Abstract: The disclosed technology provides techniques, systems, and apparatus for containing and recovering from uncorrectable memory errors in distributed computing environment. An aspect of the disclosed technology includes a hypervisor or virtual machine manager that receives signaling of an uncorrectable memory error detected by a host machine. The virtual machine manager then uses information received via the signaling to identify virtual memory addresses or memory pages associated with the corrupted memory element so as to allow for containment and recovery from the error.

Abstract: Technology is disclosed herein for managing parity data in non-volatile memory. As user data is programming into respective groups of non-volatile memory cells, the system accumulates parity data. The system may accumulate XOR parity based on successive bitwise XOR operations of user data. After programming is complete, the system performs a post-program read test of the data stored into each respective group of memory cells. The system re-calculates the parity data such that the parity data is no longer based on the user data that was stored in any group of memory cells for which the post-program read test failed. For example, the system will perform an additional bitwise XOR between the accumulated XOR parity data with the user data that was stored in the group of memory cells for which the post-program read test failed. The parity data is programmed to a group of memory cells.

Abstract: Techniques for migrating virtual machines (VMs) in the presence of uncorrectable memory errors are provided. According to one set of embodiments, a source host hypervisor of a source host system can determine, for each guest memory page of a VM to be migrated from the source host system to a destination host system, whether the guest memory page is impacted by an uncorrectable memory error in a byte-addressable memory of the source host system. If the source host hypervisor determines that the guest memory page is impacted, the source host hypervisor can transmit a data packet to a destination host hypervisor of the destination host system that includes error metadata identifying the guest memory page as being corrupted. Alternatively, if the source host hypervisor determines that the guest memory page is not impacted, the source host hypervisor can attempt to read the guest memory page from the byte-addressable memory in a memory exception-safe manner.

Abstract: Methods, systems, and devices for reporting control information errors are described. A state of a memory array may be monitored during operation. After detecting an error (e.g., in received control information), the memory device may enter a first state (e.g., a locked state) and may indicate to a host device that an error was detected, the state of the memory array before the error was detected , and/or at least a portion of a control signal carrying the received control information. The host device may diagnose a cause of the error based on receiving the indication of the error and/or the copy of the control signal. After identifying and/or resolving the cause of the error, the host device may transmit one or more commands (e.g., unlocking the memory device and returning the memory array to the original state) based on receiving the original state from the memory device.

Abstract: A system and method for detecting writes of data to errant locations in storage arrays. Address information and information redundant with address information is encoded and stored in proximity with data. Upon reading the stored data, the corresponding address information is decoded and compared to the address of the intended read. A mismatch indicates a possible write to an errant location.

Abstract: One embodiment provides an accelerator circuitry. The accelerator circuitry includes accelerator processor circuitry; accelerator memory circuitry; processor trace (PT) decoder circuitry and control flow integrity (CFI) checker circuitry. The PT decoder circuitry is to at least one of receive and/or retrieve PT data from a host device. The PT decoder circuitry is further to extract a target instruction pointer (TIP) packet from the PT data and to decode the TIP packet to yield a runtime target address. The CFI checker circuitry is to determine, at runtime, whether a control flow transfer of an indirect branch instruction to the runtime target address corresponds to a control flow violation based, at least in part, on control flow (CF) information (info) stored to an accelerator CF info store.

Abstract: A memory device may include a memory cell array, a bloom-filter circuit, a cache memory circuit, and a selecting circuit. The bloom-filter circuit may be configured to output a determination result signal that indicates that there is a possibility that a received address is one of failed addresses corresponding to failed cells of the memory cell array. The cache memory circuit may be configured to, store the failed addresses and a first set of data corresponding to the respective failed addresses, and configured to, when the determination result signal indicates a possibility, provide a comparison result signal by determining whether received address coincides with one of the failed addresses. The selecting circuit may be configured to output either first data of the first set of data or second data of the memory cell array corresponding to the received address based on determination result signal and comparison result signal.

Abstract: Systems and methods are provided for detecting and correcting address errors in a memory system. In the memory system, a memory device generates an error-detection code based on an address transmitted via an address bus and transmits the error-detection code to a memory controller. The memory controller transmits an error indication to the memory device in response to the error-detection code.

