Abstract: Techniques for performing load testing and profiling of services in a provider network are described. A load testing and profiling service is disclosed that analyzes profile data generated by a service and generates profile results associated with the service when the service operates at varying and/or increasing load capacities. The profile results are indicative of the performance of one or more functions performed by a service when the service operates at different load capacities. In certain embodiments, the load testing and profiling service can be invoked as part of a Continuous Deployment/Continuous Integration (CD/CI) environment that executes a load test against a test stack (e.g., test requests) before, for example, promoting code to production. For instance, the load testing and profiling service may be invoked as a step in a code deployment pipeline, e.g., for deploying a software product to a test environment, or to a production environment.

Abstract: A software-testing device includes a conversion unit configured to convert a PLC program for operating a programmable logic controller into a general-purpose language program described in a general-purpose programming language, and a test execution unit configured to perform a test on the general-purpose language program.

Abstract: Processing prefetch memory operations and transactions. A local processor receives a write prefetch request from a remote processor. Prior to execution of a write prefetch request received from a remote processor, determining whether a priority of the write prefetch request is greater than a priority of a pending transaction of a local processor. The write prefetch request is executed in response to a determination that the priority of the write prefetch request is greater than the priority of a pending transaction. Prefetch data produced by execution of the write prefetch request is provided to the remote processor.

Abstract: A computer storage device having a host interface, a controller, non-volatile storage media, and firmware. The firmware instructs the controller to: store a namespace map to map blocks of logical addresses defined in a namespace to first blocks of logical addresses defined in a capacity of the non-volatile storage media; without changing a size of the namespace, adjust the namespace map to map the blocks of the logical addresses defined in the namespace to second blocks of the logical addresses defined in the capacity of the non-volatile storage media (e.g., to consolidate blocks for performance improvement); and translate the logical addresses in the namespace to physical addresses for the non-volatile storage media using the namespace map.

Abstract: An upper system of an NVM device transmits, to the NVM device, a write command that designates a logical address, the write command being associated with an expiration date corresponding to a data expiration date correlated with write target data. The NVM device correlates an expiration date correlated with the write command with a logical address specified from the write command. The NVM device writes pieces of data of which the remaining time which is the time to an expiration date belongs to the same remaining time range to the same physical storage area among the plurality of physical storage areas. The NVM device erases data from a physical storage area when the expiration dates of all pieces of data in the physical storage area have expired.

Abstract: Systems, methods, and apparatus including computer-readable mediums for managing block arrangement of super blocks in a memory such as NAND flash memory are provided. In one aspect, a memory controller for managing block arrangement of super blocks in a memory includes control circuitry coupled to the memory having at least two planes of physical blocks and configured to maintain block information of each individual physical block in the planes and select one or more physical blocks from the planes for a super block based on the block information of the physical blocks in the planes.

Abstract: Systems and methods for allocation of overprovisioned blocks for minimizing write amplification in solid state drives are disclosed.

Abstract: A processing device in a memory system determines whether a first data block of a plurality of data blocks on the memory component satisfies a first threshold criterion pertaining to a first number of the plurality of data blocks having a lower amount of valid data than a remainder of the plurality of data blocks. Responsive to the first data block satisfying the first threshold criterion, the processing device determines whether the first data block satisfies a second threshold criterion pertaining to a second number of the plurality of data blocks having been written to more recently than the remainder of the plurality of data blocks. Responsive to the first data block satisfying the second threshold criterion, the processing device determines whether a rate of change of an amount of valid data on the first data block satisfies a third threshold criterion.

Abstract: A method, computer readable medium, and system are disclosed for a distributed cache that provides multiple processing units with fast access to a portion of data, which is stored in local memory. The distributed cache is composed of multiple smaller caches, and each of the smaller caches is associated with at least one processing unit. In addition to a shared crossbar network through which data is transferred between processing units and the smaller caches, a dedicated connection is provided between two or more smaller caches that form a partner cache set. Transferring data through the dedicated connections reduces congestion on the shared crossbar network. Reducing congestion on the shared crossbar network increases the available bandwidth and allows the number of processing units to increase. A coherence protocol is defined for accessing data stored in the distributed cache and for transferring data between the smaller caches of a partner cache set.

