Abstract: An embodiment of a semiconductor apparatus may include technology to create two or more logical to physical translation maps for a persistent storage media, associate a respective group with each of the two or more logical to physical translation maps, assign priority information to the respective groups, and initialize the respective groups at boot time based on the assigned priority information. Another embodiment may further include technology to mark an initialized group as ready for commands. Other embodiments are disclosed and claimed.

Abstract: A memory system includes a plurality of memory channels, each of the plurality of memory channels includes a plurality of memory dies and a die processor, each of the plurality of memory dies includes a plurality of memory blocks; and a memory controller including a monarch processor, coupled to the plurality of memory channels, wherein the die processor on each of the plurality of memory channels is configured in parallel to process to find last written data within at least a predetermined block of the plurality of memory dies; and provide information regarding the last written data to the monarch processor, the monarch processor determines which boot record to be used to identify firmware images based on the information.

Abstract: A memory system includes a plurality of memory channels, each of the plurality of memory channels includes a plurality of memory dies and a die processor, each of the plurality of memory dies includes a plurality of memory blocks; and a memory controller including a monarch processor, coupled to the plurality of memory channels, wherein the die processor on each of the plurality of memory channels is configured in parallel to process to find last written data within at least a predetermined block of the plurality of memory dies; and provide information regarding the last written data to the monarch processor, the monarch processor determines which boot record to be used to identify firmware images based on the information.

Abstract: Systems and methods for early warnings of power loss in solid state storage drives are disclosed. Early warnings of power loss can be used to power the drive to force the drive into a low power states before the energy in backup power sources, such as backup capacitors, is used. The low power states can allow for the reduction of power use by the drive which can provide cost savings and reduction in the risk that the drive will be rendered reconfigurable by a power failure event.

Abstract: Systems and methods for early warnings of power loss in solid state storage drives are disclosed. Early warnings of power loss can be used to power the drive to force the drive into a low power states before the energy in backup power sources, such as backup capacitors, is used. The low power states can allow for the reduction of power use by the drive which can provide cost savings and reduction in the risk that the drive will be rendered reconfigurable by a power failure event.

Abstract: Systems and methods for testing non-volatile storage devices are disclosed that provide functionality to control when testing of the non-volatile storage device is performed. In one embodiment, information stored in persistent memory indicates whether testing is enabled or disabled. For example, the testing information may indicate that testing is to be performed upon a first initialization of a non-volatile storage device, but not in connection with subsequent power-up events. Furthermore, functionality is disclosed for re-running and/or bypassing testing of the non-volatile storage device.

Abstract: An electronic device is disclosed comprising a non-volatile memory storing a first version of a control program (CP), a first header comprising a first version identifier (VID) identifying the first version of the CP and a first VID check code generated in response to at least the first VID. The non-volatile memory further stores a second version of the CP, and a second header comprising a second VID identifying the second version of the CP and a second VID check code generated in response to at least the second VID. When the first and second VIDs are valid, the electronic device selects between the first version and the second version of the CP in response to the first and second VIDs, and executes the selected version of the CP.

Abstract: Methods and apparatus for subdividing a hard partition of a computer server system into one or more soft partitions using partition management programming installed within firmware of the server system. The partition management firmware may be disposed at least partially on a central service processor and may be programmed to present generic interfaces, so that operating systems do not require modification to interface with the partition management programming.

Abstract: A method of allocating a resource in a computer system having a plurality of operating systems, and related system, are disclosed. In at least one embodiment, the method includes providing an advanced configuration and power interface (ACPI) operating to facilitate interactions between at least one of the plurality of the operating systems and one or more of the resource, a hardware device, and firmware, and determining whether the resource is allocated to a first of the plurality of operating systems. The method further includes ejecting the resource from the first operating system, and allocating the resource to a second of the plurality of operating systems.

Abstract: Methods and apparatus for subdividing a hard partition of a computer server system into one or more soft partitions using partition management programming installed within firmware of the server system. The partition management firmware may be disposed at least partially on a central service processor and may be programmed to present generic interfaces, so that operating systems do not require modification to interface with the partition management programming.

