Systems and methods for performing data protection operations including garbage collection operations and copy forward operations. For deduplicated data stored in a cloud-based storage or in a cloud tier that stores containers containing dead and live segments or dead and live regions such as compression regions, the dead compression regions are deleted by copying the live compression regions into new containers and then deleting the old containers. The copy forward is based on a recipe from a data protection system and is performed using a serverless approach.

Technologies for providing shared memory for accelerator sleds includes an accelerator sled to receive, with a memory controller, a memory access request from an accelerator device to access a region of memory. The request is to identify the region of memory with a logical address. Additionally, the accelerator sled is to determine from a map of logical addresses and associated physical address, the physical address associated with the region of memory. In addition, the accelerator sled is to route the memory access request to a memory device associated with the determined physical address.

An apparatus to facilitate memory data compression is disclosed. The apparatus includes a memory and having a plurality of banks to store main data and metadata associated with the main data and a memory management unit (MMU) coupled to the plurality of banks to perform a hash function to compute indices into virtual address locations in memory for the main data and the metadata and adjust the metadata virtual address locations to store each adjusted metadata virtual address location in a bank storing the associated main data.

A processing system is provided that includes a memory for storing an input bit stream and a processing logic, operatively coupled to the memory, to generate a first score based on: a first set of matching data related to a match between a first bit subsequence and a candidate bit subsequence within the input bit stream, and a first distance of the candidate bit subsequence from the first set of matching data. A second score is generated based on a second set of matching data related to a match between a second bit subsequence and the candidate bit subsequence, and a second distance of the candidate bit subsequence from the second set of matching data. A code to replace the first or second bit subsequence in an output bit stream is identified. Selection of the one of the bit subsequences to replace is based on a comparison of the scores.

Described herein is a graphics processing unit (GPU) comprising a first processing cluster to perform parallel processing operations, the parallel processing operations including a ray tracing operation and a matrix multiply operation; and a second processing cluster coupled to the first processing cluster, wherein the first processing cluster includes a floating-point unit to perform floating point operations, the floating-point unit is configured to process an instruction using a bfloat16 (BF16) format with a multiplier to multiply second and third source operands while an accumulator adds a first source operand with output from the multiplier.

A compressed memory system includes a memory region that includes cache lines having priority levels. The compressed memory system also includes a compressed memory region that includes compressed cache lines. Each compressed cache line includes a first set of data bits configured to hold, in a first direction, either a portion of a first cache line or a portion of the first cache line after compression, the first cache line having a first priority level. Each compressed cache line also includes a second set of data bits configured to hold, in a second direction opposite to the first direction, either a portion of a second cache line or a portion of the second cache line after compression, the second cache line having a priority level lower than the first priority level. The first set of data bits includes a greater number of bits than the second set of data bits.

A compressed memory system of a processor-based system includes a memory partitioning circuit for partitioning a memory region into data regions with different priority levels. The system also includes a cache line selection circuit for selecting a first cache line from a high priority data region and a second cache line from a low priority data region. The system also includes a compression circuit for compressing the cache lines to obtain a first and a second compressed cache line. The system also includes a cache line packing circuit for packing the compressed cache lines such that the first compressed cache line is written to a first predetermined portion and the second cache line or a portion of the second compressed cache line is written to a second predetermined portion of the candidate compressed cache line. The first predetermined portion is larger than the second predetermined portion.

Disclosed is a storage system comprising: receiving a first data segment and first metadata associated with the first data segment to be stored in the storage system; storing the first data segment and the first metadata in a persistent storage device of the storage system; compressing the first data segment using a predetermined compression algorithm to generate a first compressed data segment; and storing the first metadata and the first compressed data segment in a solid state drive (SSD) cache device of the storage system, including aligning the first metadata and the first compressed data segment to a page boundary of the SSD device to reduce a number of input and output (IO) operations required for accessing the first metadata and the first compressed data segment from the SSD cache device.

Techniques described herein relate to systems and methods of data storage, and more particularly to providing layering of file system functionality on an object interface. In certain embodiments, file system functionality may be layered on cloud object interfaces to provide cloud-based storage while allowing for functionality expected from a legacy applications. For instance, POSIX interfaces and semantics may be layered on cloud-based storage, while providing access to data in a manner consistent with file-based access with data organization in name hierarchies. Various embodiments also may provide for memory mapping of data so that memory map changes are reflected in persistent storage while ensuring consistency between memory map changes and writes. For example, by transforming a ZFS file system disk-based storage into ZFS cloud-based storage, the ZFS file system gains the elastic nature of cloud storage.

Embodiments are generally directed to compression in machine learning and deep learning processing. An embodiment of an apparatus for compression of untyped data includes a graphical processing unit (GPU) including a data compression pipeline, the data compression pipeline including a data port coupled with one or more shader cores, wherein the data port is to allow transfer of untyped data without format conversion, and a 3D compression/decompression unit to provide for compression of untyped data to be stored to a memory subsystem and decompression of untyped data from the memory subsystem.