A system and method to compress application control data, such as weights for a layer of a convolutional neural network, is disclosed. A multi-core system for executing at least one layer of the convolutional neural network includes a storage device storing a compressed weight matrix of a set of weights of the at least one layer of the convolutional network and a decompression matrix. The compressed weight matrix is formed by matrix factorization and quantization of a floating point value of each weight to a floating point format. A decompression module is operable to obtain an approximation of the weight values by decompressing the compressed weight matrix through the decompression matrix. A plurality of cores executes the at least one layer of the convolutional neural network with the approximation of weight values to produce an inference output.

A system and method to compress application control data, such as weights for a layer of a convolutional neural network, is disclosed. A multi-core system for executing at least one layer of the convolutional neural network includes a storage device storing a compressed weight matrix of a set of weights of the at least one layer of the convolutional network and a decompression matrix. The compressed weight matrix is formed by matrix factorization and quantization of a floating point value of each weight to a floating point format. A decompression module is operable to obtain an approximation of the weight values by decompressing the compressed weight matrix through the decompression matrix. A plurality of cores executes the at least one layer of the convolutional neural network with the approximation of weight values to produce an inference output.

A system and method to compress application control data, such as weights for a layer of a convolutional neural network, is disclosed. A multi-core system for executing at least one layer of the convolutional neural network includes a storage device storing a compressed weight matrix of a set of weights of the at least one layer of the convolutional network and a decompression matrix. The compressed weight matrix is formed by matrix factorization and quantization of a floating point value of each weight to a floating point format. A decompression module is operable to obtain an approximation of the weight values by decompressing the compressed weight matrix through the decompression matrix. A plurality of cores executes the at least one layer of the convolutional neural network with the approximation of weight values to produce an inference output.

An arithmetic encoder for encoding a plurality of symbols having symbol values is configured to derive an interval size information for an arithmetic encoding of one or more symbol values to be encoded based on a plurality of state variable values representing statistics of a plurality of previously encoded symbol values with different adaptation time constants. The arithmetic encoder is configured to map a first state variable value, or a scaled and/or rounded version thereof, using a lookup-table and to map a second state variable value, or a scaled and/or rounded version thereof using the lookup-table, in order to obtain the interval size information describing an interval size for the arithmetic encoding of one or more symbols to be encoded. Further arithmetic encoders, arithmetic decoders, video encoders, video decoder, methods for encoding, methods for decoding and computer programs are also disclosed which are based on the same concept and on other concepts.

An arithmetic encoder for encoding a plurality of symbols having symbol values is configured to derive an interval size information for an arithmetic encoding of one or more symbol values to be encoded based on a plurality of state variable values representing statistics of a plurality of previously encoded symbol values with different adaptation time constants. The arithmetic encoder is configured to map a first state variable value, or a scaled and/or rounded version thereof, using a lookup-table and to map a second state variable value, or a scaled and/or rounded version thereof using the lookup-table, in order to obtain the interval size information describing an interval size for the arithmetic encoding of one or more symbols to be encoded. Further arithmetic encoders, arithmetic decoders, video encoders, video decoder, methods for encoding, methods for decoding and computer programs are also disclosed which are based on the same concept and on other concepts.

An arithmetic encoder for encoding a plurality of symbols having symbol values is configured to derive an interval size information for an arithmetic encoding of one or more symbol values to be encoded based on a plurality of state variable values representing statistics of a plurality of previously encoded symbol values with different adaptation time constants. The arithmetic encoder is configured to map a first state variable value, or a scaled and/or rounded version thereof, using a lookup-table and to map a second state variable value, or a scaled and/or rounded version thereof using the lookup-table, in order to obtain the interval size information describing an interval size for the arithmetic encoding of one or more symbols to be encoded. Further arithmetic encoders, arithmetic decoders, video encoders, video decoder, methods for encoding, methods for decoding and computer programs are also disclosed which are based on the same concept and on other concepts.

An arithmetic encoder for encoding a plurality of symbols having symbol values is configured to derive an interval size information for an arithmetic encoding of one or more symbol values to be encoded based on a plurality of state variable values representing statistics of a plurality of previously encoded symbol values with different adaptation time constants. The arithmetic encoder is configured to map a first state variable value, or a scaled and/or rounded version thereof, using a lookup-table and to map a second state variable value, or a scaled and/or rounded version thereof using the lookup-table, in order to obtain the interval size information describing an interval size for the arithmetic encoding of one or more symbols to be encoded. Further arithmetic encoders, arithmetic decoders, video encoders, video decoder, methods for encoding, methods for decoding and computer programs are also disclosed which are based on the same concept and on other concepts.

Described herein are systems and methods for conversion of numeric values between different number base formats, for use with software applications. In accordance with an embodiment, an integral part of a passed floating-point numeric value in a source number base (e.g., binary) format is isolated and converted to an integer. A fractional part of the numeric value is also isolated and converted to an integer, while limiting the isolation and conversion of the fractional part to a required precision or number of digits, depending on the particular requirements of a software application. The fractional part can be rounded, including determining an exact roundoff as appropriate, and if necessary propagating the rounding to the integral part. Digits from the resulting integers representing the integral and fractional parts can then be collected and used to prepare a representation of the original numeric value in a target number base (e.g., decimal) format.

Described herein are systems and methods for conversion of numeric values between different number base formats, for use with software applications. In accordance with an embodiment, an integral part of a passed floating-point numeric value in a source number base (e.g., binary) format is isolated and converted to an integer. A fractional part of the numeric value is also isolated and converted to an integer, while limiting the isolation and conversion of the fractional part to a required precision or number of digits, depending on the particular requirements of a software application. The fractional part can be rounded, including determining an exact roundoff as appropriate, and if necessary propagating the rounding to the integral part. Digits from the resulting integers representing the integral and fractional parts can then be collected and used to prepare a representation of the original numeric value in a target number base (e.g., decimal) format.

A method compares text strings having Unicode encoding. The method receives a first string S=s.sub.1s.sub.2 . . . s.sub.n and a second string T=t.sub.1t.sub.2 . . . t.sub.m, where s.sub.1, s.sub.2, . . . , s.sub.n and t.sub.1, t.sub.2, . . . , t.sub.m are Unicode characters. The method computes a first string weight for the first string S according to a weight function ƒ. When S consists of ASCII characters, ƒ(S)=S. when S includes one or more non-replaceable non-ASCII characters, the first string weight ƒ(S) is a concatenation of an ASCII weight prefix ƒ.sub.A(S) and a Unicode weight suffix ƒ.sub.U(S). The method also computes a second string weight for the second text string T. Equality of the strings is tested using the string weights.