US20230135645A1

US20230135645A1 - Management of workload processing using distributed networked processing units

Info

Publication number: US20230135645A1
Application number: US18/090,764
Authority: US
Inventors: Francesc Guim Bernat; Karthik Kumar; Kshitij Arun Doshi; Marcos E. Carranza
Original assignee: Individual
Current assignee: Intel Corp
Priority date: 2022-11-16
Filing date: 2022-12-29
Publication date: 2023-05-04
Also published as: US20230136612A1; US20230132992A1; US20230137879A1; US20230135938A1; US20230136615A1; US20230136048A1; US20230134683A1; US20230133020A1; US20230140252A1

Abstract

Various approaches for deploying and controlling distributed compute operations with the use of infrastructure processing units (IPUs) and similar networked processing units are disclosed. A system that includes a networked processing unit may perform workload processing with operations that: receive, from another networked processing unit, workload information for a workload, for a workload having respective tasks to be processed among distributed computing entities; perform an analysis of network conditions for a predicted execution of the workload, based on the workload information, to analyze network availability among the distributed computing entities; perform an analysis of compute conditions for the predicted execution of the workload, based on the workload information, to analyze processing availability among the distributed computing entities; and identify locations of the distributed computing entities to deploy the workload, based on the analysis of network conditions and the analysis of compute conditions.

Description

PRIORITY CLAIM

This application claims the benefit of priority to U.S. Provisional Patent Application No. 63/425,857, filed Nov. 16, 2022, and titled “COORDINATION OF DISTRIBUTED NETWORKED PROCESSING UNITS”, which is incorporated herein by reference in its entirety.

TECHNICAL FIELD

Embodiments described herein generally relate to data processing, network communication, and communication system implementations of distributed computing, including the implementations with the use of networked processing units such as infrastructure processing units (IPUs) or data processing units (DPUs).

BACKGROUND

System architectures are moving to highly distributed multi-edge and multi-tenant deployments. Deployments may have different limitations in terms of power and space. Deployments also may use different types of compute, acceleration and storage technologies in order to overcome these power and space limitations. Deployments also are typically interconnected in tiered and/or peer-to-peer fashion, in an attempt to create a network of connected devices and edge appliances that work together.
Edge computing, at a general level, has been described as systems that provide the transition of compute and storage resources closer to endpoint devices at the edge of a network (e.g., consumer computing devices, user equipment, etc.). As compute and storage resources are moved closer to endpoint devices, a variety of advantages have been promised such as reduced application latency, improved service capabilities, improved compliance with security or data privacy requirements, improved backhaul bandwidth, improved energy consumption, and reduced cost. However, many deployments of edge computing technologies—especially complex deployments for use by multiple tenants—have not been fully adopted.

BRIEF DESCRIPTION OF THE DRAWINGS

In the drawings, which are not necessarily drawn to scale, like numerals may describe similar components in different views. Like numerals having different letter suffixes may represent different instances of similar components. Some embodiments are illustrated by way of example, and not limitation, in the figures of the accompanying drawings in which:

FIG. 1 illustrates an overview of a distributed edge computing environment, according to an example;

FIG. 2 depicts computing hardware provided among respective deployment tiers in a distributed edge computing environment, according to an example;

FIG. 3 depicts additional characteristics of respective deployments tiers in a distributed edge computing environment, according to an example;

FIG. 4 depicts a computing system architecture including a compute platform and a network processing platform provided by an infrastructure processing unit, according to an example;

FIG. 5 depicts an infrastructure processing unit arrangement operating as a distributed network processing platform within network and data center edge settings, according to an example;

FIG. 6 depicts functional components of an infrastructure processing unit and related services, according to an example;

FIG. 7 depicts a block diagram of example components in an edge computing system which implements a distributed network processing platform, according to an example;

FIG. 8 depicts an arrangement of distributed processing provided at an edge computing network layer, using a distributed infrastructure processing unit mesh network, according to an example;

FIG. 9 depicts an arrangement of processing use cases for a distributed infrastructure processing unit mesh network, according to an example; and

FIG. 10 depicts a flowchart of an example method of workload processing in an edge computing arrangement, according to an example.

