Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

4344 results about "Bus interface" patented technology

Data processing system and method

A powerful, scaleable, and reconfigurable image processing system and method of processing data therein is described. This general purpose, reconfigurable engine with toroidal topology, distributed memory, and wide bandwidth I/O are capable of solving real applications at real-time speeds. The reconfigurable image processing system can be optimized to efficiently perform specialized computations, such as real-time video and audio processing. This reconfigurable image processing system provides high performance via high computational density, high memory bandwidth, and high I/O bandwidth. Generally, the reconfigurable image processing system and its control structure include a homogeneous array of 16 field programmable gate arrays (FPGA) and 16 static random access memories (SRAM) arranged in a partial torus configuration. The reconfigurable image processing system also includes a PCI bus interface chip, a clock control chip, and a datapath chip. It can be implemented in a single board. It receives data from its external environment, computes correspondence, and uses the results of the correspondence computations for various post-processing industrial applications. The reconfigurable image processing system determines correspondence by using non-parametric local transforms followed by correlation. These non-parametric local transforms include the census and rank transforms. Other embodiments involve a combination of correspondence, rectification, a left-right consistency check, and the application of an interest operator.
Owner:INTEL CORP

Method for accelerating convolution neutral network hardware and AXI bus IP core thereof

The invention discloses a method for accelerating convolution neutral network hardware and an AXI bus IP core thereof. The method comprises the first step of performing operation and converting a convolution layer into matrix multiplication of a matrix A with m lines and K columns and a matrix B with K lines and n columns; the second step of dividing the matrix result into matrix subblocks with m lines and n columns; the third step of starting a matrix multiplier to prefetch the operation number of the matrix subblocks; and the fourth step of causing the matrix multiplier to execute the calculation of the matrix subblocks and writing the result back to a main memory. The IP core comprises an AXI bus interface module, a prefetching unit, a flow mapper and a matrix multiplier. The matrix multiplier comprises a chain type DMA and a processing unit array, the processing unit array is composed of a plurality of processing units through chain structure arrangement, and the processing unit of a chain head is connected with the chain type DMA. The method can support various convolution neutral network structures and has the advantages of high calculation efficiency and performance, less requirements for on-chip storage resources and off-chip storage bandwidth, small in communication overhead, convenience in unit component upgrading and improvement and good universality.
Owner:NAT UNIV OF DEFENSE TECH

Universal serial bus (USB) RAM architecture for use with microcomputers via an interface optimized for integrated services device network (ISDN)

A RAM-based interrupt-driven interface device is disclosed for establishing a communication link between a universal serial bus (USB) host and a microcontroller device for providing a control function, the interface device being operative to receive digital information in the form of command, data and control packets from the host and to process the packets and communicate the processed digital information to the microcontroller device, and in response thereto, the microcontroller device being operative to communicate digital information to the interface device for processing and transfer thereof to the host. The interface device includes means for receiving a command generated by the host through a USB bus, means for storing the host-generated command and for generating an interface device interrupt signal upon storage of said host-generated command for use by the microcontroller device in responding to the host-generated command, a microcontroller bus for transferring microcontroller information and the interface device interrupt signal between the interface device and the microcontroller device. The interface device further includes means for receiving a microcontroller command from the microcontroller device in response to said interface device interrupt signal and means for storing the microcontroller command and it is operative to generate a microcontroller device interrupt signal upon storage of the microcontroller command for use by the interface device in developing an address for identification of the interface device to the host during subsequent communications therebetween, wherein during communication between the host and the interface device, the interface device-developed address is used by the interface device to identify host-provided information in the form of packets, and upon processing of the host-provided information, to provide the microcontroller device with the necessary information to allow it to respond to the host thereby allowing a generic microcontroller device to be flexibly interfaced with a USB, host for communication therebetween.
Owner:SK HYNIX INC

