摘要:
A cache coherent distributed shared memory multi-processor computer system is provided with a memory controller which includes a recall unit. The recall unit allows selective forced write-backs of dirty cache lines to the home memory. After a request is posted in the recall unit, a recall (“flush”) command is issued which forces the owner cache to write-back the dirty cache line to be flushed. The memory controller will inform the recall unit as each recall operation is completed. The recall unit operation will be interrupted when all flush requests are completed.
摘要:
A caching method for using cache tag and cache data stored in dynamic RAM embedded in a logic chip. In general, there are at least two cache applications where this method can be employed. First, there are caches integral to a processor and interfaced to a processor pipeline. Second, there are caches external to a processor and interfaced with a shared bus.
摘要:
A memory access circuit and a corresponding method are provided. The memory access circuit includes a crypto block in communication with a memory that encrypts data of a data block on a block basis. The memory access circuit also includes a fault injection block configured to inject faults to the data in the data block. The memory access circuit further includes a data scrambler and an address scrambler. The data scrambler is configured to scramble data in the memory by shuffling data bits within the data block in a plurality of rounds and mash the shuffled data bits with random data. The address scrambler is configured to distribute the scrambled data across the memory. A memory system including the memory access circuit is also disclosed to implement the corresponding method.
摘要:
A method to transmit data using a device having a plurality of physical input/output (I/O) interfaces is provided. The method comprises receiving data and determining a topology according to which data is to be transmitted. Data is transmitted in sequential order via a single physical interface for a first topology and in random order via a plurality of physical interfaces for a second topology.A System On Chip (SOC) unit enabled to transmit data via one or more physical interfaces is provided. The SOC comprises a processor and a network interface including multiple physical input/output (I/O) interfaces coupled to the processor. In response to receiving data for transmission, the processor is enabled to select a single I/O interface for sequential data transmission according to a first topology or select multiple physical I/O interfaces for random order data transmission according to a second topology.
摘要:
Certain embodiments of the invention may be found in a method and system for an adaptive cache for caching context and for adapting to collisions in session lookup table. A network processor chip may comprise an on-chip cache that stores transport control blocks (TCB) from a TCB array in external memory to reduce latency in active transmission control protocol/Internet protocol (TCP/IP) sessions. The on-chip cache may comprise a tag portion implemented using a content addressable memory (CAM) and a data portion implemented using a random access memory (RAM). When a session collision occurs the context of a subsequent network connection may be stored in a data overflow portion of an overflow table in the on-chip cache. A search key associated with the subsequent network connection that comprises network connection parameters may be stored in a tag overflow portion of the overflow table.
摘要:
Disclosed herein is an apparatus which may comprise a plurality of nodes. In one example embodiment, each of the plurality of nodes may include one or more central processing units (CPUs), a random access memory device, and a parallel link input/output port. The random access memory device may include a local memory address space and a global memory address space. The local memory address space may be accessible to the one or more CPUs of the node that comprises the random access memory device. The global memory address space may be accessible to CPUs of all the nodes. The parallel link input/output port may be configured to send data frames to, and receive data frames from, the global memory address space comprised by the random access memory device(s) of the other nodes.
摘要:
Methods, systems and computer program products to implement hardware memory locks are described herein. A system to implement hardware memory locks is provided. The system comprises an off-chip memory coupled to a SOC unit that includes a controller and an on-chip memory. Upon receiving a request from a requester to access a first memory location in the off-chip memory, the controller is enabled to grant access to modify the first memory location based on an entry stored in a second memory location of the on-chip memory. In an embodiment, the on-chip memory is Static Random Access Memory (SRAM) and the off-chip memory is Random Access Memory (RAM).
摘要:
Methods, systems and computer program products to implement hardware memory locks are described herein. A system to implement hardware memory locks is provided. The system comprises an off-chip memory coupled to a System-On-a-Chip(SOC) unit that includes a controller and an on-chip memory. Upon receiving a request from a requester to access a first memory location in the off-chip memory, the controller is enabled to grant access to modify the first memory location based on an entry stored in a second memory location of the on-chip memory. In an embodiment, the on-chip memory is Static Random Access Memory (SRAM) and the off-chip memory is Random Access Memory (RAM).
摘要:
Methods, systems and computer program products to maintain cache coherency in a System-On-a-Chip (SOC) which is part of a distributed shared memory system are described. A local SOC unit that includes a local controller and an on-chip memory is provided. In response to receiving a request from a remote controller of a remote SOC to access a memory location, the local controller determines whether the local SOC has exclusive ownership of the requested memory location, sends data from the memory location if the local SOC has exclusive ownership of the memory location and stores an entry in the on-chip memory that identifies the remote SOC as having requested data from the memory location. The entry specifies whether the request from the remote SOC is for exclusive ownership of the memory location. The entry also includes a field that identifies the remote SOC as the requester. The requested memory location may be external or internal to the local SOC unit.
摘要:
In one aspect, there is provided a method for use by an edge device for establishing a connection with a server to support a full TCP connection between a client and the edge device. The method comprises establishing a full TCP connection with the server using a full TCP socket, allocating a first light TCP socket for supporting a first light TCP connection with the server, associating a first light session ID with the first light TCP connection, sending a first open session message to the server via the full TCP connection with the server, establishing the first light TCP connection with the server via the full TCP connection, associating first data with the first light session ID, and delivering the first data associated with the first light session ID to the server using the first light TCP connection via the full TCP connection.