Abstract: Disclosed herein are systems and methods for executing programs written in functional style. A distributed computing system receives a program that expresses computation upon one or more sets of distributed key-value pairs (DKVs) and one or more global variables (GVs). The system distributes an assembly that includes at least a compiled binary of the program to the nodes of a computing cluster, with different portions of the DKVs being stored across the plurality of nodes of the computing cluster. The system causes execution of the assembly by each of the plurality of nodes of the computing cluster, the ones of the plurality of nodes executing the assembly using the different portions of the one or more DKVs stored thereon.

Abstract: An audio encoder receives multi-channel audio data comprising a group of plural source channels and performs channel extension coding, which comprises encoding a combined channel for the group and determining plural parameters for representing individual source channels of the group as modified versions of the encoded combined channel. The encoder also performs frequency extension coding. The frequency extension coding can comprise, for example, partitioning frequency bands in the multi-channel audio data into a baseband group and an extended band group, and coding audio coefficients in the extended band group based on audio coefficients in the baseband group. The encoder also can perform other kinds of transforms. An audio decoder performs corresponding decoding and/or additional processing tasks, such as a forward complex transform.

Abstract: An audio decoder provides a combination of decoding components including components implementing base band decoding, spectral peak decoding, frequency extension decoding and channel extension decoding techniques. The audio decoder decodes a compressed bitstream structured by a bitstream syntax scheme to permit the various decoding components to extract the appropriate parameters for their respective decoding technique.

Abstract: A “Universal Rate Control Mechanism with Parameter Adaptation” (URCMPA) improves real-time communication (RTC) sessions in terms of delay, loss, throughput, and PSNR. The URCMPA automatically learns network characteristics including bottleneck link capacity, inherent queuing delay, inherent packet loss rates, etc., during RTC sessions. The URCMPA uses this information to dynamically adapt rate control parameters in a utility maximization (UM) framework. The URCMPA operates reliable RTC sessions across a wide range and combination of networks near full throughput rates while maintaining low operating congestion levels (e.g., low queuing delay and low packet loss). Examples of networks applicable for use with the URCMPA include, but are not limited to, combinations of mobile broadband (e.g., 3G, 4G, etc.), WiMAX, Wi-Fi hotspots, etc., and physical networks based on cable, fiber, ADSL, etc.

Abstract: A method and system that enhances a user's performance while interacting with an interactive internet application such as a Massively Multiplayer Online (MMO) game is provided. The network latency experienced by users participating in the MMO game is minimized by dynamically determining an optimal transmission action for a message generated by the MMO game. In one embodiment, determining the optimal transmission action for a message includes dynamically determining the optimal number of redundant Forward Error Correction (FEC) packets to add to a message prior to transmitting a message to a receiving device. The optimal number of FEC packets is determined based on a wide range of varying network conditions.

Abstract: An audio decoder provides a combination of decoding components including components implementing base band decoding, spectral peak decoding, frequency extension decoding and channel extension decoding techniques. The audio decoder decodes a compressed bitstream structured by a bitstream syntax scheme to permit the various decoding components to extract the appropriate parameters for their respective decoding technique.

Abstract: Embodiments are directed to controlling bandwidth usage using a token-based crediting and debiting scheme and to allowing connections to temporarily exceed bandwidth allocations using token credits. In one scenario, a bandwidth managing service receives a request to establish a connection with a network. The connection is associated with various subscribers that are part of a subscription. The bandwidth managing service assigns tokens to the connection, which are distributed from a pool of tokens that represents a total available bandwidth for the network. The bandwidth managing service receives a data transfer request from a logical user to transfer data over the network connection, where the data transfer request includes at least some of the assigned tokens. The bandwidth managing service also allocates to the connection a specified amount of bandwidth commensurate with the number of assigned tokens provided in the data transfer request.

Abstract: The subject disclosure is directed towards partitioning a file into chunks that satisfy a chunk size restriction, such as maximum and minimum chunk sizes, using a sliding window. For file positions within the chunk size restriction, a signature representative of a window fingerprint is compared with a target pattern, with a chunk boundary candidate identified if matched. Other signatures and patterns are then checked to determine a highest ranking signature (corresponding to a lowest numbered Rule) to associate with that chunk boundary candidate, or set an actual boundary if the highest ranked signature is matched. If the maximum chunk size is reached without matching the highest ranked signature, the chunking mechanism regresses to set the boundary based on the candidate with the next highest ranked signature (if no candidates, the boundary is set at the maximum). Also described is setting chunk boundaries based upon pattern detection (e.g., runs of zeros).

Abstract: The subject disclosure is directed towards predicting compressibility of a data block, and using the predicted compressibility in determining whether a data block if compressed will be sufficiently compressible to justify compression. In one aspect, data of the data block is processed to obtain an entropy estimate of the data block, e.g., based upon distinct value estimation. The compressibility prediction may be used in conjunction with a chunking mechanism of a data deduplication system.

Abstract: An encoder performs context-adaptive arithmetic encoding of transform coefficient data. For example, an encoder switches between coding of direct levels of quantized transform coefficient data and run-level coding of run lengths and levels of quantized transform coefficient data. The encoder can determine when to switch between coding modes based on a pre-determined switch point or by counting consecutive coefficients having a predominant value (e.g., zero). A decoder performs corresponding context-adaptive arithmetic decoding.