Data processing system and method

A powerful, scaleable, and reconfigurable image processing system and method of processing data therein is described. This general purpose, reconfigurable engine with toroidal topology, distributed memory, and wide bandwidth I / O are capable of solving real applications at real-time speeds. The reconfigurable image processing system can be optimized to efficiently perform specialized computations, such as real-time video and audio processing. This reconfigurable image processing system provides high performance via high computational density, high memory bandwidth, and high I / O bandwidth. Generally, the reconfigurable image processing system and its control structure include a homogeneous array of 16 field programmable gate arrays (FPGA) and 16 static random access memories (SRAM) arranged in a partial torus configuration. The reconfigurable image processing system also includes a PCI bus interface chip, a clock control chip, and a datapath chip. It can be implemented in a single board. It receives data from its external environment, computes correspondence, and uses the results of the correspondence computations for various post-processing industrial applications. The reconfigurable image processing system determines correspondence by using non-parametric local transforms followed by correlation. These non-parametric local transforms include the census and rank transforms. Other embodiments involve a combination of correspondence, rectification, a left-right consistency check, and the application of an interest operator.
Owner:INTEL CORP

Architecture for a multi-port adapter with a single media access control (MAC)

A multi-port adapter having a single MAC chip has reduced logic circuits for transferring data between a host system and a TDM communication system. The MAC chip includes a transmit MAC and a receive MAC, each coupled at one end to a port multiplexer through an interface and at the other end to respective storage registers. The port multiplexer is coupled to the Physical Layer of each port. Transmit and receive state registers track the state of each port in the transfer of data in the transmit and receive directions. The storage registers are coupled through a host bus interface to a host bus and to the host system. Control logic is coupled to the storage register to control the transfer of data between the system and the storage registers. A port selector coupled between the multiplexer and the transmit and receive state registers selects ports for transfer of data in succession. On each chip clock cycle, the port selector selects a state machine register to determine the state of the MACs for processing the data and a section of the FIFO's to write or read data for the selected port. At the end of the cycle, the state registers are set and stay set until selected again. The process repeats for each port in a cyclic manner. Once data is accumulated in the receive storage register, control logic reads the data of the host bus. Once space is available in the transmit storage register, the control logic writes data from the host system to the transmit storage register.
Owner:IBM CORP

Complex pipeline collision optimization method of subway electromechanical engineering

ActiveCN103093061AOvercome the shortcomings of error-prone, omission and bump-to-missSolving technical issues with cross collisionsSpecial data processing applicationsNODALCollision analysis
The invention belongs to the technical field of electromechanical device installation and discloses a complex pipeline collision optimization method of subway electromechanical engineering. According to the method, three-dimensional bus interface module (BIM) software is used for establishing different professional virtual BIM models which are consistent with completed engineering and then output to three-dimensional collision software for establishment of a combined three-dimensional collision model for collision analysis, collision nodes are then processed and optimized, and then decorative texture mapping and animation roaming are carried out on the combined, analysed and processed three-dimensional collision model without the collision node problem through 3D - MAX software, and therefore collision optimization of complex pipelines of the subway electromechanical engineering is achieved. According to the complex pipeline collision optimization method of the subway electromechanical engineering, the BIM technology is utilized to solve the problem that collision of various complex pipelines causes construction ceasing during electromechanical installation, reasonable planning and utilization of electromechanical pipeline equipment and the like are achieved by means of the optimized design, construction waste is reduced, construction time is shortened, working efficiency at site is improved greatly, and initial investment of a proprietor is reduced.
Owner:ELECTRIFICATION ENG CO LTD OF CHINA RAILWAY 22TH BUREAU GRP +1

Stereoscopic vision based emergency treatment device and method for running vehicles

The invention relates to a stereoscopic vision based emergency treatment device and method for running vehicles, wherein the device comprises a binocular-vision image pick-up unit, an on-board bus interface, a central processing unit, a vehicle braking control system and an acousto-optic alarm circuit. The binocular-vision image pick-up unit is used for capturing an image of a road in front of a vehicle; the DSP (digital signal processor) based central processing unit is adopted for carrying out real-time quick calculation on a visual image so as to obtain a three-dimensional road scene, and compares the obtained three-dimensional road scene with a safe driving road model set up by a system so as to judge whether obstacles or dangers exist in the traveling direction of the vehicle; when adanger is found, the vehicle braking control system is started so as to reduce the speed of the vehicle and send an acousto-optic alarm to a driver; meanwhile, the central processing unit is connected with a vehicle sensor by an inter-vehicle bus so as to detect the state of the vehicle, and when the vehicle has mechanical or circuit faults, a braking system is started so as to reduce the speed of the vehicle and send an acousto-optic alarm. The device disclosed by the invention can be arranged on ordinary motor vehicles so as to avoid the occurrence of accidents or reduce the accident loss, thereby improving the driving safety performance.
Owner:HOHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products