Abstract: Techniques are presented for performing maintenance operations, such as garbage collection, on non-volatile memory systems will still respecting the maximum latency, or time-out, requirements of a protocol. A safety guard band in the space available for storing host data, control data, or both, is provided. If, on an access of the memory, it is determined that the guard band space is exceeded, the system uses a recovery back to the base state by triggering and prioritizing clean-up operations to re-establish all safety guard bands without breaking the timing requirements. To respect these timing requirements, the operations are split into portions and done in a phased manner during allowed latency periods.

Abstract: Methods and apparatus for writing data to non-volatile memory include maintaining one or more lists of obsolete blocks of the non-volatile memory and limiting the lists to a predetermined value. If a write operation would result in a list exceeding its predetermined value, a block erase operation is performed on one of the obsolete blocks. Valid data contained in an obsolete block selected for erasure is relocated prior to erasure.

Abstract: A re-programmable non-volatile memory system, such as a flash EEPROM system, having its memory cells grouped into blocks of cells that are simultaneously erasable is operated to perform memory system housekeeping operations in the foreground during execution of a host command, wherein the housekeeping operations are unrelated to execution of the host command. Both one or more such housekeeping operations and execution of the host command are performed within a time budget established for executing that particular command. One such command is to write data being received to the memory. One such housekeeping operation is to level out the wear of the individual blocks that accumulates through repetitive erasing and re-programming.

Abstract: A non-volatile memory organized into flash erasable blocks sorts units of data according to a temperature assigned to each unit of data, where a higher temperature indicates a higher probability that the unit of data will suffer subsequent rewrites due to garbage collection operations. The units of data either come from a host write or from a relocation operation. Among the units more likely to suffer subsequent rewrites, a smaller subset of data super-hot is determined. These super-hot data are then maintained in a dedicated portion of the memory, such as a resident binary zone in a memory system with both binary and MLC portions.

Abstract: A non-volatile memory organized into flash erasable blocks sorts units of data according to a temperature assigned to each unit of data, where a higher temperature indicates a higher probability that the unit of data will suffer subsequent rewrites due to garbage collection operations. The units of data either come from a host write or from a relocation operation. The data are sorted either for storing into different storage portions, such as SLC and MLC, or into different operating streams, depending on their temperatures. This allows data of similar temperature to be dealt with in a manner appropriate for its temperature in order to minimize rewrites. Examples of a unit of data include a logical group and a block.

Abstract: A memory device recognizes that data corruption is present in a block. In response, rather than skip the block and continue write operations into a different uncorrupted block, the memory device continues to write data into the corrupted block. The memory device may write data on the basis of logical groups. The logical groups may be smaller than a block and larger than a page, but other sizes are also possible. In response to write corruption in the block (e.g., from power loss during a write operation), the memory device may skip certain parts of the block and continue writing into the block. For example, the memory device may skip the remainder of the page range in which the logical group was going to be written when data corruption occurred, and instead write that logical group into the block from the start of the next logical group unit, the next available page, or any other boundary.

Abstract: A method and system maintains an address table for mapping logical groups to physical addresses in a memory device. The method includes receiving a request to set an entry in the address table and selecting and flushing entries in an address table cache depending on the existence of the entry in the cache and whether the cache meets a flushing threshold criteria. The flushed entries include less than the maximum capacity of the address table cache. The flushing threshold criteria includes whether the address table cache is full or if a page exceeds a threshold of changed entries. The address table and/or the address table cache may be stored in a non-volatile memory and/or a random access memory. Improved performance may result using this method and system due to the reduced number of write operations and time needed to partially flush the address table cache to the address table.

Abstract: A portion of a nonvolatile memory is partitioned from a main multi-level memory array to operate as a cache. The cache memory is configured to store at less capacity per memory cell and finer granularity of write units compared to the main memory. In a block-oriented memory architecture, the cache has multiple functions, not merely to improve access speed, but is an integral part of a sequential update block system. The cache memory has a capacity dynamically increased by allocation of blocks from the main memory in response to a demand to increase the capacity. Preferably, a block with an endurance count higher than average is allocated. The logical addresses of data are partitioned into zones to limit the size of the indices for the cache.

Abstract: In a nonvolatile memory with block management system, critical data such as control data for the block management system is maintained in duplicates. Various methods are described for robustly writing and reading two copies of critical data in multi-state memory. In another aspect of the invention, a preemptive garbage collection on memory block containing control data avoids an undesirable situation where a large number of such memory blocks need be garbage collected at the same time.

Abstract: A method and system for managing maintenance operations in a multi-bank non-volatile storage device is disclosed. The method includes receiving a data write command and associated data from a host system for storage in the non-volatile storage device and directing a head of the data write command to a first bank in the and a tail of the data write command to a second bank, where the head of the data write command only includes data having logical block addresses preceding logical block addresses of data in the tail of the data write command. When a status of the first bank delays execution of the data write command the controller executes a second bank maintenance procedure in the second bank while the data write command directed to the first and second banks is pending. The system includes a plurality of banks, where each bank may be associated with the same or different controllers, and the one or more controllers are adapted to execute the method noted above.

