Abstract: Per channel thermal management techniques are described herein. In one example, a memory controller receives channel temperature information for one or more channels of one or more dies in the stack. The memory controller can then throttle commands at a channel-level based on the channel temperature information. In one example, row commands and column commands to a channel are throttled at independent rates based on the channel temperature information. In one example, a row command throttling rate or column command throttling rate is based on a ratio of alternating on-time to off time of throttling signals, or a window of time in which commands are enabled or disabled to a channel. In one example, the row and column command throttling signals can be staggered across channels or pseudo channels.

Abstract: A system can predict memory device failure through identification of correctable error patterns based on the memory architecture. The failure prediction can thus account for the circuit-level of the memory rather than the mere number or frequency of correctable errors. A failure prediction engine correlates hardware configuration of the memory device with correctable errors (CEs) detected in data of the memory device to predict an uncorrectable error (UE) based on the correlation.

Abstract: A memory subsystem includes memory devices with space dynamically allocated for improvement of reliability, availability, and serviceability (RAS) in the system. Error checking and correction (ECC) logic detects an error in all or a portion of a memory device. In response to error detection, the system can dynamically perform one or more of: allocate active memory device space for sparing to spare a failed memory segment; write a poison pattern into a failed cacheline to mark it as failed; perform permanent fault detection (PFD) and adjust application of ECC based on PFD detection; or, spare only a portion of a device and leave another portion active, including adjusting ECC based on the spared portion. The error detection can be based on bits of an ECC device, and error correction based on those bits and additional bits stored on the data devices.

Abstract: A memory is described. The memory includes row buffer circuitry to store a page. The page is divided into sections, wherein, at least one of the sections of the page is to be sequestered for the storage of meta data, and wherein, a first subset of column address bits is to: 1) define a particular section of the page, other than the at least one sequestered sections of the page, whose data is targeted by a burst access; and, 2) define a field within the at least one of the sequestered sections of the page that stores meta data for the particular section.

Abstract: A memory device having on-die error checking and correction (ECC) circuitry can provide uncorrected data in response to a read command. The ECC circuitry can perform error correction for errors detected, generating the corrected data in parallel with providing the uncorrected data. The memory device stores the corrected data internally to the memory device. When an error is detected, the memory device provides an indication to the memory controller, which can then request the corrected data.

Abstract: A memory chip is described. The memory chip includes storage cells along a row of the memory chip's storage cell array to store a count value of the row's activations and error correction code (ECC) information to protect the count value. The memory chip includes ECC read logic circuitry to correct an error in the count value. The memory chip includes a comparator to compare the count value against a threshold. The memory chip includes circuitry to increment the count value if the count value is deemed not to have reached the threshold and ECC write logic circuitry to determine new ECC information for the incremented count value, and write driver circuitry to write the incremented count value and the new ECC information into the storage cells. The memory chip includes circuitry to cause the row to be refreshed if the count value is deemed to have reached the threshold.

Abstract: Techniques to couple a high bandwidth memory device on a silicon substrate and a package substrate are disclosed. Examples include selectively activating input/out (I/O) or command and address (CA) contacts on a bottom side of a logic layer for the high bandwidth device based on a mode of operation. The I/O and CA contacts are for accessing one or more memory devices include in the high bandwidth memory device via one or more data channels.

Abstract: In embodiments herein, an integrated circuit device includes a logic die with processor circuitry and a memory die coupled to the logic die. The memory die includes a first memory module comprising a first memory bank and first control circuitry, a second memory module comprising a second memory bank and second control circuitry, and a scribe line on a surface of the memory die between the first memory module and the second memory module. The first memory module is not electrically connected to the second memory module, and each memory module include through silicon vias (TSVs) to electrically connect a top side of the memory module and a bottom side of the memory module (e.g., for three-dimensional stacking in the integrated circuit device).

Abstract: In a memory system, a memory device has a memory array with multiple rows of memory having logical addresses mapped to their physical addresses and at least one spare row not having a logical address mapped to its physical address. A controller detects a failure of one of the multiple rows of memory (“failure row”) and executes a post package repair (PPR) mode. The controller can be internal to the memory device or external to the memory device. The memory device includes an internal scratchpad to allow transfer of data contents from the failure row to the spare row. The controller can map the logical address of the failure row from the physical address of the failure row to the physical address of the spare row, transfer data contents from the failure row to the internal scratchpad, and transfer the data contents from the internal scratchpad to the spare row.

