摘要:
An in-memory computing (IMC) processor includes IMC macros, and includes a static random access memory (SRAM) IMC device including the plurality of IMC macros, and configured to perform a multiply and accumulate (MAC) operation between input data and first weight data of a first weight map applied to a first of IMC macros in a first direction in which an input feature map including the input data is written to the first IMC macro, and a two-dimensional (2D) shift accumulator configured to perform a shift operation on partial sums corresponding to respective MAC operation results of the IMC macros and accumulate a result of the shift operation.
摘要:
A binary number represented by time spaced electrical pulses and intervals is multiplied by a binary multiplier represented by electrical conditions at plural spaced-apart terminals. The multiplicand is multiplied sequentially by the successive digits of the multiplier to produce partial products. The partial products are applied to binary adders and cumulatively added to produce a final product. The multiplications are done by selectively inhibiting and partially enabling gates at the inputs to the adders in accordance with the digits of the multiplier. The multiplicand signals are applied through a shift register to the gates in sequence. The adders are arranged for serial addition and in cascade.
摘要:
Bit-serial processors quickly multiply multiple-bit operands using significantly fewer clock cycles as compared to conventional bit-serial implementations. Exemplary embodiments process groups of operand bits simultaneously to provide the significant speed increases. Advantageously, however, the exemplary embodiments utilize logic and memory architectures which are fully compatible with, and fully useful for, conventional bit-serial applications, and the embodiments thus provide fast multiple-bit multiplications while at the same time providing all of the advantages typically associated with conventional bit-serial processors.
摘要:
A serial digital multiplier includes m identical cascaded stages for generating the rounded product of an n-bit binary data word and an m-bit binary coefficient word. The multiplier further includes means for applying a logic 1 signal to the first stage to effect rounding of the final product at the output of the multiplier.
摘要:
A serial-parallel two''s complement binary multiplier circuit featuring a tightly clocked arrangement facilitating the formation of a product signal in an interval of duration shorter than the arrival interval for a serial multiplicand word. Hence, the multiplier circuit is capable of processing butted-word inputs in real time with only minor constraints on word formats. The multiplication algorithm features a pairwise summation of partial products on a least-significant-bit-first basis which gives rise to a tree-like structure of substantially identical circuit modules. Negative multiplicands are treated using a postmultiplication correction circuit.
摘要:
A data processing apparatus is provided. An A×B multiplier array has a group of logic gates clocked by a first clock signal, where A and B are both integers. A C×D multiplier array, separate from the A×B multiplier array, has second group of logic gates clocked by a second clock signal, where C and D are both integers. Addition circuitry performs an addition operation between a first at least partial product produced by the A×B multiplier array and a second at least partial product produced by the C×D multiplier array.
摘要:
In the case of a calculating unit for serial multiplication of a binary multiplicand with a binary multiplier, the multiplicand is inserted into a shift register in serial form. The development of the product is achieved by suitably providing change-over switches at positions of the shift register conforming to binary ones of the multiplier. The product is filled with the sign digit to the required number of digits by the change-over switches which then connect the output with a sign register.