Abstract: A memory system may comprise a plurality of data strobe transfer paths assigned to a plurality of data transfer paths such that each of the plurality of data strobe transfer paths may be shared by the plurality of data transfer paths. At least one selected data strobe transfer path is selected and data signals transferred through the plurality of data transfer paths are sampled using at least one data strobe signal transferred through the selected data strobe transfer path. Reliability of data communication is enhanced through a redundant data strobe scheme by assigning a plurality of data strobe transfer paths to a plurality of data transfer paths such that the plurality of data strobe transfer paths may be shared by the plurality of data transfer paths.

Abstract: A tensor computation dataflow accelerator semiconductor circuit is disclosed. The data flow accelerator includes a DRAM bank and a peripheral array of multiply-and-add units disposed adjacent to the DRAM bank. The peripheral array of multiply-and-add units are configured to form a pipelined dataflow chain in which partial output data from one multiply-and-add unit from among the array of multiply-and-add units is fed into another multiply-and-add unit from among the array of multiply-and-add units for data accumulation. Near-DRAM-processing dataflow (NDP-DF) accelerator unit dies may be stacked atop a base die. The base die may be disposed on a passive silicon interposer adjacent to a processor or a controller. The NDP-DF accelerator units may process partial matrix output data in parallel. The partial matrix output data may be propagated in a forward or backward direction. The tensor computation dataflow accelerator may perform a partial matrix transposition.

Abstract: A general matrix-matrix multiplication (GEMM) dataflow accelerator circuit is disclosed that includes a smart 3D stacking DRAM architecture. The accelerator circuit includes a memory bank, a peripheral lookup table stored in the memory bank, and a first vector buffer to store a first vector that is used as a row address into the lookup table. The circuit includes a second vector buffer to store a second vector that is used as a column address into the lookup table, and lookup table buffers to receive and store lookup table entries from the lookup table. The circuit further includes adders to sum the first product and a second product, and an output buffer to store the sum. The lookup table buffers determine a product of the first vector and the second vector without performing a multiply operation. The embodiments include a hierarchical lookup architecture to reduce latency. Accumulation results are propagated in a systolic manner.

Abstract: A memory module includes: a non-volatile memory; and an asynchronous memory interface to interface with a memory controller. The asynchronous memory interface may use repurposed pins of a double data rate (DDR) memory channel to send an asynchronous data to the memory controller. The asynchronous data may be device feedback indicating a status of the non-volatile memory.

Abstract: A memory module includes: a non-volatile memory; and an asynchronous memory interface to interface with a memory controller. The asynchronous memory interface may use repurposed pins of a double data rate (DDR) memory channel to send an asynchronous data to the memory controller. The asynchronous data may be device feedback indicating a status of the non-volatile memory.

Abstract: A high bandwidth memory (HBM) system includes a first HBM+ card. The first HBM+ card includes a plurality of HBM+ cubes. Each HBM+ cube has a logic die and a memory die. The first HBM+ card also includes a HBM+ card controller coupled to each of the plurality of HBM+ cubes and configured to interface with a host, a pin connection configured to connect to the host, and a fabric connection configured to connect to at least one HBM+ card.

Abstract: A memory module includes a memory array, an interface and a controller. The memory array includes an array of memory cells and is configured as a dual in-line memory module (DIMM). The DIMM includes a plurality of connections that have been repurposed from a standard DIMM pin out configuration to interface operational status of the memory device to a host device. The interface is coupled to the memory array and the plurality of connections of the DIMM to interface the memory array to the host device. The controller is coupled to the memory array and the interface and controls at least one of a refresh operation of the memory array, control an error-correction operation of the memory array, control a memory scrubbing operation of the memory array, and control a wear-level control operation of the array, and the controller to interface with the host device.

Abstract: A memory system includes: one or more memory modules, each comprising a plurality of memory devices having corresponding write commit policies; and one or more memory controllers coupled to the one or more memory modules, the one or more memory controllers having a configurable write operation protocol to operate with the memory devices according to the corresponding write commit policies.

Abstract: A hardware coding mechanism is described. The coding mechanism may include a first encoder to produce a first code using a base number of bits and a second encoder to produce a second code using a supplementary number of bits. The second code and the first code together may be stronger than the first code alone. A mode register stored in a storage may specify whether a switch to the second encoder is open or closed: the first coder is always used.

