Abstract: A computer program product, including: a computer readable storage device to store a computer readable program, wherein the computer readable program, when executed by a processor within a computer, causes the computer to perform operations for logging. The operations include: receiving a transaction including data and a log record corresponding to the data; writing the data to a data storage device; and writing the log record to a log space on a persistent memory device coupled to the data storage device.

Abstract: A method performed by a computing system includes, with the computing system, caching, within a cache module of the computing system, a resource request result from a web service, storing, by the computing system, metadata associated with the resource request result, the metadata including a set of entities used to produce the resource request result, wherein the metadata further includes a version of each entity associated with the resource request result, with the computing system, in response to determining that an entity from the set of entities has changed since the resource request result was cached, invalidating the cached resource request result, wherein determining that the entity from the set of entities has changed comprises determining that a version of the entity has changed.

Abstract: Embodiments of the present invention include methods and systems for domain name system (DNS) pre-caching. A method for DNS pre-caching is provided. The method includes receiving uniform resource locator (URL) hostnames for DNS pre-fetch resolution prior to a user hostname request for any of the URL hostnames. The method also includes making a DNS lookup call for at least one of the URL hostnames that are not cached by a DNS cache prior to the user hostname request. The method further includes discarding at least one IP address provided by a DNS resolver for the URL hostnames, wherein a resolution result for at least one of the URL hostnames is cached in the DNS cache in preparation for the user hostname request. A system for DNS pre-caching is provided. The system includes a renderer, an asynchronous DNS pre-fetcher and a hostname table.

Abstract: An example method of configuring an application to manage persistent memory (PM) in a computer system includes: modifying, by a compiler during compilation of the application, source code of the application to add instructions to update tracking metadata for store instructions in the source code that target memory blocks mapped to the PM; compiling, by the compiler, the source code to generate an executable process; and issuing, by a synchronization routine executing on the computer, write-back instructions during execution of the executable process based on the tracking metadata.

Abstract: A processing device includes multiple processing units and multiple memory devices respectively assigned to the multiple processing units. Each of the multiple processing units includes a cache memory configured to retain data stored in the memory device assigned to itself, and fetched data taken out from the memory device of the processing unit other than itself. When an access request for the fetched data is received from a source processing unit from which the fetched data has been taken out, the cache memory determines occurrence of a crossing in which the access request is received after the cache memory issues write back information instructing to write back the fetched data to the memory device assigned to the source processing unit. If the crossing has occurred, crossing information indicating that the crossing has occurred is output as a response to the access request.

Abstract: A method for automatic data synchronization between a source system and a buffer system. The method includes identifying a configurable set of penalties, wherein each penalty defines a number of penalty points associated with a respective one of a plurality of events related to data set stored by the source system. The method also includes, in response detecting one or more events, calculating a total penalty score using the penalty points corresponding to each of the events. The method also includes determining that the total penalty score satisfies a predetermined penalty threshold indicating that the copy of the data set stored on the buffer system is presumed stale and, in response, initiating a data replication operation that updates the copy of data set stored on the buffer system with current data from the data set stored on the source system.

Abstract: A streaming engine employed in a digital data processor specifies a fixed read only data stream defined by plural nested loops. An address generator produces addresses of data elements. A steam head register stores data elements next to be supplied to functional units for use as operands. Stream metadata is stored in response to a stream store instruction. Stored stream metadata is restored to the stream engine in response to a stream restore instruction. An interrupt changes an open stream to a frozen state discarding stored stream data. A return from interrupt changes a frozen stream to an active state.

Abstract: A system and method for metadata processing that can be used to encode an arbitrary number of security policies for code running on a stored-program processor. This disclosure adds metadata to every word in the system and adds a metadata processing unit that works in parallel with data flow to enforce an arbitrary set of policies, such that metadata is unbounded and software programmable to be applicable to a wide range of metadata processing policies. This instant disclosure is applicable to a wide range of uses including safety, security, and synchronization.

Abstract: Protecting in-memory configuration state registers. A request to access an in-memory configuration state register, such as a read or write request, is obtained. The in-memory configuration state register is mapped to memory. Error correction code of the memory is used to protect the access to the in-memory configuration state register.

