Abstract: Technologies for load balancing a storage network include a system. The system includes circuitry to adjust routing rules in a network interface controller to deliver a packet from one of multiple uplinks to one of any physical functions, circuitry to remap, in response to a failure of a switch, a port from one physical function to another physical function, and circuitry to communicate control data between a software defined network controller and one or more agents in one or more host endpoints with a hierarchical distributed hashing table.

Abstract: Technologies for managing disaggregated resources in a data center includes a compute device configured to determine that a service related task has been generated and create one or more microservices to perform the created service related task using at least one of a plurality of services managed by the microservice resource controller circuitry. The compute device is further configuration to generate one or more microtasks to compose at least one service based on the one or more microservices. Other embodiments are described herein.

Abstract: Examples described herein provide a central processing unit (CPU) to reserve a region of memory for use to store both a boot firmware code and a second boot firmware code and to perform the second boot firmware code without reboot. The reserved region of memory can be a region that is not configured for access by an operating system (OS). The reserved region of memory comprises System Management Random Access Memory (SMRAM). If a first interrupt handler is not overwritten after a second boot firmware code is stored, the CPU can roll back to use of the first interrupt handler.

Abstract: Technologies for utilizing a runtime code present in an option read only memory (ROM) include a sled that includes a device having an option ROM with runtime code indicative of a runtime function of the device. The sled is to detect, in a boot process, the device on the sled, access, in the boot process, the runtime code in the option ROM of the detected device to identify the runtime function, and execute, in a runtime process, the runtime function associated with the runtime code. Other embodiments are also described and claimed.

Abstract: 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.

Abstract: Apparatuses for computing are disclosed herein. An apparatus may include a set of data reduction modules to perform data reduction operations on sets of (key, value) data pairs to reduce an amount of values associated with a shared key, wherein the (key, value) data pairs are stored in a plurality of queues located in a plurality of solid state drives remote from the apparatus. The apparatus may further include a memory access module, communicably coupled to the set of data reduction modules, to directly transfer individual ones of the sets of queued (key, value) data pairs from the plurality of remote solid state drives through remote random access of the solid state drives, via a network, without using intermediate staging storage. Other embodiments may be disclosed or claimed.

Abstract: Techniques and mechanisms for a processor to efficiently identify a circuit resource as being a source of data poisoning. In an embodiment, metadata is communicated, in association with a communication of poisoned data to which the metadata pertains, to a first circuit block of a processor. The metadata indicates a poisoned state of the data, wherein the metadata identifies a second circuit block—which is included in or coupled to the processor—as being a poisoner of the data. Based on the metadata, the first circuit block generates a fault message which identifies the second circuit block as the poisoner of the data. In another embodiment, the processor further comprises the second circuit block, which poisons the data (based on the detection of an error condition) by providing in the metadata a unique identifier which is assigned to the second circuit block.

Abstract: A modular microcode (uCode) patch method to support runtime persistent update and associated apparatus. The method enables BIOS uCode patches to be received during platform runtime operations and written to first and second uCode extension regions as uCode images for a firmware device layout that further includes a uCode base region in which a current uCode image is stored. Following a platform reset, the first and second uCode extension regions are inspected to determine if one or more valid and newer uCode images (than the current uCode image) are present. If so, the newest uCode image is booted rather than the current uCode image. Following a successful boot, the newest uCode image is copied to the uCode base region to sync-up the current uCode image to the newest version. In one aspect, received uCode images are written to the first and second uCode extension regions in an alternating manner to support roll-back.

Abstract: Technologies for enabling and metering the utilization of components on demand include a compute device. The compute device includes a network interface controller and circuitry configured to receive, through a network and with the network interface controller, a request to enable a component of a sled to assist in the execution of a workload. The circuitry is further configured to enable, in response to the request, the component to assist in the execution of the workload, and meter the utilization of the component by the workload to determine a total monetary cost to a customer associated with the workload for the utilization of the component.

Abstract: Mechanisms for SAS-free cabling in Rack Scale Design (RSD) environments and associated methods, apparatus, and systems. Pooled compute drawers containing multiple compute nodes are coupled to pooled storage drawers using fabric infrastructure, such as Ethernet links and switches. The pooled storage drawers includes a storage distributor that is coupled to a plurality of storage devices and includes one or more fabric ports and a PCIe switch with multiple PCIe ports. Under one configuration, the PCIe ports are connected to one or more IO hubs including a PCIe switch coupled to multiple storage device interfaces that are coupled to the storage devices. In another configuration, the PCIe ports are connected directly to PCIe storage devices. The storage distributor implements a NVMe-oF server driver that interacts with an NVMe-oF client driver running on compute nodes or a fabric switch.

