Abstract: A method of forming a semiconductor device includes forming vertical contact fingers in a substrate having side portions that are flexible. Contact fingers are formed near one or more edges of the flexible side portions of the substrate. After semiconductor dies are mounted to and electrically coupled to the substrate, the semiconductor device may be encapsulated by placing the device in a mold chase including upper and lower mold plates. The lower mold plate is sized smaller than the substrate so that the flexible side portions of the substrate including the contact fingers fold vertically upward to fit within the mold.

Abstract: Disclosed are systems and methods for accelerating commands from accelerators in data storage devices using accelerator queues. A data storage device includes accelerator interfaces, each accelerator interface couples a controller to a respective accelerator. The device also includes a device memory comprising one or more memories and one or more sets of queues. Each set of queues corresponds to a respective memory, at least one queue is configured to queue one or more tasks associated with an accelerator, and each queue is associated with a respective priority level of a plurality of priority levels. A controller is configured to: receive an accelerator command, identify a first memory corresponding to a task for the accelerator command; and enqueue the task to a first queue corresponding to the first memory, the first queue configured to queue one or more tasks associated with the first accelerator corresponding to the first accelerator interface.

Abstract: A non-volatile memory system separately performs a memory operation for multiple sub-blocks of a block in order from previously determined slowest sub-block of the block to a previously determined faster sub-block of the block. As a slower sub-block is more likely to fail, this order of is more likely to identify a failure earlier in the process thereby saving time and reducing potential for a disturb. In some embodiments, the proposed order of operation can be used in conjunction with a programming process that concurrently programs blocks in multiple planes using completion of programming of a fastest plane to a data state as a trigger to test for program failure of other planes to the data state.

Abstract: In order to achieve tight and uniform erased threshold voltage distributions in a non-volatile memory system that includes non-volatile memory cells arranged in blocks that have multiple sub-blocks and has an erase process using gate induced drain leakage (GIDL) to generate charge carriers that change threshold voltage of the memory cells, the magnitude of the GIDL is adjusted separately for the sub-blocks.

Abstract: Some areas (e.g., boundary wordlines) in a block of memory can be more error prone than others. Typically, errors in these areas are not detected until after the entire block is programmed. Handling such errors then can result in performance penalties and large data relocations. With the embodiments presented herein, a two-stage programming operation is provided. In the first stage, only the error-prone areas of the block are programmed, and a check is made to determine if an error occurred in that programming. In the second stage, the remaining portions of the block are programmed, but that only occurs after it is determined that the error-prone areas have been programmed successfully. Detecting and dealing with errors in the error-prone areas before the entire block is programmed avoid the performance penalties and large data relocations noted above.

Abstract: To provide more test data during the manufacture of non-volatile memories and other integrated circuits, machine learning is used to generate virtual test values. Virtual test results are interpolated for one set of tests for devices on which the test is not performed based on correlations with other sets of tests.

Abstract: A non-volatile memory system comprises a plurality of non-volatile memory cells divided into three or more tiers. The memory cells can be programmed, erased and read. In order to achieve uniform erase speed for the three or more tiers, the erase process comprises applying a larger voltage bias to control gates of non-volatile memory cells in the outer tiers than the voltage bias applied to control gates of non-volatile memory cells in one or more inner tiers.

Abstract: Systems, methods, and data storage devices for image grouping in an end user device using trained machine learning group classifiers are described. The end user device may include an image group classifier configured to classify new image data objects using an image classification algorithm and set of machine learning parameters previously trained for a specific image group. The end user device may determine embeddings that quantify features of the target image object and use those embeddings and the image group classifier to selectively associate group identifiers with each new image data object received or generated by the end user device. Calibration, including selection and training, of the image group classifiers and ranking of classified images are also described.

Abstract: A data storage device having a flash translation layer configured to handle file-system defragmentation in a manner that avoids, reduces, and/or optimizes physical data movement in flash memory. In an example embodiment, the memory controller maintains in a volatile memory thereof a lookaside table that supplants pertinent portions of the logical-to-physical table. Entries of the lookaside table are configured to track source and destination addresses of the host defragmentation requests and are logically linked to the corresponding entries of the logical-to-physical table such that end-to-end data protection including the use of logical-address tags to the user data can be supported by logical means and without physical data rearrangement in the flash memory. In some embodiments, physical data rearrangement corresponding to the file-system defragmentation is performed in the flash memory in response to certain trigger events, which can improve the input/output performance of the data-storage device.

Abstract: An apparatus is provided that includes a block including a word line coupled to a plurality of memory cells, and a control circuit coupled to the word line. The control circuit is configured to program the plurality of memory cells by applying program pulses to the word line in a plurality of program loops, determining a first count of a number of the program loops used to complete programming a first subset of the plurality of memory cells to a first programmed state, first comparing the first count to a corresponding first lower limit and a corresponding first upper limit, and determining whether programming the plurality of memory cells has failed based on a result of the first comparing step.

