Intel Corporation

Agere Systems Inc.

Lsi Corporation

Jian-Guo Chen

Joseph Williams

Kameran Azadet

Samer Lutfi Hijazi

Meng-Lin Yu

Nevin C Heintze

Ambalavanar Arulambalam

Ivan Leonidovich Mazurenko

Alexander Alexandrovich Petyushko

Jun Zhao

Qian Xu

David Sonnier

Kent E Wires

Cheng Gang Duan

Steven Pinault

David E Clune

Hakan I Pekcan

Albert Molina

Zoran Zivkovic

Joseph H Othmer

Chengzhou Li

Lin Hua

Hanan Z Moller

Parakalan Venkataraghavan

Ramon Sanchez Perez

Kamran Azadet

Jay O'Neill

David T Dougherty

Hong Wan

David Dougherty

Techniques are disclosed for the use of fused vector processor instructions by a vector processor architecture. Each fused vector processor instruction may include a set of fields associated with individual vector processing instructions. The vector processor architecture may implement local buffers facilitating a single vector processor instruction to be used to execute each of the individual vector processing instructions without re-accessing vector registers between each executed individual vector processing instruction. The vector processor architecture enables less communication across the interconnection network, thereby increasing interconnection network bandwidth and the speed of computations, and decreasing power usage.

Vector processor utilizing massively fused operations

Systems, methods, and apparatuses relating to a user defined formatting instruction to configure multicast Benes network circuitry are described. In one embodiment, a processor includes a decoder to decode a single instruction into a decoded single instruction, the single instruction having fields that identify packed input data, packed control data, and a packed data destination; and an execution unit to execute the decoded single instruction to: send the packed control data to respective control inputs of a circuit that comprises an inverse butterfly circuit coupled in series to a butterfly circuit, wherein the inverse butterfly circuit comprises a first plurality of stages of multicast switches and the butterfly circuit comprises a second plurality of stages of multicast switches, read, once from storage separate from the circuit, each element of the packed input data as respective inputs of the circuit, route the packed input data through the circuit according to the packed control data, and store resultant packed data from the circuit into the packed data destination.

Apparatuses, methods, and systems for a user defined formatting instruction to configure multicast Benes network circuitry

Software Digital Front End (SoftDFE) signal processing techniques are provided. One or more digital front end (DFE) functions are performed on a signal in software by executing one or more specialized instructions on a processor to perform the one or more digital front end (DFE) functions on the signal, wherein the processor has an instruction set comprised of one or more of linear and non-linear instructions. A block of samples comprised of a plurality of data samples is optionally formed and the digital front end (DFE) functions are performed on the block of samples. The specialized instructions can include a vector convolution function, a complex exponential function, an xfunction, a vector compare instruction, a vector max( ) instruction, a vector multiplication instruction, a vector addition instruction, a vector sqrt( ) instruction, a vector 1/x instruction, and a user-defined non-linear instruction.

Software digital front end (SoftDFE) signal processing

In one embodiment, the present invention is a method for performing incremental preamble detection in a wireless communication network. The method processes non-overlapping chunks of incoming antenna data, where each chunk is smaller than the preamble length, to detect the signature of the transmitted preamble. For each chunk processed, chips of the chunk are correlated with possible signatures employed by the wireless network to update a set of correlation profiles, each profile comprising a plurality of profile values. Further, an intermediate detection is performed by comparing the updated profile values to an intermediate threshold that is also updated for each chunk. Upon receiving the final chunk, the correlation profiles are updated, and a final preamble detection is made by comparing the updated profile values to a final threshold. Detections are performed on an incremental basis to meet latency requirements of the wireless network.

Incremental preamble detection

A digital signal processor and method are disclosed with one or more non-linear functions using factorized polynomial interpolation. A digital signal processor evaluates a non-linear function for a value, x, by obtaining two or more values from at least one look-up table for said non-linear function that are near said value, x; and interpolating said two or more obtained values to obtain a value, y, using a factorized polynomial interpolation.

Digital signal processor with one or more non-linear functions using factorized polynomial interpolation

A digital signal processor is provided having an instruction set with an xfunction that uses a reduced look-up table. The disclosed digital signal processor evaluates an xfunction for an input value, x, by computing Log(x) in hardware; multiplying the Log(x) value by K; and determining the xfunction by applying an exponential function in hardware to a result of the multiplying step. One or more of the computation of Log(x) and the exponential function employ at least one look-up table having entries with a fewer number of bits than a number of bits in the input value, x.

[object Object]

In one embodiment, a programmable vector processor performs preamble detection in a wireless communication network. Implementation of preamble detection in the vector processor is made possible by a set of vector instructions that include (i) a circular load instruction for loading vectors of received data, (ii) a correlation instruction for correlating the vectors of received data with vectors of the scrambling code to concurrently generate a plurality of complex correlations, (iii) a partial-transpose instruction for arranging vectors of the complex correlations for use by a Fast Hadamard Transform (FHT) processor, and (iv) an FHT instruction for performing FHT processing on a vector of complex correlations. Implementing preamble detection in the vector processor allows more of the received data to be processed concurrently. As a result, preamble detectors of the disclosure may detect preambles using fewer clock cycles than that of comparable preamble detectors implemented using hardware accelerators.