DETAILED DESCRIPTION

One technical challenge encountered in edge computing settings involves the variation in service needs, traffic, and network and processing loads, especially with the deployment of microservices and workloads that may require many resources to be made available very quickly. In a distributed computing environment, this technical challenge raises the related technical problem of where to perform compute and data operations.
With existing approaches, one metric used to decide where to perform workload operations is based on locations of respective compute resources (e.g., how far away, often measured in latency or geographic distance), and when resources are available at the respective compute locations. Other approaches attempt to efficiently distribute workloads and jobs among multiple compute locations, but may encounter network congestion and other interruptions. Likewise, some approaches are primarily based on evaluating service requirements, but may encounter similar issues or inefficiencies.
The following presents a hybrid approach for distributed computing, including with the use of networked processing units for coordinating and distributing workloads. Among other considerations, this approach includes the evaluation of priority requirements and availability, power requirements and availability, and resource requirements and availability. For instance, power may be constrained at a particular compute resources based on the use of battery or solar power. Likewise, there may be a set of compute resources such as compute cores that may be available but are not active. The approaches discussed herein introduce methods performed by networked processing units to perform congestion control and network flow reshaping, including performed by network processing units located among network gateways and base stations, to quickly evaluate and distribute workload requests that arrive at very high speed.
The approaches discussed herein are able to evaluate a distributed computing environment relative to available capabilities to stream or pool resources, while ensuring that requirements are met for multiple types of users. The approaches discussed herein are able to consider real-time usage of core compute services based on relevant conditions (e.g., power or network conditions), including to migrate workloads, instances, and services that are activated. Additionally, the approaches discussed herein enable resources to be turned off or conserved. In a power constrained environment, for example, certain resources may benefit from being powered down as much as possible.
These and other approaches are enabled through specialized congestion control, task deadline/priority analyses, and traffic flow reshaping logic, implemented at networked processing units such as an infrastructure processing unit (IPU). Here, one or more IPUs are enabled to act as a “traffic cop” to identify workload requests and map the requests to the appropriate resources. A particular IPU or set of IPUs can also track the availability of resources in an infrastructure by using of a heat map or other mappings. The IPU can also coordinate various commands, interrupts, and requests to activate compute entities while balancing/minimizing power, and maintaining congestion control. These and other distributed compute coordination operations are discussed in more details in the sections below, after an overview of edge computing and operational environments of IPUs.
FIG. 1 is a block diagram 100 showing an overview of a distributed edge computing environment, which may be adapted for implementing the present techniques for distributed networked processing units. As shown, the edge cloud 110 is established from processing operations among one or more edge locations, such as a satellite vehicle 141, a base station 142, a network access point 143, an on premise server 144, a network gateway 145, or similar networked devices and equipment instances. These processing operations may be coordinated by one or more edge computing platforms 120 or systems that operate networked processing units (e.g., IPUs, DPUs) as discussed herein.
The edge cloud 110 is generally defined as involving compute that is located closer to endpoints 160 (e.g., consumer and producer data sources) than the cloud 130, such as autonomous vehicles 161, user equipment 162, business and industrial equipment 163, video capture devices 164, drones 165, smart cities and building devices 166, sensors and IoT devices 167, etc. Compute, memory, network, and storage resources that are offered at the entities in the edge cloud 110 can provide ultra-low or improved latency response times for services and functions used by the endpoint data sources as well as reduce network backhaul traffic from the edge cloud 110 toward cloud 130 thus improving energy consumption and overall network usages among other benefits.
Compute, memory, and storage are scarce resources, and generally decrease depending on the edge location (e.g., fewer processing resources being available at consumer end point devices than at a base station or a central office data center). As a general design principle, edge computing attempts to minimize the number of resources needed for network services, through the distribution of more resources that are located closer both geographically and in terms of in-network access time.