Abstract: A method and apparatus of a device that includes a shared memory hash table that notifies one or more readers of changes to the shared memory hash table is described. In an exemplary embodiment, a device receives a key that corresponds to the value, where the key used to retrieve the value form the shared memory hash table and the shared memory hash table is written to by a writer and read from by a plurality of readers. In addition, the device retrieves an index from a local values table, where the local values table stores a plurality of indices for one of the plurality of readers and the index is an index into an entry in the shared memory hash table. The device further retrieves the value from the shared memory hash table using the index.

Abstract: Examples of techniques for memory transaction prioritization for a memory are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method includes allocating, by a memory controller, a reserved portion of the memory controller to execute transactions. The method further includes receiving, by the memory controller, a priority based transaction from a processor to the memory. The method further includes determining, by the memory controller, whether to accommodate the priority based transaction based at least in part on a current processing state of the memory controller. The method further includes, based at least in part on determining to accommodate the priority based transaction, accommodating the priority based transaction by performing at least one of dropping a speculative command in a queue or using the reserved portion of the memory controller to execute the priority based transaction.

Abstract: Various embodiments provide for a system that prefetches data from a main memory to a cache and then evicts unused data to a lower level cache. The prefetching system will prefetch data from a main memory to a cache, and data that is not immediately useable or is part of a data set which is too large to fit in the cache can be tagged for eviction to a lower level cache, which keeps the data available with a shorter latency than if the data had to be loaded from main memory again. This lowers the cost of prefetching useable data too far ahead and prevents cache trashing.

Abstract: A node controller for a first processor socket group may include a node memory storing a coherence directory and logic. Logic may cause the node controller to: receive a memory operation request directly from a second processor socket group, follow a coherence protocol based on the memory operation request and the coherence directory and directly access a socket group memory of the first processor socket group based on the request.

Abstract: Disclosed embodiments relate to a streaming engine employed in, for example, a digital signal processor. A fixed data stream sequence including plural nested loops is specified by a control register. The streaming engine includes an address generator producing addresses of data elements and a steam head register storing data elements next to be supplied as operands. The streaming engine fetches stream data ahead of use by the central processing unit core in a stream buffer. Parity bits are formed upon storage of data in the stream buffer which are stored with the corresponding data. Upon transfer to the stream head register a second parity is calculated and compared with the stored parity. The streaming engine signals a parity fault if the parities do not match. The streaming engine preferably restarts fetching the data stream at the data element generating a parity fault.

Abstract: An apparatus and method for efficiently reclaiming demoted cache lines. For example, one embodiment of a processor comprises: a cache hierarchy including at least one Level 1 (L1) cache and one or more lower level caches; a decoder to decode a cache line (CL) demote instruction specifying at least a first cache line; and execution circuitry to demote the first cache line responsive to the CL demote instruction, the execution circuitry to implement a writeback operation on the first cache line if the first cache line has been modified and homed in a specified memory tier or a default memory tier specified in a register.

Abstract: An apparatus and method are provided for handling access requests. The apparatus has processing circuitry for processing a plurality of program threads to perform data processing operations on data, where the operations identify the data using virtual addresses, and the virtual addresses are mapped to physical addresses within a memory system. The cache storage has a plurality of cache entries to store data, an aliasing condition existing when multiple virtual addresses map to the same physical address, and allocation of data into the cache storage being constrained to prevent multiple cache entries of the cache storage simultaneously storing data for the same physical address.

Abstract: A storage system having an adaptive workload-based command processing clock is provided. In one embodiment, a storage system has a memory, a command processing path, and a controller in communication with the memory and the command processing path. The controller is configured to adapt an input clock signal based on a current workload of the controller and provide the adapted clock signal to the command processing path in the controller.

Abstract: A fleet of query accelerator nodes is established for a data store. Each accelerator node caches data items of the data store locally. In response to determining that an eviction criterion has been met, one accelerator node removes a particular data item from its local cache without notifying any other accelerator node. After the particular data item has been removed, a second accelerator node receives a read query for the particular data item and provides a response using a locally-cached replica of the data item.

