41809 results about "Parallel computing" patented technology

A distributed memory switching hub interconnecting heterogeneous local area networks operating at different transmission speeds for receiving, storing and forwarding frames of data. The distributed memory switching hub employs a distributed memory architecture in which memory storage for frames of data received and to be transmitted is located at each low speed LAN port of the distributed memory switching hub. A distributed memory architecture renders unnecessary the need for a central programmable processor or shared common memory to store and forward frames received by the distributed memory switching hub.

A digital data file storage system is disclosed in which original data files to be stored are dispersed using some form of information dispersal algorithm into a number of file “slices” or subsets in such a manner that the data in each file share is less usable or less recognizable or completely unusable or completely unrecognizable by itself except when combined with some or all of the other file shares. These file shares are stored on separate digital data storage devices as a way of increasing privacy and security. As dispersed file shares are being transferred to or stored on a grid of distributed storage locations, various grid resources may become non-operational or may operate below at a less than optimal level. When dispersed file shares are being written to a dispersed storage grid which not available, the grid clients designates the dispersed data shares that could not be written at that time on a Rebuild List. In addition when grid resources already storing dispersed data become non-available, a process within the dispersed storage grid designates the dispersed data shares that need to be recreated on the Rebuild List. At other points in time a separate process reads the set of Rebuild Lists used to create the corresponding dispersed data and stores that data on available grid resources.

An endoscope system comprises a scope and a processor. The scope has an imaging sensor, a first image-processing unit that performs primary image processing, a first memory, and a second memory. The first and second memories are non-volatile. The processor has a second image-processing unit that performs secondary image processing, and a processor memory that is non-volatile. The first memory stores an system data that includes parameters for the primary and secondary image processing. The processor memory stores the system data. The second memory is used for storing the system data stored in the processor memory when it is determined that the system data stored in the first memory is older than the system data stored in the processor memory. The system data stored in the second memory is overwritten onto the first scope memory after the system data is stored in the second memory.

A memory device and a method thereof allow programming and sensing a plurality of memory cells in parallel in order to minimize errors caused by coupling from fields of neighboring cells and to improve performance. The memory device and method have the plurality of memory cells linked by the same word line and a read / write circuit is coupled to each memory cells in a contiguous manner. Thus, a memory cell and its neighbors are programmed together and the field environment for each memory cell relative to its neighbors during programming and subsequent reading is less varying. This improves performance and reduces errors caused by coupling from fields of neighboring cells, as compared to conventional architectures and methods in which cells on even columns are programmed independently of cells in odd columns.

Systems and methods for massively parallel processing on an accelerator that includes a plurality of processing cores. Each processing core includes multiple processing chains configured to perform parallel computations, each of which includes a plurality of interconnected processing elements. The cores further include multiple of smart memory blocks configured to store and process data, each memory block accepting the output of one of the plurality of processing chains. The cores communicate with at least one off-chip memory bank.

In a parallel operational processing device having an operational processing unit arranged between memory blocks each having a plurality of memory cells arranged in rows and columns, the respective columns of each memory block are alternately connected to the operational processing units on the opposite sides of the memory block. By selecting one word line in one memory block, data can be transferred to two operational processing units. The number of the word lines selected per one operational processing unit is reduced, and power consumption is reduced. The bit operation units and sense amplifiers / write drivers of the operational processing units have arrangement pitch conditions mitigated and are reduced in number, and an isolation region between the memory blocks is not required and the layout area is reduced. Thus, the parallel operational processing device with a layout area and the power consumption reduced, can achieve a fast operation.

In one embodiment, a method comprises executing a plurality of virtual machines on a plurality of nodes of a cluster computing system, wherein at least one application is executed within each of the plurality of virtual machines, generating data that is related to performance of applications in the virtual machines, analyzing, by a management process, the data in view of parameters that encode desired performance levels of applications, and migrating, by the management process, a virtual machine on a first node to a second node of the plurality of nodes in response to the analyzing.

A method for recording and replaying execution of distributed programs on a computer system in a distributed environment, includes identifying an execution order of critical events of a program, generating groups of critical events of the program, wherein for each group, critical events belonging to the group belong to a common execution thread, and generating for each execution thread a logical thread schedule that identifies a sequence of the groups so as to allow deterministically replaying a non-deterministic arrival of stream socket connection requests, a non-deterministic number of bytes received during message reads, and a non-deterministic binding of stream sockets to local ports.

Embodiments of the present invention enable virtual-to-physical memory address translation using optimized bank and partition interleave patterns to improve memory bandwidth by distributing data accesses over multiple banks and multiple partitions. Each virtual page has a corresponding page table entry that specifies the physical address of the virtual page in linear physical address space. The page table entry also includes a data kind field that is used to guide and optimize the mapping process from the linear physical address space to the DRAM physical address space, which is used to directly access one or more DRAM. The DRAM physical address space includes a row, bank and column address. The data kind field is also used to optimize the starting partition number and partition interleave pattern that defines the organization of the selected physical page of memory within the DRAM memory system.

