Processing Element Memory Patents (Class 712/14)
-
Publication number: 20100241758Abstract: Systems and methods for hardware accelerated multi-channel content-based data routing and filter. Data packets are received at a filtering circuit from one or more sources. The packets are filtered in accordance with parameters established by a system user to select specific information of relevance to the system user. The filtering may be facilitated by the assignment of a content identifier to a data element and routing data elements with the assigned content identifier to a memory associated with a processor core for collection and processing. The filtering, collection and processing is performed without calls to an operating system. The data are then distributed to data consumers over a network for further processing and use.Type: ApplicationFiled: February 12, 2010Publication date: September 23, 2010Inventors: John Oddie, Ken Tregidgo
-
Publication number: 20100199068Abstract: Described herein is a reconfigurable processor which uses a distributed configuration memory structure and an operation method thereof in which power consumption is reduced. A processing unit which configures the reconfigurable processor includes a functional unit, a distributed configuration memory, a no-operation (NOP) register, and a controller. The NOP register stores information which represents whether or not a NOP operation is performed at each clock cycle. The controller controls to deactivate the distributed configuration memory at a clock cycle at which a NOP operation is performed.Type: ApplicationFiled: October 30, 2009Publication date: August 5, 2010Inventors: Bernhard Egger, Soo-jung Ryu, Dong-hoon Yoo
-
Patent number: 7765338Abstract: Techniques for providing improved data distribution to and collection from multiple memories are described. Such memories are often associated with and local to processing elements (PEs) within an array processor. Improved data transfer control within a data processing system provides support for radix 2, 4 and 8 fast Fourier transform (FFT) algorithms through data reordering or bit-reversed addressing across multiple PEs, carried out concurrently with FET computation on a digital signal processor (DSP) array by a DMA unit. Parallel data distribution and collection through forms of multicast and packet-gather operations are also supported.Type: GrantFiled: July 9, 2007Date of Patent: July 27, 2010Assignee: Altera CorporationInventors: Edwin Franklin Barry, Nikos P. Pitsianis, Kevin Coopman
-
Patent number: 7734894Abstract: An integrated circuit comprises a plurality of tiles. Each tile comprises a processor including a storage module, wherein the processor is configured to process multiple streams of instructions, a switch including switching circuitry to forward data received over data paths from other tiles to the processor and to switches of other tiles, and to forward data received from the processor to switches of other tiles, and coupling circuitry configured to couple data resulting from processing an instruction from at least one of the streams of instructions to the storage module and to the switch.Type: GrantFiled: April 28, 2008Date of Patent: June 8, 2010Assignee: Tilera CorporationInventors: David Wentzlaff, Anant Agarwal
-
Patent number: 7694151Abstract: An architecture, system and method for operating on encrypted and/or hidden information (e.g., code and/or data). The invention enables creators, owners and/or distributors of proprietary code to keep such code inaccessible to users and user-controlled software programs. A memory architecture includes first and second protected memory spaces, respectively storing operating system instructions and a decrypted version of the encrypted information. The first protected memory space may further store a table linking the locations of the encrypted and/or hidden, decrypted information with a decryption and/or authorization key. The system includes the memory architecture and a processor for executing instructions, and the method loads, stores and operates on the encrypted and/or hidden information according to the memory architecture functionality and/or constraints.Type: GrantFiled: November 20, 2003Date of Patent: April 6, 2010Inventors: Richard C. Johnson, Andrew Morgan, H. Peter Anvin, Linus Torvalds
-
Patent number: 7664928Abstract: A technique that improves both processor performance and associated data bandwidth through user-defined interfaces that can be added to a configurable and extensible microprocessor core. These interfaces can be used to communicate status or control information and to achieve synchronization between the processor and any external device including other processors. These interfaces can also be used to achieve data transfer at the rate of one data element per interface in every clock cycle. This technique makes it possible to design multiprocessor SOC systems with high-speed data transfer between processors without using the memory subsystem. Such a system and design methodology offers a complete shift from the standard bus-based architecture and allows designers to treat processors more like true computational units, so that designers can more effectively utilize programmable solutions rather than design dedicated hardware.Type: GrantFiled: January 19, 2005Date of Patent: February 16, 2010Assignee: Tensilica, Inc.Inventors: Nupur B. Andrews, James Kim, Himanshu A. Sanghavi, William A. Huffman, Eileen Margaret Peters Long
-
