Abstract: A method for generating the reflection of data in a plurality of processing elements comprises shifting the data along, for example, each row in the array until each processing element in the row has received all the data held by every other processing element in that row. Each processing element stores and outputs final data as a function of its position in the row. A similar reflection along a horizontal line can be achieved by shifting data along columns instead of rows. Also disclosed is a method for reflecting data in a matrix of processing elements about a vertical line comprising shifting data between processing elements arranged in rows. An initial count is set in each processing element according to the expression (2×Col_Index)×Mod (array size). In one embodiment, a counter counts down from the initial count in each processing element as a function of the number of shifts that have peen performed. Output is selected as a function of the current count.

Abstract: An integrated circuit architecture for multimedia processing. A single integrated circuit (IC) operates as a system or subsystem, and is adaptable to processing a variety of multimedia algorithms, whether proprietary or open. Hard macros, either analog or digital, can be incorporated. The IC can also contain audio/video CODECs to suit different standards, as well as other peripheral devices which may be required for multimedia applications. An electronic component (e.g., integrated circuit) incorporating the technique is suitably included in a system or subsystem having electrical functionality, such as general purpose computers, telecommunications devices, and the like.

Abstract: A programmable interface controller for transmitting data to an output device that is suitable in both fully synchronous systems and in systems that span clock domains. The illustrative embodiments comprise: receiving a plurality of field identifiers and an indication of an order by which each of the plurality of field identifiers is to be uniquely associated with each field in a sequence of fields; receiving a stream of data that comprises the sequence of fields and an indication of the boundary between successive fields in the sequence of fields; and processing each field in the stream of data in accordance with the field identifier uniquely associated with that field.

Abstract: A method and computer graphics system capable of implementing multiple pipelines for the parallel processing of graphics data. For certain data, a requirement may exist that the data be processed in order. The graphics system may use a set of tokens to reliably switch between ordered and unordered data modes. Furthermore, the graphics system may be capable of super-sampling and performing real-time convolution. In one embodiment, the computer graphics system may comprise a graphics processor, a sample buffer, and a sample-to-pixel calculation unit. The graphics processor may be configured to receive graphics data and to generate a plurality of samples for each of a plurality of frames. The sample buffer, which is coupled to the graphics processor, may be configured to store the samples. The sample-to-pixel calculation unit is programmable to generate a plurality of output pixels by filtering the rendered samples using a filter.

Abstract: 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.

Abstract: A method and apparatus for providing local control of processing elements in a network of multiple context processing elements (MCPEs). A MCPE stores configuration memory contexts and maintains data of a current configuration. State information is received from at least one other MCPE. A configuration control signal is generated in response to the state information and current configuration data. A MCPE is selected in response to the configuration control signal to control the MCPE. Each MCPE in the networked array has an assigned physical and virtual identification. Data comprising control data, configuration data, an address mask, and a destination identification is transmitted to a MCPE. The transmitted address mask is applied to either a physical or a virtual identification, and to a destination identification. The masked physical or virtual identification is compared to the masked destination identification.

Abstract: A multiplicity of processor elements that are arranged in rows and columns individually execute data processing in accordance with instruction codes that are individually set as data and supply event data as output. A state control unit is composed of a plurality of units that successively switch the instruction codes of the multiplicity of processor elements in accordance with a computer program and the event data, these state control units communicating with each other to realize linked operation as necessary. An event distributing means distributes event data to this plurality of state control units that intercommunicate to realize linked operation, whereby the plurality of state control units can realize linked operation to control a large-scale state transition.