Abstract: A system and process for recompacting digital storage space involves continuously maintaining a first log of free storage space available from multiple storage regions of a storage system such as a RAID system, and based on the first log, maintaining a second log file including a bitmap identifying the free storage space available from a given storage chunk corresponding to the storage regions. Based on the bitmaps, distributions corresponding to the storage regions are generated, where the distributions represent the percentage of free space available from each chunk, and a corresponding weight is associated with each storage region. The storage region weights may then be sorted and stored in RAM, for use in quickly identifying a particular storage region that includes the maximum amount of free space available, for recompaction.

Abstract: An apparatus has a number of data holding elements for holding data values which are reset to a reset value in response to a transition of a signal at a reset signal input of the data holding element from a first value to a second value. A reset tree is provided to distribute a reset signal received at root node of the reset tree to the reset signal inputs of the data holding elements. At least one reset attack detection element is provided, with its reset signal input coupled to a given node of the reset tree, to assert an error signal when its reset signal input transitions from the first value to a second value. Reset error clearing circuitry triggers clearing of the error signal, when the reset signal at the root node of the reset tree transitions from the second value to the first value.

Abstract: A method for synchronizing primary and secondary read cache in a data replication environment is disclosed. In one embodiment, such a method includes monitoring contents of a primary read cache at a primary site. The method periodically sends, from the primary site to a secondary site, information regarding the contents of the primary read cache, such as a list of storage elements cached in the primary read cache. In certain embodiments, the information also includes temperature information indicating how frequently the storage elements are accessed. The method uses, at the secondary site, the information to substantially synchronize a secondary read cache with the primary read cache. A corresponding system and computer program product are also disclosed herein.

Abstract: A memory storage device, a memory control circuit unit and a data storage method for a rewritable non-volatile memory module are disclosed. The method includes: receiving first data; mapping a logical unit of the first data to a first physical unit in a first management unit and not storing the first data to the rewritable nonvolatile memory module if a data content of the first data is identical to a data content of second data stored in the first physical unit. The method also includes storing logical-to-physical bit map information to a second physical unit in the first management unit, wherein the logical-to-physical bit map information corresponds to at least one logical-to-physical mapping table and is configured for identifying valid data in the first management unit. Identifiers or symbols of data content may be compared to determine if first and second data are identical.

Abstract: A computer processing system includes a plurality of nodes, each node having at least one processor core and at least one level of cache memory which is private to the node, a shared, last level cache (LLC) memory device and a shared, last level cache location buffer containing cache location entries, each cache location entry storing an address tag and a plurality of location information. The location information stored in a cache location entry points to an identified cacheline location within the LLC that stores a cacheline associated with the location information. The cacheline stored in the LLC has associated information identifying the cache location entry.

Abstract: Technologies for managing lookup tables are described. The lookup tables may be used for a two-level lookup scheme for packet processing. When the tables need to be updated with a new key for packet processing, information about the new key may be added to a first-level lookup table and a second-level lookup table. The first-level lookup table may be used to identify a handling node for an obtained packet, and the handling node may perform a second-level table lookup to obtain information for further packet processing. The first lookup table may be replicated on all the nodes in a cluster, and the second-level lookup table may be unique to each node in the cluster. Other embodiments are described herein and claimed.

Abstract: Provided are techniques for destaging pinned retryable data in cache. A ranks scan structure is created with an indicator for each rank of multiple ranks that indicates whether pinned retryable data in a cache for that rank is destageable. A cache directory is partitioned into chunks, wherein each of the chunks includes one or more tracks from the cache. A number of tasks are determined for the scan of the cache. The number of tasks are executed to scan the cache to destage pinned retryable data that is indicated as ready to be destaged by the ranks scan structure, wherein each of the tasks selects an unprocessed chunk of the cache directory for processing until the chunks of the cache directory have been processed.

Abstract: A host divides a dataset into stripes and sends the stripes to respective data chips of a distributed memory buffer system, where the data chips buffer the respective slices. Each data chip can buffer stripes from multiple datasets. Through the use of: (i) error detection methods; (ii) tagging the stripes for identification; and (iii) acknowledgement responses from the data chips, the host keeps track of the status of each slice at the data chips. If errors are detected for a given stripe, the host resends the stripe in the next store cycle, concurrently with stripes for the next dataset. Once all stripes have been received error-free across all the data chips, the host issues a store command which triggers the data chips to move the respective stripes from buffer to memory.

