Abstract: A method of accelerating memory operations using virtualization information includes executing a hypervisor on hardware resources of a computing system. A plurality of domains are created under the control of the hypervisor. Each domain is allocated memory resources that include accessible memory space that is exclusively accessible by that domain. Each domain is allocated one or more processor resources. The hypervisor identifies domain layout information that includes a boundary of accessible memory space of each domain. The hypervisor provides the domain layout information to each processor resource. Each processor resource is configured to implement, on a per domain basis, a restricted coherency protocol based on the domain layout information. The restricted coherency protocol bypasses, relative to the domain, downstream caches when a cache line falls within the accessible memory space of that domain.

Abstract: Methods and apparatuses are provided for data resource provision. A method may include receiving a request for a first data resource. The request may include an indication of an additional data resource that may be requested in a future request. The method may further include determining the indicated additional data resource. The method may additionally include causing caching of the additional data resource in preparation for a future request for the additional data resource. Corresponding apparatuses are also provided.

Abstract: A coherent attached processor proxy (CAPP) that participates in coherence communication in a primary coherent system on behalf of an attached processor external to the primary coherent system tracks delivery of data to destinations in the primary coherent system via one or more entries in a data structure. Each of the one or more entries specifies with a destination tag a destination in the primary coherent system to which data is to be delivered from the attached processor. In response to initiation of recovery operations for the CAPP, the CAPP performs data recovery operations, including transmitting, to at least one destination indicated by the destination tag of one or more entries, an indication of a data error in data to be delivered to that destination from the attached processor.

Abstract: A micro-architecture may provide a hardware and software of a high bandwidth write command. The micro-architecture may invoke a method to perform the high bandwidth write command. The method may comprise sending a write request from a requester to a record keeping structure. The write request may have a memory address of a memory that stores requested data. The method may further determine copies of the requested data being present in a distributed cache system outside the memory, sending invalidation requests to elements holding copies of the requested data in the distributed cache system, sending a notification to the requester to inform presence of copies of the requested data and sending a write response message after a latest value of the requested data and all invalidation acknowledgements have been received.

Abstract: Subject matter disclosed herein relates to sub-block accessible cache memory.

Abstract: In one embodiment, a method includes receiving a read request from a first caching agent and if a directory entry associated with the request is in an unknown state, an invalidating snoop message is sent to at least one other caching agent to invalidate information in a cache location of the other caching agent corresponding to the location of the read request, to enable setting of the directory entry into a known state. Other embodiments are described and claimed.

Abstract: A cache layer leverages a logical address space and storage metadata of a storage layer (e.g., storage layer) to cache data of a backing store. The cache layer maintains access metadata to track data characteristics of logical identifiers in the logical address space, including accesses pertaining to data that is not in the cache. The access metadata may be separate and distinct from the storage metadata maintained by the storage layer. The cache layer determines whether to admit data into the cache using the access metadata. Data may be admitted into the cache when the data satisfies cache admission criteria, which may include an access threshold and/or a sequentiality metric. Time-ordered history of the access metadata is used to identify important/useful blocks in the logical address space of the backing store that would be beneficial to cache.

Abstract: A method and apparatus for providing a memory model for hardware attributes to support transactional execution is herein described. Upon encountering a load of a hardware attribute, such as a test monitor operation to load a read monitor, write monitor, or buffering attribute, a fault is issued in response to a loss field indicating the hardware attribute has been lost. Furthermore, dependency actions, such as blocking and forwarding, are provided for the attribute access operations based on address dependency and access type dependency. As a result, different scenarios for attribute loss and testing thereof are allowed and restricted in a memory model.

Abstract: Systems, apparatus, and method of monitoring synchronization in a distributed cache are described. In an exemplary embodiment, a first and second processing core process a first and second thread respectively. A first and second distributed cache slices store data for either or both of the first and second processing cores. A first and second core interface co-located with the first and second processing cores respectively maintain a finite state machine (FSM) to be executed in response to receiving a request from a thread of its co-located processing core to monitor a cache line in the distributed cache.

