Abstract: The present disclosure generally relates to improved optimization of a cache lookup operation by structuring the write cache buffers differently using a link-list. Rather than executing a read command first and then executing a write command only after the read command is executed, this disclosure suggests reordering the command executions. A device waits before executing the read command giving the opportunity to obtain the overlap write command. The device then reorders the command execution and executes first the write command and then executes the read command by accessing the write cache instead of the NAND. When two write commands need to be executed consecutively, the link-list operation is used. The controller finds the relevant buffer in the cache that is needed and overwrites the buffer with the new data. The new data is then written to the cache without accessing the cache multiple times.

Abstract: The present disclosure generally relates to read and write operations utilizing barrier commands. Using barrier commands and a snapshot of doorbell states of submission queues (SQs), the necessary write commands to perform a read may be identified and executed to reduce any wait time of the host. As such, host delays during reads and writes are reduced. In absence of a barrier command, the host needs to wait for writes to complete before performing a read. When a barrier command is used, the host needs to wait for the barrier command to complete before performing a read. The controller will execute the post barrier reads only after completing the pre-barrier writes. As will be discussed herein, the controller completes the barrier command as soon as a doorbell snapshot is taken even though the pre-barrier writes may not yet be completed.

Abstract: The present disclosure generally relates to improved address translation. Rather than fetching translated addresses using ATS/ATC, a HIM address translation search engine (HATS) is used through implementing the ATC in a layer above per an NVMe command. The HATS is an engine that will monitor pointers with untranslated addresses and will fetch the translated addresses for the pointers. Once the translated addresses are fetched for the pointer, the HATS will overwrite the untranslated address with the translated address. The HATS will then update the status of the pointers. When a translation request fails, the device will use PRI to request the translated address. During a translation request fail the device will drain any incoming requests while skipping the data transfer phase. The device will not block any other requests in a queue. Once that translated address is received through the PRI flow, the status of the pointer will be updated.

Abstract: Systems and methods for offloading data storage processing tasks from a data storage device to a graphics processing unit data are described. Data storage devices may include a peripheral interface configured to connect to a host system and provide access to a host memory buffer. The data storage device may store task input data to the host memory buffer. The data storage device may notify a processor device including the graphics processing unit to initiate the storage processing task. The processor device may access the task input data from the host memory buffer and store the task output data to the host memory buffer for access by the data storage device.

Abstract: The present disclosure generally relates to reducing exit latency when transitioning from non-operational power states. Before entering a non-operational power state, specific data in databases and/or tables can be identified as being recently utilized by the host device. In addition to saving the databases and/or tables, a recovery code is also stored to identify that specific data. Upon transitioning back to an operational power state, the recovery code is detected and the specific data can be recovered rather than recovering the entire database and/or table. Data not identified in the recovery code need not be recovered from always-on memory. In so doing, when transitioning back to an operational power state, the latency will be reduced compared to a situation where all data is stored in always-on memory.

Abstract: Embodiments of the present disclosure generally relate to an NVMe storage device having a controller memory manager and a method of accessing an NVMe storage device having a controller memory manager. In one embodiment, a storage device comprises a non-volatile memory, a volatile memory, and a controller memory manager. The controller memory manager is operable to store one or more NVMe data structures within the non-volatile memory and the volatile memory.

Abstract: Methods and apparatus for power management in data storage devices are provided. One such data storage device (DSD) includes a non-volatile memory (NVM), a set of hardware processing engines, and a power sensor to detect a total power consumption of the set of hardware processing engines. A processor is configured to determine a power-per-processing event value for each of the set of processing engines based on total power consumption measurements, then control delivery of power to the processing engines based on the power-per-processing event values in accordance with a power budget. In some examples, the DSD employs a least-squares procedure to estimate the power-per-processing event values so the values can be determined without needing to measure the individual power consumption of the processing engines. Exemplary processing engines include a Read engine, a Write engine, etc. A recursive least-squares update procedure is also described.

Abstract: The present disclosure generally relates to aborting a command efficiently using the host memory buffer (HMB). The command contains pointers that direct the data storage device to various locations on the data storage device where relevant content is located. Once the abort command is received, the content of the host pointers stored in the data storage device RAM are changed to point to the HMB. The data storage device then waits until any already started transactions over the interface bus that are associated with the command have been completed. Thereafter, a failure completion command is posted to the host device.

Abstract: Methods and apparatus for power management in data storage devices are provided. One such data storage device (DSD) includes a non-volatile memory (NVM), a set of hardware processing engines, and a power sensor to measure a total power consumption of the set of hardware processing engines. A processor is configured to determine a power-per-processing event value for each of the set of processing engines based on total power consumption measurements, then control delivery of power to the processing engines based on the power-per-processing event values in accordance with a power budget. In some examples, the DSD employs a least-squares procedure to estimate the power-per-processing event values so the values can be determined without needing to measure the individual power consumption of the processing engines. Procedures are also provided for assessing the accuracy of the power-per-processing event values and for controlling further operations based on the assessment.

Abstract: The present disclosure generally relates to improved host memory buffer (HMB) segment selection at the initialization phase. Rather than selecting an HMB segment strictly on one parameter, the selection process will consider multiple factors of the HMB segments. Instead of just selecting a HMB segments based on the size of the HMB segment, the data storage device will perform some basic performance measurements on the provided HMB segments before selecting HMB segments. The selection will be based also on the performance results from the various experiments. The experiments are performed in the initialization phase so the performance of the solid state drive (SSD) will not be impacted. The basic experiments include read, write, and mixed operations toward the HMB segments while measuring the performance and QoS.