Abstract: A method and an apparatus for configuration of multiple context processing elements (MCPEs)are described. According to one aspect of the invention, the structure that joins the MCPE cores into a complete array in one embodiment is actually a set of several mesh-like interconnect structures. Each interconnect structure forms a network, and each network is independent in that it uses different paths, but the networks join at MCPE input switches. The network structure of one embodiment of the present invention is comprised of a local area broadcast network (level 1), a switched interconnect network (level 2), a shared bus network (level 3), and a broadcast network. In one embodiment, the level 3 network is used to carry configuration data for the MCPEs while the broadcast network is used to carry configuration data for the level 3 network drivers and switches. In one embodiment, the level 3 network is bidirectional and dynamically routable.

Abstract: To execute all processing in an array section of an array-type processor, each processor must execute processing of different types, i.e., processing of an operating unit and processing of a random logic circuit, which limits its size and processing performance. A data path section including processors arranged in an array are connected via programmable switches to primarily execute processing of operation and a state transition controller configured to easily implement a state transition function to control state transitions are independently disposed. These sections are configured in customized structure for respective processing purposes to efficiently implement and achieve the processing of operation and the control operation.

Abstract: A parallel-processing apparatus includes a plurality of cells, variable-delay circuits, a signal output unit, a delay counter, and an accumulation unit. Each cell has a processing circuit for performing arbitrary processing. The variable-delay circuits change the signal propagation delay in accordance with the processing results of the processing circuits. The signal output unit outputs a measurement input signal to the first variable-delay circuit of a variable-delay circuit array. The delay counter receives the measurement input signal output form the signal output unit and a measurement output signal output from the variable-delay circuit array, and obtains the signal propagation delay time of the variable-delay circuit array upon the basis of the measurement input and output signals. The accumulation unit accumulates the processing results of the processing circuits. A parallel processing method is also disclosed.

Abstract: A messaging scheme that conserves system memory bandwidth during a memory read operation in a multiprocessing computer system is described. A source processing node sends a memory read command to a target processing node to read data from a designated memory location in a system memory associated with the target processing node. The target node transmits a read response to the source node containing the requested data and also concurrently transmits a probe command to one or more of the remaining nodes in the multiprocessing computer system. In response to the probe command each remaining processing node checks whether the processing node has a cached copy of the requested data. If a processing node, other than the source and the target nodes, finds a modified cached copy of the designated memory location, that processing node responds with a memory cancel response sent to the target node and a read response sent to the source node.

Abstract: An associative processor includes a plurality of arrays of content addressable memory (CAM) cells and a plurality of tags registers in a tags logic block. Different tags registers are associated with different CAM cell arrays at will, to support parallel execution of the same or different arithmetical operations on two or more CAM cell arrays, and to support pipelined arithmetical operations by having two CAM cell arrays share a tags register to transfer data from one CAM cell array to another using appropriate compare and write operations. All the CAM cell arrays share the same mask and pattern registers. Preferably, at least one tags register is located physically between two of the CAM cell arrays.

Abstract: The present invention relates to the control of an array of processing elements in a parallel processor using row and column select lines. For each column in the array, a column select line connects to all of the processing elements in the column. For each row in the array, a row select line connecting to all of the processing elements in the row. A processing element in the array may be selected by activation of its row and column select lines.

Abstract: A method, system, and apparatus of recording information generated by a data processing system prior to completion enablement of programmed input/output services for the data processing system is provided. In one embodiment, a service processor receives an attention interrupt from a host processor. The service processor then stops the operation of all host processors in the data processing system. The service processor then reads the information, such as a system checkpoint, from a buffer within the host processor's system memory and writes the information into a non-volatile random access memory as well as displays the information to a user via a video display. The service processor then restarts the host processors.

Abstract: A system and method for synchronization of video raster display outputs from multiple PC graphics subsystems to facilitate synchronized output onto multiple displays are disclosed. The system and method allow multiple graphics subsystems, in a single or multiple chassis, to be used to provide multiple synchronized view ports of a single 3D database or a wide desktop with reduced inter-monitor artifacts and interference.