Abstract: The present invention provides a microcontroller which can continue operation even at the time of a failure without making a memory redundant to suppress increase in chip area. The microcontroller includes three or more processors executing the same process in parallel and a storage device. The storage device includes a memory mat having a storage region which is not redundant, an address selection part, a data output part, and a failure recovery part. The address selection part selects a storage region in the memory mat on the basis of three or more addresses issued at the time of an access by the processors. The data output part reads data from the storage region in the memory mat selected by the address selection part. The failure recovery part corrects or masks a failure of predetermined number or less which occurs in the memory mat, the address selection part, and the data output part.

Abstract: It is provided a storage system, comprising a storage device for storing data and at least one controller for controlling reading/writing of the data from/to the storage device. The at least one controller each includes a first cache memory for temporarily storing the data read from the storage device by file access, and a second cache memory for temporarily storing the data to be read/written from/to the storage device by block access. The processor reads the requested data from the storage device in the case where data requested by a file read request received from a host computer is not stored in the first cache memory, stores the data read from the storage device in the first cache memory without storing the data in the second cache memory, and transfers the data stored in the first cache memory to the host computer that has issued the file read request.

Abstract: A fuse test mode detection device is disclosed, which relates to a technology for improving detection efficiency of a fuse test mode. The fuse test mode detection device includes: a fuse unit configured to scan a plurality of fuses in a boot-up operation, and output fuse data; a counter configured to count the fuse data in response to a clock signal; a decoding unit configured to output a decoding signal for controlling a fuse test mode in response to an output signal of the counter; an encoder configured to encode the output signal of the decoding unit, and output a code signal; and a comparator configured to compare the fuse data with the code signal, and output a comparison signal.

Abstract: A method for testing an array fuse block of a semiconductor apparatus may include a series of operations for testing an array fuse block of the semiconductor apparatus as a test program is executed. The series operations may include the following steps: generating a test source file containing information for accessing the array fuse block; generating a test vector using the test source file; extracting repair confirmation information by performing a simulation using the test vector; extracting a repair confirmation information expected value from the test source file; and determining a pass or fail by comparing the repair confirmation information to the repair confirmation information expected value.

Abstract: A read only memory (ROM) with redundancy and methods of use are provided. The ROM with redundancy includes a programmable array coupled to a repair circuit having one or more redundant repairs. The one or more redundant repairs include a word address match logic block, a data I/O address, and a tri-state buffer. The word address match logic block is provided to the tri-state buffer as a control input and the data I/O address is provided to the tri-state buffer as an input. An output of the tri-state buffer of each redundant repair is provided as a first input to one or more logic devices. One or more data outputs of a ROM bit cell array is provided as a second input to a respective one of the one or more logic devices.

Abstract: According to one embodiment, a memory system includes a non-volatile memory, a resource managing unit that reclaims resources associated with the non-volatile memory and increases the resources, when the usage of the resources associated with the non-volatile memory reaches the predetermined amount, a transmission rate setting unit that calculates a setting value of the transmission rate to receive the write data from a host device, and a transmission control unit that receives the write data from the host device and transmits the received write data to the non-volatile memory. The transmission rate setting unit calculates a small setting value when the usage of the resources associated with the non-volatile memory increases. The transmission control unit executes the reception of the write data from the host device at the transmission rate of the setting value, while the resource managing unit reclaims the resources.

Abstract: A data integrity (DI) protection circuit and method provide overlapping DI protection without increasing memory requirements. Write data parity is checked after write data error correcting code (ECC) check bits are generated, which is stored with the write data in memory without storing the write data parity. A corrupt location cache stores the write address and a write response error is generated when a write data parity error or write address parity error is detected. Read data and read data ECC check bits retrieved from the memory are checked and single bit errors are corrected, while double-bit errors result in a read error response. Read data parity is generated, and the corrected read data and corrected read data ECC check bits are then checked for bit errors. The corrupt location cache is searched for the read address, and a cache hit results in a read error response.