Abstract: In a memory that is programmable page by page and each page having multiple sectors that are once-programmable, even if successive writes are sequential, the data recorded to an update block may be fragmented and non-sequential. Instead of recording update data to an update block, the data is being recorded in at least two interleaving streams. When a full page of data is available, it is recorded to the update block. Otherwise, it is temporarily recorded to the scratch pad block until a full page of data becomes available to be transferred to the update block. Preferably, a pipeline operation allows the recording to the update block to be set up as soon as the host write command indicates a full page could be written. If the actual write data is incomplete due to interruptions, the setup will be canceled and recording is made to the scratch pad block instead.

Abstract: The invention is directed to a modified T cell receptor (TCR) comprising an amino acid sequence of a wild-type (WT) TCR with no more than three amino acid substitutions, wherein the modified TCR, as compared to the WT TCR, (i) has an enhanced ability to recognize target cells when expressed by CD4+ T cells and (ii) does not exhibit a decrease in antigen specificity when expressed by CD8+ T cells. Polypeptides, proteins, nucleic acids, recombinant expression vectors, host cells, populations of cells, antibodies, and pharmaceutical compositions related to the modified TCR also are part of the invention. Further, the invention is directed to methods of detecting a diseased cell in a host, methods of treating or preventing a disease in a host, and methods of identifying a candidate adoptive immunotherapy TCR.

Abstract: The present invention presents techniques for the linking of physical blocks of a non-volatile memory into composite logical structures or “metablocks”. After determining an initial linking of good physical blocks into metablocks, a record of the linking is maintained in the non-volatile memory where it can be readily accessed when needed. In one set of embodiments, the initially linking is deterministically formed according to an algorithm and can be optimized according to the pattern of any bad blocks in the memory. As additional bad blocks arise, the linking is updated using by replacing the bad blocks in a linking with good blocks, preferably in the same sub-array of the memory as the block that they are replacing.

Abstract: In a nonvolatile memory with block management system that supports update blocks with non-sequential logical units, an index of the logical units in a non-sequential update block is buffered in RAM and stored periodically into the nonvolatile memory. In one embodiment, the index is stored in a block dedicated for storing indices. In another embodiment, the index is stored in the update block itself. In yet another embodiment, the index is stored in the header of each logical unit. In another aspect, the logical units written after the last index update but before the next have their indexing information stored in the header of each logical unit. In this way, after a power outage, the location of recently written logical units can be determined without having to perform a scanning during initialization. In yet another aspect, a block is managed as partially sequential and partially non-sequential, directed to more than one logical subgroup.

Abstract: In a nonvolatile memory with block management system, critical data such as control data for the block management system is maintained in duplicates. Various methods are described for robustly writing and reading two copies of critical data in multi-state memory. In another aspect of the invention, a preemptive garbage collection on memory block containing control data avoids an undesirable situation where a large number of such memory blocks need be garbage collected at the same time.

Abstract: A portion of a nonvolatile memory is partitioned from a main multi-level memory array to operate as a cache. The cache memory is configured to store at less capacity per memory cell and finer granularity of write units compared to the main memory. In a block-oriented memory architecture, the cache has multiple functions, not merely to improve access speed, but is an integral part of a sequential update block system. Decisions to write data to the cache memory or directly to the main memory depend on the attributes and characteristics of the data to be written, the state of the blocks in the main memory portion and the state of the blocks in the cache portion.

Abstract: The invention is directed to a modified T cell receptor (TCR) comprising an amino acid sequence of a wild-type (WT) TCR with no more than three amino acid substitutions, wherein the modified TCR, as compared to the WT TCR, (i) has an enhanced ability to recognize target cells when expressed by CD4+ T cells and (ii) does not exhibit a decrease in antigen specificity when expressed by CD8+ T cells. Polypeptides, proteins, nucleic acids, recombinant expression vectors, host cells, populations of cells, antibodies, and pharmaceutical compositions related to the modified TCR also are part of the invention. Further, the invention is directed to methods of detecting a diseased cell in a host, methods of treating or preventing a disease in a host, and methods of identifying a candidate adoptive immunotherapy TCR.

Abstract: Techniques are presented for performing maintenance operations, such as garbage collection, on non-volatile memory systems will still respecting the maximum latency, or time-out, requirements of a protocol. A safety guard band in the space available for storing host data, control data, or both, is provided. If, on an access of the memory, it is determined that the guard band space is exceeded, the system uses a recovery back to the base state by triggering and prioritising clean-up operations to re-establish all safety guard bands without breaking the timing requirements. To respect these timing requirements, the operations are split into portions and done in a phased manner during allowed latency periods.

Abstract: In a nonvolatile memory with block management system, critical data such as control data for the block management system is maintained in duplicates. Various methods are described for robustly writing and reading two copies of critical data in multi-state memory. In another aspect of the invention, a preemptive garbage collection on memory block containing control data avoids an undesirable situation where a large number of such memory blocks need be garbage collected at the same time.

Abstract: Techniques for the management of spare blocks in re-programmable non-volatile memory system, such as a flash EEPROM system, are presented. In one set of techniques, for a memory partitioned into two sections (for example a binary section and a multi-state section), where blocks of one section are more prone to error, spare blocks can be transferred from the more error prone partition to the less error prone partition. In another set of techniques for a memory partitioned into two sections, blocks which fail in the more error prone partition are transferred to serve as spare blocks in the other partition. In a complementary set of techniques, a 1-bit time stamp is maintained for free blocks to determine whether the block has been written recently. Other techniques allow for spare blocks to be managed by way of a logical to physical conversion table by assigning them logical addresses that exceed the logical address space of which a host is aware.