Abstract: Disclosed is a memory device including self-ID information. The memory device has a storage unit for storing information related to the memory device, such as a manufacturing factory, a manufacturing date, a wafer number, coordinates on a wafer and the like. Each bank of the memory device stores self-ID information related to the memory device and outputs the self-ID information out of a chip when an address is applied thereto during a test mode.

Abstract: A cache memory system may be is organized as a set of numbered banks. If two clients need to access the cache, a contention situation may be resolved by a contention resolution process. The contention resolution process may be based on relative priorities of the clients.

Abstract: In one embodiment, a system includes a plurality of memory controllers each coupled between a processor and a respective memory. Each memory controller includes a plurality of decoders. Each decoder of a given memory controller may be independently configurable to match on a respective value of a subset of address bits such as the low-order cache line address bits, for example, received in a memory request. In one specific implementation, the number of decoders included on a given memory controller may correspond to the number of ways in which the memory is interleaved.

Abstract: A method for in-place interleaving and de-interleaving of a memory includes, in one embodiment, generating a new address corresponding to a new location in the memory by performing a bit-wise XOR operation on a number of bits of a first portion of a current address and a number of bits of a different portion of the current address. The current address corresponds to a current location in the memory. In addition, the method includes performing a data swap on data stored at the current location with data stored at the new location.

Abstract: A central processor unit (CPU) accesses memory to read and write data and to read and execute program instructions. A problem arises when accessing slower Flash or electrically programmable read only memory (EPROM) with a faster CPU. A method and system has been devised which uses interleaving techniques and memory sub-sections. A memory interlace controller interfaces a faster CPU to several sub-sections of slower memory. The memory interlace controller interlaces the access of the slower memory and thus optimizing the CPU system speed.

Abstract: A processor having the capability to dispatch multiple parallel operations, including multiple load operations, accesses a cache which is divided into banks. Each bank supports a limited number of simultaneous read and write access operations. A bank prediction field is associated with each memory access operation. Memory access operations are selected for dispatch so that they are predicted to be non-conflicting. Preferably, the processor automatically maintains a bank predict value based on previous bank accesses, and a confirmation value indicating a degree of confidence in the bank prediction. The confirmation value is preferably an up-or-down counter which is incremented with each correct prediction and decremented with each incorrect prediction.

Abstract: The invention relates to a method and respective system for accessing a cache memory in a computer system, wherein the cache memory is split up in at least two segments, wherein the cache memory is accessed by a plurality of competing cache memory requests via a number of commonly used input registers, wherein a cache segment model is utilized for reflecting the cache use by said competing requests, wherein cache memory requests are processed by a processing pipe and wherein each cache-request, before entering the processing pipe, is checked whether the segments of the cache memory are available at the cycle it needs, wherein said memory comprises the steps of: a) marking a segment model cell as busy with storing, if a store-request targeting to a cache segment corresponding to said model cell has received pipe access, b) blocking off from pipe access a fetch-request targeting to a segment model cell, which is marked busy with a store operation; and c) blocking off any store-request from pipe access, if at

Abstract: One or more external control pins and/or addressing pins on a memory device are used to set one or both of a burst length and burst type of the memory device.

Abstract: The performance of an application is improved by identifying and eliminating items with dead time-stamps and eliminating work on items with irrelevant time-stamps. An algorithm executing in each node of a task graph computes and propagates guarantees which are used to eliminate both items with dead time-stamps and irrelevant computation on dead time-stamps. A continuous garbage collector eliminates items with dead time-stamps while the node continues to process received items. Unnecessary computations are reduced by automatically discerning the interest set of downstream modules for time-stamps and feeding the interest set back to upstream modules.

Abstract: A processor includes controller circuitry operative to control the storage of a plurality of separate linked list data structures for protocol data units received by the processor. The linked list data structures are stored in memory circuitry associated with the processor, and the memory circuitry is arranged in a plurality of banks. The plurality of banks are configured to store respective ones of the plurality of separate linked list data structures, such that each of the plurality of banks stores a corresponding one of the plurality of separate linked list data structures. The linked list data structures are accessed in an alternating manner that reduces the likelihood of access conflicts between the banks. The processor may be configured as a network processor integrated circuit to provide an interface between a network and a switch fabric in a router or switch.

