Huawei Technologies Co., Limited

Tencent Technology (shenzhen) Company Limited

Future Wei Technologies, Inc.

Xi'an Zhongxing New Software Co., Ltd.

Tencent Technology Company Limited

Yu Meng

Yunxiang Wu

Xiaobing Lee

Feng Yang

Lixin Zhang

Xiaoyu Yu

Jianping Zhu

Yuwei Wang

Jianlin Gao

LiXin Zhang

Junsheng Chu

A data processing method, device, and storage medium that reads a parallel control code; reads, according to the parallel control code, first data that has been cached in a data cache space, processes the read first data, and outputs the processed first data to the data cache space; and simultaneously moves second data from a data storage space to the data cache space according to the parallel control code, the second data being the next data of the first data. Data processing and data moving are performed simultaneously according to the parallel control code, to reduce a duration of the data processing waiting for the data moving, thereby improving a processing speed and processing efficiency.

Data processing method and chip, device, and storage medium

The present disclosure describes methods, devices, and storage mediums for adjusting computing resource. The method includes obtaining an expected pooling time of a target pooling layer and a to-be-processed data volume of the target pooling layer; obtaining a current clock frequency corresponding to at least one computing resource unit used for pooling; determining a target clock frequency according to the expected pooling time of the target pooling layer and the to-be-processed data volume of the target pooling layer; and in response to that the convolution layer associated with the target pooling layer completes convolution and the current clock frequency is different from the target clock frequency, switching the current clock frequency of the at least one computing resource unit to the target clock frequency, and performing pooling in the target pooling layer based on the at least one computing resource unit having the target clock frequency.

Neural network operational method and apparatus, and related device

The present disclosure discloses a method and an apparatus for adjusting a working status of an aggregated link. The method includes: when determining to switch a modulation mode of a first sub-link of an aggregated link from a first modulation mode to a second modulation mode, determining a transmission delay of transmitting a data slice in the second modulation mode by using the first sub-link; comparing the transmission delay of transmitting a data slice in the second modulation mode by using the first sub-link with a transmission delay of transmitting a data slice by using another sub-link of the aggregated link, to obtain a difference; and if the difference meets a preset condition, sending information for controlling a working status of the first sub-link to a transmit end device, so that the transmit end device controls the working status of the first sub-link in the second modulation mode.

Method, apparatus, terminal device, and system for adjusting working status of aggregated link

An apparatus comprises a hybrid-memory multi-chip package (MCP) including a non-volatile memory (NVM) in an NVM die; a dynamic random access memory (DRAM) in two or more DRAM die, wherein a portion of the DRAM is allocated as a cache memory for the NVM; and a hybrid controller for the NVM and DRAM. The hybrid controller includes an NVM interface to the NVM; a DRAM interface to the cache memory; a host interface to communicate data with a host processor, wherein the host interface includes a parallel data bus for reading and writing data directly with both of the DRAM and the NVM; and logic circuitry configured to interleave access by the host processor and hybrid controller to the DRAM and NVM.

Hybrid LPDDR4-DRAM with cached NVM and flash-NAND in multi-chip packages for mobile devices

Hybrid LPDDR4-DRAM with cached NVM and flash-nand in multi-chip packages for mobile devices

A method for gracefully shutdown a virtual system is disclosed, and the method includes: gracefully shutdown configuration information configured for the virtual system is received and stored; and sequential shutting down of virtual machines is performed according to the stored gracefully shutdown configuration information when a request for shutting down the virtual system is received, so as to solve problems caused by the fact that virtual machines are shut down according completely to a reverse order of starting-up in the prior art.

Method and system for gracefully shutdown virtual system

The present disclosure discloses network devices and systems for sending and receiving service packet. The network device is configured to: receive an insensitive service packet; obtain a current slicing length according to a modulation mode of a communication link; perform slicing processing once on the insensitive service packet according to the current slicing length to obtain one slice, and send the slice through the communication link, If the current slicing length is smaller than a length of the insensitive service packet, for the remaining part of the insensitive service packet which has undergone the slicing processing once, the network device repeats the obtaining of the current slicing length, the slicing processing, and the sending the slice, until the insensitive service packet is completely sent.

Growing community of inventors

Shenzhen, China

Yu Meng