Qualcomm Incorporated

Vito Remo Bica

Amin Ansari

Richard Senior

Jinxia Bai

Adrienne Milner

David Jonathan Julian

Paul E Bender

Zhanfeng Jia

Noam A Ziv

Chinnappa K Ganapathy

Rahul Anand

James William Dolter

Sreekanth Vietla

Edward Harrison Teague

Qingjiang Tian

Harinath Garudadri

Lu Xiao

Brian Michael Buesker

David Merrill Jacobson

Rexford Alan Hill

Stephen S Carter

Rodolfo Beraha

Jin Guo

Gregory K Woods

Jared S Grubb

Sruthikesh Surineni

In one embodiment, a depth-first deep convolutional network (DCN) having a first convolutional layer having a first first-layer kernel and adapted to convolve a first input and a second convolutional layer having a first second-layer kernel and adapted to convolve a second-layer input. A method for the DCN includes initiating convolution in the first convolution layer of the first input tensor with the first first-layer kernel to generate a value strip for the second input tensor and, prior to completion of the convolution in the first convolution layer, initiating convolution in the second convolution layer of the second input with the first second-layer kernel to generate a value strip for a third layer.

Depth-first convolution in deep neural networks

Aspects for generating compressed data streams with lookback pre-fetch instructions are disclosed. A data compression system is provided and configured to receive and compress an uncompressed data stream as part of a lookback-based compression scheme. The data compression system determines if a current data block was previously compressed. If so, the data compression system is configured to insert a lookback instruction corresponding to the current data block into the compressed data stream. Each lookback instruction includes a lookback buffer index that points to an entry in a lookback buffer where decompressed data corresponding to the data block will be stored during a separate decompression scheme. Once the data blocks have been compressed, the data compression system is configured to move a lookback buffer index of each lookback instruction in the compressed data stream into a lookback pre-fetch instruction located earlier than the corresponding lookback instruction in the compressed data stream.

Generating compressed data streams with lookback pre-fetch instructions for pre-fetching decompressed data from a lookback buffer

A system for data decompression may include a processor coupled to a remote memory having a remote dictionary stored thereon and coupled to a decompression logic having a local memory with a local dictionary. The processor may decompress data during execution by accessing the local dictionary, and if necessary, the remote dictionary.

System, apparatus, and method for decompressing data

One feature provides a method for a client node to establish a session key with a group node by obtaining an epoch identity value associated with a current epoch, wherein obtaining the epoch identity value includes one of computing the epoch identity value based on a node real time or negotiating the epoch identity value with the group node, computing a restricted key using a shared secret key, the epoch identity value, and a group node identity associated with the group node, and executing a session key establishment protocol with the group node to derive the session key using the restricted key as a master key in the session key establishment protocol. The session key may be established between the group node and the client node even though communications between the group node and the central node is only intermittently available during the current epoch.

Method and apparatus for virtual pairing with a group of semi-connected devices

Data compression systems, methods, and computer program products are disclosed. For each successive input word of an input stream, it is determined whether the input word matches an entry in a lookback table. The lookback table is updated in response to the input word. Input words may be of a number of data types, including zero runs and full or partial matches with an entry in the lookback table. A codeword is generated by entropy encoding a data type corresponding to the input word. The lookback table may be indexed by the position of the input word in the input stream.

Compressed caching in a virtual memory system

A multi-pass compression iteratively removes combinations of bits from locations in each word of a cache line of an uncompressed data stream. For each combination of removed bits, the remaining bits in the word values of the cache line are analyzed to generate a compression score. A highest compression score triggers the building of a dictionary from the remaining bits in the word values of the cache line. After a dictionary is built, the method may continue iteratively to create subsequent dictionaries from the words that remain uncompressed in the cache line. To decompress a word, a first bit section of the compressed word is used to identify a dictionary that is then queried for bits indexed in a second bit section of the compressed word. The uncompressed word is reconstructed by interleaving the queried bits with the removed combination of bits from a third bit section of the word.

System and method for dictionary-based cache-line level code compression for on-chip memories using gradual bit removal

Lempel-Ziv (LZ)-based data compression employing implicit variable-length distance coding is disclosed. Distances in LZ-based data compression length and distance blocks are implicit variable-length encoded during data compression to avoid padding encoded distances with extra bits (e.g., trailing 0's) that require fewer bits for storage than the number of bits needed to store maximum distance length. This reduces distance bit lengths in compressed output data to further reduce data size. During data compression, a distance table is generated that contains entries each having an assigned base and a number of extra bits to be read in compressed data during data decompression. In this manner, during data decompression, the entries in the distance table can be consulted to determine the number of bits in the variable-encoded distance in the compressed data to be read since the encoded distances can be encoded in the compressed data in fewer bits and without bit padding.

Lempel-Ziv (LZ)-based data compression employing implicit variable-length distance coding

The various embodiments provide systems, devices, and methods which include an acoustic tag configured to transmit an acoustic signal through a contact medium that may be received by an acoustic modem, with the acoustic signal configured to transmit information. By modulating sound traveling through an acoustic connection between the fluid container and a pump, meter or valve, information such as an identifier of the fluid or container may be transmitted without risk of confusion with other fluid containers in the vicinity. In a medical embodiment, IV fluid and the IV drip tube provide a fluid and plastic acoustic connection to an IV pumping or metering device and an IV bag through which sound may be transmitted. The transmission of identification information through this physical connection may insure that the pumping or metering device only communicates with the IV bag coupled to the pump. Acoustic tags may be active or passive.

Acoustic modem for fluid monitoring in medical and industrial applications

An apparatus includes first and second components, a memory, and an allocator configured to allocate a portion of the memory to the first component, wherein the first component is configured to access the allocated portion of the memory and to send information to the second component to provide the second component with access to the allocated portion of the memory.

Optimized transfer of packets in a resource constrained operating environment

A system and method for media access control are disclosed. The method comprises providing concurrent orthogonal channels to access media using pulse division multiple access to define pulse positions, wherein the pulse division multiple access includes a time hopping sequence and an offset to distinguish the concurrent orthogonal channels. In addition, the method comprises processing signals associated with at least one of the orthogonal channels.

System and method to implement concurrent orthogonal channels in an ultra-wide band wireless communications network

The present apparatus comprises a radio access network element having at least one processor, and at least one memory operably connected to the at least one processor, whereby the radio access network element is adapted to execute instructions stored in the memory comprising discovery of at least one other element in a radio access network. The radio access element further comprises instructions for removal or addition of network elements, instructions for determining a paging area and instructions for forwarding messages from a mobile to a controller in another domain.

Growing community of inventors

Poway, CA, United States of America

Vito Remo Bica