Patent number: 7636835Abstract: An integrated circuit comprises a plurality of tiles. Each tile comprises a processor, and a switch including switching circuitry to forward data received over data paths from other tiles to the processor and to switches of other tiles, and to forward data received from the processor to switches of other tiles. The integrated circuit further comprises one or more interface modules including circuitry to transfer data to and from a device external to the tiles; and a sub-port routing network including circuitry to route data between a port of a switch and a plurality of sub-ports coupled to one or more interface modules.Type: GrantFiled: April 14, 2006Date of Patent: December 22, 2009Assignee: Tilera CorporationInventors: Carl G. Ramey, David Wentzlaff, Anant Agarwal
-
Patent number: 7584332Abstract: Embodiments of the present invention provide a class of computer architectures generally referred to as lightweight multi-threaded architectures (LIMA). Other embodiments may be described and claimed.Type: GrantFiled: February 15, 2007Date of Patent: September 1, 2009Assignees: University of Notre Dame du Lac, Cray, Inc.Inventors: Peter M. Kogge, Jay B. Brockman, David Tennyson Harper, III, Burton Smith, Charles David Callahan, II
-
Patent number: 7581079Abstract: A shared memory network for communicating between processors using store and load instructions is described. A new processor architecture which may be used with the shared memory network is also described that uses arithmetic/logic instructions that do not specify any source operand addresses or target operand addresses. The source operands and target operands for arithmetic/logic execution units are provided by independent load instruction operations and independent store instruction operations.Type: GrantFiled: March 26, 2006Date of Patent: August 25, 2009Inventor: Gerald George Pechanek
-
Patent number: 7539845Abstract: An integrated circuit comprises a plurality of tiles. Each tile comprises a processor, and a switch including switching circuitry to forward data received over data paths from other tiles to the processor and to switches of other tiles, and to forward data received from the processor to switches of other tiles. The integrated circuit further comprises an interface coupled to a plurality of the tiles to transfer data between one or more switches of the tiles and one or more switches of tiles in an externally coupled integrated circuit.Type: GrantFiled: April 14, 2006Date of Patent: May 26, 2009Assignee: Tilera CorporationInventors: David Wentzlaff, Carl G. Ramey, Anant Agarwal
-
Publication number: 20090125538Abstract: A method is disclosed for the decoding and encoding of a block-based video bit-stream such as MPEG2, H.264-AVC, VC1, or VP6 using a system containing one or more high speed sequential processors, a homogenous array of software configurable general purpose parallel processors, and a high speed memory system to transfer data between processors or processor sets. This disclosure includes a method for load balancing between the two sets of processors.Type: ApplicationFiled: March 28, 2008Publication date: May 14, 2009Applicant: ELEMENTAL TECHNOLOGIES, INC.Inventors: Jesse J. Rosenzweig, Brian Gregory Lewis
-
Patent number: 7519793Abstract: A method, computer program product and system for facilitating inter-digital signal processing (DSP) data communications. A direct memory access (DMA) controller may be configured to facilitate transfers of data between a first and a second DSP processor core coupled to the DMA controller. The DMA controller may read a data structure, referred to as a “buffer descriptor block,” to perform the data transfer. The buffer descriptor block may store both a source address and a destination address indicating where the data is to be retrieved and stored. The buffer descriptor block may further store a value, e.g., number of bytes, indicating a size of the data to be transferred. The DMA controller may then transfer the data located at the source address in the first DSP processor core, with a size, e.g., number of bytes, indicated from the buffer descriptor block, to the destination address in the second DSP processor core.Type: GrantFiled: November 21, 2007Date of Patent: April 14, 2009Assignee: International Business Machines CorporationInventors: Youseff Abdelilah, Bartholomew Blaner, Gordon Taylor Davis, Jeffrey Haskell Derby, Joseph Franklin Garvey, Malcolm Scott Ware, Hua Ye
-
Patent number: 7503046Abstract: A method of determining an interleave pattern for n lots of A and y lots of B, when n plus y equals a power of two such that the expression 2z?n may be used to represent the value of y, includes generating a key including the reverse bit order of a serially indexed count from 0 to 2z. An interleave pattern can be generated from the key in which all values less than n are replace by A and all other values are replaced by B. The key can be used to generate a table that contains all possible combinations of values of A and B. The table can then be stored such that an interleave pattern can be automatically selected based on either the number of lots of A or the number of lots of B.Type: GrantFiled: October 20, 2003Date of Patent: March 10, 2009Assignee: Micron Technology, Inc.Inventor: Mark Beaumont
-
