Abstract: Methods and apparatus relating to de-prioritizing speculative code lines in on-chip caches are described. In an embodiment, logic circuitry determines whether a storage structure includes a reference to a code miss request prior to transmission of the code miss request to a shared cache. The logic circuitry causes de-prioritization of a code line, corresponding to the code miss request, in the shared cache in response to an absence of the reference in the storage structure. Other embodiments are also disclosed and claimed.

Abstract: Methods and apparatus relating to memory side prefetch architecture for improved memory bandwidth are described. In an embodiment, logic circuitry transmits a Direct Memory Controller Prefetch (DMCP) request to cause a prefetch of data from memory. A memory controller receives the DMCP request and issues a plurality of read operations to the memory in response to the DMCP request. Data read from the memory is stored in a storage structure in response to the plurality of read operations. Other embodiments are also disclosed and claimed.

Abstract: The present disclosure provides a method for reducing memory traffic in a distributed memory system. The method may include storing a presence vector in a directory of a memory slice, said presence vector indicating whether a line in local memory has been cached. The method may further include protecting said memory slice from cache coherency violations via a home agent configured to transmit and receive data from said memory slice, said home agent configured to store a copy of said presence vector. The method may also include receiving a request for a block of data from at least one processing node at said home agent and comparing said presence vector with said copy of said presence vector stored in said home agent. The method may additionally include eliminating a write update operation between said home agent and said directory if said presence vector and said copy are equivalent. Of course, many alternatives, variations and modifications are possible without departing from this embodiment.

Abstract: The present disclosure provides a method for reducing memory traffic in a distributed memory system. The method may include storing a presence vector in a directory of a memory slice, said presence vector indicating whether a line in local memory has been cached. The method may further include protecting said memory slice from cache coherency violations via a home agent configured to transmit and receive data from said memory slice, said home agent configured to store a copy of said presence vector. The method may also include receiving a request for a block of data from at least one processing node at said home agent and comparing said presence vector with said copy of said presence vector stored in said home agent. The method may additionally include eliminating a write update operation between said home agent and said directory if said presence vector and said copy are equivalent. Of course, many alternatives, variations and modifications are possible without departing from this embodiment.

Abstract: Selectively transmitting cache misses within multiple-node shared-memory systems employing coherence protocols is disclosed. A cache-coherent system includes a number of nodes employing a coherence protocol to maintain cache coherency, as well as memory that is divided into a number of memory units. There is a cache within each node to temporarily store contents of the memory units. Each node further has logic to determine whether a cache miss relating to a memory unit should be transmitted to one or more of the other nodes lesser in number than the total number of nodes within the system. This determination is based on whether, to ultimately reach the owning node for the memory unit, such transmission is likely to reduce total communication traffic among the total number of nodes and unlikely to increase latency as compared to broadcasting the cache miss to all the nodes within the system.

Abstract: A method and apparatus for a multiprocessor system to simultaneously process multiple data write command issued from one or more peripheral component interface (PCI) devices by controlling and limiting notification of invalidated address information issued by one memory controller managing one group of multiprocessors in a plurality of multiprocessor groups. The method and apparatus permits a multiprocessor system to almost completely process a subsequently issued write command from a PCI device or other type of computer peripheral device before a previous write command has been completely processed by the system. The disclosure is particularly applicable to multiprocessor computer systems which utilize non-uniform memory access (NUMA).