Abstract: Provided is a method for restarting a computing platform to a state in which applications run in less time than an initial start, including powering on a computing platform having a plurality of devices; identifying one or more of the devices which are not critical to running applications; storing information about the non-critical devices; restarting the computing platform; retrieving the information about the non-critical devices; disabling the non-critical devices; performing at least one of testing and initialization of at least one device of the plurality of devices that are critical to running the applications before the restart is completed; offloading at least one of testing and initialization of at least one of the non-critical devices; enabling devices which are not non-critical; and enabling the non-critical devices after the restart is completed.

Abstract: Provided is a method for restarting a computing platform to a state in which applications run in less time than an initial start, comprising powering on a computing platform having a plurality of devices; identifying one or more of the devices which are not critical to running applications; storing information about the non-critical devices; restarting the computing platform; retrieving the information about the non-critical devices; disabling the non-critical devices; enabling devices which are not non-critical; and enabling the non-critical devices after the restart is completed.

Abstract: Implementations of speedy boot for computer systems are disclosed. In an exemplary embodiment, a method of speedy boot for a computer system may include invoking a platform management interrupt (PMI) to soft reset a processor without resetting hardware for the processor. The method may also include bypassing at least some initialization procedures and tests to speed recovery of the computer system to a usable state. The method may also include resetting operating system interfaces and loading the operating system.

Abstract: Systems, methodologies, media, and other embodiments associated with acquiring processor executable instructions from an option ROM are described. One exemplary method embodiment includes discovering input/output devices operably connected to a processor and updating a data structure with information concerning the input/output devices. The example method embodiment may also include obtaining a device driver from an option ROM associated with an input/output device, storing the device driver in non-MMIO memory and making the device driver available to input/output devices physically connected to the processor and for which information is stored in the data structure.

Abstract: A method of allocating a resource in a computer system having a plurality of operating systems, and related system, are disclosed. In at least one embodiment, the method includes providing an advanced configuration and power interface (ACPI) operating to facilitate interactions between at least one of the plurality of the operating systems and one or more of the resource, a hardware device, and firmware, and determining whether the resource is allocated to a first of the plurality of operating systems. The method further includes ejecting the resource from the first operating system, and allocating the resource to a second of the plurality of operating systems.

Abstract: Systems, methodologies, media, and other embodiments associated with power management are described. One exemplary system embodiment includes an uninterrupted power supply (UPS) manager logic configured to determine a power status of one or more UPS devices attached to one or more external peripheral devices. The UPS manager logic can be configured to notify an appropriate operating system of a power loss to a selected external device.

Abstract: Provided is a method for restarting a computing platform to a state in which applications run in less time than an initial start, including powering on a computing platform having a plurality of devices; identifying one or more of the devices which are not critical to running applications; storing information about the non-critical devices; restarting the computing platform; retrieving the information about the non-critical devices; disabling the non-critical devices; performing at least one of testing and initialization of at least one device of the plurality of devices that are critical to running the applications before the restart is completed; offloading at least one of testing and initialization of at least one of the non-critical devices; enabling devices which are not non-critical; and enabling the non-critical devices after the restart is completed.

Abstract: Provided is a method for restarting a computing platform to a state in which applications run in less time than an initial start, comprising powering on a computing platform having a plurality of devices; identifying one or more of the devices which are not critical to running applications; storing information about the non-critical devices; restarting the computing platform; retrieving the information about the non-critical devices; disabling the non-critical devices; enabling devices which are not non-critical; and enabling the non-critical devices after the restart is completed.

Abstract: A system and method updating firmware of cells in cellular, high availability, computing systems. One or more cells having missing, obsolete, corrupt, or otherwise errored firmware when compared to other cells in the partition are identified as mismatched cells. An update cell having desired firmware transmits an update message to each mismatched cell via a manageability system slow speed interconnect. In response to the update message, each mismatched cell enables a high speed interconnect over which they can receive the desired firmware. The update cell transmits the update firmware to each mismatched cell via the high speed interconnect.

Abstract: A computer program version checking system checks at least one version of software running on a computing device including a plurality of programmable devices. A version of software running on the computing device is identified and compared to a version of the software in a recipe that is previously determined to be a correct version of the software. A determination is made as to whether the versions match.