1552 results about "RAID processing unit" patented technology

The invention discloses an intelligent bracelet. The intelligent bracelet comprises a sensor module, an audio module, a power module, a central processing unit and a wireless communication module, wherein the sensor module is electrically connected with the central processing unit and is used for detecting information on an intelligent bracelet wearer and transmitting the information to the central processing unit; the audio module comprises a speaker, a microphone and a DSP (Digital Signal Processing) chip and is used for encoding and decoding an audio signal; the central processing unit comprises a master control MCU (Micro Control Unit) and is used for receiving and storing information acquired by the sensor module and coordinating the work of the audio module and the wireless communication module; the wireless communication module is used for realizing wireless communication connection between the intelligent bracelet and an intelligent mobile phone of a user, so that the interactive transmission of the audio signal between the intelligent bracelet and the intelligent mobile phone is realized. The intelligent bracelet disclosed by the invention can be in wireless synchronous connection with the intelligent mobile phone, and the intelligent bracelet has a call receiving function.

A processor for use in a router, the processor having a systolic array pipeline for processing data packets to determine to which output port of the router the data packet should be routed. In one embodiment, the systolic array pipeline includes a plurality of programmable functional units and register files arranged sequentially as stages, for processing packet contexts (which contain the packet's destination address) to perform operations, under programmatic control, to determine the destination port of the router for the packet. A single stage of the systolic array may contain a register file and one or more functional units such as adders, shifters, logical units, etc., for performing, in one example, very long instruction word (vliw) operations. The processor may also include a forwarding table memory, on-chip, for storing routing information, and a cross bar selectively connecting the stages of the systolic array with the forwarding table memory.

The invention discloses a method for accelerating an LSTM neural network algorithm on an FPGA platform. The FPGA is a field-programmable gate array platform and comprises a general processor, a field-programmable gate array body and a storage module. The method comprises the following steps that an LSTM neural network is constructed by using a Tensorflow pair, and parameters of the neural networkare trained; the parameters of the LSTM network are compressed by adopting a compression means, and the problem that storage resources of the FPGA are insufficient is solved; according to the prediction process of the compressed LSTM network, a calculation part suitable for running on the field-programmable gate array platform is determined; according to the determined calculation part, a softwareand hardware collaborative calculation mode is determined; according to the calculation logic resource and bandwidth condition of the FPGA, the number and type of IP core firmware are determined, andacceleration is carried out on the field-programmable gate array platform by utilizing a hardware operation unit. A hardware processing unit for acceleration of the LSTM neural network can be quicklydesigned according to hardware resources, and the processing unit has the advantages of being high in performance and low in power consumption compared with the general processor.

A system includes one or more processing units coupled to a network interface unit. The network interface unit may include a network port for connection to a network and a virtual interface that may be configured to distribute an available communication bandwidth of the network port between the one or more processing units. The network port may include a shared media access control (MAC) unit. The virtual interface may include a plurality of processing unit resources each associated with a respective one of the one or more processing units. Each of the processing unit resources may include an I / O interface unit coupled to a respective one of the one or more processing units via an I / O interconnect, and an independent programmable virtual MAC unit that is programmably configured by the respective one of the one or more processing units. The virtual interface may also include a receive datapath and a transmit datapath that are coupled between and shared by the plurality of processing unit resources and the network port.

A secure memory interface includes a reader block, a writer block, and a mode selector for detecting fault injection into a memory device when a secure mode is activated. The mode selector activates or deactivates the secure mode using memory access information from a data processing unit. Thus, the data processing unit flexibly specifies the amount and location of the secure data stored into the memory device.