Abstract: A memory system performs an erase process for the non-volatile memory cells including performing erase verify for the non-volatile memory cells. The erase verify comprises comparing threshold voltages of the non-volatile memory cells to an erase verify reference voltage and determining whether an amount of the non-volatile memory cells having a threshold voltage greater than the erase verify reference voltage is less than an allowed bit count. During the erase process, the system compares threshold voltages of the non-volatile memory cells to an intermediate reference voltage that is greater than the erase verify reference voltage and determines an amount of non-volatile memory cells having threshold voltages greater than the intermediate reference voltage. The Allowed Bit Count is increased (during the erase process) by the amount of non-volatile memory cells having threshold voltages greater than the intermediate reference voltage.

Abstract: Technology for read in a cross-point memory array. Drive transistors pass read and write currents to the cross-point memory array. The read current charges a selected word line to turn on a threshold switching selector of a selected memory cell. While the threshold switching selector is on, the current (read or write) passes through the selected memory cell. The memory system applies a smaller overdrive voltage to a drive transistor when the drive transistor is passing the read current than when the drive transistor is passing the write current. A smaller overdrive voltage increases the resistance of the drive transistor. Increasing the resistance of the drive transistor increases the resistance seen by the threshold switching selector in the selected memory cell, which reduces the Ihold of the threshold switching selector.

Abstract: A memory apparatus and method of operation are provided. The apparatus includes drain-side select gate transistors for coupling to a drain-side of memory holes of memory cells and configured to retain a transistor threshold voltage. The memory holes are arranged in rows comprising strings. A control means is configured to program drain-side select gate transistors of the memory holes to an initial transistor threshold voltage using pulses increasing in magnitude by a first transistor step amount during each of a plurality of foggy loops of a foggy program operation. The control means is also configured to program the drain-side select gate transistors of the memory holes to a target transistor threshold voltage using pulses increasing in magnitude by a second transistor step amount during each of a plurality of fine loops of a fine program operation. The first transistor step amount is greater than the second transistor step amount.

Abstract: System and method of verifying validity of a metadata modification request to prevent improper metadata operations. During initialization of a volume in a storage device and once a metadata area is reserved for a metadata structure, information characterizing the metadata structure and metadata area is stored in the storage device, which may be in the form of an area legend composed of descriptors such as a magic signature, a node size, a clump size of reservation, and extent of the metadata area. Responsive to a request for operating on metadata, relevant information provided in the request is verified against the stored characteristic information. If the verification discovers an inconsistency between the information provided in the request and the stored characteristic information, the request modification is treated as invalid and blocked from operation.

Abstract: A method includes forming a first electrode layer over a substrate, forming an ovonic threshold switch (OTS) material layer over the first electrode layer, microwave annealing the OTS material layer, and forming a second electrode layer over the OTS material layer.

Abstract: A data storage device includes a substrate including a number of contact pads and a number of passive component packages coupled to the contact pads. The data storage device further includes a memory controller coupled to the substrate, and one or more NAND die stacks coupled to the substrate and in electrical communication with the memory controller. One or more of the passive component packages include a first passive component, a second passive component electrically connected to the first passive component, and a first terminal coupled to the first passive component. The passive component packages further include a second terminal coupled to the second passive component, and a third terminal coupled to a common node of the first passive component and the second passive component.

Abstract: The present disclosure generally relates to an embedded physical layer (EPHY) for a field programmable gate array (FPGA). The EPHY for the FPGA is for a testing device that can receive and transmit in both the high speed PHYs, as well as low speed PHYs, such as MIPI PHYS (MPHYs), to meet universal flash storage (UFS) specifications. The testing device with the EPHY for the FPGA provides flexibility to support any specification updates without the need of application specific (ASIC) production cycles.

Abstract: The present disclosure generally relates to methods of operating storage devices. The storage device comprises a controller and a media unit. The capacity of the media unit is divided into a plurality of zones. The controller is configured to make informed use of errors by update zone metadata to indicate one or more first logical block addresses were skipped and to indicate the next valid logical block address is available to store data. The controller is further configured to update zone metadata to recommend to the host device to reset one or more full zones, to recommend to the host device to transition one or more open zones to a full state, to alert the host device that one or more open zones have been transitioned to the full state, and to notify the host device of the writeable zone capacity of each of the plurality of zones.

Abstract: The present disclosure generally relates to methods of operating storage devices. The storage device comprises a controller comprising first random access memory (RAM1), second random access memory (RAM2), and a storage unit divided into a plurality of streams. When a write command is received to write data to a stream, change log data is generated and stored in the RAM1, the previous delta data for the stream is copied from the RAM2 to the RAM1 to be updated with the change log data, and the updated delta data is copied to the RAM2. The delta data stored in the RAM2 is copied to the storage unit periodically. The controller tracks which delta data has been copied to the RAM2 and to the storage unit. During a power failure, the delta data and the change log data are copied from the RAM1 or the RAM2 to the storage unit.

Abstract: Techniques for storage-free message authentication for error-correcting-codes are disclosed. A storage controller of a storage device receives a request to encode a message in a format having an error-correcting code schema that generates a parity code. A key generator generates a pseudorandom transposition of the message and the parity code as a first part of a secret key. A pseudorandom character string is determined as a second part of the secret key. The output of the pseudorandom transposition and the pseudorandom character string are combined to generate the encoded message which is returned in response to the request. The secret key associated with the message is stored in non-volatile memory.