Intel Corporation

Sony Group Corporation

Sk Hynix Nand Product Solutions Corp.

Sony Corporation

Bill Nale

Kuljit Singh Bains

Christopher E Cox

James A McCall

George Vergis

Robert G Blankenship

Raj K Ramanujan

Tessil Thomas

Brian S Morris

Taarinya Polepeddi

Jun Zhu

Rajat Agarwal

Muthukumar Swaminathan

Murugasamy K Nachimuthu

Pete D Vogt

Wei P Chen

Kirk S Yap

Tuan M Quach

John B Halbert

Jeffrey Charles Swanson

Debaleena Das

Chong J Zhao

John R Goles

Eric L Hendrickson

Christopher P Mozak

Suneeta Sah

Akshith Vasanth

David Wyatt

Arvind A Kumar

Yen-Cheng Liu

Raghunandan Makaram

Jongwon Lee

Mahesh S Natu

Jun Shi

Animesh Mishra

Howard S David

Tonia G Morris

Jacob Doweck

John V Lovelace

Jeff Willey

Sandeep K Jain

Sreenivas Mandava

Duane E Galbi

Jonathan C Jasper

Tomer Levy

Konika Ganguly

Dean-Dexter R Eugenio

Aiswarya M Pious

Phani Kumar Alaparthi

Zibing Yang

Amir Ali Radjai

Thomas Dean Skelton

Ronald D Anderson

Murugasamy M Nachimuthu

Muthukuman P Swaminathan

Lawrence Blankenbeckler

Yanjie Zhu

Raji James

James A Mccall

A memory device can internally track row address activates for perfect row hammer tracking, incrementing an activate count for each row when an access command is received for a row. Instead of incrementing the count for each activate, the memory controller can indicate a number greater than one for the memory device to increment the count, and then indicate not to increment the count for subsequent accesses up to the number indicated. The memory controller can determine whether the row address of an activate command is one of N recent row addresses that received the access command. The memory controller can indicate an increment of zero if the row address is one of the N recent addresses, and indicate an increment of a number higher than one if the row address is not one of the N recent addresses.

Perfect row hammer tracking with multiple count increments

A memory subsystem includes multiple memory resources connected in parallel, including a first memory resource and a second memory resource. The memory subsystem can split a portion of data into multiple sub-portions. Split into smaller portions, the system needs fewer ECC (error checking and correction) bits to provide the same level of ECC protection. The portion of data can include N ECC bits for error correction, and the sub-portions can each include a sub-portion of (N−M) ECC bits for error correction. The system can then use M bits of data for non-ECC purposes, such as metadata.

Distribution of error checking and correction (ECC) bits to allocate ECC bits for metadata

A memory chip includes row hammer threat detection circuitry. The memory chip includes an output. The memory chip includes backpressure signal generation circuitry coupled between the row hammer detection circuitry and the output. The backpressure signal generation circuitry is to generate a backpressure signal to be sent from the output in response to detection by the row hammer threat detection circuitry of a row hammer threat.

Method and apparatus for memory chip row hammer threat backpressure signal and host side response

A method is described. The method includes a buffer semiconductor chip receiving a plurality of data signals. The method includes the buffer chip calculating first CRC information from the plurality of data signals. The method includes the buffer chip transmitting the plurality of data signals in parallel with the first CRC information if a read burst transfer sequence is being performed, the buffer chip receiving second CRC information in parallel with the plurality of data signals and comparing the first CRC information with the second CRC information if a write burst transfer sequence is being performed.

Buffer that supports burst transfers having parallel CRC and data transmissions

For a memory device where a data fetch accesses N/2 data bits, and the memory device is to transfer N bits over a data burst of length M in response to a read command, the memory device accesses the same bank twice to access the N bits. Instead of accessing N/2 bits from two different banks, the memory device accesses a single bank twice. The memory device can control the timing of the data transfer to enable sending all N data bits to the memory controller for the read command. The memory device can send data as a first transfer of burst length M/2 of a first N/2 data bit portion and a second transfer of burst length M/2 of a second N/2 data bit portion.

Double fetch for long burst length memory data transfer

A system provides a mailbox communication register for communication between a host and a mode register. The mode register is to store configuration information, and write of configuration information to the mode register by the host takes less time than a read of the configuration information from the mode register by the host. The communication register is separate from the mode register and provides a location to store the configuration information for a read by the host. In response to a read request by the host, the mode register can copy the configuration information to the communication register and allow the host to read the register based on different timing rules than those that apply to the mode register. Instead of reading directly from a register that has timing variance between read and write, the host can read from a communication register.