Patent number: 7493468Abstract: A method for broadcasting instructions/data to a plurality of processors in a multiprocessor device via aliasing is provided. In order to broadcast data to a plurality of processors, a control processor writes to the registers that store the identifiers of the processors and sets two or more of these registers to a same value. The control processor may write the desired data/instructions to be broadcast to a portion of memory corresponding to the starting address associated with the processor identifier of the two or more processors. When the two or more processors look for a starting address of their local store from which to read, the two or more processors will identify the same starting address, essentially aliasing the memory region. The two or more processors will read the instructions/data from the same aliased memory region starting at the identified starting address and process the same instructions/data.Type: GrantFiled: June 1, 2006Date of Patent: February 17, 2009Assignee: International Business Machines CorporationInventors: Adam P. Burns, Steven L. Roberts, Christopher J. Spandikow, Todd E. Swanson
-
Patent number: 7461236Abstract: An integrated circuit includes a plurality of tiles. Each tile comprises a processor; and a switch including switching circuitry to forward data over data paths from other tiles to the processor and to switches of other tiles according to a switch instruction indicating an input port to which each of multiple output ports of the switch is to be coupled. The switch is able to operate in a first mode in which successive input data arriving at the switch are forwarded according to a different switch instruction, and a second mode in which successive input data arriving at the switch are forwarded according to the same switch instruction.Type: GrantFiled: December 21, 2005Date of Patent: December 2, 2008Assignee: Tilera CorporationInventor: David Wentzlaff
-
Publication number: 20080282060Abstract: A command engine for an active memory receives high level tasks from a host and generates corresponding sets of either DCU commands to a DRAM control unit or ACU commands to a processing array control unit. The DCU commands include memory addresses, which are also generated by the command engine, and the ACU command include instruction memory addresses corresponding to an address in an array control unit where processing array instructions are stored.Type: ApplicationFiled: July 9, 2008Publication date: November 13, 2008Applicant: Micron TechnologyInventor: Graham Kirsch
-
Patent number: 7451292Abstract: Quantum gaps exist between an origin and a destination that heretofore have prevented reliably utilizing the advantages of quantum computing. To predict the outcome of instructions with precision, the input data, preferably a qubit, is collapsed to a point value within the quantum gap based on a software instruction. After collapse the input data is restructured at the destination, wherein dynamics of restructuring are governed by a plurality of gap factors as follows: computational self-awareness; computational decision logic; computational processing logic; computational and network protocol and logic exchange; computational and network components, logic and processes; provides the basis for excitability of the Gap junction and its ability to transmit electronic and optical impulses, integrates them properly, and depends on feedback loop logic; computational and network component and system interoperability; and embodiment substrate and network computational physical topology.Type: GrantFiled: August 8, 2003Date of Patent: November 11, 2008Inventor: Thomas J Routt
-
Patent number: 7428629Abstract: A memory management mechanism a nodal having multiple processors in a massively parallel computer system dynamically configures nodal memory on demand. A respective variable-sized subdivision of nodal memory is associated with each processor in the node. A processor may request additional memory, and the other processor(s) may grant or veto the request. If granted, the requested memory is added to the subdivision of the requesting processor. A processor can only access memory within its own subdivision. Preferably, each subdivision contains a daemon which monitors memory usage and generates requests for additional memory.Type: GrantFiled: August 8, 2006Date of Patent: September 23, 2008Assignee: International Business Machines CorporationInventors: Jay Symmes Bryant, Nicholas Bruce Goracke, Daniel Paul Kolz, Dharmesh J. Patel
-
Patent number: 7409528Abstract: A DSP (Digital Signal Processing) architecture with a wide memory bandwidth and a memory mapping method thereof. The DSP architecture includes: a first communication port; first, second, and third memory devices, which are connected with the first communication port and are arranged in a first row direction of the DSP architecture; a fourth memory device, a calculation element, and a fifth memory device, which are arranged in a second row direction below a first row direction of the DSP architecture; and sixth, seventh, and eighth memory devices, which are connected with the first communication port and arranged in a third row direction of the DSP architecture, wherein the calculation element is connected with the first through the eight memory devices.Type: GrantFiled: March 25, 2004Date of Patent: August 5, 2008Assignee: Samsung Electronics Co., Ltd.Inventors: Hyun-kyu Yun, Han-tak Kwak
-
Patent number: 7409529Abstract: A system and method for using wider data paths within Processing Elements (PEs) of a Massively Parallel Array (MPP) to speed the computational performance of the PEs and the MPP array while still allowing for use of the simple 1-bit interconnection network to transfer data between PEs in the MPP is disclosed. A register having a data width equal to the data width of the PE for holding data for movement from one PE to another is provided in each PE. The register can be loaded in parallel within the PE, and operated as a shift register to transfer a fill data width word from one PE to another PE using a 1-bit wide serial interconnection.Type: GrantFiled: November 28, 2006Date of Patent: August 5, 2008Assignee: Micron Technology, Inc.Inventor: Graham Kirsch