Abstract: Systems and methods for maintaining cache coherency between a first controller and a redundant peer controller while reducing communication overhead processing involved in the coherency message exchange. Header or meta-data information is accumulated in a buffer in a first controller along with updated cache data (if any) and forwarded to the peer controller. The accumulating information may be double buffered so that a buffer is filling as a previously filled buffer is transmitting to the peer controller. The peer controller processes the received information to update its mirror cache to maintain coherency with the first controller's cache memory with respect to dirty data. The method and systems avoid the need to update cache coherency in response to every flush operation performed within the first controller to thereby improve overall system performance.

Abstract: One embodiment disclosed relates to a method of selecting a default locality for a memory object requested by a process running on a CPU in a multiprocessor system. A determination is made as to whether the memory object comprises a shared-memory object. If the memory object comprises said shared-memory object, then the default locality is selected to be within interleaved memory in the system. If not, a further determination may be made as to whether the memory object comprises a stack-type object. If the memory object comprises said stack-type object, then the default locality may be selected to be within local memory at a same cell as the requesting CPU. If not, a further determination may be made as to whether the requesting process has threads running on multiple cells.

Abstract: A memory system is divided into memory subsystems. Each subsystem includes a slave controller. Each slave controller is coupled to a serial link. A master controller is coupled to the slave controllers via the serial links, and the master controller is capable of initiating a memory access to a memory subsystem by communicating with the slave controller via the serial link. Each memory subsystem includes memory arrays coupled to the slave controller. Each memory array includes memory channels. Memory accesses to a memory array on a memory subsystem are interleaved by the slave controller between the memory channels, and memory accesses to a memory subsystem are striped by the slave controller between the memory arrays on the memory subsystem. Memory accesses are striped between memory subsystems by the master controller. The master controller and slave controllers communicate by sending link packets and protocol packets over the serial links.

Abstract: In one embodiment, the present invention is directed to a processor that comprises an instruction pipeline for executing processor instructions wherein the processor instructions define a memory access size and a cache memory for storing cache lines in a plurality of memory banks that have a block size that is greater than the memory access size, the cache memory including mapping logic for storing contiguous groups of bits, of size equal to the memory access size, in different ones of the plurality of memory banks.

Abstract: Methods and apparatus for implementing a pixel page system providing pixel pages optimized for use with a GLV (grating light valve). In one implementation, a system includes: a data source, providing pixel data for pixels in a first order, each pixel in a frame having rows and columns of pixels; a data destination, receiving pixel data for pixels in a second order; at least one memory device including memory pages having memory locations; pixel data for each pixel corresponds to an entry in a pixel page, each pixel page having rows and columns and including pixels, the pixel pages optimized for use with a GLV. Pixel data is stored to memory in the first order and retrieved in the second order. And each memory page stores pixel data in multiple locations according to the first order and stores pixel data in multiple locations according to the second order.

Abstract: A deinterleaver for performing high-speed multi-channel forward error correction using external SDRAM is provided. According to one exemplary aspect, the deinterleaver performs both read and write accesses to the SDRAM that are burst-oriented by hiding active and precharge cycles in order to achieve high data rate operations. The data bus length of the SDRAM is designed to be twice the deinterleaving symbol size thereby allowing bandwidth to be increased. The deinterleaver accesses data in the SDRAM as read blocks and write blocks. Each block includes a predetermined number of data words to be interleaved/deinterleaved. The ACTIVE command for one block is issued when a preceding block is being processed. Data in one read/write block has the same row address within the same bank of the SDRAM.

Abstract: A microprocessor, having interleaved cache and two parallel processing pipelines adapted to access all of the interleaved cache. The microprocessor comprising: a cache directory for each of the parallel processing pipelines wherein each said cache directory is split according to the interleaved cache and interleaving of the cache directory is independent of address bits used for cache interleaving.