FIG. 2 depicts examples of computing hardware provided among respective deployment tiers in a distributed edge computing environment. Here, one tier at an on-premise edge system is an intelligent sensor or gateway tier 210, which operates network devices with low power and entry-level processors and low-power accelerators. Another tier at an on-premise edge system is an intelligent edge tier 220, which operates edge nodes with higher power limitations and may include a high-performance storage.
Further in the network, a network edge tier 230 operates servers including form factors optimized for extreme conditions (e.g., outdoors). A data center edge tier 240 operates additional types of edge nodes such as servers, and includes increasingly powerful or capable hardware and storage technologies. Still further in the network, a core data center tier 250 and a public cloud tier 260 operate compute equipment with the highest power consumption and largest configuration of processors, acceleration, storage/memory devices, and highest throughput network. In the examples of managed workload processing using distributed IPUs, discussed herein, network monitoring and resource allocation for the distributed IPU serve an important role to manage resources among these different tiers.
In each of these tiers, various forms of Intel® processor lines are depicted for purposes of illustration; it will be understood that other brands and manufacturers of hardware will be used in real-world deployments. Additionally, it will be understood that additional features or functions may exist among multiple tiers. One such example is connectivity and infrastructure management that enable a distributed IPU architecture, that can potentially extend across all of tiers 210, 220, 230, 240, 250, 260. Other relevant functions that may extend across multiple tiers may relate to security features, domain or group functions, and the like.
FIG. 3 depicts additional characteristics of respective deployment tiers in a distributed edge computing environment, based on the tiers discussed with reference to FIG. 2 . This figure depicts additional network latencies at each of the tiers 210, 220, 230, 240, 250, 260, and the gradual increase in latency in the network as the compute is located at a longer distance from the edge endpoints. Additionally, this figure depicts additional power and form factor constraints, use cases, and key performance indicators (KPIs).
With these variations and service features in mind, edge computing within the edge cloud 110 may provide the ability to serve and respond to multiple applications of the use cases in real-time or near real-time and meet ultra-low latency requirements. As systems have become highly-distributed, networking has become one of the fundamental pieces of the architecture that allow achieving scale with resiliency, security, and reliability. Networking technologies have evolved to provide more capabilities beyond pure network routing capabilities, including to coordinate quality of service, security, multi-tenancy, and the like. This has also been accelerated by the development of new smart network adapter cards and other type of network derivatives that incorporated capabilities such as ASICs (application-specific integrated circuits) or FPGAs (field programmable gate arrays) to accelerate some of those functionalities (e.g., remote attestation).
In these contexts, networked processing units have begun to be deployed at network cards (e.g., smart NICs), gateways, and the like, which allow direct processing of network workloads and operations. One example of a networked processing unit is an infrastructure processing unit (IPU), which is a programmable network device that can be extended to provide compute capabilities with far richer functionalities beyond pure networking functions. Another example of a network processing unit is a data processing unit (DPU), which offers programmable hardware for performing infrastructure and network processing operations. The following discussion refers to functionality applicable to an IPU configuration, such as that provided by an Intel® line of IPU processors. However, it will be understood that functionality will be equally applicable to DPUs and other types of networked processing units provided by ARM®, Nvidia®, and other hardware OEMs.
FIG. 4 depicts an example compute system architecture that includes a compute platform 420 and a network processing platform comprising an IPU 410. This architecture—and in particular the IPU 410—can be managed, coordinated, and orchestrated by the functionality discussed below, including with the functions described with reference to FIG. 6 .
The main compute platform 420 is composed by typical elements that are included with a computing node, such as one or more CPUs 424 that may or may not be connected via a coherent domain (e.g., via Ultra Path Interconnect (UPI) or another processor interconnect); one or more memory units 425; one or more additional discrete devices 426 such as storage devices, discrete acceleration cards (e.g., a field-programmable gate array (FPGA), a visual processing unit (VPU), etc.); a baseboard management controller 421; and the like. The compute platform 420 may operate one or more containers 422 (e.g., with one or more microservices), within a container runtime 423 (e.g., Docker containerd). The IPU 410 operates as a networking interface and is connected to the compute platform 420 using an interconnect (e.g., using either PCIe or CXL). The IPU 410, in this context, can be observed as another small compute device that has its own: (1) Processing cores (e.g., provided by low-power cores 417), (2) operating system (OS) and cloud native platform 414 to operate one or more containers 415 and a container runtime 416; (3) Acceleration functions provided by an ASIC 411 or FPGA 412; (4) Memory 418; (5) Network functions provided by network circuitry 413; etc.