Abstract: Techniques are disclosed for identifying data streams in a processor that are likely to benefit from data prefetching. A prefetcher receives at least a first request in a plurality of requests to pre-fetch data from a stream in a plurality of streams. The prefetcher assigns a confidence level to the the first request based on an amount of confirmations observed in the stream. The request is in a confident state if the confidence level exceeds a specified value. The first request is in a non-confident state if the confidence level does not exceed the specified value. Doing so allows a memory controller to determine whether to drop the at least the first request based on the confidence level and a memory resource utilization threshold.

Abstract: A system including: a reader; a writer; and a shared memory shared by the reader and the writer, wherein the writer is configured to: specify, in the shared memory, first and second cache lines as unsafe to read; prefetch sole ownership of the first and second cache lines; specify, after the prefetching, that the first and second prefetched cache lines are safe to read; write data to the first prefetched cache line in the shared memory; and in response to completing writing data to the first prefetched cache, relinquish control of the first prefetched cache line to a reader.

Abstract: Method and apparatus for managing data in a data storage system. A storage array controller device is coupled to a plurality of storage devices by an external data path, with the storage devices used for non-volatile memory (NVM) storage of user data from a host. A copy back operation is initiated by issuing a copy back transfer command that identifies a selected data set stored in a source device and a unique identifier (ID) value that identifies a destination device. A peer-to-peer connection is established over the external data path in response to the copy back transfer command so that the selected data set is transferred from the source device to the destination device while bypassing the storage array controller device. Normal data transfers can be carried out between the storage array controller and the respective source and destination devices during the copy back operation.

Abstract: Systems, methods, and software described herein facilitate servicing of data requests based on quality of service assigned to processing jobs. In one example, a method of prioritizing data requests in a computing system based on quality of service includes identifying a plurality of data requests from a plurality of processing jobs. The method further includes prioritizing the plurality of data requests based on a quality of service assessed to each of the plurality of processing jobs, and assigning cache memory in the computing system to each of the plurality of data requests based on the prioritization.

Abstract: A data analysis system to analyze data. The data analysis system includes a data buffer configured to receive data to be analyzed. The data analysis system also includes a state machine lattice. The state machine lattice includes multiple data analysis elements and each data analysis element includes multiple memory cells configured to analyze at least a portion of the data and to output a result of the analysis. The data analysis system includes a buffer interface configured to receive the data from the data buffer and to provide the data to the state machine lattice.

Abstract: A high bandwidth memory system. In some embodiments, the system includes: a memory stack having a plurality of memory dies and eight 128-bit channels; and a logic die, the memory dies being stacked on, and connected to, the logic die; wherein the logic die may be configured to operate a first channel of the 128-bit channels in: a first mode, in which a first 64 bits operate in pseudo-channel mode, and a second 64 bits operate as two 32-bit fine-grain channels, or a second mode, in which the first 64 bits operate as two 32-bit fine-grain channels, and the second 64 bits operate as two 32-bit fine-grain channels.

Abstract: A method, system, and computer program product for maintaining a cache obtain request data associated with a plurality of previously processed requests for aggregated data; predict, based on the request data, (i) a subset of the aggregated data associated with a subsequent request and (ii) a first time period associated with the subsequent request; determine, based on the first time period and a second time period associated with a performance of a data aggregation operation that generates the aggregated data, a third time period associated with instructing a memory controller managing a cache to evict cached data stored in the cache and load the subset of the aggregated data into the cache; and provide an invalidation request to the memory controller managing the cache to evict the cached data stored in the cache and load the subset of the aggregated data into the cache during the third time period.

Abstract: An apparatus is described. The apparatus includes a memory controller to interface to a multi-level system memory having first and second different cache structures. The memory controller has circuitry to service a read request by concurrently performing a look-up into the first and second different cache structures for a cache line that is targeted by the read request.