Abstract: A data processor controller comprising a first processor for generating data processor instructions at a first rate and an instruction multiplying circuit for receiving the data processor instructions at the first rate and being a arranged to multiply the instructions and forward the multiplied instructions to a data processor at a second rate substantially greater than the first rate is disclosed. The first processor outputs a stream of compounded data processor instructions and the multiplying circuit separates the compounded instructions into a single stream of individual instructions in a non-compounded format. Multiplication is effectively achieved by repeating both single and blocks of data processor instructions. The effective bandwidth between the first processor and the data processor is multiplied by the multiplying circuit which takes advantage of the different sizes of data pathways available between the first processor and the data processor.

Abstract: An apparatus for concurrently executing controller single instruction single data (SISD) instructions and single instruction multiple data (SIMD) processing element instructions comprising a combined controller and processing element. At least first and second simplex instructions each comprise a mode of operation bit, said mode of operation bit in the first simplex instruction specifying a controller SISD operation for execution by the controller, and the mode of operation bit in the second simplex instruction specifying a procesing element SIMD operation for execution by the processsing element. A very long instruction word (VLIW) contains said at least first and second simplex instructions.

Abstract: Irregularities are provided in at least one dimension of a torus or mesh network for lower average path length and lower maximum channel load while increasing tolerance for omitted end-around connections. In preferred embodiments, all nodes supported on each backplane are connected in a single cycle which includes nodes on opposite sides of lower dimension tori. The cycles in adjacent backplanes hop different numbers of nodes.

Abstract: A data-processing arrangement comprises a plurality of elementary circuits such as processing circuits [PRC] and memory circuits [MEM]. The data-processing arrangement further comprises a controller [MCP]. The controller [MCP] is programmed to successively apply, in response to a task-initialization data [TID], control data [CD] to different subsets of elementary circuits. This causes the data-processing arrangement to process a block of data [DB] in accordance with a certain data-processing chain [DPC]. Each subset of elementary circuits implements a different element [E] of the data-processing chain [DPC].

Abstract: An indirect VLIW (iVLIW) architecture is described which contains a minimum of two instruction memories. The first instruction memory (SIM) contains short-instruction-words (SIWs) of a fixed length. The second instruction memory (VIM), contains very-long-instruction-words (VLIWs) which allow execution of multiple instructions in parallel. Each SIW may be fetched and executed as an independent instruction by one of the available execution units. A special class of SIW is used to reference the VIM indirectly to either execute or load a specified VLIW instruction (called an “XV” instruction for “eXecute VLIW”, or LV for “Load VLIW”). In these cases, the SIW instruction specifies how the location of the VLIW is to be accessed. Other aspects of this approach relate to the application of data memory addressing techniques for execution or loading of VLIWs that parallel the addressing modes used for data memory accesses.

Abstract: A hierarchical instruction set architecture (ISA) provides pluggable instruction set capability and support of array processors. The term pluggable is from the programmer's viewpoint and relates to groups of instructions that can easily be added to a processor architecture for code density and performance enhancements. One specific aspect addressed herein is the unique compacted instruction set which allows the programmer the ability to dynamically create a set of compacted instructions on a task by task basis for the primary purpose of improving control and parallel code density. These compacted instructions are parallelizable in that they are not specifically restricted to control code application but can be executed in the processing elements (PEs) in an array processor. The ManArray family of processors is designed for this dynamic compacted instruction set capability and also supports a scalable array of from one to N PEs.

Abstract: A method and apparatus for providing local control of processing elements in a network of multiple context processing element are provided. A multiple context processing element is configured to store a number of configuration memory contexts. This multiple context processing element maintains data of a current configuration. State information is received from at least one other multiple context processing element. At least one configuration control signal is generated in responses to the state information and the data of a current configuration. One of multiple configuration memory contexts is selected in response to the configuration control signal, the selected configuration memory context controlling the multiple context processing element. Each multiple context processing element in the networked array of multiple context processing elements has an assigned physical and virtual identification.