Abstract: A method, computer program product, and computing system for receiving an indication of an intent to restore at least a portion of a data array based upon a historical record of the data array. One or more changes made to the content of that data array after the generation of the historical record may be identified, thus generating a differential record. One or more data entries within a cache memory system associated with the at least a portion of a data array may be invalidated based, at least in part, upon the differential record.

Abstract: The invention concerns a processing system comprising: a compute node (20) having one or more processors and one or more memory devices storing software enabling virtual computing resources and virtual memory to be assigned to support a plurality of virtual machines (VM1); a reconfigurable circuit (301) comprising a dynamically reconfigurable portion (302) comprising one or more partitions (304) that are reconfigurable during runtime and implement at least one hardware accelerator (ACC #1 to #N) assigned to at least one of the plurality of virtual machines (VM); and a virtualization manager (306) providing an interface between the at least one hardware accelerator (ACC #1 to #N) and the compute node (202) and comprising a circuit (406) adapted to translate, for the at least one hardware accelerator, virtual memory addresses into corresponding physical memory addresses to permit communication between the one or more hardware accelerators and the plurality of virtual machines.

Abstract: A method for rendering data invalid within a memory array is described. The method includes establishing governing metadata for a memory location within a memory array. The method also includes receiving a request to retrieve data from the memory location. The method also includes determining whether color metadata associated with the data matches the governing metadata. The method also includes returning the data when the color metadata matches the governing metadata. The method also includes returning invalidated data when the color metadata does not match the governing metadata.

Abstract: A system and method for detecting replay attacks on secure data are disclosed. A system on a chip (SOC) includes a security processor. Blocks of data corresponding to sensitive information are stored in off-chip memory. The security processor uses an integrity data structure, such as an integrity tree, for the blocks. The intermediate nodes of the integrity tree use nonces which have been generated independent of any value within a corresponding block. By using only the nonces to generate tags in the root at the top layer stored in on-chip memory and the nodes of the intermediate layers stored in off-chip memory, an amount of storage used is reduced for supporting the integrity tree. When the security processor detects events which create access requests for one or more blocks, the security processor uses the integrity tree to verify a replay attack has not occurred and corrupted data.

Abstract: A processor of an aspect includes a plurality of logical processors. A first logical processor of the plurality is to execute software that includes a memory access synchronization instruction that is to synchronize accesses to a memory. The processor also includes memory access synchronization relaxation logic that is to prevent the memory access synchronization instruction from synchronizing accesses to the memory when the processor is in a relaxed memory access synchronization mode.

Abstract: In an embodiment, a processor for invalidating cache entries comprises: at least one processing unit; a processor cache; and direct cache unit. The direct cache unit is to receive, from a first device, a direct read request for data in a first cache entry in the processor cache; determine whether the direct read request is an invalidating read request; in response to a determination that the direct read request is an invalidating read request: send the data in the first cache entry directly from the processor cache to the first device without accessing a main memory; and invalidate the first cache entry in the processor cache. Other embodiments are described and claimed.

Abstract: A data processing apparatus includes a memory, a processor which outputs write data when making a write request to the memory, and which inputs read data when making a read request to the memory, a parity generating circuit which generates a parity comprising a plurality of parity bits from the write data, the parity being written with the write data into the memory, and a parity check circuit which is coupled between the memory and the processor, and which detects a presence or absence of an error of one bit or two bits in the read data and the parity read from the memory, wherein the parity generating circuit generates the parity so that at least one of a first write data bit and a second write data bit included in the write data contributes to generation of at least two parity bits.

Abstract: In one embodiment, a computer-implemented method includes capturing a consistent state of data blocks in a namespace cache of a deduplicating storage system. The data blocks contains data for a file system namespace organized in a hierarchical data structure. Each leaf page of the hierarchical data structure contains one or more data blocks. The method further includes determining, for each data block, whether the data block has been written to base on the captured consistent state. For at least one of the written data blocks in the namespace cache, the method includes searching, in the hierarchical data structure, adjacent data blocks to find in the namespace cache one or more data blocks that have also been written to, and upon finding the one or more adjacent written data blocks, flushing the written data block and the found one or more adjacent written data blocks together into a common storage unit.