-
Patent number: 7404066Abstract: A command engine for an active memory receives high level tasks from a host and generates corresponding sets of either DCU commands to a DRAM control unit or ACU commands to a processing array control unit. The DCU commands include memory addresses, which are also generated by the command engine, and the ACU command include instruction memory addresses corresponding to an address in an array control unit where processing array instructions are stored.Type: GrantFiled: January 24, 2007Date of Patent: July 22, 2008Assignee: Micron Technology, Inc.Inventor: Graham Kirsch
-
Patent number: 7398368Abstract: Atomic operations may be implemented on a processor system having a main memory and two or more processors including a power processor element (PPE) and a synergistic processor element (SPE) that operate on different sized register lines. A main memory address containing a primitive is divided into a parity byte and two or more portions, wherein the parity byte includes at least one bit. A value of the parity byte determines which of the two or more portions is a valid portion and which of them is an invalid portion. The primitive is of a memory size that is larger than a maximum size for atomic operation with the PPE and less than or equal to a maximum size for atomic operation with the SPE. Read with reservation and conditional write instructions are used by both the PPE and SPE to access or update a value of the atomic.Type: GrantFiled: December 1, 2005Date of Patent: July 8, 2008Assignee: Sony Computer Entertainment Inc.Inventors: James E. Marr, John P. Bates, Attila Vass, Tatsuya Iwamoto
-
Patent number: 7386689Abstract: A method and apparatus for connecting the processor array of an MPP array to a memory such that data conversion by software is not necessary, and the data can be directly stored in either a normal mode or vertical mode in the memory is disclosed. A connection circuit is provided in which multiple PEs share their connections to multiple data bits in the memory array. Each PE is associated with a plurality of memory buffer registers, which stores data read from (or to be written to) one or two memory data bits. In horizontal (normal) mode connection the memory bits are selected so that all the bits of a given byte are stored in the same PE, i.e., each set of buffer registers associated with a respective PE contains one byte as seen by an external device. In vertical (bit serial) mode, each set of buffer registers contains the successive bits at successive locations in the memory corresponding to that PEs position in the memory word.Type: GrantFiled: May 4, 2005Date of Patent: June 10, 2008Assignee: Micron Technology, Inc.Inventor: Graham Kirsch
-
Patent number: 7369683Abstract: In an imaging device of the present invention, an imaging element 2 is driven in a thinning read-out mode for reading out signal charges from a subset of pixels, or in an all-pixels read-out mode for reading out signal charges from all pixels. When the imaging element 2 is driven in the thinning read-out mode, the imaging device processes and records a series of first image data that is obtained by reading out signal charges from the subset of pixels and that constitutes the moving images. When the imaging element 2 is driven in the all-pixels read-out mode, the imaging device processes and records a series of second image data constituting moving images after the number of pixels of the second image data is thinned, and processes and records a portion of the second image data as a still image without thinning when an instruction to pick up the still image is given while picking up the moving images.Type: GrantFiled: August 4, 2004Date of Patent: May 6, 2008Assignee: Sanyo Electric Co., Ltd.Inventors: Akio Kobayashi, Shigeru Miki
-
Patent number: 7370046Abstract: Disclosed are a sort processing method and a sort processing apparatus, which, in a computer or data processing, compare magnitudes of pieces of data input by hardware, rearrange the pieces of data in accordance with a predetermined order and output the rearranged pieces of data. The sort processing apparatus includes first basic cells, each of which is composed of a first data comparator for comparing magnitudes of pieces of input data with each other and for outputting a first select signal, and a first data selector for rearranging said compared pieces of input data in a magnitude order on the basis of said first select signal, wherein said first basic cells having the same number as that of combinations of pieces of input data to be compared are arranged in a pipeline configuration.Type: GrantFiled: February 5, 2002Date of Patent: May 6, 2008Assignee: Sony CorporationInventor: Masatoshi Imai
-
Publication number: 20080104368Abstract: A storage element has data protection functionality for receiving a data-writing and a data-reading from a functional module. The storage element comprises a storage unit that has a memory region with a predetermined capacity for storing the data and stores the data written by the functional module, a data amount management register that stores an amount of the data written by the functional module so as to be readable from the functional module and a control unit that controls, when the data stored in the storage unit is read by the functional module, to disable a data-reading from a portion of the memory region of the storage unit where data corresponding to the read data is stored, until a data-writing is performed by the functional module.Type: ApplicationFiled: February 7, 2007Publication date: May 1, 2008Applicant: Fujitsu LimitedInventor: Eiji Hasegawa