Abstract: A data processing system includes a first master having a cache, a second master, a memory operably coupled to the first master and the second master via a system interconnect. The cache includes a cache controller which implements a set of cache coherency states for data units of the cache. The cache coherency states include an invalid state; an unmodified non-coherent state indicating that data in a data unit of the cache has not been modified and is not guaranteed to be coherent with data in at least one other storage device of the data processing system, and an unmodified coherent state indicating that the data of the data unit has not been modified and is coherent with data in the at least one other storage device of the data processing system.

Abstract: Maintaining cache coherence in a multi-node, symmetric multiprocessing computer, the computer composed of a plurality of compute nodes, including, broadcasting upon a cache miss by the first compute node to other compute nodes a request for the cache line; if at least two of the compute nodes has a correct copy of the cache line, selecting which compute node is to transmit the correct copy of the cache line to the first node, and transmitting from the selected compute node to the first node the correct copy of the cache line; and updating by each node the state of the cache line in each node, in dependence upon one or more of the states of the cache line in all the nodes.

Abstract: A mechanism is provided for effectively validating cache coherency within a processor. For each node in a set of nodes, responsive to a node in a set of nodes being a controlling node, at least one action is performed on each controlled node mapped to the controlling node. After performing the at least one action on each controlled node mapped to the controlling node or responsive to the node failing to be a controlling node, a self-modifying branch test pattern is executed based on the selected execution pattern in the condition register through the set of nodes. Responsive to the self-modifying branch test pattern ending, values output from the execution unit during execution of the self-modifying branch test pattern are compared to a set of expected results. Responsive to a match of the comparison for the execution patterns in the set of execution patterns, the execution unit is validated.

Abstract: Methods, systems and apparatuses for selecting graphics data of a server system for transmission are disclosed. One method includes reading data from graphics memory of the server system. The data read from the graphics memory is placed in a transmit buffer if the data is being read for the first time, and was not written by a processor of the server system. One system includes a server system including graphics memory, a frame buffer and a processor. The server system is operable to read data from the graphics memory. The server system is operable to place the data in a transmit buffer if the data is being read for the first time, and was not written by the processor during rendering.

Abstract: A method for managing caches, including: broadcasting, by a first cache agent operatively connected to a first cache and using a first physical network, a first peer-to-peer (P2P) request for a memory address; issuing, by a second cache agent operatively connected to a second cache and using a second physical network, a first response to the first P2P request based on a type of the first P2P request and a state of a cacheline in the second cache corresponding to the memory address; issuing, by a third cache agent operatively connected to a third cache, a second response to the first P2P request; and upgrading, by the first cache agent and based on the first response and the second response, a state of a cacheline in the first cache corresponding to the memory address.

Abstract: Various embodiments of the present invention allow concurrent accesses to a cache. A request to update an object stored in a cache is received. A first data structure comprising a new value for the object is created in response to receiving the request. A cache pointer is atomically modified to point to the first data structure. A second data structure comprising an old value for the cached object is maintained until a process, which holds a pointer to the old value of the cached object, at least one of one of ends and indicates that the old value is no longer needed.

Abstract: A method for minimizing cache conflict misses is disclosed. A translation table capable of facilitating the translation of a virtual address to a real address during a cache access is provided. The translation table includes multiple entries, and each entry of the translation table includes a page number field and a hash value field. A hash value is generated from a first group of bits within a virtual address, and the hash value is stored in the hash value field of an entry within the translation table. In response to a match on the entry within the translation table during a cache access, the hash value of the matched entry is retrieved from the translation table, and the hash value is concatenated with a second group of bits within the virtual address to form a set of indexing bits to index into a cache set.

Abstract: A data processing apparatus having a memory configured to store tables having virtual to physical address translations, a cache configured to store a subset of the virtual to physical address translations and cache management circuitry configured to control transactions received from the processor requesting virtual address to physical address translations. The data processing apparatus identifies where a faulting transaction has occurred during execution of a context and whether the faulting transaction has a transaction stall or transaction terminate fault. The cache management circuitry is responsive to identification of the faulting transaction having a transaction terminate fault to invalidate all address translations in the cache that relate to the context of the faulting transaction such that a valid bit associated with each entry in the cache is set to invalid for the address translations.