Abstract: An embodiment of the invention is a processor for providing simultaneous access to the same data for a plurality of requests. The processor includes cache storage having an address sliced directory lookup structure. A same line detection unit receives a plurality of first instruction fields and a plurality of second instruction fields. The same line detection unit generates a same line signal in response to the first instruction fields and the second instruction fields. The cache storage simultaneously reads data from a single line in the cache storage in response to the same line signal.

Abstract: An embodiment of the invention is a processor for providing simultaneous access to the same data for a plurality of requests. The processor includes cache storage having an address sliced directory lookup structure. A same doubleword detection unit receives a first instruction including a plurality of first instruction fields on a first pipe and a second instruction including a plurality of second instruction fields on a second pipe. The same doubleword detection unit generates a same doubleword signal in response to the first instruction fields and the second instruction fields. The cache storage reads data from a single doubleword in the cache storage and simultaneously provides the doubleword to the first pipe and the second pipe in response to the same doubleword signal.

Abstract: A chip-multiprocessing system with scalable architecture, including on a single chip: a plurality of processor cores; a two-level cache hierarchy; an intra-chip switch; one or more memory controllers; a cache coherence protocol; one or more coherence protocol engines; and an interconnect subsystem. The two-level cache hierarchy includes first level and second level caches. In particular, the first level caches include a pair of instruction and data caches for, and private to, each processor core. The second level cache has a relaxed inclusion property, the second-level cache being logically shared by the plurality of processor cores. Each of the plurality of processor cores is capable of executing an instruction set of the ALPHA™ processing core. The scalable architecture of the chip-multiprocessing system is targeted at parallel commercial workloads.

Abstract: A signal record reproduction device 1 of the invention comprises a microcomputer 12 and a memory 17. A series of data blocks are divided into a plurality of items of element data. The element data is interleaved and stored to the memory 17. A memory incorporated in the microcomputer 12 stores a table and a function expression for deriving address data representing an address to store each element data in memory regions positioned sufficiently apart one another in address space.

Abstract: Counter control section 101 increments a row number and column number on a two-dimensional array for a block interleave expressed by a matrix two-dimensional array, outputs the incremented numbers as the read address values, bit inversion apparatus 102 performs bit inversion using the read address values as inputs, column conversion section 103 outputs the address values corresponding to the bit inversion output values and the column numbers from counter control section 101 as the column conversion values, shift register 104 bit-shifts the output values of bit inversion apparatus 102 and outputs as the address offset values, adder 106 adds up the address offset values and column conversion values and size comparison section 106 compares the addition value with the interleave size and outputs data which is not greater than the interleave size as address values.

Abstract: Interleaver for iterative decoder. A memory management scheme allows for single plane/single port memory devices to be used by the interleaver. The design is adaptable to soft-in soft-out (SISO) decoders that perform iterative decoding. The interleaver may be implemented within communication devices that implement two distinct SISOs that operate cooperatively or within communication devices that employ a single SISO (in a recycled embodiment) that functionally performs the analogous decoding operations that would be performed by the two distinct SISO implementation. The use of single plane/single port memory devices by the interleaver allows for a great deal of savings from many perspectives: the sizes of the required interleaver memory and the interleaver pattern memory are both cut in half using this approach, and a cost savings may also be realized, in that, cheaper, slower memories may be used since each respective interleaver memory is read only every other cycle.

Abstract: Memory interleaving includes providing a non-power of two number of channels in a computing system and interleaving memory access among the channels.

Abstract: One embodiment of a distributed memory module cache includes tag memory and associated logic implemented at the memory controller end of a memory channel. The memory controller is coupled to at least one memory module by way of a point-to-point interface. The data cache and associated logic are located in one or more buffer components on each of the memory modules.