-
Patent number: 7363304Abstract: A method and system for sorting a number of items in a computer system. The sort is based on a plurality of values of a key. Each item has a value of the plurality of values. The method and system include providing plurality of stages, providing at least one switch coupled between the plurality of stages, and providing a final switch coupled with a last stage. Each of the plurality of stages has a pair of first-in-first-out buffers (FIFOs) that store twice as many of the items as the pair of FIFOs in a previous stage. Each switch is for merging and sorting a first portion of the number of items from the pair of FIFOs in the previous stage based on the key and for providing the first portion of the number plurality of items to a first FIFO of the pair of FIFOs of the stage in order.Type: GrantFiled: June 29, 2004Date of Patent: April 22, 2008Assignee: Broadcom CorporationInventors: Michael C. Lewis, Aleksandr Movshovich
-
Publication number: 20080046684Abstract: A uniprocessor that can run multiple threads (programs) simultaneously is achieved by use of a plurality of low-frequency minicore processors, each minicore for receiving a respective thread from a high-frequency cache and processing the thread. A superscalar processor may be used in conjunction with the uniprocessor to process threads requiring high throughput.Type: ApplicationFiled: August 17, 2006Publication date: February 21, 2008Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventor: Philip G. Emma
-
Patent number: 7325122Abstract: A method, computer program product and system for facilitating inter-digital signal processing (DSP) data communications. A direct memory access (DMA) controller may be configured to facilitate transfers of data between a first and a second DSP processor core coupled to the DMA controller. The DMA controller may read a data structure, referred to as a “buffer descriptor block,” to perform the data transfer. The buffer descriptor block may store both a source address and a destination address indicating where the data is to be retrieved and stored. The buffer descriptor block may further store a value, e.g., number of bytes, indicating a size of the data to be transferred. The DMA controller may then transfer the data located at the source address in the first DSP processor core, with a size, e.g., number of bytes, indicated from the buffer descriptor block, to the destination address in the second DSP processor core.Type: GrantFiled: February 20, 2004Date of Patent: January 29, 2008Assignee: International Business Machines CorporationInventors: Youseff Abdelilah, Bartholomew Blaner, Gordon Taylor Davis, Jeffrey Haskell Derby, Joseph Franklin Garvey, Malcolm Scott Ware, Hua Ye
-
Patent number: 7272691Abstract: A data processor apparatus comprises a plurality of processor elements, a memory having a plurality of parts, and a first switching element associated with the first processor element for switchably coupling the first processor element to its associated memory part for at least one of read and write access.Type: GrantFiled: January 17, 2007Date of Patent: September 18, 2007Assignee: Mtekvision Co., Ltd.Inventors: Malcolm Stewart, Eric Giernalcyzk, Richard Beriault
-
Publication number: 20070198785Abstract: Embodiments of the present invention provide a class of computer architectures generally referred to as lightweight multi-threaded architectures (LIMA). Other embodiments may be described and claimed.Type: ApplicationFiled: February 15, 2007Publication date: August 23, 2007Inventors: Peter M. Kogge, Jay B. Brockman, David Tennyson Harper, Burton Smith, Charles David Callahan
-
Patent number: 7237087Abstract: An expanded arithmetic and logic unit (EALU) with special extra functions is integrated into a configurable unit for performing data processing operations. The EALU is configured by a function register, which greatly reduces the volume of data required for configuration. The cell can be cascaded freely over a bus system, the EALU being decoupled from the bus system over input and output registers. The output registers are connected to the input of the EALU to permit serial operations. A bus control unit is responsible for the connection to the bus, which it connects according to the bus register. The unit is designed so that distribution of data to multiple receivers (broadcasting) is possible. A synchronization circuit controls the data exchange between multiple cells over the bus system. The EALU, the synchronization circuit, the bus control unit, and registers are designed so that a cell can be reconfigured on site independently of the cells surrounding it.Type: GrantFiled: May 28, 2002Date of Patent: June 26, 2007Assignee: Pact XPP Technologies AGInventors: Martin Vorbach, Robert Münch
-
Patent number: 7181593Abstract: A command engine for an active memory receives high level tasks from a host and generates corresponding sets of either DCU commands to a DRAM control unit or ACU commands to a processing array control unit. The DCU commands include memory addresses, which are also generated by the command engine, and the ACU command include instruction memory addresses corresponding to an address in an array control unit where processing array instructions are stored.Type: GrantFiled: July 28, 2003Date of Patent: February 20, 2007Assignee: Micron Technology, Inc.Inventor: Graham Kirsch
-