Abstract: A method for improving data bus integrity includes a selectable data bus integrity feature that can improve the integrity of a data bus in a memory system. An external controller generates error correction data in response to associated data to be transmitted. The error correction data is divided into multiple data packets and appended to the corresponding data for transmission over the data bus. The memory device can use the ECC data, if the feature is enabled, to attempt to correct the corresponding data and store both the corrected data and the ECC data.

Abstract: A method and a system embodying the method for receiving a remote direct memory access packet comprising an opaque data, a virtual address, and a payload at a virtual network interface card that generated the opaque data; reconstructing a stream identifier by separating the opaque data into an encrypted stream identifier and a first digest; decrypting the encrypted stream identifier; verifying the decrypted stream identifier using the first digest; providing the verified stream identifier to a system memory management unit; and mapping the virtual address and the provided stream identifier by the system memory management unit to a physical address, is disclosed.

Abstract: A computer-implemented method of detecting memory that may be reclaimed from application data objects that are no longer in use. When at least a first virtual memory region is newly committed for heap block storage, a pre-leak detection scan of other virtual memory regions can be performed to identify at least one non-pointer data item in the other virtual memory regions, the non-pointer data item comprising data that corresponds to an address of a memory location within the first virtual memory region, but that is not a memory pointer. A leak detection scan can be performed to identify potential memory pointers, wherein the identified non-pointer data item is excluded from the identified potential memory pointers. A list of leaked heap blocks can be output. Each leaked heap block can exclusively comprise memory locations that do not have a corresponding potential memory pointer.

Abstract: A method is described for monitoring a data memory in which an error detection method is used to detect and/or correct incorrect data words stored in memory lines of the data memory, an address of the data memory at which a data word evaluated as incorrect by the error detection method is stored being written to an auxiliary memory and being made available to a checking program.

Abstract: In one embodiment, a system includes a memory, and a memory controller coupled to the memory via an address bus, a data bus, and an error code bus. The memory stores data at an address and stores an error code at the address. The error code is generated based on a function of the corresponding data and address.

Abstract: A first page in a memory unit is programmed with one or more pages of the secondary memory. A first time corresponding to the start of the programming of the first page is recorded. A second time corresponding to the completion of the programming of the one or more pages is recorded. A time difference between the first time and the second time is determined. It is determined if the time difference is greater than a threshold. In response to the time difference being greater than the threshold, a retention based defecting process is for the memory unit is disabled.

Abstract: Embodiments of the invention describe a system main memory comprising two levels of memory that include cached subsets of system disk level storage. This main memory includes “near memory” comprising memory made of volatile memory, and “far memory” comprising volatile or nonvolatile memory storage that is larger and slower than the near memory. The far memory is presented as “main memory” to the host OS while the near memory is a cache for the far memory that is transparent to the OS, thus appearing to the OS the same as prior art main memory solutions. The management of the two-level memory may be done by a combination of logic and modules executed via the host CPU. Near memory may be coupled to the host system CPU via high bandwidth, low latency means for efficient processing. Far memory may be coupled to the CPU via low bandwidth, high latency means.

Abstract: Described herein are methods for accessing a block-based storage device having a memory-mapped interface and a block interface. In one embodiment, an apparatus (e.g., block-based storage device) includes a storage array to store data and a memory-mapped interface that is coupled to the storage array. The memory-mapped interface includes memory-mapped memory space. The memory-mapped interface receives direct access requests from a host to directly access memory-mapped files. The apparatus also includes a block interface that is coupled to the storage array. The block interface receives block requests from a storage driver to access the storage array.

Abstract: This document discusses, among other things, an example system and methods for memory expansion. An example embodiment includes receiving a memory request from a memory controller over a channel. Based on the memory request, the example embodiment includes selecting a location in memory to couple to a sub-channel of the channel and configuring the set of field effect transistors to couple the channel with the sub-channel. In the example embodiment, data may be allowed to flow between the memory controller and the location in the memory over the channel and the sub-channel.