Abstract: An apparatus and method for unaligned cache reads is implemented. Data signals on a system bus are remapped into a cache line wherein a plurality of data values to be read from the cache are output in a group-wise fashion. The remapping defines a grouping of the data values in the cache line. A multiplexer is coupled to each group of storage units containing the data values, wherein a multiplexer input is coupled to each storage unit in the corresponding group. A logic array coupled to each MUX generates a control signal for selecting the data value output from each MUX. The control signal is generated in response to the read address which is decoded by each logic array.

Abstract: An electronic device may include a source memory device partitioned into N elementary source memories for storing a sequence of input data sets, and a processor clocked by a clock signal and having N outputs for producing, per cycle of the clock signal, N output data sets respectively associated with the N input data sets stored in the N elementary source memories at respective source addresses. The electronic device may also include N single port target memories, N interleaving tables including, for each relative source address, the number of a target memory and the respective target address thereof, N cells connected in a ring structure. Further, each cell may also be connected between an output of the processor, an interleaving table, and a target memory.

Abstract: Methods and apparatus for implementing a pixel page system providing swapped pixel pages for use with a GLV (grating light valve).

Abstract: The present invention relates to a cache directory configuration method and an information processing device that implements the same. In an embodiment of this invention, each cache directory is divided up into a plurality of units that can be operated in a parallel manner. A plurality of search requests can be processed by each cache directory concurrently. Thus this embodiment allows the hardware requirements for the cache directory to be restricted while providing cache directory search performance higher than that of the conventional technology.

Abstract: An n-way interleaved set-associative external cache utilizes standard burst memory devices such as DDR (double data rate) memory devices. The interleaved set-associative cache organization scheme is designed to fully utilize burst efficiencies during snoop and invalidation operations. Cache lines are interleaved in such a way that a first burst transfer from the cache to the cache controller brings in a plurality of tags. The contents of the memory level device locations associated with each tag are stored in an alternating pattern in contiguous memory locations.

Abstract: A microprocessor, having interleaved cache and two parallel processing pipelines adapted to access all of the interleaved cache. The microprocessor comprising: a cache directory for each of the parallel processing pipelines wherein each said cache directory is split according to the interleaved cache and interleaving of the cache directory is independent of address bits used for cache interleaving.

Abstract: New devices having horizontally-disposed nanofabric articles and methods of making same are described. A discrete electromechanical device includes a structure having an electrically-conductive trace. A defined patch of nanotube fabric is disposed in spaced relation to the trace; and the defined patch of nanotube fabric is electromechanically deflectable between a first and second state. In the first state, the nanotube article is in spaced relation relative to the trace, and in the second state the nanotube article is in contact with the trace. A low resistance signal path is in electrical communication with the defined patch of nanofabric. Under certain embodiments, the structure includes a defined gap into which the electrically conductive trace is disposed. The defined gap has a defined width, and the defined patch of nanotube fabric spans the gap and has a longitudinal extent that is slightly longer than the defined width of the gap.

Abstract: Methods and apparatus for storing data using two-dimensional arrays mapped to memory locations.

Abstract: A chip-multiprocessing system with scalable architecture, including on a single chip: a plurality of processor cores; a two-level cache hierarchy; an intra-chip switch; one or more memory controllers; a cache coherence protocol; one or more coherence protocol engines; and an interconnect subsystem. The two-level cache hierarchy includes first level and second level caches. In particular, the first level caches include a pair of instruction and data caches for, and private to, each processor core. The second level cache has a relaxed inclusion property, the second-level cache being logically shared by the plurality of processor cores. Each of the plurality of processor cores is capable of executing an instruction set of the ALPHA™ processing core. The scalable architecture of the chip-multiprocessing system is targeted at parallel commercial workloads.

Abstract: A multi-entry register file cell includes multiple memory elements. A value stored in each of the multiple memory elements may be individually read from the register file cell in response to asserting a single word line.

Abstract: The present invention relates generally to a protocol engine for use in a multiprocessor computer system. The protocol engine, which implements a cache coherence protocol, includes a clock signal generator for generating signals denoting interleaved even clock periods and odd clock periods, a memory transaction state array for storing entries, each denoting the state of a respective memory transaction, and processing logic. The memory transactions are divided into even and odd transactions whose states are stored in distinct sets of entries in the memory transaction state array. The processing logic has interleaving circuitry for processing during even clock periods the even memory transactions and for processing during odd clock periods the odd memory transactions.

