Abstract: A method, including loading, to a first address in a memory of a computer, an interposing method having an interposing name that is identical to an original name of an original method in a library of original methods that are to be dynamically loaded by a software application running on the computer, and identifying a second address in the memory of a dynamic linking method associated with the library. A request is then intercepted from the application, the request including a specified name for one of the methods in the library. When the specified name matches the interposing name, the application is directed to the first address so as to run the interposing method. However, when the specified name does not match any interposing name, the application is directed to the second address so as to run the dynamic linking method to run one of the original methods.

Abstract: A method for training a Neural-Network (NN), the method includes receiving a plurality of NN training tasks, each training task including (i) a respective preprocessing phase that preprocesses data to be provided as input data to the NN, and (ii) a respective computation phase that trains the NN using the preprocessed data. The plurality of NN training tasks is executed, including: (a) a commonality is identified between the input data required by computation phases of two or more of the training tasks, and (b) in response to identifying the commonality, one or more preprocessing phases are executed that produce the input data jointly for the two or more training tasks.

Abstract: An amplified optical link having a fault-protection capability that is based, at least in part, on the ability to selectively and independently power up and down different groups of optical amplifiers within the link. In an example embodiment, the optical link is implemented using an optical fiber cable having an electrical power line and arrays of optical amplifiers connected between successive optical fiber segments to form a plurality of disjoint groups of parallel optical paths between the ends of the optical fiber cable. The electrical power line is operable to selectively power, as a group, the optical amplifiers of at least some of the disjoint groups. In various embodiments, different optical paths can be implemented using different respective strands of a single-core optical fiber, different respective cores of a multi-core optical fiber, and/or different respective sets of spatial modes of a multimode optical fiber.

Abstract: An optical transport system configured to compensate nonlinear signal distortions using a backward-propagation algorithm in which some effects of polarization mode dispersion on the nonlinear signal distortions are accounted for by employing two or more different approximations of said effects within the bandwidth of the optical communication signal. In an example embodiment, the corresponding digital signal processor (DSP) is configured to switch between different approximations based on a comparison, with a fixed threshold value, of a difference between frequencies of various optical waves contributing to the nonlinear signal distortions, e.g., through four-wave-mixing processes. In different embodiments, the backward-propagation algorithm can be executed by the transmitter's DSP or the receiver's DSP.

Abstract: An optical transport system configured to compensate nonlinear signal distortions using a backward-propagation algorithm in which some effects of polarization mode dispersion on the nonlinear signal distortions are accounted for by employing two or more different approximations of said effects within the bandwidth of the optical communication signal. In an example embodiment, the corresponding digital signal processor (DSP) is configured to switch between different approximations based on a comparison, with a fixed threshold value, of a difference between frequencies of various optical waves contributing to the nonlinear signal distortions, e.g., through four-wave-mixing processes. In different embodiments, the backward-propagation algorithm can be executed by the transmitter's DSP or the receiver's DSP.

Abstract: An optical transport system configured to compensate nonlinear signal distortions using a backward-propagation algorithm in which some effects of polarization mode dispersion on the nonlinear signal distortions are accounted for by employing two or more different approximations of said effects within the bandwidth of the optical communication signal. In an example embodiment, the corresponding digital signal processor (DSP) is configured to switch between different approximations based on a comparison, with a fixed threshold value, of a difference between frequencies of various optical waves contributing to the nonlinear signal distortions, e.g., through four-wave-mixing processes. In different embodiments, the backward-propagation algorithm can be executed by the transmitter's DSP or the receiver's DSP.

Abstract: A method for training a Neural-Network (NN), the method includes receiving a plurality of NN training tasks, each training task including a respective preprocessing phase that preprocesses data to be provided as input data to the NN, and (ii) a respective computation phase that trains the NN using the preprocessed data. The plurality of NN training tasks is executed, including: (a) a commonality is identified between the input data required by computation phases of two or more of the training tasks, and (b) in response to identifying the commonality, one or more preprocessing phases are executed that produce the input data jointly for the two or more training tasks.

Abstract: A method that may include receiving a block of signals from a certain wavelength division multiplex (WDM) channel out of a set of WDM channels; analyzing at least a first sub-block of signals of the block of signals to provide analysis results indicative of interferences that affect the first sub-block of signals and result from transmissions over other WDM channels of the set of WDM channels; and mitigating interferences that affect the block of signals in response to the analysis results.

Abstract: An amplified optical link having a fault-protection capability that is based, at least in part, on the ability to selectively and independently power up and down different groups of optical amplifiers within the link. In an example embodiment, the optical link is implemented using an optical fiber cable having an electrical power line and arrays of optical amplifiers connected between successive optical fiber segments to form a plurality of disjoint groups of parallel optical paths between the ends of the optical fiber cable. The electrical power line is operable to selectively power, as a group, the optical amplifiers of at least some of the disjoint groups. In various embodiments, different optical paths can be implemented using different respective strands of a single-core optical fiber, different respective cores of a multi-core optical fiber, and/or different respective sets of spatial modes of a multimode optical fiber.

