the first electronic circuit having processed the highest rank coefficient of the coefficients. A second input is configured to receive a variable X and the second electronic circuit is configured to implement a Homer method and deliver a value of the polynomial for the variable X on the output of the second electronic circuit.

A digital signal processor includes K first electronic circuits. The first inputs receive K groups of G successive coefficients of a polynomial. The polynomial are of degree N with N+1 coefficients, where K is a sub-multiple of N+1 greater than or equal to two and G is equal to (N+1)/K. The first electronic circuits are configured to simultaneously implement K respective Homer methods and deliver K output results. A second electronic circuit includes a first input configured to successively receive the output results of the first electronic circuits starting with the output result of the first electronic circuit having processed the highest rank coefficient of the coefficients. A second input is configured to receive a variable X and the second electronic circuit is configured to implement a Homer method and deliver a value of the polynomial for the variable X on the output of the second electronic circuit.

A memory device for CIM has a memory array including a plurality of memory cells arranged in an array of rows and columns. The memory cells have a first group of memory cells and a second group of memory cells. Each row of the array has a corresponding word line, with each memory cell of a row of the array coupled to the corresponding word line. Each column of the array has a corresponding bit line, with each memory cell of a column of the array coupled to the corresponding bit line. A control circuit is configured to select the first group of memory cells or the second group of memory cells in response to a group enable signal.

A memory device for CIM has a memory array including a plurality of memory cells arranged in an array of rows and columns. The memory cells have a first group of memory cells and a second group of memory cells. Each row of the array has a corresponding word line, with each memory cell of a row of the array coupled to the corresponding word line. Each column of the array has a corresponding bit line, with each memory cell of a column of the array coupled to the corresponding bit line. A control circuit is configured to select the first group of memory cells or the second group of memory cells in response to a group enable signal.

Various aspects relate to a multiply and accumulate circuit, the multiply and accumulate circuit including: a plurality of multiply operation cells configured in a matrix arrangement. A respective multiply operation cell of the multiply operation cells includes: a field-effect transistor and a programmable switch in a series connection, wherein the field-effect transistor and the programmable switch are configured to control a current flow through the respective multiply operation cell to realize a multiplication operation. The multiply operation cells of a set of the plurality of multiply operation cells share a corresponding control line to realize an accumulation operation in addition to the multiply operations carried out by the set of multiply operation cells.

Various aspects relate to a multiply and accumulate circuit, the multiply and accumulate circuit including: a plurality of multiply operation cells configured in a matrix arrangement. A respective multiply operation cell of the multiply operation cells includes: a field-effect transistor and a programmable switch in a series connection, wherein the field-effect transistor and the programmable switch are configured to control a current flow through the respective multiply operation cell to realize a multiplication operation. The multiply operation cells of a set of the plurality of multiply operation cells share a corresponding control line to realize an accumulation operation in addition to the multiply operations carried out by the set of multiply operation cells.

The present disclosure discloses a processing element and a neural processing device including the processing element. The processing element includes a weight register configured to store a weight, an input activation register configured to store an input activation, a flexible multiplier configured to receive a first sub-weight of a first precision included in the weight, receive a first sub-input activation of the first precision included in the input activation, and generate result data by performing multiplication calculation of the first sub-weight and the first sub-input activation as the first precision or a second precision different from the first precision according to the first sub-weight and the first sub-input activation and a saturating adder configured to generate a partial sum by using the result data.

The present disclosure discloses a processing element and a neural processing device including the processing element. The processing element includes a weight register configured to store a weight, an input activation register configured to store an input activation, a flexible multiplier configured to receive a first sub-weight of a first precision included in the weight, receive a first sub-input activation of the first precision included in the input activation, and generate result data by performing multiplication calculation of the first sub-weight and the first sub-input activation as the first precision or a second precision different from the first precision according to the first sub-weight and the first sub-input activation and a saturating adder configured to generate a partial sum by using the result data.

The present disclosure describes methods, devices, and storage mediums for adjusting computing resource. The method includes obtaining an expected pooling time of a target pooling layer and a to-be-processed data volume of the target pooling layer; obtaining a current clock frequency corresponding to at least one computing resource unit used for pooling; determining a target clock frequency according to the expected pooling time of the target pooling layer and the to-be-processed data volume of the target pooling layer; and in response to that the convolution layer associated with the target pooling layer completes convolution and the current clock frequency is different from the target clock frequency, switching the current clock frequency of the at least one computing resource unit to the target clock frequency, and performing pooling in the target pooling layer based on the at least one computing resource unit having the target clock frequency.

The present disclosure describes methods, devices, and storage mediums for adjusting computing resource. The method includes obtaining an expected pooling time of a target pooling layer and a to-be-processed data volume of the target pooling layer; obtaining a current clock frequency corresponding to at least one computing resource unit used for pooling; determining a target clock frequency according to the expected pooling time of the target pooling layer and the to-be-processed data volume of the target pooling layer; and in response to that the convolution layer associated with the target pooling layer completes convolution and the current clock frequency is different from the target clock frequency, switching the current clock frequency of the at least one computing resource unit to the target clock frequency, and performing pooling in the target pooling layer based on the at least one computing resource unit having the target clock frequency.