Abstract: A memory device includes a non-volatile first memory in which a conversion table is stored, a second memory, and a controller configured to control the first memory and the second memory, and including a cache control circuit. The cache control circuit is configured to set up a circular buffer with a write pointer, and store portions of the conversion table in the circular buffer. Each of the portions of the conversion table contain a plurality of logical address to physical address mappings, and each of the portions have a corresponding entry in a management table stored in the second memory, and each entry of the management table includes an address field for storing an address of the circular buffer used in locating the corresponding portion of the conversion table and a size field for storing a size of the corresponding portion.

Abstract: The disclosed computer-implemented method includes receiving an indication that cache data is to be copied from an originating cluster having a specified number of replica nodes to a destination cluster having an arbitrary number of replica nodes. The method further includes copying the cache data to a cache dump and creating a log that identifies where the cache data is stored in the cache dump. The method further includes copying the cache data from the cache dump to the replica nodes of the destination cluster. The copying includes writing the copied data in a distributed manner, such that at least a portion of the copied data is distributed over each of the replica nodes in the destination cluster. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A method and an information handling system having a plurality of processors connected by a cross-processor network, where each of the plurality of processors preferably has a filter construct having an outgoing filter list that identifies logical partition identifications (LPIDs) that are exclusively assigned to that processor and/or an incoming filter list that identifies LPIDs on that processor and at least one additional processor in the system. In operation, if the LPID of the outgoing translation invalidation instruction is on the outgoing filter list, the address translation invalidation instruction is acknowledged on behalf of the system. If the LPID of the incoming invalidation instruction does not match any LPID on the incoming filter list, then the translation invalidation instruction is acknowledged, and if the LPID of the incoming invalidation instruction matches any LPID on the incoming filter list, then the invalidation instruction is sent into the respective processor.

Abstract: Systems, apparatuses, and methods related to a computer system having a page table entry containing permission bits for predefined types of memory accesses made by executions of routines in predefined domains are described. The page table entry can be used to map a virtual memory address to a physical memory address. In response to a routine accessing the virtual memory address, a permission bit corresponding to the execution domain of the routine and a type of the memory access can be extracted from the page table entry to determine whether the memory access is to be rejected.

Abstract: This disclosure provides techniques hierarchical address virtualization within a memory controller and configurable block device allocation. By performing address translation only at select hierarchical levels, a memory controller can be designed to have predictable I/O latency, with brief or otherwise negligible logical-to-physical address translation time. In one embodiment, address transition may be implemented entirely with logical gates and look-up tables of a memory controller integrated circuit, without requiring processor cycles. The disclosed virtualization scheme also provides for flexibility in customizing the configuration of virtual storage devices, to present nearly any desired configuration to a host or client.

Abstract: A computer system includes a translation lookaside buffer (TLB) and a processor. The TLB comprises a first TLB array and a second TLB array, and stores entries comprising virtual address information and corresponding real address information. The processor is configured to receive a first virtual address for translation, and to concurrently determine if the TLB stores a physical address associated with the first virtual address based on a first portion and a second portion of the first virtual address. The first portion is associated with a first page size and the second portion is associated with a second page size (different from the first page size). The first portion is used to perform lookup in either one of the first TLB array and the second TLB array and the second portion is used for performing lookup in other one of the first TLB array and the second TLB array.

Abstract: An approach is described that accesses data in a shared memory that is shared amongst nodes that include a local node and remote nodes. The local node receives a name corresponding to a named data element in a Coordination Namespace, the Coordination Namespace having been created in a memory distributed amongst the nodes. A hash function is applied to at least a portion of the name with a result of the hash function being a natural node indicator. Data corresponding to the named data element is requested from a natural node identified by the indicator. Based on the request, a response is received from the natural node.

Abstract: Embodiments of the present invention are directed to a computer-implemented method for cache eviction. The method includes detecting a first data in a shared cache and a first cache in response to a request by a first processor. The first data is determined to have a mid-level cache eviction priority. A request is detected from a second processor for a same first data as requested by the first processor. However, in this instance, the second processor has indicated that the same first data has a low-level cache eviction priority. The first data is duplicated and loaded to a second cache, however, the data has a low-level cache eviction priority at the second cache.