Abstract: A method and apparatus for interconnecting multiple programmable logic devices. In a preferred embodiment of the invention, an interconnect chip couples one programmable logic device to another programmable logic device. The interface between devices takes place within the interconnect chip, which can be configured using available routing software, thereby sparing the user the task of routing the connections between devices on the board.

Abstract: A method for controlling a processor array by a host computer involves creating a graph of a plurality of nodes using a data connection component, configuring a broadcast tree from a spanning tree of the graph, propagating a first command from the host computer to a member of the processor array using the broadcast tree, configuring a reply tree from a spanning tree of the graph, transmitting a response from the member of the processor array to the host computer using the reply tree, and configuring the data connection component to send at least one message selected from the first command and the response on at least one run mode communication path.

Abstract: A method and apparatus for providing local control of processing elements in a network of multiple context processing element are provided. A multiple context processing element is configured to store a number of configuration memory contexts. This multiple context processing element maintains data of a current configuration. State information is received from at least one other multiple context processing element. At least one configuration control signal is generated in responses to the state information and the data of a current configuration. One of multiple configuration memory contexts is selected in response to the configuration control signal, the selected configuration memory context controlling the multiple context processing element. Each multiple context processing element in the networked array of multiple context processing elements has an assigned physical and virtual identification.

Abstract: A pattern recognition apparatus for detecting a predetermined pattern contained in an input signal is provided with plural detecting processing parts and 4A for detecting respectively different features for a same input, plural integrating processing parts for spatially integrating, for each process results, the features detected by the plural detecting processing parts, plural detecting memories for retaining the process results of the detecting processing parts, plural integrating memories for retaining the process results of the integrating processing parts, a global data line 1030 to which all the predetermined detecting processing parts and all the predetermined integrating memories are connected at a certain timing, and plural local data lines each of which is connected to a predetermined set of the detecting processing parts, the integrating processing parts and the detecting memory.

Abstract: An efficient DSP or MPU is combined with efficient DRAM on a single IC die. To optimize the embedded memory, the chip includes wide-band connections to DRAM. Row and column addresses of DRAM can be applied at the same time using wide address busses. Additional metal lines lower the resistance of the word line in the DRAM circuits. For certain process steps, the processor block is masked off and the process steps unique to the fabrication of memory are performed on the memory block, and vice-versa. Process steps which are common to the processor and memory blocks can be performed simultaneously on the processor and memory blocks without masking off either block. Certain process steps can be employed in the fabrication of the one of the two processor and memory blocks in addition to or in lieu of processes normally used in the fabrication of that block. An electronic component (e.g.

Abstract: A method and apparatus for solving the output dependence problem in an explicit parallelism architecture microprocessor with consideration for implementation of the precise exception. In case of an output dependence hazard, the issue into bypass of a result of the earlier issued operation having an output hazard is cancelled. Latencies of short instructions are aligned by including additional stages on the way of writing the results into the register file in shorter executive units, which allows to save the issue order while writing the results into the register file. For long and unpredictable latencies of the instructions, writing of the result of the earlier issued operation having an output dependence hazard into the register file is cancelled after checking for no precise exception condition. All additional stages are connected to the bypass not to increase the result access time in case of this result use in the following operations.

Abstract: A parallel computer of this invention includes a plurality of memory elements and a plurality of processing elements and each of the processing elements is connected to logically adjacent memory elements. For example, the processing elements which corresponds to a logical position (i, j) is connected to the memory elements which correspond to a plurality of logical positions (i, j), (i, j+1), (i+1, j) and (i+1, j+1). It is preferable if each of the memory elements can be accessed from the exterior. According to this invention, efficient memory access can be made and the parallel processing can be performed at high speed without increasing the hardware amount and making the control operation complicated. Further, the operation speed of the image processing can be enhanced by constructing an image memory by use of a plurality of memory elements and causing the processing element to effect the image processing in a distributed and cooperative manner.