Abstract: Techniques for simulation of objects in a multi-node environment are described herein. Ownership of objects in a simulation scenario is assigned to a plurality of nodes based on a first set of criteria. Simulation authority of the first object is assumed by a second node based on a second set of criteria. Simulation of the first object is performed by the second node without previous acknowledgment, by the first node, of the assumption of simulation authority. Ownership of the first object is maintained by the first node during the time that the second node has simulation authority of the first object.

Abstract: A streaming engine employed in a digital data processor specifies a fixed read only data stream defined by plural nested loops. An address generator produces addresses of data elements. A steam head register stores data elements next to be supplied to functional units for use as operands. Stream metadata is stored in response to a stream store instruction. Stored stream metadata is restored to the stream engine in response to a stream restore instruction. An interrupt changes an open stream to a frozen state discarding stored stream data. A return from interrupt changes a frozen stream to an active state.

Abstract: Embodiments of techniques and systems for increasing efficiencies in computing systems using virtual memory are described. In embodiments, instructions which are located in two memory pages in a virtual memory system, such that one of the pages does not permit execution of the instructions located therein, are identified and then executed under temporary permissions that permit execution of the identified instructions. In various embodiments, the temporary permissions may come from modified virtual memory page tables, temporary virtual memory page tables which allow for execution, and/or emulators which have root access. In embodiments, per-core virtual memory page tables may be provided to allow two cores of a computer processor to operate in accordance with different memory access permissions. In embodiments, a physical page permission table may be utilized to provide for maintenance and tracking of per-physical-page memory access permissions. Other embodiments may be described and claimed.

Abstract: A host data processing system provides a virtual operating environment for a guest data processing system. A transaction is initiated for translation of a guest system memory address to a host system physical address in response to a transaction request from a device overseen by a guest system. For a stalled transaction incurring an error, the following are performed: (i) storing identification information relating to that transaction including data identifying the requesting device; (ii) providing translation error condition information to the overseeing guest system; and (iii) deferring handling of the stalled transaction until a subsequent command is received from that guest system. Initiation of a closure process for a guest system initiates cancellation of certain stalled transactions.

Abstract: An example system on a chip (SoC) includes a cache, a processor, and a predictor circuit. The cache may store data. The processor may be coupled to the cache and store a first data set at a first location in the cache and receive a first request from an application to write a second data set to the cache. The predictor circuit may be coupled to the processor and determine that a second location where the second data set is to be written to in the cache is nonconsecutive to the first location, where the processor is to perform a request-for-ownership (RFO) operation for the second data set and write the second data set to the cache.

Abstract: Systems and methods for performing operations on memory of a computing device are disclosed. According to an aspect, a method includes storing update data on a first memory of a computing device, wherein the update data comprises data for updating a second memory on the computing device. The method also includes initiating an update mode on the second memory. Further, the method includes suspending an I/O operation of the second memory. The method also includes switching the computing device to a system management mode (SMM) while the second memory is in the update mode. Further, the method includes retrieving the update data from the first memory. The method also includes determining whether the update data is valid. The method also includes resuming the I/O operation of the second memory for updating the second memory based on the retrieved update data in response to determining that the update data is valid.

Abstract: A web server cache performs verification of cached computational results by storing a computed function result as a cached value in a cache, and upon receiving a subsequent invocation of the function, examining a duration of the value in the cache. The web server compares, if the duration exceeds a staleness detection threshold, a result of a subsequent execution of the function to the cached value in response to the subsequent invocation by recomputing, a result from execution of the function for validating the cached value, and flags an error if the duration exceeds the staleness detection threshold and the result differs from the cached value. Alternatively, the method returns, if the duration of the cache value is within the staleness detection threshold, the cache value as the result of the subsequent invocation.

Abstract: Processing logic and a method to provide single thread access to a specific memory region without suspending processing activity for all other cores and/or threads within or in association with a processor, computer system, or other processing apparatus. Single thread access may be provided through implementation of microcode which may control thread access to model specific registers (“MSRs”) within a processor. One MSR may provide a mutex, which a single thread may claim, and another MSR may provide a range of memory locations, which may be accessed by the thread that has claimed the mutex.

