International Business Machines Corporation

Mitsubishi Denki Kabushiki Kaisha

Lenovo (singapore) Pte. Ltd.

Takao Moriyama

Kei Kawase

Hideaki Komatsu

Moriyoshi Ohara

Hiroshi Inoue

Yukihiko Sohda

Fusashi Nakamura

Seiichi Kawano

Akira Koseki

Motohiro Kawahito

Tadanobu Inoue

Kohji Takano

Hassan Hajji

Makoto Ono

Michiaki Tatsubori

Tatsuya Ishikawa

Munetaka Ohtani

Yoshihisa Takatsu

Takashi Matsumoto

Paolo Fraccaro

In a method for training temporal precipitation interpolation models, the method may include receiving an initial image, a first intermediate image, and a final image, computing a first preliminary forward optical flow vector field from the initial image, and a first preliminary backward optical flow vector field, computing a first refined forward optical flow vector field and a first refined backward optical flow vector field using a terrain factor, among other things, and computing backpropagation losses to train neural networks by comparing the first intermediate image to an interpolated frame calculated using the first refined forward optical flow vector field and the first refined backward optical flow vector field.

Temporal interpolation of precipitation

A method, a system, and a computer program product provide for changing a boundary between zones. This includes setting a location of a boundary which defines a part of a zone; detecting that an object moves into the zone across the boundary; and in response to the detection, changing the location of the boundary in a direction away from the object, compared to the location of the boundary before the change.

Dynamic boundary setting

Data transfer during processor context switching is reduced, particularly in relation to a time-sharing microtasking programming model. Prior to switching context of a processor having local memory from a first to a second process, a portion of the local memory that does not require transfer to system memory for proper saving of data associated with the first process is determined. The context of the processor is then switched from the first to the second process, including transferring all of the local memory as the data associated with the first process, to system memory&#x2014;except for the portion of the local memory that has been determined as not requiring saving to the system memory for proper saving of the data associated with the first process. Therefore, switching the context from the first to the second process results in a reduction of data transferred from the local memory to the system memory.

Reduced data transfer during processor context switching

Unsecure system software and secure system software on the same computer system is switched between. A computer system includes one or more processors, which may not have any built-in security features, memory, and firmware. The memory stores secure system software and unsecure system software. In response to receiving a user signal, the firmware switches from the unsecure system software running on the processors to the secure system software running on the processors (and back again). While the unsecure system software is running, the secure system software is protected from tampering by the unsecure system software.

Switching between unsecure system software and secure system software

An object is to calculate an accurate motion vector with a small computational effort. To this end, provided is a system for compressing a motion picture generated by projecting objects onto a screen, the objects moving relatively to the screen in a 3D space, the system including: a motion calculating component which calculates a motion vector of the object within the screen by projecting onto the screen a motion of the object in the 3D space between a time corresponding to a compression target frame and a time corresponding to another frame; and a compressing component which compresses the compression target frame by motion compensation based on the motion vector.

Compression system, program and method

A compiler system and method for calculating a value to be assigned to a variable for optimizing a program. The apparatus includes a subrange analysis unit for analyzing, for an instruction to assign a value to a variable in the program, a range of the value being assignable to the variable by the instruction, as a subrange of the variable in a case where instruction is executed; a determination unit for determining if the execution result of the program changes if the instruction assigns any value in the subrange of the variable to the variable on the basis of the analyzed subrange of the variable; and a replacement unit for replacing the instruction to assign the value to the variable with an instruction to assign a constant value in the subrange of the variable to the variable.

Compiler for optimizing program

Provided is a complier which optimizes parallel processing. The complier records the number of execution cores, which is the number of processor cores that execute a target program. First, the compiler detects a dominant path, which is a candidate of an execution path to be consecutively executed by a single processor core, from a target program. Subsequently, the compiler selects dominant paths with the number not larger than the number of execution cores, and generates clusters of tasks to be executed by a multi-core processor in parallel or consecutively. After that, the compiler computes an execution time for which each of the generated clusters is executed by the processor cores with the number equal to one or each of a plurality natural numbers selected from the natural numbers not larger than the number of execution cores. Then, the compiler selects the number of processor cores to be assigned for execution of each of the clusters based on the computed execution time.

Preprocessor to improve the performance of message-passing-based parallel programs on virtualized multi-core processors

For communication between a display device and a processing apparatus (host), two connection modes are prepared, a wired connection mode, for communication along a wired connection path, and a wireless connection mode, for communication along a wireless connection path. Before entering the wireless connection mode, the processing apparatus (host) transmits, along the wired connection path to the display device, data required for the wireless connection of the display devicealong the wireless connection path, and data required for authentication to permit information to be accessed using the wireless connection path.

System and method for dual path terminal connection

Delimiter lookup is accomplished using a processor permutation instruction. A 256-bit bitmap is defined and stored within two sixteen-byte registers. Each bit of the bitmap represents an eight-bit character occurrable within a character string, such as a section of eXtensible Markup Language (XML) code, and has a value indicating whether the character is a target character, such as a delimiter. The character string has a number of eight-bit characters at a corresponding number of positions. The first position within the character string at which one of the target characters occurs is determined, using the 256-bit bitmap and a processor permutation instruction. The first position within the character string at which one of the target characters occurs, as has been determined, is output.

Delimiter lookup using processor permutation instruction

The programmable controller composed of a main body unit and a plurality of input/output extension blocks is provided with type identifying means for identifying the number of input output points and present organization storing means. Upon receiving an organization update instruction signal, it can allocate input and output numbers in various ways by rewrite setting means in a system memory and can select a second allocation method with which existing input and output numbers are not changed or a first allocation method with which input and output numbers are completely changed anew. When input and output numbers are completely changed anew, it can automatically change input and output numbers accompanying an instruction in a program memory by instruction changing means in the system memory.

Programmable controller

A system and method which dynamically changes the load balance of assigned loads for each group in a sequence of processes from a first stage to an n-th stage in a computer having a plurality of processors, wherein the plurality of processors are grouped into at least two groups, comprises the steps of: detecting a change in a characteristic value in a queue for transferring a processing result between the groups; and changing the assignment of assigned processes for each group based on the change in the characteristic value. A characteristic value stored in a queue represents a value related to work load, and a queue seldom becomes full or empty if the load balance is changed referring to this characteristic value.

Growing community of inventors

Kanagawa-ken, Japan

Takao Moriyama