Abstract: Featured is a device controller in a system having a multiplicity of such controllers and a conveying system and method for controlling a multiplicity of devices using such controllers. Each controller includes a plurality of bi-directional communications ports, a processor that processes information and provides outputs, where at least one output controls the device, and an applications program for execution within the processor that includes instructions and criteria for processing the information and providing the processor outputs. Specifically, the applications program includes instructions and criteria for communicating information between and among controllers; instructions and criteria for processing information received by a controller; and instructions and criteria for modifying the operation of a device responsive to the communicated information. For a conveying system having a multiplicity of conveying sections, a controller is provided for each section.

Abstract: A method and apparatus for providing local control of processing elements in a network of multiple context processing element are provided. A multiple context processing element is configured to store a number of configuration memory contexts. This multiple context processing element maintains data of a current configuration. State information is received from at least one other multiple context processing element. At least one configuration control signal is generated in response to the state information and the data of a current configuration. One of multiple configuration memory contexts is selected in response to the configuration control signal, the selected configuration memory context controlling the multiple context processing element. Each multiple context processing element in the networked array of multiple context processing elements has an assigned physical and virtual identification.

Abstract: A field programmable processor includes a regular array of processing elements, each of which is adapted to perform a fixed arithmetic function on packets of data. The processing elements are interconnected by an array of signal conductors extending adjacent the processing elements. Switching means are provided for selectively connecting the processing elements to the adjacent signal conductors so as to interconnect the processing elements. Program data representing desired processing element interconnections is stored, the switches are controlled in accordance with the stored program data to achieve the desired processing element interconnections. The packets of data are transmitted between the interconnected processing elements.

Abstract: A method and apparatus for reducing instruction cycles in a digital signal processor wherein the processor includes a multiplier unit, an adder, a memory, and at least one pair of first and second accumulators. The accumulators include respective guard, high and low parts. The method and apparatus enable vectoring the respective first and second high parts from the accumulators to define a single vectored register responsive to a single instruction cycle and processing the data in the vectored register.

Abstract: In an image processing system or method, an image element memorizing device memorizes image elements which are image data that are subjects of process. An image element processing state memorizing device memorizes present processing states of the image elements in the image element memorizing device. A detecting device detects, in response to the present processing states, a pointer of one of the image elements that is capable of being processed by the image processing system. A temporary pointer memorizing device memorizes the pointer from the detecting device. A calculating device reads the pointer from the temporary pointer memorizing device to process an image in response to the image element of the pointer which is read.

Abstract: A parallel computer of this invention includes a plurality of memory elements and a plurality of processing elements and each of the processing elements is connected to logically adjacent memory elements. For example, the processing elements which corresponds to a logical position (i, j) is connected to the memory elements which correspond to a plurality of logical positions (i, j), (i, j+1), (i+1, j) and (i+1, j+1). It is preferable if each of the memory elements can be accessed from the exterior. According to this invention, efficient memory access can be made and the parallel processing can be performed at high speed without increasing the hardware amount and making the control operation complicated. Further, the operation speed of the image processing can be enhanced by constructing an image memory by use of a plurality of memory elements and causing the processing element to effect the image processing in a distributed and cooperative manner.

Abstract: A method/operator is disclosed that modifies dimension structures and relations during processing in a multidimensional data cube. The online “blowup” operator disclosed uses one or more hierarchical structures to expand a hypercube in order to reveal internal connections between attributes in relations associated with the hypercube. The operator is generic and may be applied to any dimension using hierarchical structures to guide the process. Furthermore, it is applicable to any data warehouse design. The methods enable a user, performing multidimensional analysis, to view, online, internal connections between attributes when going from one level to another in the hierarchical structures. Such as when comparing complex health related statistics for individuals across different age periods or for individuals versus their ancestors. The methods disclosed, facilitate OLAP for more complex data than current designs do.

