Macronix International Co., Ltd.

Silicon Motion, Inc.

Hung-Sheng Chang

Yuan-Hao Chang

Hsiang-Pang Li

Tei-Wei Kuo

Yu-Ming Chang

Han-Wen Hu

Hang-Ting Lue

Nai-Ping Kuo

Wei-Chieh Huang

Wei-Chen Wang

Ting-Yu Liu

Li-Chun Huang

Chien-Hsin Liu

Cheng-Yuan Wang

Chien-Chung Ho

Pi-Cheng Hsiu

Yi-Ching Liu

Kuo-Pin Chang

Chih-Chang Hsieh

Te-Wei Chen

Chia-Lin Yang

Tse-Yuan Wang

Yiching Liu

Hsiang-Yun Cheng

Yueh-Han Wu

Hung-Sen Kuo

Ming-Wan Kuan

Chun-Ta Lin

Ping-Chun Chang

Tzu-Hsien Yang

I-Ching Tseng

Chun-Hung Lai

A circuit for in-memory multiply-and-accumulate functions includes a plurality of NAND blocks. A NAND block includes an array of NAND strings, including B columns and S rows, and L levels of memory cells. W word lines are coupled to (B*S) memory cells in respective levels in the L levels. A source line is coupled to the (B*S) NAND strings in the block. String select line drivers supply voltages to connect NAND strings on multiple string select lines to corresponding bit lines simultaneously. Word line drivers are coupled to apply word line voltages to a word line or word lines in a selected level. A plurality of bit line drivers apply input data to the B bit lines simultaneously. A current sensing circuit is coupled to the source line.

NAND block architecture for in-memory multiply-and-accumulate operations

A processor receives, from an input device, input data for processing. Upon determining that the input data corresponds to an artificial intelligence (AI) application, the processor generates an AI command for performing read or write operations for a memory device that is configured to store data for a plurality of applications including the AI application, the AI command characterized by an operational code and including information about one or more components of the AI application corresponding to the input data. The processor sends the AI command and the input data to a storage controller managing the memory device, wherein the read or write operations for the memory device are performed by the storage controller using the operational code and the information included in the AI command. The processor receives, from the storage controller, a result of the read or write operations performed on the memory device.

Data storage for artificial intelligence-based applications

A memory device includes: a memory array used for implementing neural networks (NN); and a controller coupled to the memory array. The controller is configured for: in updating and writing unrewritable data into the memory array in a training phase, marching the unrewritable data into a buffer zone of the memory array; and in updating and writing rewritable data into the memory array in the training phase, marching the rewritable data by skipping the buffer zone.

Memory device and wear leveling method for the same

A computation method and a computation apparatus exploiting weight sparsity, adapted for a processor to perform multiply-and-accumulate operations on a memory including multiple input and output lines crossing each other. In the method, weights are mapped to the cells of each operation unit (OU) in the memory. The rows of the cells of each OU are compressed by removing at least one row of the cells each mapped with a weight of 0, and an index including values each indicating a distance between every two rows of the cells including at least one cell mapped with a non-zero weight for each OU is encoded. Inputs are inputted to the input lines corresponding to the rows of each OU excluding the rows of the cells with the weight of 0 according to the index and outputs are sensed from the output lines corresponding to the OU to compute a computation result.

Computation method and apparatus exploiting weight sparsity

A memory device includes: a memory array used for implementing neural networks (NN), the NN including a plurality of layers; and a controller coupled to the memory array, the controller being configured for: determining a computation duration of a first data of a first layer of the plurality of layers; selecting a first program operation if the computation duration of the first data of the first layer is shorter than a threshold; and selecting a second program operation if the computation duration of the first data of the first layer is longer than the threshold, wherein the second program operation has a longer program pulse time than the first program operation.

Memory device for neural networks

A computing in memory method for a memory device is provided. The computing in memory method includes: based on a stride parameter, unfolding a kernel into a plurality of sub-kernels and a plurality of complement sub-kernels; based on the sub-kernels and the complement sub-kernels, writing a plurality of weights into a plurality of target memory cells of a memory array of the memory device; inputting an input data into a selected word line of the memory array; performing a stride operation in the memory array; temporarily storing a plurality of partial sums; and summing the stored partial sums into a stride operation result when all operation cycles are completed.

