Abstract: Technology for a memory pool arbitration apparatus is described. The apparatus can include a memory pool controller (MPC) communicatively coupled between a shared memory pool of disaggregated memory devices and a plurality of compute resources. The MPC can receive a plurality of data requests from the plurality of compute resources. The MPC can assign each compute resource to one of a set of compute resource priorities. The MPC can send memory access commands to the shared memory pool to perform each data request prioritized according to the set of compute resource priorities. The apparatus can include a priority arbitration unit (PAU) communicatively coupled to the MPC. The PAU can arbitrate the plurality of data requests as a function of the corresponding compute resource priorities.

Abstract: System and techniques for multifactor intelligent agent control are described herein. A workload request may be received from a user device via a network. The workload may be instantiated in an isolated environment on an edge computing platform. Here, the isolated environment may be a container or a virtual machine. The instantiation of the workload may include using a hardware security component (SEC) of the mobile edge computing platform to prevent access to data or code of the workload from other environments hosted by the mobile edge computing platform. The workload may then be executed in the isolated environment and a result of the workload returned to the user device.

Abstract: There is disclosed in one example a computing apparatus, including: a processor; a multilevel cache including a plurality of cache levels; a peripheral device configured to write data directly to a directly writable cache; and a cache monitoring circuit, including cache counters La to be incremented when a cache line is allocated into the directly writable cache, Lp to be incremented when a cache line is processed by the processor and deallocated from the directly writable cache, and Le to be incremented when a cache line is evicted from the directly writable cache to the memory, wherein the cache monitoring circuit is to determine a direct write policy according to the cache counters.

Abstract: Particular embodiments described herein provide for an electronic device that can be configured to receive a request for a timestamp associated with a virtual machine, determine a current time from a timestamp counter, and subtract a timing compensation from the current time from the timestamp counter to create the timestamp, where the timing compensation includes an amount of time that execution of the virtual machine was suspended. In an example, a VM_EXIT instruction was used to suspend execution of the virtual machine and the timestamp counter was read before the VM_EXIT instruction was processed by a hypervisor.

Abstract: Examples include techniques to manage cache resource allocations associated with one or more cache class of service (CLOS) assignments for a processor cache. Examples include flushing portions of an allocated cache resource responsive to reassignments of CLOS.

Abstract: Methods and apparatus for accelerating VM-to-VM Network Traffic using CPU cache. A virtual queue manager (VQM) manages data that is to be kept in VM-VM shared data buffers in CPU cache. The VQM stores a list of VM-VM allow entries identifying data transfers between VMs that may use VM-VM cache “fast-path” forwarding. Packets are sent from VMs to the VQM for forwarding to destination VMs. Indicia in the packets (e.g., in a tag or header) is inspected to determine whether a packet is to be forwarded via a VM-VM cache fast path or be forwarded via a virtual switch. The VQM determines the VM data already in the CPU cache domain while concurrently coordinating with the data to and from the external shared memory, and also ensures data coherency between data kept in cache and that which is kept in shared memory.

Abstract: Method and system for performing data movement operations is described herein. One embodiment of a method includes: storing data for a first memory address in a cache line of a memory of a first processing unit, the cache line associated with a coherency state indicating that the memory has sole ownership of the cache line; decoding an instruction for execution by a second processing unit, the instruction comprising a source data operand specifying the first memory address and a destination operand specifying a memory location in the second processing unit; and responsive to executing the decoded instruction, copying data from the cache line of the memory of the first processing unit as identified by the first memory address, to the memory location of the second processing unit, wherein responsive to the copy, the cache line is to remain in the memory and the coherency state is to remain unchanged.

Abstract: Technologies for managing quality of service of a platform interconnect include a compute device. The compute device includes one or more processors, one or more resources capable of being utilized by the one or more processors, and a platform interconnect to facilitate communication of messages between the one or more processors and the one or more resources. The compute device is to obtain class of service data for one or more workloads to be executed by the compute device. The class of service data is indicative of a capacity of one or more of the resources to be utilized in the execution of each corresponding workload. The compute device is also to execute the one or more workloads and manage the amount of traffic transmitted through the platform interconnect for each corresponding workload as a function of the class of service data as the one or more workloads are executed.

Abstract: Technologies for providing adaptive platform quality of service include a compute device. The compute device is to obtain class of service data for an application to be executed, execute the application, determine, as a function of one or more resource utilizations of the application as the application is executed, a present phase of the application, set a present class of service for the application as a function of the determined phase, wherein the present class of service is within a range associated with the determined phase, determine whether a present performance metric of the application satisfies a target performance metric, and increment, in response to a determination that the present performance metric does not satisfy the target performance metric, the present class of service to a higher class of service in the range. Other embodiments are also described and claimed.

Abstract: Examples may include techniques to live migrate a virtual machine (VM) using disaggregated computing resources including compute and memory resources. Examples include copying data between allocated memory resources that serve as near or far memory for compute resources supporting the VM at a source or destination server in order to initiate and complete the live migration of the VM.

