摘要:
Methods and arrangements to extend message signal interrupt (MSI) transactions with additional data to reduce the latency associated with servicing interrupts included in the transactions are contemplated. Some embodiments may comprise a chipset that transmits the MSI to a processor to service the interrupt. The chipset may identify that a transaction is an extended MSI transaction by determining that the MSI has more than a four bytes. In several embodiments, the chipset may validate the MSI by determining that the MSI comprises at least six bytes and, in further embodiments, by determining that the extended MSI has a valid signature byte. Another embodiment comprises a processor to receive the extended MSI transaction and store the data to service the corresponding interrupt(s) in a low latency buffer. The processor may then service the interrupt(s) based upon the data when the processor becomes available.
摘要:
A discussion of a local memory with at least a command block section and a cache section that facilitates an efficient interrupt processing. The command-block section is allocated on a per interrupt basis and contains pointers to cache-lines. When an interrupt is recognized an interrupt, the proposal uses the pointers in the command-block to prefetch the corresponding cache-lines from the cache section of the local memory, which it loads into its local cache buffer. Thus, when the CPU recognizes an interrupt, the information for the context-switch is already available in cache.
摘要:
Technologies for identifying a cache line of a network packet for eviction from an on-processor cache of a network device communicatively coupled to a network controller. The network device is configured to determine whether a cache line of the cache corresponding to the network packet is to be evicted from the cache based on a determination that the network packet is not needed subsequent to processing the network packet, and provide an indication that the cache line is to be evicted from the cache based on an eviction policy received from the network controller.
摘要:
A method and apparatus for high performance volatile disk drive (VDD) memory access using an integrated direct memory access (DMA) engine. In one embodiment, the method includes the detection of a data access request to VDD memory implemented within volatile system memory. Once a data access request is detected, a VDD driver may issue a DMA data request to perform the data access request from the VDD. Accordingly, in one embodiment, the job of transferring data to/from a VDD memory implemented within an allocated portion of volatile system memory is offloaded to a DMA engine, such as, for example, an integrated DMA engine within a memory controller hub (MCH). Other embodiments are described and claimed.
摘要:
A method and apparatus for high performance volatile disk drive (VDD) memory access using an integrated direct memory access (DMA) engine. In one embodiment, the method includes the detection of a data access request to VDD memory implemented within volatile system memory. Once a data access request is detected, a VDD driver may issue a DMA data request to perform the data access request from the VDD. Accordingly, in one embodiment, the job of transferring data to/from a VDD memory implemented within an allocated portion of volatile system memory is offloaded to a DMA engine, such as, for example, an integrated DMA engine within a memory controller hub (MCH). Other embodiments are described and claimed.
摘要:
A method and apparatus for high performance volatile disk drive (VDD) memory access using an integrated direct memory access (DMA) engine. In one embodiment, the method includes the detection of a data access request to VDD memory implemented within volatile system memory. Once a data access request is detected, a VDD driver may issue a DMA data request to perform the data access request from the VDD. Accordingly, in one embodiment, the job of transferring data to/from a VDD memory implemented within an allocated portion of volatile system memory is offloaded to a DMA engine, such as, for example, an integrated DMA engine within a memory controller hub (MCH). Other embodiments are described and claimed.