Abstract: A computer-implemented method and system for determining documents that are nearest to a query are provided herein. The method includes constructing a vantage point tree based on a number of document vectors. The method also includes searching the vantage point tree to determine a number of nearest neighbor document vectors to a query vector by removing a portion of the document vectors from the vantage point tree based on one or more vantage points for each of a number of nodes in the vantage point tree and a specified search radius centered about the query vector.

Abstract: An audio decoder provides a combination of decoding components including components implementing base band decoding, spectral peak decoding, frequency extension decoding and channel extension decoding techniques. The audio decoder decodes a compressed bitstream structured by a bitstream syntax scheme to permit the various decoding components to extract the appropriate parameters for their respective decoding technique.

Abstract: In various embodiments, methods and systems are disclosed for integrating a remote presentation protocol with a datagram based transport. In one embodiment, an integrated protocol is configured to support lossless or reduced loss transport based on Retransmission (ARQ) combined with Forward Error Correction (FEC). The protocol involves encoding and decoding of data packets including feedback headers and FEC packets, continuous measurement of RTT, RTO and packet delay, dynamically evaluating loss probability to determine and adjust the ratio of FEC, congestion management based on dynamically detecting increase in packet delay, and fast data transmission rate ramp-up based on detecting a decrease in packet delay.

Abstract: An encoder performs context-adaptive arithmetic encoding of transform coefficient data. For example, an encoder switches between coding of direct levels of quantized transform coefficient data and run-level coding of run lengths and levels of quantized transform coefficient data. The encoder can determine when to switch between coding modes based on a pre-determined switch point or by counting consecutive coefficients having a predominant value (e.g., zero). A decoder performs corresponding context-adaptive arithmetic decoding.

Abstract: An audio decoder provides a combination of decoding components including components implementing base band decoding, spectral peak decoding, frequency extension decoding and channel extension decoding techniques. The audio decoder decodes a compressed bitstream structured by a bitstream syntax scheme to permit the various decoding components to extract the appropriate parameters for their respective decoding technique.

Abstract: Traditional audio encoders may conserve coding bit-rate by encoding fewer than all spectral coefficients, which can produce a blurry low-pass sound in the reconstruction. An audio encoder using wide-sense perceptual similarity improves the quality by encoding a perceptually similar version of the omitted spectral coefficients, represented as a scaled version of already coded spectrum. The omitted spectral coefficients are divided into a number of sub-bands. The sub-bands are encoded as two parameters: a scale factor, which may represent the energy in the band; and a shape parameter, which may represent a shape of the band. The shape parameter may be in the form of a motion vector pointing to a portion of the already coded spectrum, an index to a spectral shape in a fixed code-book, or a random noise vector. The encoding thus efficiently represents a scaled version of a similarly shaped portion of spectrum to be copied at decoding.

Abstract: Described are techniques to use adaptive learning to control bandwidth or rate of transmission of a computer on a network. Congestion observations such as packet delay and packet loss are used to compute a congestion signal. The congestion signal is correlated with information about actual congestion on the network, and the transmission rate is adjusted according to the degree of correlation. Transmission rate may not adjust when packet delay or packet loss is not strongly correlated with actual congestion. The congestion signal is adaptively learned. For instance, the relative effects of loss and delay on the congestion signal may change over time. Moreover, an operating congestion level may be minimized by adaptive adjustment.

Abstract: In various embodiments, methods and systems are disclosed for a hybrid rate plus window based congestion protocol that controls the rate of packet transmission into the network and provides low queuing delay, practically zero packet loss, fair allocation of network resources amongst multiple flows, and full link utilization. In one embodiment, a congestion window may be used to control the maximum number of outstanding bits, a transmission rate may be used to control the rate of packets entering the network (packet pacing), a queuing delay based rate update may be used to control queuing delay within tolerated bounds and minimize packet loss, and aggressive ramp-up/graceful back-off may be used to fully utilize the link capacity and additive-increase, multiplicative-decrease (AIMD) rate control may be used to provide fairness amongst multiple flows.

Abstract: In various embodiments, methods and systems are disclosed for a hybrid rate plus window based congestion protocol that controls the rate of packet transmission into the network and provides low queuing delay, practically zero packet loss, fair allocation of network resources amongst multiple flows, and full link utilization. In one embodiment, a congestion window may be used to control the maximum number of outstanding bits, a transmission rate may be used to control the rate of packets entering the network (packet pacing), a queuing delay based rate update may be used to control queuing delay within tolerated bounds and minimize packet loss, and aggressive ramp-up/graceful back-off may be used to fully utilize the link capacity and additive-increase, multiplicative-decrease (AIMD) rate control may be used to provide fairness amongst multiple flows.

Abstract: An audio encoder encodes side information into a compressed audio bitstream containing encoding parameters used by the encoder for one or more encoding techniques, such as a noise-mask-ratio curve used for rate control. A transcoder uses the encoder generated side information to transcode the audio from the original compressed bitstream having an initial bit-rate into a second bitstream having a new bit-rate. Because the side information is derived from the original audio, the transcoder is able to better maintain audio quality of the transcoding. The side information also allows the transcoder to re-encode from an intermediate decoding/encoding stage for faster and lower complexity transcoding.