A method includes generating an extended result from a first operation circuitry having a result register bit width greater than a bus width associated with a residue check path of a second operation circuitry associated with a floating point unit. An extended result residue less a first portion residue of the extended result received from the residue check path is stored as a first partial result residue. The first partial result residue is compared with a first result residue of the second operation circuitry. The extended result residue less both the first partial result residue and a second portion residue of the extended result received from the residue check path as a second partial result residue is compared with a second result residue of the second operation circuitry.

Apparatuses and methods for determining soft data for fractional digit memory cells are provided. One example apparatus can include a controller to determine states of memory cells of a group of memory cells operated as fractional digit memory cells, and determine soft data based, at least partially, on dimensions to which particular memory cells correspond with respect to the group of memory cells, determined states of the memory cells with respect to a state adjacent a state corresponding to a swapping shell, and whether a particular memory cell is a candidate for swapping.

A semiconductor system includes a first semiconductor device and a second semiconductor device. The first semiconductor device generates a first error scrub control signal and a second error scrub control signal according to a logic level combination of an error code including information on the error occurrence number of times. The second semiconductor device performs an error scrub operation of a memory area on a first cycle time in response to the first error scrub control signal during a refresh operation and performs the error scrub operation of the memory area on a second cycle time in response to the second error scrub control signal during the refresh operation.

A data processing circuit and a fault-mitigating method are provided. A first data is written into a memory. A computed result is determined according to one or more adjacent bits of the first data at faulty bits. According to the computed result, new values are determined. The new values replace the values of the first data at the faulty bits to form a second data. The first data includes multiple bits. The first data is image-related data, weights used by a multiply-accumulate (MAC) for extracting features of images, and/or values used by an activation calculation. The adjacent bits are adjacent to the faulty bits. The computed result is obtained through computing the values of the first data at non-faulty bits of the memory. Accordingly, an influence of a memory fault is reduced.

Apparatuses and methods for determining soft data for fractional digit memory cells are provided. One example apparatus can include a controller to determine states of memory cells of a group of memory cells operated as fractional digit memory cells, and determine soft data based, at least partially, on dimensions to which particular memory cells correspond with respect to the group of memory cells, determined states of the memory cells with respect to a state adjacent a state corresponding to a swapping shell, and whether a particular memory cell is a candidate for swapping.

An operating method of a controller, comprising: generating, when a first ECC decoding operation to codeword read from a semiconductor memory device according to a hard read voltage fails, an optimization information corresponding the result of the first ECC decoding operation; generating one or more quantization intervals determined by the optimization information; and performing a second ECC decoding operation to codeword read from the semiconductor memory device according to soft read voltages determined by the quantization intervals and the hard read voltage, wherein the optimization information includes: deterioration information of a memory block; ECC decoder parameter information; and constituent code parameter information.

A multiplication and accumulation (MAC) operator includes a data input circuit configured to receive first operands and second operands and configured to output the first operands and third operands, a multiplication circuit configured to generate multiplication data by performing a multiplication operation on the first operands and the third operands, an addition circuit configured to generate multiplication addition data by performing an addition operation on the multiplication data, an accumulating circuit configured to generate accumulative data by performing an accumulative addition operation on the multiplication addition data and feedback data, and an error correction circuit configured to detect a computational error in the accumulative data when a computational error occurs, and configured to output, as MAC result data, accumulative data having the computational error corrected.

Introduced here is a technique to detect and/or correct errors in computation. The ability to correct errors in computation can increase the speed of the processor, reduce the power consumption of the processor, and reduce the distance between the transistors within the processor because the errors thus generated can be detected and corrected. In one embodiment, an error correcting module, running either in software or in hardware, can detect an error in matrix multiplication, by calculating an expected sum of all elements in the resulting matrix, and an actual sum of all elements in the resulting matrix. When there is a difference between the expected sum and the resulting sum, the error correcting module detects an error. In another embodiment, in addition to detecting the error, the error correcting module can determine the location and the magnitude of the error, thus correcting the erroneous computation.

Methods, systems, and apparatus for detecting single event effects. The system includes a first-modulus digital logic unit and a second-modulus digital logic unit each configured to reduce one or more operands by a respective modulus, apply an arithmetic compute logic to the reduced operands to produce a respective compute output, and reduce the respective compute output by their respective modulus. The system includes a kernel digital logic unit configured to apply the arithmetic compute logic to the operands to produce a kernel compute output, output the kernel compute output reduced by the first modulus, and output the kernel compute output reduced by the second modulus. The system includes a detector configured to detect a single event effect based on the reduced first compute output, the kernel compute output reduced by the first modulus, the reduced second compute output, and the kernel compute output reduced by the second modulus.

A semiconductor system includes a first semiconductor device and a second semiconductor device. The first semiconductor device generates a first error scrub control signal and a second error scrub control signal according to a logic level combination of an error code including information on the error occurrence number of times. The second semiconductor device performs an error scrub operation of a memory area on a first cycle time in response to the first error scrub control signal during a refresh operation and performs the error scrub operation of the memory area on a second cycle time in response to the second error scrub control signal during the refresh operation.