Abstract: A processor including a memory that stores a system management mode (SMM) value indicative of whether the processor is in SMM, a translation address cache (TAC) that includes multiple entries for storing address translations, in which each entry includes an SMM identifier, hit logic that compares a lookup address with address translations stored in the TAC for determining a hit, in which the hit logic determines a hit only when a corresponding SMM identifier of an entry matches the SMM value, and entry logic that selects an entry of the TAC for storing a determined address translation and that programs an SMM identifier of the selected entry of the TAC to match the SMM value. The processor may include flush logic that distinguishes SMM entries, and processing logic that commands flushing upon entering and/or exiting SMM. Non-SMM entries may remain in the TAC when entering and exiting SMM.

Abstract: The described embodiments include a computing device with two or more types of processors and a memory that is shared between the two or more types of processors. The computing device performs operations for handling cache coherency between the two or more types of processors. During operation, the computing device sets a cache coherency indicator in metadata in a page table entry in a page table, the page table entry information about a page of data that is stored in the memory. The computing device then uses the cache coherency indicator to determine operations to be performed when accessing data in the page of data in the memory. For example, the computing device can use the coherency indicator to determine whether a coherency operation is to be performed when a processor of a given type accesses data in the page of data in the memory.

Abstract: Systems and methods relate to performing address translations in a multithreaded memory management unit (MMU). Two or more address translation requests can be received by the multithreaded MMU and processed in parallel to retrieve address translations to addresses of a system memory. If the address translations are present in a translation cache of the multithreaded MMU, the address translations can be received from the translation cache and scheduled for access of the system memory using the translated addresses. If there is a miss in the translation cache, two or more address translation requests can be scheduled in two or more translation table walks in parallel.

Abstract: One or more techniques and/or systems are provided for hosting a virtual machine from a snapshot. In particular, a snapshot of a virtual machine hosted on a primary computing device may be created. The virtual machine may be hosted on a secondary computing device using the snapshot, for example, when a failure of the virtual machine on the primary computing device occurs. If a virtual machine type (format) of the snapshot is not supported by the secondary computing device, then the virtual machine within the snapshot may be converted to a virtual machine type supported by the secondary computing device. In this way, the virtual machine may be operable and/or accessible on the secondary computing device despite the failure. Hosting the virtual machine on the secondary computing device provides, among other things, fault tolerance for the virtual machine and/or applications comprised therein.

Abstract: A cache and a method for operating a cache are disclosed. In an embodiment, the cache includes a cache controller, data cache and a delay write through cache (DWTC), wherein the data cache is separate and distinct from the DWTC, wherein cacheable write accesses are split into shareable cacheable write accesses and non-shareable cacheable write accesses, wherein the cacheable shareable write accesses are allocated only to the DWTC, and wherein the non-shareable cacheable write accesses are not allocated to the DWTC.

Abstract: Various embodiments provide for a system that prefetches data from a main memory to a cache and then evicts unused data to a lower level cache. The prefetching system will prefetch data from a main memory to a cache, and data that is not immediately useable or is part of a data set which is too large to fit in the cache can be tagged for eviction to a lower level cache, which keeps the data available with a shorter latency than if the data had to be loaded from main memory again. This lowers the cost of prefetching useable data too far ahead and prevents cache trashing.

Abstract: A method includes linking together a set of cache lines, tracking historical changes to the cache coherency protocol states of the set of cache lines, and prefetching to a cache the set of cache lines based at least on the historical changes to the set of cache lines. A cache circuit includes one or more random access memories (RAMs) to store cache lines and cache coherency protocol states of the cache lines and a prefetch logic unit to link together a set of cache lines, to track historical changes to cache coherency protocol states of the set of cache lines, and to prefetch to the cache circuit the set of cache lines based at least on the historical changes to the set of cache lines.

Abstract: A completion packet may be returned before a data packet is written to a memory, if a field of the data packet indicates the data packet was sent due to a cache capacity eviction. The completion packet is returned after the data packet is written to the memory, if the field indicates the data packet was sent due to a flush operation.