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 method includes determining, by a tracker controller of a hardware security module, that a first processor has submitted a first request to access a computing resource. The method also includes determining, by the tracker controller, whether the first request and a second request both request access to the same computing resource. The second request is submitted by a second processor. The method also includes preventing access to the computing resource based on a determination that the first request and the second request do not request access to the same computing resource. The method also includes permitting access to the computing resource based on a determination that the first request and the second request both request access to the same computing resource.

Abstract: A security system includes a physical unclonable function circuit, a write-in protection circuit, a memory, and a readout decryption circuit. The physical unclonable function circuit provides a plurality of random bit strings. The write-in protection circuit receives a write-in address and original data, and includes an address scrambling unit. The address scrambling unit generates a scrambled address by scrambling a write-in address according to a random bit string provided by the physical unclonable function circuit. The memory stores the storage data corresponding to the original data according to the scrambled address. The readout decryption circuit reads out the storage data from the memory according to the write-in address to derive the original data.

Abstract: Systems, apparatuses, and methods related to a domain register of a processor in a computer system are described. The computer system has a memory configured to at least store instructions of routines that are classified in multiple predefined, non-hierarchical domains. The processor stores in the domain register an identifier of a current domain of a routine that is being executed in the processor. The processor is configured to perform security operations based on the content of the domain register and the security settings specified respectively for the predefined, non-hierarchical domains.

Abstract: Caches may be vulnerable to side-channel attacks, such as Spectre and Meltdown, that involve speculative execution of instructions, revealing information about a cache that the attacker is not permitted to access. Access permission may be stored in the cache, such as in an entry of a cache table or in the region information for a cache table. Optionally, the access permission may be re-checked if the access permission changes while a memory instruction is pending. Optionally, a random index value may be stored in a cache and used, at least in part, to identify a memory location of a cacheline. Optionally, cachelines that are involved in speculative loads for memory instructions may be marked as speculative. On condition of resolving the speculative load as non-speculative, the cacheline may be marked as non-speculative; and on condition of resolving the speculative load as mis-speculated, the cacheline may be removed from the cache.

Abstract: A buffer manager is generated by executing a script with respect to a buffer architecture template and a configuration file specifying parameters for the buffer such as, for example, number of memory banks, width of memory banks, depth of memory banks, and client bridge FIFO depth. The script converts the buffer architecture template into a hardware description language (HDL) description of a buffer manager having the parameters. Client bridges accumulate requests for memory banks in FIFO that is provided to a buffer manager upon the client bridge being granted arbitration. Accesses of memory banks may be performed one at a time in consecutive clock cycles in a pipelined manner. Client bridges and the buffer manager may operate in different clock domains. The clock frequency of the buffer manager may be increased or decreased according to requests from client devices.

Abstract: A shared memory controller is to service load and store operations received, over data links, from a plurality of independent nodes to provide access to a shared memory resource. Each of the plurality of independent nodes is to be permitted to access a respective portion of the shared memory resource. Interconnect protocol data and memory access protocol data are sent on the data links and transitions between the interconnect protocol data and memory access protocol data can be defined and identified.

Abstract: According to some example embodiments according to the present disclosure, a device includes a printed circuit board (PCB); a solid state drive (SSD) connected at a first side of the PCB via at least one SSD connector; at least one field programmable gate array (FPGA) attached to the PCB at a second side of the PCB; and at least one front end connector attached to the PCB at a third side of the PCB, wherein the device is configured to process data stored in the SSD based on a command received via the at least one front end connector.

Abstract: A memory system is disclosed, which relates to technology for an accelerator of a high-capacity memory device. The memory system includes a plurality of memories configured to store data therein, and a pooled memory controller (PMC) configured to perform map computation by reading the data stored in the plurality of memories and storing resultant data produced by the map computation in the plurality of memories.