Patent number: 7149876Abstract: A system and method for using wider data paths within Processing Elements (PEs) of a Massively Parallel Array (MPP) to speed the computational performance of the PEs and the MPP array while still allowing for use of the simple 1-bit interconnection network to transfer data between PEs in the MPP is disclosed. A register having a data width equal to the data width of the PE for holding data for movement from one PE to another is provided in each PE. The register can be loaded in parallel within the PE, and operated as a shift register to transfer a full data width word from one PE to another PE using a 1-bit wide serial interconnection.Type: GrantFiled: June 9, 2004Date of Patent: December 12, 2006Assignee: Micron Technology, Inc.Inventor: Graham Kirsch
-
Patent number: 7100020Abstract: An integrated circuit (203) for use in processing streams of data generally and streams of packets in particular. The integrated circuit (203) includes a number of packet processors (307, 313, 303), a table look up engine (301), a queue management engine (305) and a buffer management engine (315). The packet processors (307, 313, 303) include a receive processor (421), a transmit processor (427) and a risc core processor (401), all of which are programmable. The receive processor (421) and the core processor (401) cooperate to receive and route packets being received and the core processor (401) and the transmit processor (427) cooperate to transmit packets. Routing is done by using information from the table look up engine (301) to determine a queue (215) in the queue management engine (305) which is to receive a descriptor (217) describing the received packet's payload.Type: GrantFiled: May 7, 1999Date of Patent: August 29, 2006Assignee: Freescale Semiconductor, Inc.Inventors: Thomas B. Brightman, Andrew T. Brown, John F. Brown, James A. Farrell, Andrew D. Funk, David J. Husak, Edward J. McLellan, Mark A. Sankey, Paul Schmitt, Donald A. Priore
-
Patent number: 7072357Abstract: A single instruction, multiple data (SIMD) architecture for controlling the processing of plurality of data streams in a digital subscriber line (DSL) system has a memory for storing the data from the channels, a processor operatively coupled with the memory for processing data from the data streams, and a controller for controlling the processor. Storing the data in the memory de-couples the operating rate of the processor and the operating rate of the data streams.Type: GrantFiled: March 27, 2001Date of Patent: July 4, 2006Assignee: Ciena CorporationInventors: Fred Stacey, Christian Bourget, Yatish Kumar
-
Patent number: 7069416Abstract: A single chip active memory includes a plurality of memory stripes, each coupled to a full word interface and one of a plurality of processing element (PE) sub-arrays. The large number of couplings between a PE sub-array and its associated memory stripe are managed by placing the PE sub-arrays so that their data paths run at right angle to the data paths of the plurality of memory stripes. The data lines exiting the memory stripes are run across the PE sub-arrays on one metal layer. At the appropriate locations, the data lines are coupled to another orthogonally oriented metal layer to complete the coupling between the memory stripe and its associated PE sub-array. The plurality of PE sub-arrays are mapped to form a large logical array, in which each PE is coupled to four other PEs. Physically distant PEs are coupled using current mode differential logical couplings an drivers to insure good signal integrity at high operational speeds. Each PE contains a small DRAM register array.Type: GrantFiled: June 4, 2004Date of Patent: June 27, 2006Assignee: Micron Technology, Inc.Inventor: Graham Kirsch
-
Patent number: 7065215Abstract: In a microprocessor, a program key for decrypting a program and a data key for encrypting/decrypting data processed by the program are handled as cryptographically inseparable pair inside the microprocessor, so that it becomes possible for the microprocessor to protect processes that actually execute the program, without an intervention of the operating system, and it becomes possible to conceal secret information of the program not only from the other user program but also from the operating system.Type: GrantFiled: October 30, 2001Date of Patent: June 20, 2006Assignee: Kabushiki Kaisha ToshibaInventors: Kenji Shirakawa, Mikio Hashimoto, Keiichi Teramoto, Satoshi Ozaki, Kensaku Fujimoto
-
Method and system for accelerating power complementary cumulative distribution function measurements
Patent number: 7058540Abstract: Data values representing the (I2+Q2) values are converted to floating-point representations and a histogram of the floating-point numbers is generated. The count for each histogram bin in the histogram is stored in a memory. Each floating-point number acts as an address for a corresponding histogram bin in the memory. The accumulated counts in the histogram bins are then grouped into a desired number of CCDF bins, and the CCDF curve is derived from the histogram data. Grouping the histogram bins into the CCDF bins may include combining one or more histogram bins into a single CCDF bin. Linear interpolation is used to divide a count value in a histogram bin between two CCDF bins when the histogram bin does not align with a single CCDF bin.Type: GrantFiled: December 15, 2003Date of Patent: June 6, 2006Assignee: Agilent Technologies, Inc.Inventors: Yi He, Gerald J. Ringel, Howard E. Hilton, Brian Barton -