Abstract: According to one general aspect, an apparatus may include a plurality of stacked integrated circuit dies that include a memory cell die and a logic die. The memory cell die may be configured to store data at a memory address. The logic die may include an interface to the stacked integrated circuit dies and configured to communicate memory accesses between the memory cell die and at least one external device. The logic die may include a reliability circuit configured to ameliorate data errors within the memory cell die. The reliability circuit may include a spare memory configured to store data, and an address table configured to map a memory address associated with an error to the spare memory. The reliability circuit may be configured to determine if the memory access is associated with an error, and if so completing the memory access with the spare memory.

Abstract: A method for addressing memory device data arranged in rows and columns indexed by a first number of row address bits and a second number of column address bits, and addressed by a row command specifying a third number of row address bits followed by a column command specifying a fourth number of column address bits, the first number being greater than the third number or the second number being greater than the fourth number, includes: splitting the first number of row address bits into first and second subsets, and specifying the first subset in the row command and the second subset in a next address command when the first number is greater than the third number; otherwise splitting the second number of column address bits into third and fourth subsets, and specifying the fourth subset in the column command and the third subset in a previous address command.

Abstract: A method of deduplicating memory in a memory module includes identifying a hash table array including hash tables each corresponding to a hash function, and each including physical buckets, each physical bucket including ways and being configured to store data, identifying a plurality of virtual buckets each including some of the physical buckets, and each sharing at least one of the physical buckets with another of the virtual buckets, hashing a block of data according to a corresponding one of the hash functions to produce a hash value, determining whether an intended physical bucket has available space for the block of data according to the hash value, and determining whether a near-location physical bucket has available space for the block of data when the intended physical bucket does not have available space, the near-location physical bucket being in a same one of the virtual buckets as the intended physical bucket.

Abstract: A method of coordinating memory commands in a high-bandwidth memory HBM+ system, the method including sending a host memory controller command from a host memory controller to a memory, receiving the host memory controller command at a coordinating memory controller, forwarding the host memory controller command from the coordinating memory controller to the memory, and scheduling, by the coordinating memory controller, a coordinating memory controller command based on the host memory controller command.

Abstract: A data chip that may pollute data is disclosed. The data chip may include a data array, read circuitry to read raw data from the data array, and a buffer to store the raw data. Using a pollution pattern stored in a mask register, a data pollution engine may pollute the raw data. Transmission circuitry may then transmit the polluted data.

Abstract: A data chip that may pollute data is disclosed. The data chip may include a data array, read circuitry to read raw data from the data array, and a buffer to store the raw data. Using a pollution pattern stored in a mask register, a data pollution engine may pollute the raw data. Transmission circuitry may then transmit the polluted data.

Abstract: A data chip that may pollute data is disclosed. The data chip may include a data array, read circuitry to read raw data from the data array, and a buffer to store the raw data. Using a pollution pattern stored in a mask register, a data pollution engine may pollute the raw data. Transmission circuitry may then transmit the polluted data.

Abstract: A method for replacing data on a volatile memory cache is provided. The volatile memory cache includes one or more memory banks and each of the memory banks includes a plurality of memory lines. The method includes: identifying a replacement ID for at least one of the memory lines to be replaced; identifying a refresh bank ID for one of the memory banks to be refreshed; determining whether or not a conflict exists between the replacement ID and the refresh bank ID; and selecting a new replacement ID if the conflict exists.

Abstract: A memory module includes a random access memory (RAM) device that includes a first storage region and a second storage region, a nonvolatile memory device, and a controller that controls the RAM device or the nonvolatile memory device under control of a host. The controller includes a data buffer that temporarily stores first data received from the host, and a buffer returning unit that transmits first release information to the host when the first data are moved from the data buffer to the first storage region or the second storage region of the RAM device and transmits second release information to the host when the first data are moved from the second storage region to the nonvolatile memory device.

Abstract: A method of page size aware scheduling and a non-transitory computer-readable storage medium having recorded thereon a computer program for executing the method of page size aware scheduling are provided. The method includes determining a size of a media page; determining if the media page is open or closed; performing, by a memory controller, a speculative read operation if the media page is determined to be open; and performing, by the memory controller, a regular read operation if the media page is determined to be closed.

Abstract: A memory module includes a plurality of memory components, an in-memory power manager, and an interface to a host computer over a memory bus. The in-memory power manager is configured to control a transition of a power state of the memory module. The transition of the power state of the memory module includes a direct transition from a low power down state to a maximum power down state.