Abstract: Provided a computer program product, system, and method for cache management of tracks in a first cache and a second cache for a storage. The first cache maintains modified and unmodified tracks in the storage subject to Input/Output (I/O) requests. Modified and unmodified tracks are demoted from the first cache. The modified and the unmodified tracks demoted from the first cache are promoted to the second cache. The unmodified tracks demoted from the second cache are discarded. The modified tracks in the second cache that are at proximate physical locations on the storage device are grouped and the grouped modified tracks are destaged from the second cache to the storage device.

Abstract: Systems and methods related to a memory system including a cache memory are disclosed. The cache memory system includes a cache memory including a plurality of cache memory lines and a dirty buffer including a plurality of dirty masks. A cache controller is configured to allocate one of the dirty masks to each of the cache memory lines when a write to the respective cache memory line is not a full write to that cache memory line. Each of the dirty masks indicates dirty states of data units in one of the cache memory lines. The cache controller stores an identification (ID) information that associates the dirty masks with the cache memory lines to which the dirty masks are allocated.

Abstract: Some embodiments of the present invention provide a system that avoids deadlock while attempting to acquire store-marks on cache lines. During operation, the system keeps track of store-mark requests that arise during execution of a thread, wherein a store-mark on a cache line indicates that one or more associated store buffer entries are waiting to be committed to the cache line. In this system, store-mark requests are processed in a pipelined manner, which allows a store-mark request to be initiated before preceding store-mark requests for the same thread complete. Next, if a store-mark request fails, within a bounded amount of time, the system removes or prevents store-marks associated with younger store-mark requests for the same thread, thereby avoiding a potential deadlock that can arise when one or more other threads attempt to store-mark the same cache lines.

Abstract: A method and apparatus for accelerated shared data migration between cores. Using an Always Migrate protocol, when a migratory probe hits a directory entry in either modified or owned state, the entry is transitioned to an owned state, and a source done command is sent without sending cache block ownership or state information to the directory.

Abstract: A cache management policy is provided, comprising a method for writing back to a memory (104) a data element set (122) stored in a cache (110). The method reduces the time some items stay in the cache, and thereby improves the utilization of the cache for some applications, especially for video applications. The method comprises determining that each one of the multiple data elements has been updated through at least one write request; marking the data element set as a write-back candidate, in dependency on said determination; and writing the write-back candidate to the memory.

Abstract: Methods and systems to intelligently cache content in a virtualization environment using virtualization software such as VMWare ESX or Citrix XenServer or Microsoft HyperV or Redhat KVM or their variants are disclosed. Storage IO operations (reads from and writes to disk) are analyzed (or characterized) for their overall value and pinned to cache if their value exceeds a certain defined threshold based on criteria specific to the New Technology File System (NTFS) file-system. Analysis/characterization of NTFS file systems for intelligent dynamic caching include analyzing storage block data associated with a Virtual Machine of interest in accordance with a pre-determined data model to determine the value of the block under analysis for long term or short term caching. Integer values assigned to different types of NTFS objects in a white list data structure called a catalog that can be used to analyze the storage block data.

Abstract: A method and apparatus for enabling a Software Transactional Memory (STM) with precompiled binaries is herein described. Upon encountering an access operation in a transaction, an annotation field associated with a memory location referenced by the access is checked. In response to the memory location representing a previous similar access within the transaction, the access is performed without access barriers. However, if the annotation field is in a default state representing no previous access during a pendancy of the transaction, then a mode of the processor is determined. If the processor mode is in implicit mode, an access handler/barrier is asynchronously executed. Conversely, in an explicit mode, a flag is set instead of asynchronously executing the handler. In addition, during compilation convert explicit and convert implicit instructions are inserted to intelligently convert modes for precompiled and newly compiled binaries.

