摘要:
A memory controller issues a targeted refresh command in response to detection by a distributed detector. A memory device includes detection logic that monitors for a row hammer event, which is a threshold number of accesses to a row within a time threshold that can cause data corruption to a physically adjacent row (a “victim” row). The memory device sends an indication of the row hammer event to the memory controller. In response to the row hammer event indication, the memory controller sends one or more commands to the memory device to cause the memory device to perform a targeted refresh that will refresh the victim row.
摘要:
Methods and apparatus to improve throughput in memory devices are described. In one embodiment, memory throughput is increased via fine granularity of precharge management. In an embodiment, three separate precharge timings may be used, e.g., optimized per memory bank, per memory bank group, and/or per a memory device. Other embodiments are also disclosed and claimed.
摘要:
Techniques and mechanisms for exchanging information between a memory controller and a memory device. In an embodiment, a memory controller receives information indicating for a memory device a threshold number of pending consolidated activation commands to access that memory device. The threshold number indicated by the information is less than a theoretical maximum number of pending consolidated activation commands, the theoretical maximum number defined based on timing parameters of the memory device. In another embodiment, the memory controller limits communication of consolidated activation commands to the memory device based on the information indicating the threshold number.
摘要:
A memory controller issues a targeted refresh command. A specific row of a memory device can be the target of repeated accesses. When the row is accessed repeatedly within a time threshold (also referred to as “hammered” or a “row hammer event”), physically adjacent row (a “victim” row) may experience data corruption. The memory controller receives an indication of a row hammer event, identifies the row associated with the row hammer event, and sends one or more commands to the memory device to cause the memory device to perform a targeted refresh that will refresh the victim row.
摘要:
Methods and apparatus to improve throughput in memory devices are described. In one embodiment, memory throughput is increased via fine granularity of precharge management. In an embodiment, three separate precharge timings may be used, e.g., optimized per memory bank, per memory bank group, and/or per a memory device. Other embodiments are also disclosed and claimed.
摘要:
Provision and use of sets of isolators to enable the caching of the contents of at least one row of memory cells within a subarray of a bank of a memory device by a row of sense amplifiers associated with the subarray to enable faster access to read the contents of that at least one row through a read operation causing the data to read from the row of sense amplifiers versus from the row of memory cells, directly.
摘要:
Techniques and mechanisms to provide selective access to data error information by a memory controller. In an embodiment, a memory device stores a first value representing a baseline number of data errors determined prior to operation of the memory device with the memory controller. Error detection logic of the memory device determines a current count of data errors, and calculates a second value representing a difference between the count of data errors and the baseline number of data errors. The memory device provides the second value to the memory controller, which is unable to identify that the second value is a relative error count. In another embodiment, the memory controller is restricted from retrieving the baseline number of data errors.
摘要:
Exposing internal error correction bits from a memory device for use as metadata bits by an external memory controller. In a first mode the memory device applies internal error correction bits for internal error correction at the memory device. In a second mode the memory device exposes the internal error correction bits to the memory controller to allow the memory controller to use the data.
摘要:
A memory controller issues a targeted refresh command. A specific row of a memory device can be the target of repeated accesses. When the row is accessed repeatedly within a time threshold (also referred to as “hammered” or a “row hammer event”), physically adjacent row (a “victim” row) may experience data corruption. The memory controller receives an indication of a row hammer event, identifies the row associated with the row hammer event, and sends one or more commands to the memory device to cause the memory device to perform a targeted refresh that will refresh the victim row.
摘要:
Techniques and mechanisms for determining a count of accesses to a row of a memory device. In an embodiment, the memory device includes a counter comprising circuitry to increment a value of the count in response to detecting a command to activate the row. Circuitry of counter may further set a value of the count to a baseline value in response to detecting a command to refresh the row. In another embodiment, the memory device includes evaluation logic to compare a value of the count to a threshold value. A signal is generated based on the comparison to indicate whether a row hammer event for the row is indicated.