Abstract: Provided is a test apparatus including: an address generator that generates an address of a memory under test; a selector that selects whether to perform bit inversion on the address generated by the address generator before supplying the address to the memory under test; an inversion processing section that outputs the address generated by the address generator after performing bit inversion on the address if the selector has selected in the affirmative, and outputs the address generated by the address generator without performing any bit inversion on the address if the selector has selected in the negative; and a supply section that supplies, to the memory under test, the address having undergone inversion control outputted from the inversion processing section and an inversion cycle signal that indicates whether the address outputted from the inversion processing section is bit inverted or not.

Abstract: A method is provided for recovering from an uncorrected memory error located at a memory address as identified by a memory device. A stored hash value for a memory page corresponding to the identified memory address is used to determine the correct data. Because the memory device specifies the location of the corrupted data, and the size of the window where the corruption occurred, the stored hash can be used to verify memory page reconstruction. With the known good part of the data in hand, the hashes of the pages using possible values in place of the corrupted data are calculated. It is expected that there will be a match between the previously stored hash and one of the computed hashes. As long as there is one and only one match, then that value, used in the place of the corrupted data, is the correct value. The corrupt data, once replaced, allows operation of the memory device to continue without needing to interrupt or otherwise affect a system's operation.

Abstract: In one example embodiment, a memory device includes a cell array configured to receive data at an associated address in response to a write command. The memory device further includes a storage unit configured to receive the associated address and the data in response to the write command and output the data to the associated address of the cell array in response to a rewrite command. The memory device further includes a violation determining unit configured to determine violation data, count a number of the violation data and determine data written to the storage unit as the violation data if a storage duration of the written data is less than a write recovery time (tWR).

Abstract: The memory controller writes and reads data in and from a nonvolatile memory. The nonvolatile memory has a plurality of memory cell blocks, each memory cell block includes a plurality of multi-level cells each capable of storing m-bit data (m is a natural number of two or more), a first page to a m-th page are allocated to the respective m bits of the multi-level cell, the memory controller sequentially writes the data to the memory cells from the first page in ascending order, and comprises a backup unit, and when a write command is received from the outside of the memory controller, in a case where a data write destination of the data in the nonvolatile memory is a n-th (n is a natural number of two to m) page of the multi-level cell, and data is already written in the first to (n-1)th pages, the backup unit copies the already written data to a nonvolatile storable backup region.

Abstract: An information processing apparatus, which includes a storage unit having a plurality of data areas, includes a measurement unit configured to measure a first data access speed in a first data area of the storage unit and a second data access speed in a second data area of the storage unit, and a detection unit configured to detect a defect at the first data area based on difference between the first data access speed and the second data access speed.

Abstract: A method is disclosed for retrieving the reservation status information of a storage area network (SAN) device, a host transmits a persistent reservation in command with service action setting of ‘read reservation’ to a first LUN, wherein the host is connected to a port of the data storage server to which the LUN belongs. The host receives a message from the LUN. The host determines that the message is a success. The host sends to the LUN a persistent reservation in command with service action setting of ‘read keys’, responsive to a success message. The host determines that the LUN responds with a zero data length. The host determines the LUN is reserved with type 2 reservation, responsive to a determination that the LUN responds with a non-zero data length.

Abstract: An memory access address comparator includes two comparators comparing an input memory access address with respective reference addresses. The comparators produce a match indication on selectable criteria, such as address size, full or partial overlap, greater than, less than, equal to, not equal to, less than or equal to, and greater than or equal to, and can be selectively chained. Input multiplexers permit memory access address bus selection. The comparator output may be selectively dependent upon corresponding data matches. The reference addresses, comparison data and control functions are enabled via central processing unit accessible memory mapped registers.

Abstract: Systems and methods for maximizing a number of available states for a version number used for memory corruption detection. A physical memory may be a DRAM comprising a plurality of regions. Version numbers associated with data structures allocated in the physical memory may be generated so that version numbers of adjacent data structures in a virtual address space are different. A reserved set and an available set of version numbers are associated with each one of the plurality of regions. A version number in a reserved set of a given region may be in an available set of another region. The processor detects no memory corruption error in response to at least determining a version number stored in a memory location in a first region identified by a memory access operation is also in a reserved set associated with the first region.