Abstract: A system controller includes an output unit which transfers an access request from an access source coupled to the system controller to an other system controller; a local snoop control unit that determines whether a destination of the access request from the access source is a local memory unit coupled to the system controller, and locks the destination when the destination is the local memory unit; a receiving unit which receives the access request from the output unit and an access request from an other system controller; a global snoop control unit which sends a response indicating whether the access request is executable or not, and controls locking of the destination of the access request when the destination is the local memory unit; and an access processing unit which unlocks the locking and accesses the memory unit when the access request from the access source becomes executable.

Abstract: A technique to track shared information in a multi-core processor or multi-processor system. In one embodiment, core identification information (“core IDs”) are used to track shared information among multiple cores in a multi-core processor or multiple processors in a multi-processor system.

Abstract: A method to eliminate the delay of multiple overlapping block invalidate operations in a multi CPU environment by overlapping the block invalidate operation with normal CPU accesses, thus making the delay transparent. The cache controller performing the block invalidate operation merges multiple overlapping requests into a parallel stream to eliminate execution delays. Cache operations other that block invalidate, such as block write back or block write back invalidate may also be merged into the execution stream.

Abstract: One embodiment of the present invention sets forth a graphics subsystem. The graphics subsystem includes a first tiling unit associated with a first set of raster tiles and a crossbar unit. The crossbar unit is configured to transmit a first set of primitives to the first tiling unit and to transmit a first cache invalidate command to the first tiling unit. The first tiling unit is configured to determine that a second bounding box associated with primitives included in the first set of primitives overlaps a first cache tile and that the first bounding box overlaps the first cache tile. The first tiling unit is further configured to transmit the primitives and the first cache invalidate command to a first screen-space pipeline associated with the first tiling unit for processing. The screen-space pipeline processes the cache invalidate command to invalidate cache lines specified by the cache invalidate command.

Abstract: A processor includes a core to execute instructions and a cache memory coupled to the core and having a plurality of entries. Each entry of the cache memory may include a data storage including a plurality of data storage portions, each data storage portion to store a corresponding data portion. Each entry may also include a metadata storage to store a plurality of portion modification indicators, each portion modification indicator corresponding to one of the data storage portions. Each portion modification indicator is to indicate whether the data portion stored in the corresponding data storage portion has been modified, independently of cache coherency state information of the entry. Other embodiments are described as claimed.

Abstract: One embodiment of the present invention sets forth a technique for synchronization between two or more processors. The technique implements a spinlock acquire function and a spinlock release function. A processor executing the spinlock acquire function advantageously operates in a low power state while waiting for an opportunity to acquire spinlock. The spinlock acquire function configures a memory monitor to wake up the processor when spinlock is released by a different processor. The spinlock release function releases spinlock by clearing a lock variable and may clear a wait variable.

Abstract: A system, method, and computer program product are provided for conditionally sending a request for data to a home node. In operation, a first request for data is sent to a first cache of a node. Additionally, if the data does not exist in the first cache, a second request for the data is sent to a second cache of the node. Furthermore, a third request for the data is conditionally sent to a home node.

Abstract: An unbounded transactional memory system which can process overflow data. The unbounded transactional memory system may include a host processor, a memory, and a memory processor. The host processor may include an execution unit to perform a transaction, and a cache to temporarily store data. The memory processor may store overflow data in overflow storage included in the memory in response to an overflow event in which the overflow data is generated in the cache during the transaction.

Abstract: A compression status bit cache provides on-chip availability of compression status bits used to determine how many bits are needed to access a potentially compressed block of memory. A backing store residing in a reserved region of attached memory provides storage for a complete set of compression status bits used to represent compression status of an arbitrarily large number of blocks residing in attached memory. Physical address remapping (“swizzling”) used to distribute memory access patterns over a plurality of physical memory devices is partially replicated by the compression status bit cache to efficiently integrate allocation and access of the backing store data with other user data.

Abstract: A method is used in managing cache pages. A location pointer is maintained in a dynamic list of entries for cache page cleaning. The dynamic list includes a list of cache pages ordered from most recently used to least recently used. Based on flags associated with the cache pages, a count of the number of cache pages processed for cache page cleaning is maintained. In response to a change in the dynamic list, the location pointer and count are updated based on the processing status of an entry to which the change pertains.