Preamble detection using vector processors

Methods and apparatus are provided for a digital signal processor having an instruction set with one or more non-linear complex functions. A method is provided for a processor. One or more non-linear complex software instructions are obtained from a program. The non-linear complex software instructions have at least one complex number as an input. One or more non-linear complex functions are applied from a predefined instruction set to the at least one complex number. An output is generated comprised of one complex number or two real numbers. A functional unit can implement the one or more non-linear complex functions. In one embodiment, a vector-based digital signal processor is disclosed that processes a complex vector comprised of a plurality of complex numbers. The processor can process the plurality of complex numbers in parallel.

Digital signal processor having instruction set with one or more non-linear complex functions

A digital signal processor is provided having an instruction set with a logarithm function that uses a reduced look-up table. The disclosed digital signal processor evaluates a logarithm function for an input value, x, by decomposing the input value, x, to a first part, N, a second part, q, and a remaining part, r, wherein the first part, N, is identified by a position of a most significant bit of the input value, x, and the second part, q, is comprised of a number of bits following the most significant bit, wherein the number is small relative to a number of bits in the input value, x; obtaining a value from a first look-up table based on the second part, q; computing an epsilon term, &#x3b5;, using the expression evaluating an expression Log(1+&#x3b5;) using a polynomial approximation, such as a cubic approximation; and determining the logarithm function for the input value, x, by summing the values of N, and Log(1+&#x3b5;).

Digital signal processor having instruction set with a logarithm function using reduced look-up table

A digital signal processor is provided having an instruction set with an exponential function that uses a reduced look-up table. The disclosed digital signal processor evaluates an exponential function for an input value, x, by decomposing the input value, x, to an integer part, N, a first fractional part, q, larger than a specified value, x, and a second fractional part, q, smaller than the specified value, x; computing 2using a polynomial approximation, such as a cubic approximation; obtaining 2from a look-up table; and evaluating the exponential function for the input value, x, by multiplying 2, 2and 2together. Look-up table entries have a fewer number of bits than a number of bits in the input value, x.

Digital signal processor having instruction set with an exponential function using reduced look-up table

A digital signal processor and method are disclosed having an instruction set with one or more non-linear functions using a look-up table of reduced size. A digital signal processor evaluates a non-linear function for a value, x, by obtaining two or more values for the non-linear function that are near the value, x, from at least one look-up table, wherein the at least one look-up table stores a subset of values for the non-linear function; and interpolating the two or more obtained values to obtain a result, y. The interpolation may comprise, for example, a linear interpolation or a polynomial interpolation. In a further variation, a modulo arithmetic operation can be employed for a periodic non-linear function.

Digital signal processor having instruction set with one or more non-linear functions using reduced look-up table

A digital signal processor and method are disclosed having an instruction set with one or more non-linear functions using a look-up table of reduced size and exponentially varying step-sizes. A digital signal processor evaluates a non-linear function for a value, x, by obtaining at least two values from at least one look-up table for the non-linear function that are near the value, x, wherein the at least one look-up table stores a subset of values for the non-linear function using exponentially-varying step sizes; and interpolating the at least two obtained values to obtain a result, y. A position of a leading zero in the value, x, can be used as an index into the at least one look-up table. The interpolation can comprise, for example, a linear interpolation or a polynomial interpolation. A modulo arithmetic operation can optionally be employed for a periodic non-linear function.

Digital signal processor having instruction set with one or more non-linear functions using reduced look-up table with exponentially varying step-size

In one embodiment, the invention is a method for performing preamble detection in a wireless communication network. The method performs a first dwell, wherein non-overlapping chunks of received data are processed to generate partial correlation values for each possible combination of a signature code and delay. Candidate selection is performed by comparing each of the partial correlation values to a candidate-selection threshold. For each detected candidate, the chunks of received data are processed to generate full correlation values. Each full correlation value is then compared to a preamble-detection threshold to detect a transmitted signature. Generating full correlation values for only the selected candidates reduces the computation complexity over prior-art methods that generate full correlation values for all signatures at all delays.

Chunk-based double-dwell preamble detection

In some examples, a protocol accelerator extracts a queue identifier from an incoming packet, for identifying a first buffer queue in which the packet is to be stored for transport layer processing. A packet having an error or condition is identified, such that the accelerator cannot perform the processing on that packet. A processor is interrupted. The identified packet is stored in a second buffer queue. The processor performs transport layer processing in response to the interrupt, while the accelerator continues transport layer processing of packets in the first buffer queue. In some examples, a TCP congestion window size is adjusted. A programmable congestion window increment value is provided. The window size is set to an initial value at the beginning of a TCP data transmission. The window size is increased by the increment value when an acknowledgement is received.

Protocol accelerator and method of using same

A method includes storing video data in a disk by way of a first queue comprising a linked list of buffers. Video data are received into the first queue by way of a tail buffer. The tail buffer is at one end of the linked list of buffers in the first queue. Video data are copied from a head buffer to the disk. The head buffer is at another end of the linked list of buffers in the first queue. The video data are displayed in real-time directly from the buffers in the queue, without retrieving the displayed video data from the disk, and without interrupting the storing step.

Growing community of inventors

Basking Ridge, NJ, United States of America

Jian-Guo Chen