Processor-guided execution of offloaded instructions using fixed function operations is disclosed. Instructions designated for remote execution by a target device are received by a processor. Each instruction includes, as an operand, a target register in the target device. The target register may be an architected virtual register. For each of the plurality of instructions, the processor transmits an offload request in the order that the instructions are received. The offload request includes the instruction designated for remote execution. The target device may be, for example, a processing-in-memory device or an accelerator coupled to a memory.

A memory expander includes a memory device having a first memory region corresponding to a first host and a second memory region corresponding to a second host. A controller communicates with the first host and the second host through a compute express link (CXL) interface. The controller receives a first CXL communication packet from the first host and performs a target data transfer operation of transferring target data stored in the first memory region to the second memory region, in response to the first CXL communication packet.

Memories and methods for performing an atomic memory operation are disclosed, including a memory having a memory store, operation logic, and a command decoder. Operation logic can be configured to receive data and perform operations thereon in accordance with internal control signals. A command decoder can be configured to receive command packets having at least a memory command portion in which a memory command is provided and data configuration portion in which configuration information related to data associated with a command packet is provided. The command decoder is further configured to generate a command control signal based at least in part on the memory command and further configured to generate control signal based at least in part on the configuration information.

A 3D-stacked memory device including: a base die including a plurality of switches to direct data flow and a plurality of arithmetic logic units (ALUs) to compute data; a plurality of memory dies stacked on the base die; and an interface to transfer signals to control the base die.

A memory device comprises a smart buffer, and a memory area divided into a first memory area and a second memory area, wherein the smart buffer comprises a priority setting unit configured to receive a sensing data and a corresponding weight from a controller, determine a priority of the sensing data based on the weight, and classify the sensing data as one of first priority sensing data and second priority sensing data, and a channel controller configured to allocate at least one channel selected from among a plurality of channels to a first channel group, allocate at least another channel selected from among the plurality of channels to a second channel group, assign the first channel group to process the first priority sensing data in relation to the first memory area, and assign the second channel group to process the second priority sensing data in relation to the second memory area, wherein a number of data input/output (I/O) pins connected to the first channel group is greater than a number of data I/O pins connected to the second channel group, wherein the memory area includes at least one memory chip, wherein the at least one memory chip includes a first chip having a first metal pad and a cell region and a second chip having a second metal pad and a peripheral circuit region, and the first chip and the second chip are vertically connected to each other by the first metal pad and the second metal pad.

A memory device including: a plurality of pins for receiving control signals from an external device; a first bank having first memory cells, wherein the first bank is activated in a first operation mode and a second operation mode; a second bank having second memory cells, wherein the second bank is deactivated in the first operation mode and activated in the second operation mode; a processing unit configured to perform an operation on first data, output from the first memory cells, and second data, output from the second memory cells, in the second operation mode; and a processing-in-memory (PIM) mode controller configured to select mode information, indicating one of the first operation mode and the second operation mode, in response to the control signals and to control at least one memory parameter, at least one mode register set (MRS) value, or a refresh mode according to the mode information.

A device and method for facilitating orthogonal data transposition during data transfers to/from a processing array and a storage memory since the data words processed by the processing array (using computational memory cells) are stored orthogonally to how the data words are stored in storage memory. Thus, when data words are transferred between storage memory and the processing array, a mechanism orthogonally transposes the data words.

A memory device including: a plurality of pins for receiving control signals from an external device; a first bank having first memory cells, wherein the first bank is activated in a first operation mode and a second operation mode; a second bank having second memory cells, wherein the second bank is deactivated in the first operation mode and activated in the second operation mode; a processing unit configured to perform an operation on first data, output from the first memory cells, and second data, output from the second memory cells, in the second operation mode; and a processing-in-memory (PIM) mode controller configured to select mode information, indicating one of the first operation mode and the second operation mode, in response to the control signals and to control at least one memory parameter, at least one mode register set (MRS) value, or a refresh mode according to the mode information.

An in-memory computing device including a plurality of memory cell arrays and a plurality of sensing amplifiers are provided. The memory cell arrays respectively receive a plurality of input signals. The input signals are divided into a plurality of groups. The groups respectively have at least one partial input signal. The at least one partial input signal of each of the groups has a same value. Numbers of the at least one partial input signal in the groups sequentially form a geometric sequence with a common ration equal to 2. The memory cell arrays respectively provide a plurality of weightings, and perform multiply-add operations respectively according to the received input signals and the weightings to generate a plurality of computation results. The sensing amplifiers respectively generate a plurality of sensing results according to the computation results.

A memory device including: a plurality of pins for receiving control signals from an external device; a first bank having first memory cells, wherein the first bank is activated in a first operation mode and a second operation mode; a second bank having second memory cells, wherein the second bank is deactivated in the first operation mode and activated in the second operation mode; a processing unit configured to perform an operation on first data, output from the first memory cells, and second data, output from the second memory cells, in the second operation mode; and a processing-in-memory (PIM) mode controller configured to select mode information, indicating one of the first operation mode and the second operation mode, in response to the control signals and to control at least one memory parameter, at least one mode register set (MRS) value, or a refresh mode according to the mode information.