Patent classifications
G06F2212/401
System, method and apparatus for accelerating fast block devices
A device, method and system is directed to fast data storage on a block storage device. New data is linearly written to an empty write block. A location of the new data is tracked. Meta data associated with the new data is linearly written. A lookup table may be updated based in part on the meta data. The new data may be read based the lookup table configured to map a logical address to a physical address.
Searching memory for a search key
To produce output from a memory block, a first index is used to access a pointer, a mode select and a function select from a first memory. The pointer, the mode select and the function select are used to produce a second index. The pointer is used to produce the second index when the mode select is a first value. A function is used to produce the second index when the mode select is a second value. The function select identifies a function to be used to produce the second index. The second index is used to access output from a second memory.
Techniques to configure physical compute resources for workloads via circuit switching
Embodiments are generally directed apparatuses, methods, techniques and so forth to select two or more processing units of the plurality of processing units to process a workload, and configure a circuit switch to link the two or more processing units to process the workload, the two or more processing units each linked to each other via paths of communication and the circuit switch.
Data compression in a multi-layer distributed datastore
A method for compressing is provided. The method including receiving a block of data to store on at least one physical disk; determining whether to store the data in a data log as uncompressed or compressed data based on a determined size of resulting compressed data. When the method determines to store the data as compressed, compressing the data and storing the compressed data in at least one sector in the data log. Otherwise, the method stores the data, uncompressed, in a plurality of sectors in the data log. The method generates a one or more state bits indicating (i) whether the data is stored as uncompressed or compressed, and (ii) if the data is stored as compressed, a size of the compressed data. The method then stores the one or more state bits in an entry of a logical map table associated with an LBA that corresponds to the data block.
COMPRESSION AND CACHING FOR LOGICAL-TO-PHYSICAL STORAGE ADDRESS MAPPING TABLES
A storage device that maps logical addresses to physical addresses includes a memory that stores machine instructions and a processor coupled to the memory that executes the machine instructions to store a compressed mapping table in the memory. The compressed mapping table correlates logical addresses to locations in a storage. The storage device also stores a bundle of uncompressed mapping table entries starting at a first location in a cache and maps a first logical address associated with the uncompressed mapping table entry to the first location.
GRAPHICS PROCESSORS AND GRAPHICS PROCESSING UNITS HAVING DOT PRODUCT ACCUMULATE INSTRUCTION FOR HYBRID FLOATING POINT FORMAT
Described herein is a graphics processing unit (GPU) configured to receive an instruction having multiple operands, where the instruction is a single instruction multiple data (SIMD) instruction configured to use a bfloat16 (BF16) number format and the BF16 number format is a sixteen-bit floating point format having an eight-bit exponent. The GPU can process the instruction using the multiple operands, where to process the instruction includes to perform a multiply operation, perform an addition to a result of the multiply operation, and apply a rectified linear unit function to a result of the addition.
APPARATUS AND METHOD FOR CONSTANT DETECTION DURING COMPRESS OPERATIONS
Apparatus and method for detecting a constant data block are described herein. An apparatus embodiment includes compression circuitry to perform compression operations on a memory block; constant detection circuitry to, concurrently with performance of the compression operations on the memory block, determine that the memory block is a constant data block comprised of only repeat instances of a constant value; and controller circuitry to associate a first indication with the memory block based on the determination, the first indication usable for controlling whether to abort the compression operations or whether to discard a compressed memory block generated from the compression operations.
METHOD AND APPARATUS FOR IMPROVING PERFORMANCE OF SEQUENTIAL LOGGING IN A STORAGE DEVICE
In one embodiment, an apparatus comprises a storage device to receive, from a computing host, a request to append data to a data log. The storage device is further to identify a memory location after a last segment of the data log, append the data to the data log by writing the data to the memory location after the last segment of the data log, and provide, to the computing host, a key comprising an identification of the memory location at which the data was appended to the data log.
Data Routing for Efficient Decompression of Compressed Data Stored in a Cache
Data routing for efficient decompressor use is described. In accordance with the described techniques, a cache controller receives requests from multiple requestors for elements of data stored in a compressed format in a cache. The requests include at least a first request from a first requestor and a second request from a second requestor. A decompression routing system identifies a redundant element of data requested by both the first requestor and the second requestor and causes decompressors to decompress the requested elements of data. The decompression includes performing a single decompression of the redundant element. After the decompression, the decompression routing system routes the decompressed elements to the plurality of requestors, which includes routing the decompressed redundant element to both the first requestor and the second requestor.
CACHE SYSTEMS
A method of operating a cache system is disclosed. Information indicating a link between associated header and payload cache entries is maintained. The link information may be used to reduce cache coherency traffic.