Reading from a mode register having different read and write timing

A method, apparatus and system. The method includes: performing one or more training iterations to tune a target clock signal frequency to be applied at a memory device, each of the one or more training iterations including: causing a modified clock signal frequency to be applied at the memory device; and decoding a quality feedback message from the memory device including an indication of a performance of the clock signal frequency at the memory device; and in response to a determination that the performance of the clock signal frequency falls within a target performance range of the memory device and that the clock signal frequency is below the target clock signal frequency, performing a subsequent training iteration of the one or more training iterations, and otherwise causing application at the memory device, during a memory operation, of a highest clock signal frequency corresponding to a training iteration for which performance of the clock signal was within the target performance range.

Apparatus, system and method to detect and improve an input clock performance of a memory device

Self-test and repair of memory cells is performed in a memory integrated circuit by two separate processes initiated by a memory controller communicatively coupled to the memory integrated circuit. To ensure that the repair process is completed in the event of an unexpected power failure, a first process is initiated by the memory controller to perform a memory Built-in Self Test (mBIST) in the memory integrated circuit and a second process is initiated by the memory controller after the mBIST has completed to perform repair of faulty memory cells detected during the MBIST process. The memory controller does not initiate the repair process if a power failure has been detected. In addition, a repair time associated with the repair process is selected such that the repair time is sufficient to complete the repair process while power is stable, if a power failure occurs after the repair process has been started.

Dynamic random access memory built-in self-test power fail mitigation

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.

Memory chip with per row activation count having error correction code protection

An apparatus is described. The apparatus includes a register clock driver (RCD) semiconductor chip having first inputs to receive first command and address (CA) signals from a first sub-channel and first outputs to drive first and second instances of the CA information that are decoded from the first CA signals. The RCD semiconductor chip has second inputs to receive second command and address (CA) signals from a second sub-channel. The RCD semiconductor chip has a multiplexer having a first input channel to receive the first CA signals and a second input channel to receive the second CA signals. The RCD semiconductor chip has second outputs to drive third and fourth instances of the first CA information or first and second instances of the second CA information that are decoded from the second CA signals depending on which of the first and second input channels of the multiplexer is selected.

High performance memory module with reduced loading

Examples described herein relate to a device that includes: a first power rail to provide a signal from a power source to a reference supply voltage pin of a memory controller; a second power rail to provide a signal from the power source to an output buffer pin of the memory controller and to an output buffer pin of a central processing unit (CPU). In some examples, the second power rail is separate from the first power rail, during a high power state, the power source is to supply a same voltage to each of the reference supply voltage pin, the output buffer pin of the memory controller, and the output buffer pin of the CPU, and during a connected standby state, the power source is to reduce voltage provided to the output buffer pin of the memory controller and the output buffer pin of the CPU using the second power rail and maintain a voltage provided to the reference supply voltage pin.

Power control of a memory device in connected standby state

A memory device with internal row hammer mitigation couples to a memory controller. The memory controller or host can assist with row hammer mitigation by sending additional refresh cycles or refresh commands. In response to an extra refresh command the memory device can perform refresh for row hammer mitigation instead of refresh for standard data integrity. The memory controller can keep track of the number of activate commands sent to the memory device, and in response to a threshold number of activate commands, the memory controller sends the additional refresh command. With the extra refresh command the memory device can refresh the potential victim rows of a potential aggressor row, instead of simply refreshing a row that has not been accessed for a period of time.

Refresh command control for host assist of row hammer mitigation

An embodiment of an electronic memory apparatus may include storage media, and logic communicatively coupled to the storage media, the logic to determine if a mode is set to one of a first mode or a second mode, perform a soft post package repair in the first mode, and undo the soft post package repair in the second mode. Other embodiments are disclosed and claimed.

Undo and redo of soft post package repair

A memory device is described. The memory device includes logic circuitry to perform calibrations of resistive network terminations and data drivers of the memory device while the memory device is within a self refresh mode.

Periodic calibrations during memory device self refresh

An apparatus is described. The apparatus includes logic circuitry to multiplex on a data bus a first data burst, a second data burst, a third data burst and a fourth data burst having different respective base target addresses that respectively target a first memory rank, a second memory rank, a third memory rank and a fourth memory rank. A first data transfer for the first data burst occurs on a first edge of a first pulse of a data strobe signal for the data bus and a second data transfer for the second data burst occurs on a second edge of the first pulse of the data strobe signal. A third data transfer for the third data burst occurs on a first edge of a second pulse of the data strobe signal for the data bus and a fourth data transfer for the fourth data burst occurs on a second edge of the second pulse. The second pulse immediately follows the first pulse on the data strobe signal. The first memory rank, the second memory rank, the third memory rank and the fourth memory rank are on a same memory module.

Synchronous dynamic random access memory (SDRAM) dual in-line memory module (DIMM) having increased per data pin bandwidth

Growing community of inventors

Livermore, CA, United States of America

Bill Nale