From a system design perspective, this arrangement provides important functionality. The IPU 410 is seen as a discrete device from the local host (e.g., the OS running in the compute platform CPUs 424) that is available to provide certain functionalities (networking, acceleration etc.). Those functionalities are typically provided via Physical or Virtual PCIe functions. Additionally, the IPU 410 is seen as a host (with its own IP etc.) that can be accessed by the infrastructure to setup an OS, run services, and the like. The IPU 410 sees all the traffic going to the compute platform 420 and can perform actions—such as intercepting the data or performing some transformation—as long as the correct security credentials are hosted to decrypt the traffic. Traffic going through the IPU goes to all the layers of the Open Systems Interconnection model (OSI model) stack (e.g., from physical to application layer). Depending on the features that the IPU has, processing may be performed at the transport layer only. However, if the IPU has capabilities to perform traffic intercept, then the IPU also may be able to intercept traffic at the traffic layer (e.g., intercept CDN traffic and process it locally).
Some of the use cases being proposed for IPUs and similar networked processing units include: to accelerate network processing; to manage hosts (e.g., in a data center); or to implement quality of service policies. However, most of functionalities today are focused at using the IPU at the local appliance level and within a single system. These approaches do not address how the IPUs could work together in a distributed fashion or how system functionalities can be divided among the IPUs on other parts of the system. Accordingly, the following introduces enhanced approaches for enabling and controlling distributed functionality among multiple networked processing units. This enables the extension of current IPU functionalities to work as a distributed set of IPUs that can work together to achieve stronger features such as, resiliency, reliability, etc.
Distributed Architectures of IPUs
FIG. 5 depicts an IPU arrangement operating as a distributed network processing platform within network and data center edge settings. In a first deployment model of a computing environment 510, workloads or processing requests are directly provided to an IPU platform, such as directly to IPU 514. In a second deployment model of the computing environment 510, workloads or processing requests are provided to some intermediate processing device 512, such as a gateway or NUC (next unit of computing) device form factor, and the intermediate processing device 512 forwards the workloads or processing requests to the IPU 514. It will be understood that a variety of other deployment models involving the composability and coordination of one or more IPUs, compute units, network devices, and other hardware may be provided.
With the first deployment model, the IPU 514 directly receives data from use cases 502A. The IPU 514 operates one or more containers with microservices to perform processing of the data. As an example, a small gateway (e.g., a NUC type of appliance) may connect multiple cameras to an edge system that is managed or connected by the IPU 514. The IPU 514 may process data as a small aggregator of sensors that runs on the far edge, or may perform some level of inline or preprocessing and that sends payload to be further processed by the IPU or the system that the IPU connects.
With the second deployment model, the intermediate processing device 512 provided by the gateway or NUC receives data from use cases 502B. The intermediate processing device 512 includes various processing elements (e.g., CPU cores, GPUs), and may operate one or more microservices for servicing workloads from the use cases 502B. However, the intermediate processing device 512 invokes the IPU 514 to complete processing of the data.
In either the first or the second deployment model, the IPU 514 may connect with a local compute platform, such as that provided by a CPU 516 (e.g., Intel® Xeon CPU) operating multiple microservices. The IPU may also connect with a remote compute platform, such as that provided at a data center by CPU 540 at a remote server. As an example, consider a microservice that performs some analytical processing (e.g., face detection on image data), where the CPU 516 and the CPU 540 provide access to this same microservice. The IPU 514, depending on the current load of the CPU 516 and the CPU 540, may decide to forward the images or payload to one of the two CPUs. Data forwarding or processing can also depend on other factors such as SLA for latency or performance metrics (e.g., perf/watt) in the two systems. As a result, the distributed IPU architecture may accomplish features of load balancing.
