摘要:
Systems and methods may be used to determine where to run a service based on workload-based conditions or system-level conditions. An example method may include determining whether power available to a resource of a compute device satisfies a target power, for example to satisfy a target performance for a workload. When the power available is insufficient, an additional resource may be provided, for example on a remote device from the compute device. The additional resource may be used as a replacement for the resource of the compute device or to augment the resource of the compute device.
摘要:
A system that may optionally be partitioned into multiple domains is disclosed. Each domain is capable of independently powering on, executing a firmware program, and loading an operating system, including a legacy operating system, as well as running an application program that is distinct from programs running on another domain. Interrupts, including boot interrupts, reset handlers, and inter-chassis communications are initialized differently, depending on whether the system is to be partitioned or not. The cost of redundant hardware and/or firmware is substantially avoided, yet the system fully supports multiple domains.
摘要:
Systems and methods of implementing server architectures that can facilitate the servicing of memory components in computer systems. The systems and methods employ nonvolatile memory/storage modules that include nonvolatile memory (NVM) that can be used for system memory and mass storage, as well as firmware memory. The respective NVM/storage modules can be received in front or rear-loading bays of the computer systems. The systems and methods further employ single, dual, or quad socket processors, in which each processor is communicably coupled to at least some of the NVM/storage modules disposed in the front or rear-loading bays by one or more memory and/or input/output (I/O) channels. By employing NVM/storage modules that can be received in front or rear-loading bays of computer systems, the systems and methods provide memory component serviceability heretofore unachievable in computer systems implementing conventional server architectures.
摘要:
A system and method are described for integrating a memory and storage hierarchy including a non-volatile memory tier within a computer system. In one embodiment, PCMS memory devices are used as one tier in the hierarchy, sometimes referred to as “far memory.” Higher performance memory devices such as DRAM placed in front of the far memory and are used to mask some of the performance limitations of the far memory. These higher performance memory devices are referred to as “near memory.”
摘要:
Configurable central processing unit (CPU) package substrates are disclosed. A package substrate is described that includes a processing device interface. The package substrate also includes a memory device electrical interface disposed on the package substrate. The package substrate also includes a removable memory mechanical interface disposed proximately to the memory device electrical interface. The removable memory mechanical interface is to allow a memory device to be easily removed from the package substrate after attachment of the memory device to the package substrate.
摘要:
A system and method are described for integrating a memory and storage hierarchy including a non-volatile memory tier within a computer system. In one embodiment, PCMS memory devices are used as one tier in the hierarchy, sometimes referred to as “far memory.” Higher performance memory devices such as DRAM placed in front of the far memory and are used to mask some of the performance limitations of the far memory. These higher performance memory devices are referred to as “near memory.”