Abstract: To increase the number of analog inputs at low cost, an analog input system includes: one or more analog slave units each connected to a bus to which a CPU unit is connected, and each including an A/D-conversion device converting an analog value outputted by an external device into a first digital value, a buffer memory buffering a second digital value to be transferred to the CPU unit, and a nonvolatile storage device containing specific information of its own unit; and an analog master unit connected to the bus and including an operation section performing operation processing based on the specific information stored in the storage device with the first digital value being used as an input, to calculate the second digital value, the master unit performing on each of the slave input units the operation processing and processing of transferring the calculated second digital value to the buffer memory.

Abstract: A command control circuit includes a command decoder configured to decode a command and generate an internal command, an error check unit configured to detect an error in the command and an address by using check data and generate an error check signal in response to the detection, and a blocking unit configured to block or pass the internal command in response to first and second states of the error check signal.

Abstract: Systems and methods are provided for detecting and correcting address errors in a memory system. In the memory system, a memory device generates an error-detection code based on an address transmitted via an address bus and transmits the error-detection code to a memory controller. The memory controller transmits an error indication to the memory device in response to the error-detection code. The error indication causes the memory device to remove the received address and prevent a memory operation.

Abstract: A data processing system 2 is provided with multiple processor cores 4, 6, 8, 10 each incorporating a data cache memory 12, 14, 16, 18. A snoop control unit 20 manages coherency between the data values stored within the data caches 12, 14, 16, 18. The snoop control unit 20 incorporates a TAG memory 22. If an error is detected within an entry of the TAG memory 22, then a hit operation is forced to the corresponding storage location one or more of the data caches 12, 14, 16, 18.

Abstract: One or more registers used to form an address usable in accessing storage are examined to determine if a zero address event has occurred in forming the address. In response to an indication that a zero address event has occurred in address formation, an alert is provided to the program using the address to access storage.

Abstract: A method is provided for recovering from an uncorrected memory error located at a memory address as identified by a memory device. A stored hash value for a memory page corresponding to the identified memory address is used to determine the correct data. Because the memory device specifies the location of the corrupted data, and the size of the window where the corruption occurred, the stored hash can be used to verify memory page reconstruction. With the known good part of the data in hand, the hashes of the pages using possible values in place of the corrupted data are calculated. It is expected that there will be a match between the previously stored hash and one of the computed hashes. As long as there is one and only one match, then that value, used in the place of the corrupted data, is the correct value. The corrupt data, once replaced, allows operation of the memory device to continue without needing to interrupt or otherwise affect a system's operation.

Abstract: A method and a device for the detection of erroneous or inopportune transactions of any entity of a microprocessor or microcontroller includes programming counters internal or external to the microcontroller, which is configured to count the number of transactions in the target area of the target interface of the microcontroller; count the total number of transactions on the target interface, and verify that the number of transactions outside of the target area of the target interface of the microcontroller is zero. Equality between the number of transactions in the target area of the target interface and the total number of transactions on the target interface of the microcontroller is verified.

Abstract: An apparatus, system, and method are disclosed for validating that correct data is read from a storage device. A hash generation module generates a hash value from a logical address of a read request for a data storage device. A read data module reads, from the data storage device, data identified by the read request and a stored hash value stored with the data. The stored hash value was generated from a logical address for data written to the data storage device. A hash check module verifies that the generated hash value matches the stored hash value read from the data storage device.

Abstract: A memory system according to the present invention includes, in addition to an computing device, a plurality of first blocks that are provided to store information including user information, and first physical addresses not overlapping one another are assigned to, respectively, and a plurality of second blocks that are provided to store first physical addresses of initial defect blocks out of the plurality of first blocks, respectively, wherein the computing device finds the first physical address corresponding a inputted given logical address, based on a given mirror logical address corresponding to the given logical address, and information stored in the second blocks.

Abstract: A method for processing a write instruction for writing data to a database stored on a logical device includes obtaining first and second addresses that specify the location of the data in respective first and second address spaces. A third address corresponding to an expected location of the data record in the first address space is then calculated. On the basis of a comparison between the first address and the third address, a determination is made as to whether to execute the write instruction.