The IPU in the computing environment 510 may be coordinated with other network-connected IPUs. In an example, a Service and Infrastructure orchestration manager 530 may use multiple IPUs as a mechanism to implement advanced service processing schemes for the user stacks. This may also enable implementing of system functionalities such as failover, load balancing etc.
In a distributed architecture example, IPUs can be arranged in the following non-limiting configurations. As a first configuration, a particular IPU (e.g., IPU 514) can work with other IPUs (e.g., IPU 520) to implement failover mechanisms. For example, an IPU can be configured to forward traffic to service replicas that runs on other systems when a local host does not respond.
As a second configuration, a particular IPU (e.g., IPU 514) can work with other IPUs (e.g., IPU 520) to perform load balancing across other systems. For example, consider a scenario where CDN traffic targeted to the local host is forwarded to another host in case that I/O or compute in the local host is scarce at a given moment.
As a third configuration, a particular IPU (e.g., IPU 514) can work as a power management entity to implement advanced system policies. For example, consider a scenario where the whole system (e.g., including CPU 516) is placed in a C6 state (a low-power/power-down state available to a processor) while forwarding traffic to other systems (e.g., IPU 520) and consolidating it.
As will be understood, fully coordinating a distributed IPU architecture requires numerous aspects of coordination and orchestration. The following examples of system architecture deployments provide discussion of how edge computing systems may be adapted to include coordinated IPUs, and how such deployments can be orchestrated to use IPUs at multiple locations to expand to the new envisioned functionality.
Distributed IPU Functionality
An arrangement of distributed IPUs offers a set of new functionalities to enable IPUs to be service focused. FIG. 6 depicts functional components of an IPU 610, including services and features to implement the distributed functionality discussed herein. It will be understood that some or all of the functional components provided in FIG. 6 may be distributed among multiple IPUs, hardware components, or platforms, depending on the particular configuration and use case involved.
In the block diagram of FIG. 6 , a number of functional components are operated to manage requests for a service running in the IPU (or running in the local host). As discussed above, IPUs can either run services or intercept requests arriving to services running in the local host and perform some action. In the latter case, the IPU can perform the following types of actions/functions (provided as a non-limiting examples).
Peer Discovery. In an example, each IPU is provided with Peer Discovery logic to discover other IPUs in the distributed system that can work together with it. Peer Discovery logic may use mechanisms such as broadcasting to discover other IPUs that are available on a network. The Peer Discovery logic is also responsible to work with the Peer Attestation and Authentication logic to validate and authenticate the peer IPU's identity, determine whether they are trustworthy, and whether the current system tenant allows the current IPU to work with them. To accomplish this, an IPU may perform operations such as: retrieve a proof of identity and proof of attestation; connect to a trusted service running in a trusted server; or, validate that the discovered system is trustworthy. Various technologies (including hardware components or standardized software implementations) that enable attestation, authentication, and security may be used with such operations.
Peer Attestation. In an example, each IPU provides interfaces to other IPUs to enable attestation of the IPU itself. IPU Attestation logic is used to perform an attestation flow within a local IPU in order to create the proof of identity that will be shared with other IPUs. Attestation here may integrate previous approaches and technologies to attest a compute platform. This may also involve the use of trusted attestation service 640 to perform the attestation operations.
Functionality Discovery. In an example, a particular IPU includes capabilities to discover the functionalities that peer IPUs provide. Once the authentication is done, the IPU can determine what functionalities that the peer IPUs provide (using the IPU Peer Discovery Logic) and store a record of such functionality locally. Examples of properties to discover can include: (i) Type of IPU and functionalities provided and associated KPIs (e.g. performance/watt, cost etc.); (ii) Available functionalities as well as possible functionalities to execute under secure enclaves (e.g., enclaves provided by Intel® SGX or TDX technologies); (iii) Current services that are running on the IPU and on the system that can potentially accept requests forwarded from this IPU; or (iv) Other interfaces or hooks that are provided by an IPU, such as: Access to remote storage; Access to a remote VPU; Access to certain functions. In a specific example, service may be described by properties such as: UUID; Estimated performance KPIs in the host or IPU; Average performance provided by the system during the N units of time (or any other type of indicator); and like properties.
