An electronic device that includes a decompression engine that includes N decoders and a decompressor decompresses compressed input data that includes N streams of data. Upon receiving a command to decompress compressed input data, the decompression engine causes each of the N decoders to decode a respective one of the N streams from the compressed input data separately and substantially in parallel with others of the N decoders. Each decoder outputs a stream of decoded data of a respective type for generating commands associated with a compression standard for decompressing the compressed input data. The decompressor next generates, from the streams of decoded data output by the N decoders, commands for decompressing the data using the compression standard to recreate the original data. The decompressor next executes the commands to recreate the original data and stores the original data in a memory or provides the original data to another entity.

To speed up decoding of a range code. A decompression circuit calculates a plurality of candidate bit values for each bit of the N-bit string based on a plurality of possible bit histories of a bit before a K-th bit in parallel for a plurality of bits, and repeatedly selects a correct bit value of the K-th bit from the plurality of candidate bit values based on a correct bit history of the bit before the K-th bit to decode the N-bit string.

Verification of discriminative models includes receiving an input; receiving a prediction from a discriminative model for the input; encoding, using an encoder, a latent variable based on the input; decoding, using a decoder, a reconstructed input based on the prediction and the latent variable; and determining, using an anomaly detection module, whether the prediction is reliable based on the input, the reconstructed input, and the latent variable. The encoder and the decoder are jointly trained to maximize an evidence lower bound of the encoder and the decoder. In some embodiments, the encoder and the decoder are further trained using a disentanglement constraint between the prediction and the latent variable. In some embodiments, the encoder and the decoder are further trained without using inputs that are out of a distribution of inputs used to train the discriminative model or that are adversarial to the discriminative model.

A disclosed information handling system includes an edge device communicatively coupled to a cloud computing resource. The edge device is configured to respond to receiving, from an internet of things (IoT) unit, a numeric value for a parameter of interest by determining a compressed encoding for the numeric value in accordance with a non-lossless compression algorithm. The edge device transmits the compressed encoding of the numeric value to the cloud computing resource. The cloud computing resource includes a decoder communicatively coupled to the encoder and configured to respond to receiving the compressed encoding by generating a surrogate for the numeric value. The surrogate may be generated in accordance with a probability distribution applicable to the parameter of interest. The compression algorithm may be a clustering algorithm such as a k-means clustering algorithm.

Methods and devices for encoding a point cloud. A current node associated with a sub-volume is split into further sub-volumes, each further sub-volume corresponding to a child node of the current node, and, at the encoder, an occupancy pattern is determined for the current node based on occupancy status of the child nodes. A probability distribution is selected from among a plurality of probability distributions based on occupancy data for a plurality of nodes neighbouring the current node. The encoder entropy encodes the occupancy pattern based on the selected probability distribution to produce encoded data for the bitstream and updates the selected probability distribution. The decoder makes the same selection based on occupancy data for neighbouring nodes and entropy decodes the bitstream to reconstruct the occupancy pattern.

A deep neural network (“DNN”) module compresses and decompresses neuron-generated activation data to reduce the utilization of memory bus bandwidth. The compression unit receives an uncompressed chunk of data generated by a neuron in the DNN module. The compression unit generates a mask portion and a data portion of a compressed output chunk. The mask portion encodes the presence and location of the zero and non-zero bytes in the uncompressed chunk of data. The data portion stores truncated non-zero bytes from the uncompressed chunk of data. A decompression unit receives a compressed chunk of data from memory in the DNN processor or memory of an application host. The decompression unit decompresses the compressed chunk of data using the mask portion and the data portion.

Lossy methods and hardware for compressing data and the corresponding decompression methods and hardware are described. The lossy compression method comprises dividing a block of pixels into a number of sub-blocks and then analysing, for each sub-block, and selecting one of a candidate set of lossy compression modes. The analysis may, for example, be based on the alpha values for the pixels in the sub-block. In various examples, the candidate set of lossy compression modes comprises at least one mode that uses a fixed alpha channel value for all pixels in the sub-block and one or more modes that encode a variable alpha channel value.

A method for decoding a data stream, including a plurality of identifiers and a bit sequence, into a sequence of data of respective predetermined types includes the following operations for obtaining each item of data of the sequence: determining a context on the basis of an identifier, from among the plurality of identifiers, with the type of the relevant item of data; and decoding one portion of the bit sequence by an entropic decoder which receives the bit sequence as an input and is parameterized in the determined context. An electronic decoding device and an associated computer program are also provided.

In various examples, metadata may be generated corresponding to compressed data streams that are compressed according to serial compression algorithms—such as arithmetic encoding, entropy encoding, etc.—in order to allow for parallel decompression of the compressed data. As a result, modification to the compressed data stream itself may not be required, and bandwidth and storage requirements of the system may be minimally impacted. In addition, by parallelizing the decompression, the system may benefit from faster decompression times while also reducing or entirely removing the adoption cycle for systems using the metadata for parallel decompression.

A method for processing data overflow in a decompression process, includes: decompressing an original text, and detecting whether a data overflow event occurs in the decompression process; in response to detecting the data overflow event, storing first data obtained by decompression in a host cache into a target memory, and closing a data read-in port of a decoding engine; decompressing data which is being decompressed in the decoding engine to obtain second data, and storing the second data into a cache of the decoding engine; calculating a position of the decompressed data in the original text; obtaining, on the basis of the position, data which is not decompressed in the original text, re-decompressing the data which is not decompressed to obtain third data, and storing the second data into the target memory; and splicing the first data, the second data, and the third data to obtain complete decompressed data.