Abstract: A system and method for double data rate (DDR) chip-kill decoding using an array of ECC erasure decoders operating in parallel to identify a location of a chip-kill event associated with a DDR memory device. The ECC erasure decoder that correctly identifies the chip-kill location is then used to decode subsequent DDR bursts transmitted from the DDR memory device.

Abstract: A method and apparatus for decoding in which a first failed decode operation is performed on raw bit values of a FEC block by a LDPC decoder. When the FEC block is determined to be a trapped block an updated LLR map is generated; the updated LLR map and either the raw bit values of the FEC block or a failed-decode-output-block from a previous failed decode operation on the trapped block are provided to the LDPC decoder; a decode operation of the LDPC decoder is performed using the updated LLR map on the bit values of the FEC block or the failed-decode-output-block from the previous failed decode operation; and the generating, the providing and the performing are repeated until the decode operation is successful or until a predetermined number of trapped-block-decoding iterations have been performed. When the decode operation is successful in decoding the FEC block the codeword is output.

Abstract: A method for memory protection includes receiving a burst-write instruction that includes data and a burst-write address. The data are segmented into a plurality of data blocks. One or more bits of the burst-write address, or a hash of the burst-write address are concatenated to respective data blocks to obtain data-and-write-address-bit (DWAB) segments. A SECDED ECC is executed on respective DWAB segments to generate a corresponding plurality of sets of parity bits (DWAB-PB). Respective DWAB-PB are concatenated to the corresponding data block to generate corresponding forward-error-correction (FEC) blocks, none of the FEC blocks including the burst-write address or the hash of the burst-write address. A burst-write command and a respective portion of a respective FEC block is sent to respective memory devices during a plurality of beats until all of the beats of the burst-write have been sent.

Abstract: A method and apparatus for decoding in which a first failed decode operation is performed on raw bit values of a FEC block by a LDPC decoder. When the FEC block is determined to be a trapped block an updated LLR map is generated; the updated LLR map and either the raw bit values of the FEC block or a failed-decode-output-block from a previous failed decode operation on the trapped block are provided to the LDPC decoder; a decode operation of the LDPC decoder is performed using the updated LLR map on the bit values of the FEC block or the failed-decode-output-block from the previous failed decode operation; and the generating, the providing and the performing are repeated until the decode operation is successful or until a predetermined number of trapped-block-decoding iterations have been performed. When the decode operation is successful in decoding the FEC block the codeword is output.

Abstract: A method for memory protection includes receiving a burst-write instruction that includes data and a burst-write address. The data are segmented into a plurality of data blocks. One or more bits of the burst-write address, or a hash of the burst-write address are concatenated to respective data blocks to obtain data-and-write-address-bit (DWAB) segments. A SECDED ECC is executed on respective DWAB segments to generate a corresponding plurality of sets of parity bits (DWAB-PB). Respective DWAB-PB are concatenated to the corresponding data block to generate corresponding forward-error-correction (FEC) blocks, none of the FEC blocks including the burst-write address or the hash of the burst-write address. A burst-write command and a respective portion of a respective FEC block is sent to respective memory devices during a plurality of beats until all of the beats of the burst-write have been sent.

Abstract: A system and method for double data rate (DDR) chip-kill decoding using an array of ECC erasure decoders operating in parallel to identify a location of a chip-kill event associated with a DDR memory device. The ECC erasure decoder that correctly identifies the chip-kill location is then used to decode subsequent DDR bursts transmitted from the DDR memory device.

Abstract: A method and apparatus for decoding are disclosed. The method includes receiving a first Forward Error Correction (FEC) block of read values, starting a hard-decode process in which a number of check node failures is identified and, during the hard-decode process comparing the identified number of check node failures to a decode threshold. When the identified number of check node failures is not greater than the decode threshold the hard-decode process is continued. When the identified number of check node failures is greater than the decode threshold, the method includes: stopping the hard-decode process prior to completion of the hard-decode process; generating output indicating that additional reads are required; receiving one or more additional FEC blocks of read values, mapping the first FEC block of read values and the additional FEC blocks of read values into soft-input values; and performing a soft-decode process on the soft-input values.