Abstract: In an example, there is disclosed a memory controller, including: a data buffer to drive a determinate value to a data bus to communicatively couple to a memory; and a register clock driver to: receive a memory initialization command from a processor; and incrementally step through a plurality of initialization addresses, sequentially driving each initialization address to an address bus to communicatively couple to the memory. There is also disclosed a computing device comprising the memory controller, and a method of initializing memory comprising incrementally stepping through a plurality of initialization addresses and sequentially writing a determinate value to each address.

Abstract: Technologies for fast boot-up of a compute device with error-correcting code (ECC) memory are disclosed. A basic input/output system (BIOS) of a compute device may assign memory addresses of the ECC memory to different processors on the compute device. The processors may then initialize the ECC memory in parallel by writing to the ECC memory. The processors may write to the ECC memory with direct-store operations that are immediately written to the ECC memory instead of being cached. The BIOS may continue to operation on one processor while the rest of the processors initialize the ECC memory.

Abstract: Examples may include a basic input/output system (BIOS) for a computing platform communicating with a controller for a non-volatile dual in-line memory module (NVDIMM). Communication between the BIOS and the controller may include a request for the controller to scan and identify error locations in non-volatile memory at the NVDIMM. The non-volatile memory may be capable of providing persistent memory for the NVDIMM.

Abstract: Examples may include sleds for a rack in a data center including physical compute resources and memory for the physical compute resources. The memory can be disaggregated, or organized into first level and second level memory. A first sled can comprise the physical compute resources and a first set of physical memory resources while a second sled can comprise a second set of physical memory resources. The first set of physical memory resources can be coupled to the physical compute resources via a local interface while the second set of physical memory resources can be coupled to the physical compute resources via a fabric.

Abstract: Examples include methods for obtaining one or more location hints applicable to a range of logical block addresses of a received input/output (I/O) request for a storage subsystem coupled with a host system over a non-volatile memory express over fabric (NVMe-oF) interconnect. The following steps are performed for each logical block address in the I/O request. A most specific location hint of the one or more location hints that matches that logical block address is applied to identify a destination in the storage subsystem for the I/O request. When the most specific location hint is a consistent hash hint, the consistent hash hint is processed. The I/O request is forwarded to the destination and a completion status for the I/O request is returned. When a location hint log page has changed, the location hint log page is processed. When any location hint refers to NVMe-oF qualified names not included in the immediately preceding query by the discovery service, the immediately preceding query is processed again.

Abstract: Technologies for dividing resources across partitions include a compute sled. The compute sled is to determine partitions among sockets of the compute sled. Each socket is associated with a corresponding processor. The compute sled is also to establish a separate memory space for each determined partition, obtain, from an application executed in one of the sockets, a request to access a logical memory address, identify the partition associated with the memory access request, determine a corresponding physical memory address as a function of the identified partition and the logical memory address, and access a memory of the compute sled at the determined physical memory address. Other embodiments are also described and claimed.

Abstract: Embodiments are generally directed apparatuses, methods, techniques and so forth to receive a sled manifest comprising identifiers for physical resources of a sled, receive results of an authentication and validation operations performed to authenticate and validate the physical resources of the sled, determine whether the results of the authentication and validation operations indicate the physical resources are authenticate or not authenticate. Further and in response to the determination that the results indicate the physical resources are authenticated, permit the physical resources to process a workload, and in response to the determination that the results indicate the physical resources are not authenticated, prevent the physical resources from processing the workload.

Abstract: Technologies for composing a managed node with multiple processors on multiple compute sleds to cooperatively execute a workload include a memory, one or more processors connected to the memory, and an accelerator. The accelerator further includes a coherence logic unit that is configured to receive a node configuration request to execute a workload. The node configuration request identifies the compute sled and a second compute sled to be included in a managed node. The coherence logic unit is further configured to modify a portion of local working data associated with the workload on the compute sled in the memory with the one or more processors of the compute sled, determine coherence data indicative of the modification made by the one or more processors of the compute sled to the local working data in the memory, and send the coherence data to the second compute sled of the managed node.

Abstract: An apparatus and method are described for detecting and correcting data fetch errors within a processor core. For example, one embodiment of an instruction processing apparatus for detecting and recovering from data fetch errors comprises: at least one processor core having a plurality of instruction processing stages including a data fetch stage and a retirement stage; and error processing logic in communication with the processing stages to perform the operations of: detecting an error associated with data in response to a data fetch operation performed by the data fetch stage; and responsively performing one or more operations to ensure that the error does not corrupt an architectural state of the processor core within the retirement stage.

Abstract: Provided are a method, system, computer readable storage medium, and switch for configuring a switch to assign partitions in storage devices to compute nodes. A management controller configures the switch to dynamically allocate partitions of at least one of the storage devices to the compute nodes based on a workload at the compute node.