Intel Corporation

John M Morgan

Marc A Goldschmidt

Edward J Pullin

Dirk Blevins

Namakkal N Venkatesan

Liang-Min Wang

Apparatus, systems, and/or methods may include a peripheral component interconnect express (PCIe) link to directly couple a slot with a network fabric. The slot may be defined by a surface and/or may accommodate a hardware module. A rack unit implementation may be utilized, such as a one rack unit (1U) implementation, a four rack unit (4U) implementation, and so on. The network fabric may be utilized when hardware modules communicate across the PCIe link, may be bypassed when hardware modules communicate across an additional PCIe link, and so on. The PCIe link may include a direct connect point-to-point PCIe link, a dual star PCIe link, and so on. In addition, the PCIe link may be utilized in a rack-scale architecture.

Computer architecture to provide flexibility and/or scalability

Apparatus, systems, and/or methods may include a peripheral component interconnect express (PCIe) link to directly couple a slot with a network fabric. The slot may be defined by a surface and/or may accommodate a hardware module. A rack unit implementation may be utilized, such as a one rack unit (1 U) implementation, a four rack unit (4 U) implementation, and so on. The network fabric may be utilized when hardware modules communicate across the PCIe link, may be bypassed when hardware modules communicate across an additional PCIe link, and so on. The PCIe link may include a direct connect point-to-point PCIe link, a dual star PCIe link, and so on. In addition, the PCIe link may be utilized in a rack-scale architecture.

An apparatus and method for implementing a shared unified cache. For example, one embodiment of a processor comprises: a plurality of processor cores grouped into modules, wherein each module has at least two processor cores grouped therein; a plurality of level 1 (L1) caches, each L1 cache directly accessible by one of the processor cores; a level 2 (L2) cache associated with each module, the L2 cache directly accessible by each of the processor cores associated with its respective module; a shared unified cache to store data and/or instructions for each of the processor cores in each of the modules; and a cache management module to manage the cache lines in the shared unified cache using a first cache line eviction policy favoring cache lines which are shared across two or more modules and which are accessed relatively more frequently from the modules.

Growing community of inventors

Townsend, MA, United States of America

John M Morgan