Abstract: A system and method for data sampler drift compensation in a SerDes receiver. Off-data values are received at a drift compensation engine from a plurality of data value selectors coupled to one of a plurality of data sampler pairs of a speculative Decision Feedback Equalizer (DFE) of a SerDes receiver. A drift compensation value for each of the data samplers is generated by the drift compensation engine based upon the off-data values received from each of the plurality of data value selectors and, a sampling level of each of the data samplers of the plurality of data sampler pairs of the DFE is adjusted based upon the drift compensation value from the drift compensation engine.

Abstract: A method and apparatus for decoding are disclosed. The method includes receiving a first Forward Error Correction (FEC) block of read values, starting a hard-decode process in which a number of check node failures is identified and, during the hard-decode process comparing the identified number of check node failures to a decode threshold. When the identified number of check node failures is not greater than the decode threshold the hard-decode process is continued. When the identified number of check node failures is greater than the decode threshold, the method includes: stopping the hard-decode process prior to completion of the hard-decode process; generating output indicating that additional reads are required; receiving one or more additional FEC blocks of read values, mapping the first FEC block of read values and the additional FEC blocks of read values into soft-input values; and performing a soft-decode process on the soft-input values.

Abstract: A system for implementing variable T BCH encoders includes: a polynomial multiplier for multiplying a message polynomial by a difference polynomial to achieve a first value, wherein the message polynomial comprises data bits as coefficients and the difference polynomial comprises minimal polynomials that are present in a T error correcting code and are absent from a T??T error correcting BCH code; a shifter/zero-padder coupled with the BCH encoder, the shifter/zero-padder for multiplying the first value by xN-{tilde over (K)} to achieve a second value; a BCH encoder coupled with the polynomial multiplier, the BCH encoder for dividing the second value by a generator polynomial of the T error correcting BCH code and calculating a remainder based on the dividing to achieve a third value; and a polynomial divider for dividing the third value by the difference polynomial to achieve a fourth value comprising parity of the T??T error correcting BCH code.

Abstract: A system and method for decision feedback equalizer (DFE) tap adaptation. An input signal is received at a DFE of a receiver, wherein the input signal comprises a serial bit stream of encoded symbols. Data samples and error samples are taken from the input signal and the data samples and the error samples are aligned establish a plurality of pairs of data samples and error samples, wherein the data sample and error sample of each of the plurality of pairs of data samples and error samples are from locations in the serial bit stream of encoded symbols that are known to be uncorrelated with each other. The DFE tap weights are then adjusted based upon the plurality of pairs of data samples and error samples.

Abstract: A system for implementing variable T BCH encoders includes: a polynomial multiplier for multiplying a message polynomial by a difference polynomial to achieve a first value, wherein the message polynomial comprises data bits as coefficients and the difference polynomial comprises minimal polynomials that are present in a T error correcting code and are absent from a T??T error correcting BCH code; a shifter/zero-padder coupled with the BCH encoder, the shifter/zero-padder for multiplying the first value by xN?{tilde over (K)} to achieve a second value; a BCH encoder coupled with the polynomial multiplier, the BCH encoder for dividing the second value by a generator polynomial of the T error correcting BCH code and calculating a remainder based on the dividing to achieve a third value; and a polynomial divider for dividing the third value by the difference polynomial to achieve a fourth value comprising parity of the T??T error correcting BCH code.

Abstract: A method and system are provided for performing Decision Feedback Equalization (DFE) and Decision Feedback Sequence Estimation (DFSE) in high-throughput applications that are not latency critical. In an embodiment, overlapping blocks of samples are used to allow for the parallelization of the computation and the breaking of the critical path. In addition, the overlap of the windows addresses issues associated with performance loss due to what is termed “ramp-up” and “ramp-down” BER loss.