Abstract: A WDM receiver configured to apply electronic equalization processing to both dispersion-compensated and dispersion-distorted versions of the received communication signal. In an example embodiment, the receiver's DSP first generates an equalized dispersion-compensated signal corresponding to the communication signal. The DSP then performs electronic dispersion-application processing on the equalized dispersion-compensated signal to generate a dispersion-distorted version thereof. The DSP then applies decision-aided electronic equalization processing to the dispersion-distorted version of the signal, subjects the resulting equalized signal to another round of dispersion-compensation processing, and recovers the data encoded in the communication signal using the resulting dispersion-compensated signal.

Abstract: An optical transport system configured to compensate nonlinear signal distortions using a backward-propagation algorithm in which some effects of polarization mode dispersion on the nonlinear signal distortions are accounted for by employing two or more different approximations of said effects within the bandwidth of the optical communication signal. In an example embodiment, the corresponding digital signal processor (DSP) is configured to switch between different approximations based on a comparison, with a fixed threshold value, of a difference between frequencies of various optical waves contributing to the nonlinear signal distortions, e.g., through four-wave-mixing processes. In different embodiments, the backward-propagation algorithm can be executed by the transmitter's DSP or the receiver's DSP.

Abstract: A WDM receiver configured to apply electronic equalization processing to both dispersion-compensated and dispersion-distorted versions of the received communication signal. In an example embodiment, the receiver's DSP first generates an equalized dispersion-compensated signal corresponding to the communication signal. The DSP then performs electronic dispersion-application processing on the equalized dispersion-compensated signal to generate a dispersion-distorted version thereof. The DSP then applies decision-aided electronic equalization processing to the dispersion-distorted version of the signal, subjects the resulting equalized signal to another round of dispersion-compensation processing, and recovers the data encoded in the communication signal using the resulting dispersion-compensated signal.

Abstract: We disclose a shaping encoder configured to use a variable-length shaping code to implement fixed-input fixed-output (FIFO) probabilistic signal shaping. In various embodiments, the variable-length shaping code can be a variable-input fixed-output code, a fixed-input variable-output code, or a variable-input variable-output code. The FIFO functionality of the shaping encoder is enabled by a control circuit that operates to: (i) check an output-overflow condition for each bit-word to be encoded using the variable-length shaping code and (ii) switch the shaping encoder from using the variable-length shaping code to using a suitable FIFO code if the output-overflow condition is satisfied. Some embodiments of the shaping encoder can incorporate a conventional FEC encoder in a manner that substantially preserves the shaping gain realized by the shaping encoder.

Abstract: A method includes storing data in a memory that includes multiple analog memory cells. After storing the data, an interference caused by a first group of the analog memory cells to a second group of the analog memory cells is estimated. The data stored in the first group is reconstructed based on the estimated interference caused by the first group to the second group.

Abstract: A method includes decoding a code word of an Error Correction Code (ECC), which is representable by a set of check equations, by performing a sequence of iterations, such that each iteration involves processing of multiple variable nodes. For one or more selected variable nodes, a count of the check equations that are defined over one or more variables held respectively by the one or more selected variable nodes is evaluated, and, when the count meets a predefined skipping criterion, the one or more selected variable nodes are omitted from a given iteration in the sequence.

Abstract: A method includes programming a group of analog memory cells by writing respective analog values into the memory cells in the group. After programming the group, the analog values are read from the memory cells in the group using a set of read thresholds so as to produce readout results. Respective optimal positions for the read thresholds in the set are identified based on the readout results. A noise level in the readout results is estimated based on the identified optimal positions of the read thresholds.

Abstract: A method includes storing data in a memory that includes multiple analog memory cells. After storing the data, an interference caused by a first group of the analog memory cells to a second group of the analog memory cells is estimated. The data stored in the first group is reconstructed based on the estimated interference caused by the first group to the second group.

Abstract: A method includes programming a group of analog memory cells by writing respective analog values into the memory cells in the group. After programming the group, the analog values are read from the memory cells in the group using a set of read thresholds so as to produce readout results. Respective optimal positions for the read thresholds in the set are identified based on the readout results. A noise level in the readout results is estimated based on the identified optimal positions of the read thresholds.

Abstract: A method includes storing data in a group of analog memory cells by writing respective analog values into the memory cells in the group. After storing the data, the analog values are read from the memory cells in the group one or more times using one or more respective read thresholds so as to produce readout results. Reliability measures are computed for the read analog values based on the readout results. An offset of the one or more read thresholds from an optimal read threshold position is estimated based on the reliability measures. The reliability measures are modified to compensate for the estimated offset, and the data stored in the analog memory cells in the group is decoded using the corrected reliability measures.

Abstract: A method includes storing data in a memory that includes multiple analog memory cells. After storing the data, an interference caused by a first group of the analog memory cells to a second group of the analog memory cells is estimated. The data stored in the first group is reconstructed based on the estimated interference caused by the first group to the second group.