Patent number: 7020764Abstract: A useful semiconductor processing device (LSI) is capable of implementing the precise setting of signals at the final stage of user system development and enabling the user to build a logic circuit in the device in a very short time. The LSI includes a CPU, a flash memory which is a nonvolatile memory, a programmable logic which is a SRAM-type field programmable gate array, and a configuration circuit which implements the logic circuit configuration operation. At the event of power-on reset, logic building data stored in the flash memory is transferred to the programmable logic to establish a logic circuit in it under control of the configuration circuit, so that the logic circuit built in the programmable logic can be used immediately after the power-on reset of the device.Type: GrantFiled: July 18, 2003Date of Patent: March 28, 2006Assignee: Renesas Technology Corp.Inventors: Hideo Kubota, Takanaga Yamazaki
-
Patent number: 7010668Abstract: General purpose flags (ACFs) are defined and encoded utilizing a hierarchical one-, two- or three-bit encoding. Each added bit provides a superset of the previous functionality. With condition combination, a sequential series of conditional branches based on complex conditions may be avoided and complex conditions can then be used for conditional execution. ACF generation and use can be specified by the programmer. By varying the number of flags affected, conditional operation parallelism can be widely varied, for example, from mono-processing to octal-processing in VLIW execution, and across an array of processing elements (PE)s. Multiple PEs can generate condition information at the same time with the programmer being able to specify a conditional execution in one processor based upon a condition generated in a different processor using the communications interface between the processing elements to transfer the conditions.Type: GrantFiled: August 28, 2003Date of Patent: March 7, 2006Assignee: PTS CorporationInventors: Thomas L. Drabenstott, Gerald G. Penchanek, Edwin F. Barry, Charles W. Kurak, Jr.
-
Patent number: 6986020Abstract: Techniques for providing improved data distribution to and collection from multiple memories are described. Such memories are often associated with and local to processing elements (PEs) within an array processor. Improved data transfer control within a data processing system provides support for radix 2, 4 and 8 fast Fourier transform (FFT) algorithms through data reordering or bit-reversed addressing across multiple PEs, carried out concurrently with FFT computation on a digital signal processor (DSP) array by a DMA unit. Parallel data distribution and collection through forms of multicast and packet-gather operations are also supported.Type: GrantFiled: September 21, 2004Date of Patent: January 10, 2006Assignee: PTS CorporationInventors: Edwin F. Barry, Nikos P. Pitsianis, Kevin Coopman
-
Patent number: 6967950Abstract: In a network of digital signal processor nodes connected in a peer-to-peer relationship, a data packet sent to a node causes a return transmission from that node. The requester digital signal processor sends a data packet to a target digital signal processor. Upon arrival at the target digital signal processor, its receiver drives the arriving request packet into an I/O memory and triggers a transmitter interrupt. Next, the pull interrupt causes the transmitter to execute on a next packet boundary the pull request packet. Finally, the execution of the pull request causes the transmitter to pull a portion of the local I/O memory and send it back to the requester digital signal processor. The same physical portion of the I/O memory is overlaid with two logical uses, a receiver channel and a transmitter code block.Type: GrantFiled: July 13, 2001Date of Patent: November 22, 2005Assignee: Texas Instruments IncorporatedInventors: Peter Galicki, Cheryl S. Shepherd, Jonathan H. Thorn
-
Patent number: 6912626Abstract: A method and apparatus for connecting the processor array of an MPP array to a memory such that data conversion by software is not necessary, and the data can be directly stored in either a normal mode or vertical mode in the memory is disclosed. A connection circuit is provided in which multiple PEs share their connections to multiple data bits in the memory array. Each PE is associated with a plurality of memory buffer registers, which stores data read from (or to be written to) one or two memory data bits. In horizontal (normal) mode connection the memory bits are selected so that all the bits of a given byte are stored in the same PE, i.e., each set of buffer registers associated with a respective PE contains one byte as seen by an external device. In vertical (bit serial) mode, each set of buffer registers contains the successive bits at successive locations in the memory corresponding to that PEs position in the memory word.Type: GrantFiled: August 31, 2000Date of Patent: June 28, 2005Assignee: Micron Technology, Inc.Inventor: Graham Kirsch
-
Patent number: 6901491Abstract: In one embodiment, a server is provided. The server includes multiple application processor chips. Each of the multiple application processor chips includes multiple processing cores. Multiple memories corresponding to the multiple processor chips are included. The multiple memories are configured such that one processor chip is associated with one memory. A plurality of fabric chips enabling each of the multiple application processor chips to access any of the multiple memories are included. The data associated with one of the multiple application processor chips is stored across each of the multiple memories. In one embodiment, the application processor chips include a remote direct memory access (RDMA) and striping engine. The RDMA and striping engine is configured to store data in a striped manner across the multiple memories. A method for allowing multiple processors to exchange information through horizontal scaling is also provided.Type: GrantFiled: October 16, 2002Date of Patent: May 31, 2005Assignee: Sun Microsystems, Inc.Inventors: Leslie D. Kohn, Michael K. Wong