Abstract: Systems and methods are provided for detecting and correcting address errors in a memory system. In the memory system, a memory device generates an error-detection code based on an address transmitted via an address bus and transmits the error-detection code to a memory controller. The memory controller transmits an error indication to the memory device in response to the error-detection code. The error indication causes the memory device to remove the received address and prevent a memory operation.

Abstract: A semiconductor memory and a data processing system having hardware for carrying out a method for the improved internal monitoring of addressing circuits in semiconductor memories or in a data processing system, in which logic levels addressing lines are tapped off, the actually selected address or subaddress is represented by additional address bit lines, the actually accessed address/subaddress is recovered using the address bit lines, and the actually selected address/subaddress is compared with the applied address/subaddress, obtained from the additional address bit lines, in order to recognize an error in the addressing circuit.

Abstract: A system includes a virtualized I/O device coupled to one or more processing units. The virtualized I/O device includes a storage for storing a resource discovery table, and programmed I/O (PIO) configuration registers corresponding to hardware resources. A system processor may allocate the plurality of hardware resources to one or more functions, and to populate each entry of the resource discovery table for each function. The processing units may execute one or more processes. Given processing units may further execute OS instructions to allocate space for an I/O mapping of a PIO configuration space in a system memory, and to assign a function to a respective process. Processing units may execute a device driver instance associated with a given process to discover allocated resources by requesting access to the resource discovery table. The virtualized I/O device protects the resources by checking access requests against the resource discovery table.

Abstract: An advanced memory having improved performance, reduced power and increased reliability. A memory device includes a memory array, a receiver for receiving a command and associated data, error control coding circuitry for performing error control checking on the received command, and data masking circuitry for preventing the associated data from being written to the memory array in response to the error control coding circuitry detecting an error in the received command. Another memory device includes a programmable preamble. Another memory device includes a fast exit self-refresh mode. Another memory device includes auto refresh function that is controlled by the characteristic device. Another memory device includes an auto refresh function that is controlled by a characteristic of the memory device.

Abstract: Detecting a fault in the operation of a computer having a processor and a memory is taught. Instrumentation code is placed within an application program during compilation, and runtime library routines are modified to support detection of invalid memory accesses. Memory space is divided into application, shadow and unmapped memories. When accessing application memory at an original address, an address in shadow memory is computed by shifting the address and adding an offset. If the value stored at the shadow address indicates that the original address is invalid (e.g., not allocated or already freed), then error reporting code is executed that indicates the type of error and the location and optionally halts the computer. Invalid memory references to heap, stack and global objects in application memory can be detected.

Abstract: A system includes a processor with a memory map specifying a user mode region with virtual address translation by a memory management unit and a kernel mode region with direct virtual address translation. The processor executes an application in the user mode region where virtual addresses are not unique. A probe receives trace information from the processor. A host system receives the trace information from the probe. The host system includes a data structure associating a process name, a process identification and a set of instruction counters. Each instruction counter is incremented upon the processing of a designated virtual address within the trace information. A profiling module processes information associated with the process name and set of instruction counters to identify a performance problem in the application.

Abstract: An apparatus, system, and method are disclosed for validating that correct data is read from a storage device. A read request receiver module receives a read storage request to read a data segment of a file or object stored on a data storage device. The storage request includes one or more source parameters for the data segment. The source parameters include one or more virtual addresses that identify the data segment. A hash generation module generates one or more hash values from the virtual addresses. A read data module reads the requested data segment and returns one or more data packets and corresponding stored hash values stored with the data packets. The stored hash values were generated from a data segment written to the data storage device that contains data of the data packets. A hash check module verifies that the generated hash values match the respective stored hash values.

Abstract: Embodiments of the invention provide a table-free technique for detecting all temporal and spatial memory access errors in programs supporting general pointers. Embodiments of the invention provide such error checking using constant-time operations. Embodiments of the invention rely on fat pointers, whose size is contained within standard scalar sizes (up to two words) so that atomic hardware support for operations upon the pointers is obtained along with meaningful casts in-between pointers and other scalars. Optimized compilation of code becomes possible since the scalarized-for-free encoded pointers get register allocated and manipulated. Backward compatibility is enabled by the scalar pointer sizes, with automatic support provided for encoding and decoding of fat pointers in place for interaction with unprotected code.