A computer includes a memory and a processor connected to the memory. The processor includes memory segment configuration registers to store defined memory address segments and defined memory address segment attributes such that the processor operates in accordance with the defined memory address segments and defined memory address segment attributes to allow kernel mode access to user space virtual addresses for enhanced kernel mode memory capacity.

Disclosed herein is an information processing apparatus including: a communication section configured to acquire application programs from external apparatus; a memory used for storing at least an application program and information relevant to the application program; an application execution section configured to execute the application program stored in the memory; and a control section configured to determine other application programs to be recommended in the course of execution of the application program in the application execution section, wherein information stored in the memory as the information relevant to the application program includes first relevant information and second relevant information which are used for determining the other application programs to be recommended in the course of execution of the application program in the application execution section

The present invention presents techniques whereby a memory system interrupts a programming process and restarts it including additional data. More specifically, when a memory system programs data into a group of cells together as programming unit, programming can begin with less than the full data content which the group can hold. In one embodiment, the present invention allows overlapped programming of upper and lower data pages, where once the memory begins programming the lower logical data page, if data is received for the upper page assigned to the same physical page, programming is interrupted and recommenced with the concurrent programming of both the upper and the loser pages. In a complimentary embodiment, when a page contains multiple sectors of data, programming of the physical page can begin when one or more, but less than all, of the sectors forming the corresponding logical page have been received, stopped and restarted to include additional sectors of the page.

An extensible protocol to replicate, integrate and synchronize distributed information is described which may be implemented in a computer system. A system and method for replicating, integrating and synchronizing distributed information is also described.

Described are techniques used in a computer system for handling data operations to storage devices. A switching fabric includes one or more fast paths for handling lightweight, common data operations and at least one control path for handling other data operations. A control path manages one or more fast paths. The fast path and the control path are utilized in mapping virtual to physical addresses using mapping tables. The mapping tables include an extent table of one or more entries corresponding to varying address ranges. The size of an extent may be changed dynamically in accordance with a corresponding state change of physical storage. The fast path may cache only portions of the extent table as needed in accordance with a caching technique. The fast path may cache a subset of the extent table stored within the control path. A set of primitives may be used in performing data operations. A locking mechanism is described for controlling access to data shared by the control paths.

A computer system includes a memory for storing instructions executable by a processor and an on-chip trace memory having a plurality of locations for storing trace information that indicates execution flow in the processor. A trace access instruction provides for access to the on-chip trace memory on the processor. The trace access instruction can be a write instruction or a read instruction. Typically, both read and write to the trace memory is provided. The system also has the capability to trace on start or restart of an executable thread by providing to the processor an indication of which executable thread to trace via a debug port. That indicates to the processor to provide trace information when the executable thread starts. When execution of the executable thread starts, the processor places an identifier corresponding to the executable thread into the trace memory to indicate that subsequent entries placed into the trace memory are part of said executable thread. The processor may also provide an entry indicating when the thread stops executing.

A local database cache enabling persistent, adaptive caching of either full or partial content of a remote database is provided. Content of tables comprising a local cache database is defined on per-table basis. A table is either: defined declaratively and populated in advance of query execution, or is determined dynamically and asynchronously populated on-demand during query execution. Based on a user input query originally issued against a remote DBMS and referential cache constraints between tables in a local database cache, a Janus query plan, comprising local, remote, and probe query portions is determined. A probe query portion of a Janus query plan is executed to determine whether up-to-date results can be delivered by the execution of a local query portion against a local database cache, or whether it is necessary to retrieve results from a remote database by executing a remote query portion of Janus query plan.

An memory module including parallel data compression and decompression engines for improved performance. The memory module includes MemoryF / X Technology. To improve latency and reduce performance degradations normally associated with compression and decompression techniques, the MemoryF / X Technology encompasses multiple novel techniques such as: 1) parallel lossless compression / decompression; 2) selectable compression modes such as lossless, lossy or no compression; 3) priority compression mode; 4) data cache techniques; 5) variable compression block sizes; 6) compression reordering; and 7) unique address translation, attribute, and address caches. The parallel compression and decompression algorithm allows high-speed parallel compression and high-speed parallel decompression operation. The memory module-integrated data compression and decompression capabilities remove system bottlenecks and increase performance. This allows lower cost systems due to smaller data storage, reduced bandwidth requirements, reduced power and noise.

A technique is provided for reducing the number of write barriers executed in mutator code without compromising garbage collector performance. Advantageously, a compiler generates two forms of a mutator code—a first version with write barriers and a second version substantially without write barriers. In operation, the first version of the code may be accessed by a vtable in a “mature” near-class and the second version may be accessed by a vtable in a “nascent” near-class. According to the invention, mapping of functionally equivalent points in the first and second versions of the mutator code may be facilitated by an associated pcmap. Further, each of the first and second versions may also be associated with a respective nr_map that facilitates mapping functionally equivalent points within different branches of guard code sequences corresponding to reference-writes to non-receiver objects.