Abstract: Provided are a computer program product, system, and method for managing unmodified tracks maintained in both a first cache and a second cache. The first cache has unmodified tracks in the storage subject to Input/Output (I/O) requests. Unmodified tracks are demoted from the first cache to a second cache. An inclusive list indicates unmodified tracks maintained in both the first cache and a second cache. An exclusive list indicates unmodified tracks maintained in the second cache but not the first cache. The inclusive list and the exclusive list are used to determine whether to promote to the second cache an unmodified track demoted from the first cache.

Abstract: A method to monitor the behavior of a working set cache of a full data set at run time and determine whether it provides a performance benefit is disclosed. An effectiveness metric of the working set cache is tracked over a period of time by efficiently computing the amount of physical memory consumption the cache saves and comparing this to a straightforward measure of its overhead. If the effectiveness metric is determined to be on an ineffective side of a selected threshold amount, the working set cache is disabled. The working set cache can be re-enabled in response to a predetermined event.

Abstract: A computer includes a memory that stores data, a cache memory that stores a copy of the data, a directory storage unit that stores directory information related to the data and includes information indicating that the data is copied to the cache memory, a directory cache storage unit that stores a copy of the directory information stored in the directory storage unit, and a control unit that controls storage of data in the directory cache storage unit, manages the data copied from the memory to the cache memory by dividing the data into an exclusive form and a shared form, and sets a priority of storage of the directory information related to the data fetched in the exclusive form in the directory cache storage unit higher than a priority of storage of the directory information related to the data fetched in the shared form in the directory cache storage unit.

Abstract: A method for managing a cache structure of a coupling facility includes receiving a conditional write command from a computing system and determining whether data associated with the conditional write command is part of a working set of data of the cache structure. If the data associated with the conditional write command is part of the working set of data of the cache structure the conditional write command is processed as an unconditional write command. If the data associated with the conditional write command is not part of the working set of data of the cache structure a conditional write failure notification is transmitted to the computing system.

Abstract: A computer cache system delays cache coherence invalidation messages related to cache lines of a common memory region to collect these messages into a combined message that can be transmitted more efficiently. This delay may be coordinated with a detection of whether the processor is executing a data-race free portion of the program so that the delay system may be used for a variety of types of programs which may have data-race and data-race free sections.

Abstract: Some embodiments provide systems and methods for validating cached content based on changes in the content instead of an expiration interval. One method involves caching content and a first checksum in response to a first request for that content. The caching produces a cached instance of the content representative of a form of the content at the time of caching. The first checksum identifies the cached instance. In response to receiving a second request for the content, the method submits a request for a second checksum representing a current instance of the content and a request for the current instance. Upon receiving the second checksum, the method serves the cached instance of the content when the first checksum matches the second checksum and serves the current instance of the content upon completion of the transfer of the current instance when the first checksum does not match the second checksum.

Abstract: Operating system virtual memory management for hardware transactional memory. A system includes an operating system deciding to unmap a first virtual page. As a result, the operating system removes the mapping of the first virtual page to the first physical page from the virtual memory page table. As a result, the operating system performs an action to discard transactional memory hardware state for at least the first physical page. Embodiments may further suspend hardware transactions in kernel mode. Embodiments may further perform soft page fault handling without aborting a hardware transaction, resuming the hardware transaction upon return to user mode, and even successfully committing the hardware transaction.

Abstract: Methods and apparatuses for processing partial write requests in a system cache within a memory controller. When a write request that updates a portion of a cache line misses in the system cache, the write request writes the data to the system cache without first reading the corresponding cache line from memory. The system cache includes error correction code bits which are redefined as word mask bits when a cache line is in a partial dirty state. When a read request hits on a partial dirty cache line, the partial data is written to memory using a word mask. Then, the corresponding full cache line is retrieved from memory and stored in the system cache.

Abstract: A cache image including only cache entries with valid durations of at least a configured deployment date for a virtual machine image is prepared via an application server for the virtual machine image. The virtual machine image is deployed to at least one other application server as a virtual machine with the cache image including only the cache entries with the valid durations of at least the configured deployment date for the virtual machine image.