Abstract: Method and apparatus for per-agent control and quality of service of shared resources in a chip multiprocessor platform is described herein. One embodiment of a system includes: a plurality of core and non-core requestors of shared resources, the shared resources to be provided by one or more resource providers, each of the plurality of core and non-core requestors to be associated with a resource-monitoring tag and a resource-control tag; a mapping table to store the resource monitoring and control tags associated with each non-core requestor; and a tagging circuitry to receive a resource request sent from a non-core requestor to a resource provider, the tagging circuitry to responsively modify the resource request to include the resource-monitoring and resource-control tags associated with the non-core requestor in accordance to the mapping table and send the modified resource request to the resource provider.

Abstract: Devices and techniques for out-of-band platform tuning and configuration are described herein. A device can include a telemetry interface to a telemetry collection system and a network interface to network adapter hardware. The device can receive platform telemetry metrics from the telemetry collection system, and network adapter silicon hardware statistics over the network interface, to gather collected statistics. The device can apply a heuristic algorithm using the collected statistics to determine processing core workloads generated by operation of a plurality of software systems communicatively coupled to the device. The device can provide a reconfiguration message to instruct at least one software system to switch operations to a different processing core, responsive to detecting an overload state on at least one processing core, based on the processing core workloads. Other embodiments are also described.

Abstract: Apparatus and methods may provide for subscribing a thread to a resource monitor through a machine specific register and subscribing the thread to a class of service through the machine specific register. The resource monitor or the class of service for the thread may be changed without interrupting the thread. The power allocated to the processor core may be changed based on the selected class of service for the thread.

Abstract: Generally discussed herein are systems, devices, and methods for network security monitoring (NSM). A hardware queue manager (HQM) may include an input interface to receive first data from at least a first worker thread, queue duplication circuitry to generate a copy of at least a portion of the first data to create first copied data, and an output interface to (a) provide the first copied data to a second worker thread, and/or (b) provide at least a portion of the first data to a third worker thread.

Abstract: In one embodiment, the present invention includes a method for receiving an interrupt from an accelerator, sending a resume signal directly to a small core responsive to the interrupt and providing a subset of an execution state of the large core to the first small core, and determining whether the small core can handle a request associated with the interrupt, and performing an operation corresponding to the request in the small core if the determination is in the affirmative, and otherwise providing the large core execution state and the resume signal to the large core. Other embodiments are described and claimed.

Abstract: Systems and methods for cache allocation with code and data prioritization. An example system may comprise: a cache; a processing core, operatively coupled to the cache; and a cache control logic, responsive to receiving a cache fill request comprising an identifier of a request type and an identifier of a class of service, to identify a subset of the cache corresponding to a capacity bit mask associated with the request type and the class of service.

Abstract: There is disclosed in an example, a fabric interface device, having: a fabric interconnect to communicatively couple to a fabric; service level agreement (SLA) input logic to receive an SLA data structure from a controller, the SLA data structure providing an end-to-end SLA for a resource flow provided by a plurality of resources, and comprising QoS metrics for the resources; and SLA output logic to propagate the QoS metrics out to the resources via the fabric interconnect.

Abstract: In one embodiment, the present invention includes a method for receiving an interrupt from an accelerator, sending a resume signal directly to a small core responsive to the interrupt and providing a subset of an execution state of the large core to the first small core, and determining whether the small core can handle a request associated with the interrupt, and performing an operation corresponding to the request in the small core if the determination is in the affirmative, and otherwise providing the large core execution state and the resume signal to the large core. Other embodiments are described and claimed.

Abstract: In accordance with some embodiments, a cloud service provider may operate a data center in a way that dynamically reallocates resources across nodes within the data center based on both utilization and service level agreements. In other words, the allocation of resources may be adjusted dynamically based on current conditions. The current conditions in the data center may be a function of the nature of all the current workloads. Instead of simply managing the workloads in a way to increase overall execution efficiency, the data center instead may manage the workload to achieve quality of service requirements for particular workloads according to service level agreements.

Abstract: Apparatus and methods implementing a hardware predictor for reducing performance inversions caused by intra-core data transfer during inter-core data transfer optimization for network function virtualizations (NFVs) and other producer-consumer workloads. An apparatus embodiment includes a plurality of hardware processor cores each including a first cache, a second cache shared by the plurality of hardware processor cores, and a predictor circuit to track the number of inter-core versus intra-core accesses to a plurality of monitored cache lines in the first cache and control enablement of a cache line demotion instruction, such as a cache line LLC allocation (CLLA) instruction, based upon the tracked accesses. An execution of the cache line demotion instruction by one of the plurality of hardware processor cores causes a plurality of unmonitored cache lines in the first cache to be moved to the second cache, such as from L1 or L2 caches to a shared L3 or last level cache (LLC).