Abstract: Systems, methods, and apparatuses relating to memory interface circuit allocation in a configurable spatial accelerator are described. In one embodiment, a configurable spatial accelerator (CSA) includes a plurality of processing elements; a plurality of request address file (RAF) circuits, and a circuit switched interconnect network between the plurality of processing elements and the RAF circuits. As a dataflow architecture, embodiments of CSA have a unique memory architecture where memory accesses are decoupled into an explicit request and response phase allowing pipelining through memory. Certain embodiments herein provide for an improved memory sub-system design via the improvements to allocation discussed herein.

Abstract: A computer system with programmable serial presence detection (SPD) data is disclosed. The computer system uses a user-programmable memory to store virtual SPD data which includes the configuration information of the memory module. The virtual SPD data is stored separately from the system boot code of the computer system. A computing unit uses a memory driver to drive the memory module. The memory driver accesses the user-programmable memory through a virtual SPD module to acquire the configuration information of the memory module.

Abstract: A data storage device may include: first and second memory devices suitable for sharing an input clock signal line and at least one I/O signal line; and a controller suitable for enabling the first and second memory devices at the same time, and controlling the first and second memory devices by transmitting an input clock signal to the input clock signal line and transmitting an input signal synchronized with the input clock signal to the I/O signal line.

Abstract: Apparatuses and methods including memory commands for semiconductor memories are described. A controller provides a memory system with memory commands to access memory. The commands are decoded to provide internal signals and commands for performing operations, such as operations to access the memory array. The memory commands provided for accessing memory may include timing command and access commands. Examples of access commands include a read command and a write command. Timing commands may be used to control the timing of various operations, for example, for a corresponding access command. The timing commands may include opcodes that set various modes of operation during an associated access operation for an access command.

Abstract: Aspects of the disclosure provide for management of a flash translation layer (FTL) for a non-volatile memory (NVM) in a Solid State Drive (SSD). The methods and apparatus provide a logical to physical (L2P) table where a first portion of the table is used for mapping frequently accessed hot data to a first subdrive in the NVM. Additionally, a second portion of the L2P table is provided for mapping cold data less frequently accessed than the hot data to a second subdrive, where logical blocks for storing the cold data in the second subdrive are larger than logical blocks storing the hot data in the first subdrive. Separation of the L2P table into hot and cold subdrives reduces the L2P table size that is needed in RAM for logical to physical memory mapping, while at the same time provides lower write amplification and latencies, especially for large capacity SSDs.

Abstract: Data transfer devices as well as methods of interfacing, configuring, and using the same are disclosed. Data transfer devices described herein allow a proper communication interface to be mounted on an input device, e.g., a scanner, connected to the data transfer device, enabling communication between the input device and a host device. The data transfer devices allow the input device to be configured for communication with the host device based on a particular type of connection, e.g., a particular hardware attachment that utilizes a particular communication interface. The data transfer device therefore enables “plug-and-play” connectivity between an input device and a host device that removes the amount of user-configuration or user-modification that is required to establish a connection or have the input device, e.g., scanner, mount a proper interface that is compatible with the data transfer device.

Abstract: According to embodiments of the present invention, machines, systems, methods and computer program products for processing events including efficiently processing interrupt service requests for peripheral devices, such as hardware accelerators, utilized in parallel processing are provided. For each core engine of a peripheral device, the peripheral device detects whether one or more interrupt signals have been generated. Information associated with the one or more interrupt signals are stored in one or more registers of peripheral device memory, for each core engine. The information is aggregated and stored in a vector of registers in the peripheral device memory, and the aggregated information is written to memory associated with a CPU to enable CPU processing of interrupt requests from each core engine of the peripheral device.

Abstract: The disclosure relates generally to improvements in caching operations in storage controllers, including caching operations utilizing direct memory access (DMA) systems, and related devices. Rather than the firmware running on the processor of the storage controller having to traverse a dirty cache sector bitmap and manipulate an original scatter-gather (SG) list in order to generate the two separate SG lists, namely one for the cache and one for the storage device, these operations are offloaded onto new specialized hardware referred to herein as a smart DMA engine in order to free up the processor of the storage controller.