-
Patent number: 6839648Abstract: An SRAM efficient ATE system that performs high speed nested loops without constraints on loop size or modularity and that loops and/or branches from any vector in a multiple vector accessed word to any vector in another multiple vector accessed word without incurring any time displacement. In one embodiment, the maximum required vector rate is less than or equal the average sustained data rate of the SDRAM and is less than or equal to the maximum access rate of the dual port SRAM's memory B. The output of the SDRAM's memory A consists of one control word and one vector (nV=1). The I/O port widths of the SRAM's memory B are the same. In another embodiment, the maximum required vector rate is greater than the average sustained data rate of the SDRAM's memory A, but is equal to or less than the maximum access rate of the SRAM's memory B. The output of the SDRAM's memory A consists of multiple control words and vectors. The input port of the SRAM's memory B is some multiple of the output port width.Type: GrantFiled: May 1, 2003Date of Patent: January 4, 2005Assignee: Inovys CorporationInventor: Philip D. Burlison
-
Publication number: 20040215928Abstract: A method for transposing data in a plurality of processing elements is comprised of a plurality of shifting operations and a plurality of storing operations. The shifting and storing operations are coordinated to enable data to be stored along a diagonal of processing elements from a first direction or first pair of directions and to be output from the diagonal in a second direction or a second pair of directions perpendicular to the first pair of directions, respectively. The plurality of storing operations are responsive to the processing elements’ positions. The first and second pairs of directions are selected from among the dimensions of the array, e.g., the +x/−x, +z/−z and +y/−y pairs of directions.Type: ApplicationFiled: October 20, 2003Publication date: October 28, 2004Inventor: Mark Beaumont
-
Patent number: 6795909Abstract: Processing element to processing element switch connection control is described using a receive model that precludes communication hazards from occurring in a synchronous MIMD mode of operation. Such control allows different communication topologies and various processing effects such as an array transpose, hypercomplement or the like to be efficiently achieved utilizing architectures, such as the manifold array processing architecture. An encoded instruction method reduces the amount of state information and setup burden on the programmer taking advantage of the recognition that the majority of algorithms will use only a small fraction of all possible mux settings available. Thus, by means of transforming the PE identification based upon a communication path specified by a PE communication instruction an efficient switch control mechanism can be used.Type: GrantFiled: April 1, 2002Date of Patent: September 21, 2004Assignee: PTS CorporationInventors: Edwin F. Barry, Gerald G. Pechanek, Thomas L. Drabenstott, Edward A. Wolff, Nikos P. Pitsianis, Grayson Morris
-
Patent number: 6775667Abstract: A method and system for sorting a number of items in a computer system is described. The sort is based on values of a key. Each item has a value. The method and system include providing stages, providing switch(es) coupled between the stages, and providing a final switch coupled with a last stage. Each stage has a pair of first-in-first-out buffers (FIFOs) that store twice as many of the items as the FIFOs in a previous stage. The switch merges and sorts a first portion of the number of items from the pair of FIFOs in the previous stage based on the key and provides the first portion of the number of items to a first FIFO of the stage in order. The switch performs an analogous function for a second FIFO in the stage. The last switch merges and sorts a third portion of the number of items to provide the number of items in order.Type: GrantFiled: June 8, 2000Date of Patent: August 10, 2004Assignee: Broadcom CorporationInventors: Michael C. Lewis, Aleksandr Movshovich
-
Patent number: 6760831Abstract: General purpose flags (ACFs) are defined and encoded utilizing a hierarchical one-, two- or three-bit encoding. Each added bit provides a superset of the previous functionality. With condition combination, a sequential series of conditional branches based on complex conditions may be avoided and complex conditions can then be used for conditional execution. ACF generation and use can be specified by the programmer. By varying the number of flags affected, conditional operation parallelism can be widely varied, for example, from mono-processing to octal-processing in VLIW execution, and across an array of processing elements (PE)s. Multiple PEs can generate condition information at the same time with the programmer being able to specify a conditional execution in one processor based upon a condition generated in a different processor using the communications interface between the processing elements to transfer the conditions.Type: GrantFiled: April 1, 2002Date of Patent: July 6, 2004Assignee: PTS CorporationInventors: Thomas L. Drabenstott, Gerald G. Pechanek, Edwin F. Barry, Charles W. Kurak, Jr.