Abstract: A memory device that performs internal ECC (error checking and correction) can selectively return read data with application of the internal ECC or without application of the internal ECC, in response to different read commands from the memory controller. The memory device can normally apply ECC and return corrected data in response to a normal read command. In response to a retry command, the memory device can return the read data without application of the internal ECC.

Abstract: Techniques to couple a high bandwidth memory device on a silicon substrate and a package substrate are disclosed. Examples include selectively activating input/out (I/O) or command and address (CA) contacts on a bottom side of a logic layer for the high bandwidth device based on a mode of operation. The I/O and CA contacts are for accessing one or more memory devices include in the high bandwidth memory device via one or more data channels.

Abstract: A memory device that performs internal ECC (error checking and correction) can treat an N-bit channel as two N/2-bit channels for application of ECC. The memory device includes a memory array to store data and prefetches data bits and error checking and correction (ECC) bits from the memory array for a memory access operation. The memory device includes internal ECC hardware to apply ECC, with a first group of a first half the data bits checked by a first half of the ECC bits in parallel with a second group of a second half of the data bits checked by a second half of the ECC bits.

Abstract: Techniques to couple a high bandwidth memory device on a silicon substrate and a package substrate are disclosed. Examples include selectively activating input/out (I/O) or command and address (CA) contacts on a bottom side of a logic layer for the high bandwidth device based on a mode of operation. The I/O and CA contacts are for accessing one or more memory devices include in the high bandwidth memory device via one or more data channels.

Abstract: A memory subsystem triggers entry and exit of a memory device from low power mode with a chip select (CS) signal line. For a system where the command bus has no clock enable (CKE) signal line, the system can trigger low power modes with CS instead of CKE. The low power mode can include a powerdown state. The low power mode can include a self-refresh state. The memory device includes an interface to the command bus, and receives a CS signal combined with command encoding on the command bus to trigger a low power mode state change. The memory device can be configured to monitor the CS signal and selected other command signals while in low power mode. The system can send an ODT trigger while the memory device is in low power mode, even without a dedicated ODT signal line.

Abstract: A memory device that performs internal ECC (error checking and correction) can selectively return read data with application of the internal ECC or without application of the internal ECC, in response to different read commands from the memory controller. The memory device can normally apply ECC and return corrected data in response to a normal read command. In response to a retry command, the memory device can return the read data without application of the internal ECC.

Abstract: A memory device that performs internal ECC (error checking and correction) can treat an N-bit channel as two N/2-bit channels for application of ECC. The ECC for an N/2-bit channel is simpler than the ECC for N bits, and thus, each N/2-bit portion can be separately correctable when treated as two N/2-bit portions. The memory device can include an additional hardware for the application of ECC to the channel as two sub-channels. For example, the memory device can include an additional subarray to store ECC bits for the internal ECC to enable the application of ECC to two sub-channels of the N-bit channel. The memory device can include an additional driver to access the additional subarray when applied.

Abstract: An embodiment of a memory device includes technology for a memory cell array logically organized in two or more banks of at least two rows and two columns per bank, and two or more local caches respectively coupled to the two or more banks of the memory cell array, where each local cache has a size which is an integer multiple of a memory page size of the memory cell array. Other embodiments are disclosed and claimed.

Abstract: Techniques to couple a high bandwidth memory device on a silicon substrate and a package substrate are disclosed. Examples include selectively activating input/out (I/O) or command and address (CA) contacts on a bottom side of a logic layer for the high bandwidth device based on a mode of operation. The I/O and CA contacts are for accessing one or more memory devices include in the high bandwidth memory device via one or more data channels.

Abstract: A memory subsystem enables managing error correction information. A memory device internally performs error detection for a range of memory locations, and increments an internal count for each error detected. The memory device includes ECC logic to generate an error result indicating a difference between the internal count and a baseline number of errors preset for the memory device. The memory device can provide the error result to an associated host of the system to expose only a number of errors accumulated without exposing internal errors from prior to incorporation into a system. The memory device can be made capable to generate internal addresses to execute commands received from the memory controller. The memory device can be made capable to reset the counter after a first pass through the memory area in which errors are counted.

Abstract: Techniques and mechanisms for providing termination for a plurality of chips of a memory device. In an embodiment, a memory device is an integrated circuit (IC) package which includes a command and address bus and a plurality of memory chips each coupled thereto. Of the plurality of memory chips, only a first memory chip is operable to selectively provide termination to the command and address bus. Of the respective on-die termination control circuits of the plurality of memory chips, only the on-die termination control circuit of the first memory chip is coupled via any termination control signal line to any input/output (I/O) contact of the IC package. In another embodiment, the plurality of memory chips are configured in a series with one another, and wherein the first memory chip is located at an end of the series.