Abstract: A method, apparatus, article of manufacture, and a memory stricture for synchronizing nodes in configuring a massively parallel processing system is disclosed. The method comprises the steps of receiving a registration request from each of the non-coordinator nodes in the coordinator node and, after a registration request has been received from all of the non-coordinator nodes, sending a wakeup message from the coordinator node to each of the non-coordinator nodes to wake the non-coordinator nodes from a sleep state. In another embodiment of the invention, the method comprises the steps of transmitting a registration request from a non-coordinator node to a coordinator node; commanding the non-coordinator node to enter a sleep state; receiving a multicast wakeup message from the coordinator node in the non-coordinator node after a registration request is received from all of the non-coordinator nodes in the coordinator node; and waking the non-coordinator node in response to the wakeup message.

Abstract: A computer system splits a data space to partition data between processors or processes. The data space may be split into sub-regions which need not be orthogonal to the axes defined the data space's parameters, using a decision tree. The decision tree can have neural networks in each of its non-terminal nodes that are trained on, and are used to partition, training data. Each terminal, or leaf, node can have a hidden layer neural network trained on the training data that reaches the terminal node. The training of the non-terminal nodes' neural networks can be performed on one processor and the training of the leaf nodes' neural networks can be run on separate processors. Different target values can be used for the training of the networks of different non-terminal nodes. The non-terminal node networks may be hidden layer neural networks.

Abstract: A parallel computer of this invention includes a plurality of memory elements and a plurality of processing elements and each of the processing elements is connected to logically adjacent memory elements. For example, the processing elements which corresponds to a logical position (i, j) is connected to the memory elements which correspond to a plurality of logical positions (i, j), (i, j+1), (i+1, j) and (i+1, j+1). It is preferable if each of the memory elements can be accessed from the exterior. According to this invention, efficient memory access can be made and the parallel processing can be performed at high speed without increasing the hardware amount and making the control operation complicated. Further, the operation speed of the image processing can be enhanced by constructing an image memory by use of a plurality of memory elements and causing the processing element to effect the image processing in a distributed and cooperative manner.

Abstract: A data-processing arrangement for a plurality of parallel data processors is disclosed. An operation carried out by at least one of the parallel processors is defined by an instruction word or code. The data-processing arrangement includes a control processor that makes compositions of instruction words using instruction-word composing software. A composition (VLIW) of instruction words defines operations which are to be carried out in parallel. The compositions are then provided to each parallel data processor as required. Storage of instruction-word composing software generally requires less memory space than storage of independent VLIW-s for each parallel data processor. The cost-saving this provides generally outweighs any additional costs associated with providing the control processor. Thus, the data-processing arrangement yields better cost and memory efficiency.

Abstract: An internal bus system for DFPs and units with two- or multi-dimensional programmable cell architectures, for managing large volumes of data with a high interconnection complexity. The bus system can transmit data between a plurality of function blocks, where multiple data packets can be on the bus at the same time. The bus system automatically recognizes the correct connection for various types of data or data transmitters and sets it up.

Abstract: A memory device which utilizes a plurality of memory modules coupled in parallel to a master I/O module through a bus. Each memory module has independent address and command decoders to enable independent operation. Thus each memory module is activated by commands on the bus only when a memory access operation is performed within the particular memory module. Each memory module has a programmable identification register which stores a communication address of the module. The communication address for each module can be changed during operation of the memory device by a command from the bus. The memory device includes redundant memory modules to replace defective memory modules. Replacement can be carried out through commands on the bus.

Abstract: A messaging scheme that conserves system memory bandwidth during a memory read operation in a multiprocessing computer system is described. A source processing node sends a memory read command to a target processing node to read data from a designated memory location in a system memory associated with the target processing node. The target node transmits a read response to the source node containing the requested data and also concurrently transmits a probe command to one or more of the remaining nodes in the multiprocessing computer system. In response to the probe command each remaining processing node checks whether the processing node has a cached copy of the requested data. If a processing node, other than the source and the target nodes, finds a modified cached copy of the designated memory location, that processing node responds with a memory cancel response sent to the target node and a read response sent to the source node.