Abstract: A two-way cache memory having multiplexed outputs and alternating ways is disclosed. Multiplexed outputs enable the cache memory to be more densely packed and implemented with fewer sense amplifiers. Alternating ways enable two distinct cache access patterns. According to a first access pattern, two doublewords in the same way may be accessed simultaneously. Such access facilities the leading of data into main memory. According to a second access pattern, two doublewords in the same location but in different ways may be accessed simultaneously. Such access facilitates the loading a particular word into a register file.

Abstract: A system and method is disclosed that reduces intrabank conflicts and ensures maximum bandwidth on accesses to strided vectors in a bank-interleaved cache memory. The computer system contains a processor including a vector execution unit, scalar processor unit, cache controller and bank-interleaved cache memory. The vector execution unit retrieves strided vectors of data and instructions stored in the bank-interleaved cache memory in a plurality of cache banks such that intrabank conflicts are reduced. Given a stride S of a vector, the strided vectors of data and instructions stored in the bank-interleaved cache memory are retrieved by determining R and T using the equation S=2T*R. If T<=W, W defining a cache bank 2W words wide, then, for 0<=i<2(W−T), 0<=j<2P, and 0<=k<2N, words addressed i+2(W−T+N)j+2(W−T)k are accessed on the same cycle.

Abstract: The invention provides a method of generating cache indexes that reduces the likelihood that adjacent addresses will map to the same cache regions. The hashing process is optimized to be sensitive to small changes in the input data so that similar sets of input data will preferably not result in the same or even similar output data. Memory accesses of the sort performed when rendering graphical images may involve numerous accesses to relatively similar memory locations Therefore, hashing of the index values that determine where the information from the memory locations will be stored while that information is in cache decreases the likelihood of similar memory locations being stored at the same cache location. Consequently, cache efficiency and performance is improved.

Abstract: A shared bus non-sequential data ordering method and apparatus are provided. A maximum bus width value and a minimum transfer value are identified. A minimum number of sub-transfers is identified responsive to the identified maximum bus width value and the minimum transfer value. A bus unit having a maximum number of chips to receive and/or send data receives data in a predefined order during multiple sub-transfers. During each data sub-transfer, a corresponding predefined word is transferred to each chip of the bus unit.

Abstract: A method for loading instruction codes to a first memory and linking said instruction codes is proposed, whereby at least one instruction code has as parameter an address which during a loading step is not determined. This address-parametered instruction code has assigned thereto an address place. A relocation information is loaded which during a linking step effects that the address becomes determined using a starting address and a relative address offset. The then determined address is put at the address place. During the loading step, directly after loading each address-parametered instruction code with its address place, the relocation information is loaded and the address is determined in the linking step.

Abstract: A method provides for interleaved access of a contiguous logical address space formed by a plurality of memories having respective overlapping address spaces. The memories are organized into memory segments, memory segments of equal size from different memories arranged or organized into interleave groups. An initial largest interleave group is selected and a corresponding first interleave entry is generated in a table. The interleave entry maps a corresponding initial logical address space into each of the memory segments corresponding to the first interleave group. A total memory size included thus far in the table is calculated and successive next larger groups that are integer divisors of the total memory, i.e., the partial sums formed by groups selected thus far. These steps are repeated until all of the contiguous logical address space has been mapped onto the memories.

Abstract: The inventive mechanism determines whether memory source and destination addresses map to the same or nearly the same cache address. If they map to different addresses, then loads and stores are ordered so that loads to one cache bank are performed on the same clock cycles as the stores to another cache bank. After a group of loads and stores are completed, then load and store operations for each bank are switched. If the source and destination addresses map to nearly the same cache address and if the source address is prior to the destination address, then a group of cache lines is loaded into registers and stored to memory without any interleaving of other loads and stores. If the source and destination addresses map to the same cache location, then an initial load of data into registers is performed. After that, additional loads are interleaved with non-cache conflicting stores to move new values into memory. Thus, loads and stores to matching cache addresses are separated by time.

