Freescale Semiconductor,inc.

Motorola Corporation

Aviel Livay

Guy Drory

Yuval Neeman

Ron Bercovich

Yonatan Naor

Ronen Shtayer

Roni Eliyahu

Inbar Schori

Ori Goren

Gil Moran

Ilia Moskovich

Ricardo Berger

Dror Gilad

Yaron Netanel

Yossy Neeman

Yosef Kazaz

Ron Berkovich

Gilad Dror

Alexander Joffe

A parallel access system including: a group of processing entities that comprises N processing entities; wherein N is a positive integer that exceeds one; a group of memory banks that stores K information elements; wherein the group of memory banks comprises N pairs of single access memory banks; each pair of memory banks comprises an even memory bank and an odd memory bank; wherein each pair of memory banks stores sub-set of K/N information elements; wherein an even memory bank of each pair of memory banks stores even address information elements of a certain sub-set of K/N information elements and an odd memory bank of each pair of memory banks stores odd address information elements of the certain sub-set of K/N information elements; wherein K/N is an even positive integer; and a non-blocking interconnect, coupled to the group of processing entities and to the group of memory banks; wherein during each fetch cycle each processing entity of the group of processing entities fetches a first information element from an odd memory unit of a pair of memory banks and fetches a second information element from an even memory unit of the pair of memory banks; wherein the first and second information elements are two consecutive interleaved address information elements.

Contention free parallel access system and a method for contention free parallel access to a group of memory banks

A semiconductor device comprising processing logic. The processing logic is arranged to configure interleaver logic to re-order data symbols of a data stream according to a quadrature permutation polynomial function. The processing logic is further arranged to: divide a cyclic group of values defined by the QPP function into a set of subgroups, the set of subgroups being capable of being defined by a set of linear functions; derive inverse functions for the set of linear functions defining the subgroups; and configure the interleaver logic to load the data symbols of the data stream into a buffer at locations within the buffer corresponding to a cyclic group of values representative of the inverse function for the QPP function based on the inverse functions of the set of linear functions defining the subgroups.

Method and apparatus for interleaving a data stream using quadrature permutation polynomial functions (QPP)

A method for calculating backward state metrics of a trellis, the method includes: performing a radix-K calculation of backward state matrices of multiple states of at least one time instance of a trellis; and performing a radix-J calculation of backward state matrices of multiple states of at least one other time instance of the trellis; wherein K differs from J.

Device and method for calculating backward state metrics of a trellis

A method and a device having interleaving capabilities, the device comprises a first interleaver; the first interleaver comprises a first register, a second register, a first adder and a second adder; wherein the first register is coupled to the first adder and to the second adder; wherein the second register is coupled to the second adder; wherein the first adder is adapted to add a current first register value to a first coefficient to provide a next first register value that is stored at the first register; wherein the second adder is adapted to add a current first register value to a second coefficient, to a third coefficient and to a current second register value to provide an interleaved output value.

Device having interleaving capabilities and a method for applying an interleaving function

A device and a method for turbo decoding, the method includes performing multiple iterations of a turbo decoding process until a turbo decoding process is completed; wherein the performing comprises repeating the stages of: (i) initializing at least one state metric of multiple windows of a channel data block for a current iteration of the turbo decoding process by at least one corresponding state metric that was calculated during a previous iteration of the turbo decoding process; and (ii) calculating in parallel, at least forward state metrics and backward state metrics of the multiple windows, during the current iteration.

Device having turbo decoding capabilities and a method for turbo decoding

A device having priority update capabilities and a method for updating priorities, the method includes: receiving a request to update to a requested priority, priorities of transaction requests stored within a first sequence of pipeline stages that precede an arbiter; updating a priority level of a transaction request stored in the first sequence to the requested priority if the transaction request is priority upgradeable and if the requested priority is higher that a current priority of the transaction request; and arbitrating between transaction requests in response to priority attributes associated with the transaction requests.

Device having priority upgrade mechanism capabilities and a method for updating priorities

A method for generating an interleaved output during a decoding of a data block, the method includes: (i) selecting, in response to a row indicator, a row register and a multiplication factor to provide a selected row register and a selected multiplication factor; wherein the selected multiplication factor is responsive to a size of the data block; (ii) multiplying a value stored in the selected row register by the selected multiplication factor to provide an intermediate result; (iii) performing a modulo P operation on the intermediate result to provide a permutated result; wherein the permutated result and the value stored in the selected row register are adjacent elements of the same permutation; wherein P is responsive to a size of the data block; (iv) writing the permutated result to the selected row register; and (v) outputting a data block element that is selected in response to the permutated result.

System and a method for generating an interleaved output during a decoding of a data block

A method (FIGS. 5-6) and a structure (FIGS. 3-4) are taught herein for prioritizing and transmitting forward monitoring cells (FMCs) for performance monitoring in an asynchronous transfer mode (ATM) system. An ATM system may have multiple physical lines which have many virtual paths which have multiple virtual connections. These paths/connections may be performance monitored by transmitting an FMC each time N ATM data cells are received for the connection/path (wherein N is number which may be different for each connection/path). The number of data cells are stored via a counter for each connection/path being monitored. Once N ATM cells are received on a given connection/path, an FMC descriptor is queued which indicates that the FMC cell for the given connection/path must be transmitted before receipt of N/2 subsequent cells received by the given connection/path. A priority (which is a function of one of the counters) is used to ensure that the N/2 requirement is satisfied.

Method and structure for prioritizing performance monitoring cells in an

An asynchronous transfer mode (ATM) address compression method uses a PHY ID (14). The PHY ID (14) is provided before the transmission of a 53-byte ATM data cell (12, 16, and 18). The PHY ID (14) (also referred to as a link) is used to access a link table (20). The link table (20) contains address compression mode information which allows for many address compression modes and an enable bit, an address pointer, and a mask value which are used to both reduce ATM addressing bits and identify a virtual path table/entry in the ATM system. In some address compression modes, the identified virtual path contains the ingress connection identifier (ICI) which identifies a physical data routing path in the ATM system. In other address compression modes, further address compression of virtual channel identifiers is required beyond the virtual path tables in order to identify a virtual channel table/entry which then contains the ICI.

Method and data structure for performing address compression in an

This invention relates to a FIFO memory system (10) comprising a plurality of FIFO memories (20) for handling transmission queues in a serial digital communication system. The memory system comprises a plurality of blocks of memory (20a-c, 21a-e), each of the plurality of FIFO memories being assigned a block (20a) of the plurality of blocks of memory, the unassigned blocks of memory forming a block pool (21a-e). The memory system further comprises memory management means (LLT, PT) for adding at least one of the unassigned blocks of memory from the block pool to a FIFO memory on writing to the FIFO memory whereby the size of the FIFO memory is selectably variable, and for returning a block of memory from a FIFO memory to the block pool once the contents of the block of memory have been read.

Growing community of inventors

Holon, Israel

Aviel Livay