Abstract: 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.

Abstract: A method/operator is disclosed that adjusts measurements during processing in a multidimensional data cube. The online “depth-of-field” operator disclosed varies the density of points in a representation of the multidimensional cube. The operator may be applied to any collection of dimensions and relations supported by the dimensions, using hierarchical structures to control the adjustments. It allows one to experiment online with the definition of relations during multidimensional possessing, thereby controlling the output of the synthesizing process. The operator may be used to equate attributes based on their hierarchical positions when processing measurements in a hypercube. Furthermore, it may be used to reveal hidden dependencies between variables when working with measurements with varying levels of granularity.

Abstract: A computing system for effecting scientific and technical calculations comprises at least a group of processor modules (1-1 . . . 1-N), a switch (2), an auxiliary switch (3), a group of associative memory modules (4-1 . . . 4-N), a buffering block (5). The computing system provides information processing without any inter-processor exchange, hence, decreasing the time for program processing.

Abstract: An enhanced memory algorithmic processor (“MAP”) architecture for multiprocessor computer systems comprises an assembly that may comprise, for example, field programmable gate arrays (“FPGAs”) functioning as the memory algorithmic processors. The MAP elements may further include an operand storage, intelligent address generation, on board function libraries, result storage and multiple input/output (“I/O”) ports. The MAP elements are intended to augment, not necessarily replace, the high performance microprocessors in the system and, in a particular embodiment of the present invention, they may be connected through the memory subsystem of the computer system resulting in it being very tightly coupled to the system as well as being globally accessible from any processor in a multiprocessor computer system.

Abstract: Network input processing is distributed to multiple CPUs on multiprocessor systems to improve network throughput and take advantage of MP scalability. Packets received on the network are distributed to N high priority threads, wherein N is the number of CPUs on the system. N queues are provided to which the incoming packets are distributed. When one of the queues is started, one of the threads is scheduled to process packets on this queue at any one of the CPUs that is availableat the time. When all of the packets on the queue are processed, the thread becomes dormant. Packets are distributed to one of the N queues by using a hashing function based on the source MAC address, source IP address, or the packet's source and destination TCP port number, or all or a combination of the foregoing. The hashing mechanism ensures that the sequence of packets within a given communication session will be preserved. Distribution is effected by the device drivers of the system.

Abstract: A processor capable of executing vector instructions includes at least an instruction sequencing unit and a vector processing unit that receives vector instructions to be executed from the instruction sequencing unit. The vector processing unit includes a plurality of multiply structures, each containing only a single multiply array, that each correspond to at least one element of a vector input operand. Utilizing the single multiply array, each of the plurality of multiply structures is capable of performing a multiplication operation on one element of a vector input operand and is also capable of performing a multiplication operation on multiple elements of a vector input operand concurrently. In an embodiment in which the maximum length of an element of a vector input operand is N bits, each of the plurality of multiply arrays can handle both N by N bit integer multiplication and M by M bit integer multiplication, where N is a non-unitary integer multiple of M.

Abstract: A hierarchical instruction set architecture (ISA) provides pluggable instruction set capability and support of array processors. The term pluggable is from the programmer's viewpoint and relates to groups of instructions that can easily be added to a processor architecture for code density and performance enhancements. One specific aspect addressed herein is the unique compacted instruction set which allows the programmer the ability to dynamically create a set of compacted instructions on a task by task basis for the primary purpose of improving control and parallel code density. These compacted instructions are parallelizable in that they are not specifically restricted to control code application but can be executed in the processing elements (PEs) in an array processor. The ManArray family of processors is designed for this dynamic compacted instruction set capability and also supports a scalable array of from one to N PEs.