Abstract: A data storage device includes a memory device and a controller coupled to the memory device. When a copy command is received by the controller from a host device, the controller reads the relevant data from one or more first locations of the memory device. The data is the processed by an Rx path, where the data is decoded, decrypted, and verified. Rather than providing the data back to the host device or being made available to the host device, a copy accelerator loops the data from the Rx path to a Tx path, where protection information is generated and added to the data and the data is encrypted and encoded. The data is then programmed back to the memory device in a second location. By using the copy accelerator, a latency associated with performing copy command operations and other data management operations may be decreased.

Abstract: The present disclosure generally relates to improved unaligned deallocated logical block transfer. Rather than stalling the data-path in unaligned deallocated LBA scenarios, the data-path will work regularly while ignoring the unaligned deallocated indication. The old and non-valid data received for the unaligned deallocated LBA will be written to the host. The device controller will detect the unaligned deallocated LBA and overwrite the data with other values such as 0's or 1's as specified in the standard. The implementation increases the performance of unaligned deallocated commands and the endurance of the NVM. The implementation also simplifies the logic implemented in the device controller.

Abstract: A data storage device whose controller is configured to apply a hash function to a logical address specified in a received host request to obtain a first portion of the corresponding physical address (e.g., the channel number or channel and die numbers). This feature of the controller enables the L2P table stored in the DRAM associated with the controller to have physical-address entries that contain therein only complementary second portions of the physical addresses, but not the first portions. Such shorter physical-address entries in the L2P table enable a corresponding beneficial reduction in the size of the DRAM and can further be leveraged to have optimized and aligned access to the L2P table in the DRAM.

Abstract: A data storage device and method for providing an adaptive data path are disclosed. In one embodiment, a data storage device is in communication with a host comprising a first processor (e.g., a graphics processing unit (GPU)), a second processor (e.g., a central processing unit (CPU)), and a queue. The data storage device chooses a data path to use to communicate with the queue based on whether the queue is associated with the first processor or with the second processor. Other embodiments are possible, and each of the embodiments can be used alone or together in combination.

Abstract: A data storage device includes a controller. The controller includes a controller memory buffer (CMB). The controller is configured to associate both the CMB and a host memory buffer (HMB) of a host device as a single buffer pool with a plurality of CMB buffers and a plurality of HMB buffers. The controller is further configured to allocate either a CMB buffer or a HMB buffer based on a tradeoff between latency and performance between using the CMB or using the HMB to store data. By leveraging the benefits of both the CMB and the HMB to store data, the overall performance of the data storage device may be improved.

Abstract: The present disclosure generally relates to improved access to the DRAM using namespace mapping. The PMR address range is mapped to LBA address space. Mapping the PMR address range in LBA address space allows the host to access the PMR indirectly using NVMe commands. The host device may hold in the namespace the most frequently accessed data and obtain highest performance and low latency. Implementation of the Power Loss Protection (PLP) feature over the PMR makes the system prefer storing the data in PMR rather in host memory. All internal SRAMs (e.g. Transfer RAMs, XOR RAMs, etc.) may be mapped in the LBA address space so the host device can access mainly for debug purposes. Some internal flops that hold important data are mapped in the LBA address space as well.

Abstract: The present disclosure generally relates partial speed changes to improve in-order data transfer. Rather than determining an ECC decoder on a first available decoder basis, the ECC decoder may be based on the ECC decoder level. A memory device will have at least one FMU that has a syndrome weight (SW). The disclosure proposes assigning FMU's based on the SW rate. At the time the command is read, the data storage device determines which level of decoder will be assigned to the FMU. The determination will then be checked according to different system environment parameters to maintain performance or reduce power consumption. The arrangement allows a more flexible system design that can adapt according to the current system status.

Abstract: The present disclosure generally relates to improving space efficiency when storing logical to physical (L2P) entries. Rather than writing a physical block address (PBA) spanning multiple entries, the PBA is split between a first portion stored in the buffer with the remaining bits of the PBA added to the metadata buffer. The metadata buffer is sub-optimal due to the small size of the metadata relative to the entry and therefore, adding extra bits to the metadata buffer will make the metadata buffer more optimal. In this scheme, the alignment is preserved, the system becomes more optimal in terms of DRAM access, and the metadata buffer can be easily optimized and adapted.

Abstract: A data storage device includes a memory device and a controller coupled to the memory device. The controller is configured to determine a maximum bandwidth of an interface, allocate a portion of the maximum bandwidth to one or more tenants, either: determine a maximum data transfer size (MDTS) setting based on quality of service (QoS) requirements, determine an aggregated queue depth (QD) setting based on QoS requirements, or determine a combined MDTS and aggregated QD setting based on QoS requirements, and provide the determined settings to the one or more tenants.

Abstract: The present disclosure generally relates to data storage devices, such as solid state drives (SSDs), specifically utilizing the data storage device memory in the execution of host commands. A controller is configured to receive a command pointer or a data chunk from a host device, mark a destination used for the command pointer or the data chunk, determine whether a last chunk of the command pointer or the data chunk has been received, and determine whether the command pointer or the data chunk uses an illegal combination of locations after determining that the last chunk of the command pointer has been received. The controller is further configured to return an error message to the host device upon determining that the command pointer or the data chunk uses an illegal combination of locations.