Memory device and computing in memory method thereof

A memory device includes an array of composite memory units. At least one of the composite memory units comprises a first memory cell of a first type, a second memory cell of a second type, a first intra-unit data path connecting the first memory cell to the second memory cell, and a first data path control switch. The first data path control switch is responsive to a data transfer enable signal which enables data transfer between the first memory cell and the second memory cell through the first intra-unit data path.

Memory devices and methods for operating the same

A flash memory device and a controlling method are provided. The flash memory device includes a memory array, an in-place update module, an out-of-place update module and a latency-aware module. The in-place update module is used for performing a program procedure or a garbage collection procedure via a bit erase operation or a page erase operation on the memory array. The out-of-place update module is used for performing the program procedure or the garbage collection procedure via a block erase operation or a migration operation on the memory array. The latency-aware module is used for determining a relationship between a first overhead of the in-place update module and a second overhead of the out-of-place update module.

Flash memory device and controlling method thereof

A circuit test method for a test device to test a device under test is provided. The circuit test method includes the steps of applying zero volts to a plurality of power pins of the device under test; applying a test voltage to a first signal pin among a plurality of signal pins of the device under test; and measuring a current on a second signal pin among the plurality of signal pins of the device under test and determining whether there is a leakage current in the device under test.

Test methods for packaged integrated circuits

Disclosed is a management system for managing a memory device having sub-chips each having a container area and a data area. A CPU selects a target sub-chip according to respective temperature of the sub-chips. When the CPU intends to access a first original data in one of the data areas, a hot date tracking device acquires a first original address of the first original data from the CPU. When the first original address is recorded in one of a plurality of tracking layers, the CPU is indicated to access a first copied data corresponding to the first original data in the container area of the target sub-chip according to a current tracking layer recording the first original address. When the first original address is not recorded in the tracking layers, the CPU accesses the first original data in the data area according to the first original address.

Management system for managing memory device and management method for managing the same

A data allocating method includes steps of: determining whether data to be written into a physical memory block is hot data or cold data; when the data is hot data, according to a hot data allocating order, searching at least one first empty sub-block from the physical memory block to allocate the data; when the data is cold data, according to a cold data allocating order, searching at least one second empty sub-block from the physical memory block to allocate the data.

Data allocating method and electric system using the same

A method for writing data into a persistent storage device includes grouping a plurality of data entries stored in a temporary storage device to form a data unit, such that the data unit has a size equal to an integer multiple of a size of an access unit of the persistent storage device. The method further includes writing the data unit into the persistent storage device.

Method, apparatus, and storage medium for writing data into persistent storage device

A memory device includes a memory controller and a non-volatile memory communicatively coupled to the memory controller and storing a mapping table and a journal table. The memory controller is configured to write data and a logical address of the data into the non-volatile memory, load mapping information related to the logical address of the data from the mapping table of the non-volatile memory into a mapping cache of the memory controller, update the mapping cache with an updated mapping relationship between the logical address of the data and a physical address of the data, and perform a journaling operation to write the updated mapping relationship into the journal table.

Memory device and operating method of same

A cache system is provided. The cache system includes a first cache and a second cache. The first cache is configured for storing a first status of a plurality of data. The second cache is configured for storing a table. The table includes the plurality of data arranged from a highest level to a lowest level. The cache system is configured to update the first status of the plurality of data in the first cache. The cache system is further configured to update the table in the second cache according to the first status of the plurality of data.

Cache controlling method for memory system and cache system thereof

A memory system is provided. The memory system includes a memory controller and a first memory block. The first memory block is configured to store a first data from a top of the first memory block in a top-down fashion. The first memory block is configured to store a first metadata corresponding to the first data from a bottom of the first memory block in a bottom-up fashion. The first data forms a first data area. The first metadata forms a first metadata area. And a first continuous space is formed between a bottom of the first data area and a top of the first metadata area.

Growing community of inventors

Taipei, Taiwan

Hung-Sheng Chang