Abstract: A cache structure, organized in terms of cache lines, for use with variable length bundles of instructions (syllables), comprising: a first cache bank that is organized in columns and rows; a second cache bank that is organized in columns and rows; logic for defining said cache line into a sequence of equal sized segments, and mapping alternate segments in said sequence of segments to the columns in said cache banks such that said first bank holds even segments and said second bank holds odd segments; logic for storing bundles across at most a first column in said first cache bank and a sequentially adjacent column in said second cache bank; and logic for accessing bundles stored in the first and second cache banks.

Abstract: An interleaver is disclosed for a turbo encoder in an UMTS. The interleaver includes a register for updating and registering a plurality of parameters for setting an operating condition of the interleaver; a controller for generating a control signal for controlling an operation of the system by receiving the operating condition from the register; an address calculator for generating a finally interleaved address using an inter-row permutation pattern T(j), an intra-row permutation pattern increment arrangement value incr(j) and an intra-row permutation basic sequence s(i), provided from the register according to the control signal generated by the controller; and a data storage for sequentially storing data input to the turbo encoder and outputting data corresponding to the address generated by the address calculator.

Abstract: A memory system, which can improve the operation speed of a data bus and is suitable for widening bandwidth by extending the width of the data bus, and memory modules used for the memory system are provided. In the memory system, data buses of a first channel and data buses of a second channel are extended from a memory controller and are arranged on the left and right of a common control and address bus, respectively. Memory modules of a first group are loaded in the data buses of the first channel and memory modules of a second group are loaded in the data buses of the second channel. Also, in the memory system, the memory modules share the common control and address bus positioned in the center. Also, the memory modules are arranged so that some parts of the memory modules overlap each other and that the memory modules of the first group and the memory modules of the second group cross each other.

Abstract: A cross memory bank, cross memory page data accessing and controlling unit that provides more efficient transfer of data between a CPU and a memory cluster is described. The data accessing and controlling unit comprises a CPU interface circuit and a memory controlling circuit. When the CPU submits consecutive data access requests to the CPU interface circuit for accessing memory, addresses of the requested data do not necessarily lie in the same memory bank or the same memory page of the memory cluster. If the requested data lie on a different page or a different bank, the CPU interface circuit sends out cross-bank or cross-page signals to the memory controlling circuit in addition to the internal data request signal. Therefore, the required page in the memory bank can be opened in advance. Consequently, time for memory access is shortened and overall efficiency of the system can be improved.

Abstract: A method and apparatus determines interleaving schemes in a computer system that supports multiple interleaving schemes. In one embodiment, a memory interleaving scheme lookup table is used to assign memory interleaving schemes based on the number of available bank bits. In another embodiment, the percentage of concurrent memory operations is increased by assigning memory interleaving schemes to bank bits based on the classification of bank bits. The present invention supports a memory organization that provides separate memory busses that support independent simultaneous memory transactions, and memory bus segments that allow memory read operations to be overlapped with memory write operations, with each memory bus segment capable of carrying single memory operation at any given time.

Abstract: A memory system has a plurality of memory banks, performs interleaving between the memory banks, and structures a memory by dividing into a plurality of memory blocks which are independently operable. The memory system includes a first address conversion table and a second address conversion table. The first address conversion table is referred by an Operating System and is controllable by dividing an absolute address space into each unit memory capacity. The second address conversion table designates the memory bank and the memory block so that the memory bank and the memory block are commonly used between memory units which forms the interleaving to each other on the basis of an output value of the first address conversion table and the number of the interleaving.

Abstract: A method and apparatus which provides a cache management policy for use with a cache memory for a multi-threaded processor. The cache memory is partitioned among a set of threads of the multi-threaded processor. When a cache miss occurs, a replacement line is selected in a partition of the cache memory which is allocated to the particular thread from which the access causing the cache miss originated, thereby preventing pollution to partitions belonging to other threads.