Abstract: Provided are a computer program product, system, and method for caching data in a storage system having multiple caches. A sequential access storage device includes a sequential access storage medium and a non-volatile storage device integrated in the sequential access storage device, received modified tracks are cached in the non-volatile storage device, wherein the non-volatile storage device is a faster access device than the sequential access storage medium. A spatial index indicates the modified tracks in the non-volatile storage device in an ordering based on their physical location in the sequential access storage medium. The modified tracks are destaged from the non-volatile storage device by comparing a current position of a write head to physical locations of the modified tracks on the sequential access storage medium indicated in the spatial index to select a modified track to destage from the non-volatile storage device to the storage device.

Abstract: A method for generating a virtual volume (VV) in a storage system architecture. The architecture comprises a host and one or more disk array subsystems. Each subsystem comprises a storage controller. One or more of the subsystems comprises a physical storage device (PSD) array. The method comprises the following steps: mapping the PSD array into a plurality of media extents (MEs), each of the MEs comprises a plurality of sections; providing a virtual pool (VP) to implement a section cross-referencing function, wherein a section index (SI) of each of the sections contained in the VP is defined by the VP to cross-reference VP sections to physical ME locations; providing a conversion method or procedure or function for mapping VP capacity into to a VV; and presenting the VV to the host. A storage subsystem and a storage system architecture performing the method are also provided.

Abstract: A method is provided for dispatching a load operation to a processing device and determining that the operation is the oldest load operation. The method also includes executing the operation in response to determining the operation is the oldest load operation. Computer readable storage media for performing the method are also provided. An apparatus is provided that includes a translation look-aside buffer (TLB) content addressable memory (CAM), and includes an oldest operation storage buffer operationally coupled to the TLB CAM. The apparatus also includes an output multiplexor operationally coupled to the TLB CAM and to the oldest operation storage buffer. Computer readable storage media for adapting a fabrication facility to manufacture the apparatus are also provided.

Abstract: A computerized method for efficient handling of a privileged instruction executed by a virtual machine (VM). The method comprises identifying when the privileged instruction causes a VM executed on a computing hardware to perform a VM exit; replacing a first virtual-to-physical address mapping to a second virtual-to-physical address mapping respective of a virtual pointer associated with the privileged instruction; and invalidating at least a cache entry in a cache memory allocated to the VM, thereby causing a new translation for the virtual pointer to the second virtual-to-physical address, wherein the second virtual-to-physical address provides a pointer to a physical address in a physical memory in the computing hardware allocated to the VM.

Abstract: A method and apparatus for accelerating lookups in an address based table is herein described. When an address and value pair is added to an address based table, the value is privately stored in the address to allow for quick and efficient local access to the value. In response to the private store, a cache line holding the value is transitioned to a private state, to ensure the value is not made globally visible. Upon eviction of the privately held cache line, the information is not written-back to ensure locality of the value. In one embodiment, the address based table includes a transactional write buffer to hold addresses, which correspond to tentatively updated values during a transaction. Accesses to the tentative values during the transaction may be accelerated through use of annotation bits and private stores as discussed herein. Upon commit of the transaction, the values are copied to the location to make the updates globally visible.

Abstract: When multiple pieces of content data are being recorded continuously to a nonvolatile storage device having page cache function, a preparation time before starting next content data recording is reduced. When a cache releasing section of a nonvolatile storage device (1) receives cache releasing from an access device (2), it releases addresses included in one logical block among multiple addresses which are cache objects at the same time. Further, the nonvolatile storage device (1) includes a cache information outputting section which outputs information regarding a time period required for releasing addresses which are cache objects outside, and the access device (2) refers to the information to select the address to be an object of releasing.

Abstract: In general, the present invention relates to data cache processing. Specifically, the present invention relates to a system that provides reconfigurable dynamic cache which varies the operation strategy of cache memory based on the demand from the applications originating from different external general processor cores, along with functions of a virtualized hybrid core system. The system includes receiving a data request, selecting an operational mode based on the data request and a predefined selection algorithm, and processing the data request based on the selected operational mode. The system is further configured to delegate computational or memory resource needs to a plurality of sub-processing cores for processing to satisfy application demands.