Abstract: A network element includes one or more ports for communicating over a network, a processor and packet processing hardware. The packet processing hardware is configured to transfer packets to and from the ports, and further includes data-transfer circuitry for data transfer with the processor. The processor and the data-transfer circuitry are configured to transfer between one another (i) one or more communication packets for transferal between the ports and the processor and (ii) one or more databases for transferal between the packet processing hardware and the processor, by (i) translating, by the processor, the transferal of both the communication packets and the databases into work elements, and posting the work elements on one or more work queues in a memory of the processor, and (ii) using the data-transfer circuitry, executing the work elements so as to transfer both the communication packets and the databases.

Abstract: In one embodiment, a Light Emitting Diode (LED) driving device for driving a plurality of LEDs has a switching matrix utilizing a plurality of one of a turn off thyristors or turn off triacs coupled to the plurality of LEDs. A controller is coupled to the switching matrix responsive to a voltage of a rectified AC halfwave, wherein combinations of the plurality of LEDs are altered to ensure a maximum operating voltage of the plurality of LEDs is not exceeded. A current limiting device is coupled to the combinations of the plurality of LED to regulate current.

Abstract: An approach is provided in which an information handling system detects a reduced capacity on a PCIe link that interfaces a host system to a PCIe I/O expansion drawer over a first/second physical cable. The information handling system verifies a first/second connection to a first/second connector on the PCIe I/O expansion drawer, receives a first/second set of vital product data over the first/second physical cable, and determines that the first physical cable and the second physical cable are connected to the same PCIe I/O expansion drawer based on analyzing the first/second set of vital product data. The information handling system then suspends operation of one or more components corresponding to the PCIe link and trains the PCIe link to an increased capacity. In turn, the information handling system resumes operation of the one or more components and restores the PCIe link to the increased capacity.

Abstract: Aligning received BDIs with received data on a cross-chip link including receiving, from the cross-chip link, a control flit comprising incoming data flit information for a plurality of incoming data flits; adding the incoming data flit information to a control structure; receiving, from the cross-chip link, the plurality of incoming data flits; directing each of the plurality of incoming data flits to virtual channel queues based on the incoming data flit information at a first read pointer in the control structure; receiving a bookend flit comprising a plurality of BDIs for the plurality of data flits; and associating each of the BDIs with the plurality of data flits based on the incoming data flit information at a second read pointer in the control structure.

Abstract: A low voltage drive circuit includes a transmit digital to analog circuit that converts transmit digital data into analog outbound data by: generating a DC component; generating a first oscillation at a first frequency; generating a second oscillation at the first frequency; and outputting the first oscillation or the second oscillation on a bit-by-bit basis in accordance with the transmit digital data to produce an oscillating component, wherein the DC component is combined with the oscillating component to produce the analog outbound data, and wherein the oscillating component and the DC component are combined to produce the analog outbound data. A drive sense circuit drives an analog transmit signal onto a bus, wherein the analog outbound data is represented within the analog transmit signal as variances in loading of the bus at the first frequency and wherein analog inbound data is represented within an analog receive signal as variances in loading of the bus at a second frequency.

Abstract: A peripheral disconnection switch system and method are provided. The system comprises at least one peripheral connected to a processor, and a hardware switch connected to the at least one peripheral. The system is operable such that engaging the hardware switch disables the at least one peripheral.

Abstract: A circuit for asynchronous data transfer includes a slave device having an asynchronous slave clock for transferring data to a master device having a master clock. The slave clock is a non-continuous clock signal. The slave device includes a clock detection circuit, a register bank, a temporary storage register, and a datapath selector. The slave device receives a data transfer command from the master device. The clock detection circuit detects a presence of the slave clock signal and generates a sync signal. To transfer the data to the master device, the datapath selector selects one of the temporary storage register and the register bank based on the sync signal. The slave device ensures seamless data transfer to the master device regardless of the presence or absence of the slave clock signal.

Abstract: Server computers often include one or more input/output (I/O) devices for communicating with a network or directly attached storage device. The data transfer latency for request can be reduced by utilizing ingress data placement logic to bypass the processor of the I/O device. For example, host memory descriptors can be stored in a memory of the I/O device to facilitate placement of the requested data.