Service Management. The IPU includes functionality to manage services that are running either on the host compute platform or in the IPU itself. Managing (orchestration) services includes performance service and resource orchestration for the services that can run on the IPU or that the IPU can affect. Two type of usage models are envisioned:
External Orchestration Coordination. The IPU may enable external orchestrators to deploy services on the IPU compute capabilities. To do so, an IPU includes a component similar to K8 compatible APIs to manage the containers (services) that run on the IPU itself. For example, the IPU may run a service that is just providing content to storage connected to the platform. In this case, the orchestration entity running in the IPU may manage the services running in the IPU as it happens in other systems (e.g. keeping the service level objectives).
Further, external orchestrators can be allowed to register to the IPU that services are running on the host may require to broker requests, implement failover mechanisms and other functionalities. For example, an external orchestrator may register that a particular service running on the local compute platform is replicated in another edge node managed by another IPU where requests can be forwarded.
In this later use case external orchestrators may provide to the Service/Application Intercept logic the inputs that are needed to intercept traffic for these services (as typically is encrypted). This may include properties such as a source and destination traffic of the traffic to be intercepted, or the key to use to decrypt the traffic. Likewise, this may be needed to terminate TLS to understand the requests that arrive to the IPU and that the other logics may need to parse to take actions. For example, if there is a CDN read request the IPU may need to decrypt the packet to understand that network packet includes a read request and may redirect it to another host based on the content that is being intercepted. Examples of Service/Application Intercept information is depicted in table 620 in FIG. 6 .
External Orchestration Implementation. External orchestration can be implemented in multiple topologies. One supported topology includes having the orchestrator managing all the IPUs running on the backend public or private cloud. Another supported topology includes having the orchestrator managing all the IPUs running in a centralized edge appliance. Still another supported topology includes having the orchestrator running in another IPU that is working as the controller or having the orchestrator running distributed in multiple other IPUs that are working as controllers (master/primary node), or in a hierarchical arrangement.
Functionality for Broker requests. The IPU may include Service Request Brokering logic and Load Balancing logic to perform brokering actions on arrival for requests of target services running in the local system. For instance, the IPU may decide to see if those requests can be executed by other peer systems (e.g., accessible through Service and Infrastructure Orchestration 630). This can be caused, for example, because load in the local systems is high. The local IPU may negotiate with other peer IPUs for the possibility to forward the request. Negotiation may involve metrics such as cost. Based on such negotiation metrics, the IPU may decide to forward the request.
Functionality for Load Balancing requests. The Service Request Brokering and Load Balancing logic may distribute requests arriving to the local IPU to other peer IPUs. In this case, the other IPUs and the local IPU work together and do not necessarily need brokering. Such logic acts similar to a cloud native sidecar proxy. For instance, requests arriving to the system may be sent to the service X running in the local system (either IPU or compute platform) or forwarded to a peer IPU that has another instance of service X running. The load balancing distribution can be based on existing algorithms such as based on the systems that have lower load, using round robin, etc.
Functionality for failover, resiliency and reliability. The IPU includes Reliability and Failover logic to monitor the status of the services running on the compute platform or the status of the compute platform itself. The Reliability and Failover logic may require the Load Balancing logic to transiently or permanently forward requests that aim specific services in situations such as where: i) The compute platform is not responding; ii) The service running inside the compute node is not responding; and iii) The compute platform load prevents the targeted service to provide the right level of service level objectives (SLOs). Note that the logic must know the required SLOs for the services. Such functionality may be coordinated with service information 650 including SLO information.
Functionality for executing parts of the workloads. Use cases such as video analytics tend to be decomposed in different microservices that conform a pipeline of actions that can be used together. The IPU may include a workload pipeline execution logic that understands how workloads are composed and manage their execution. Workloads can be defined as a graph that connects different microservices. The load balancing and brokering logic may be able to understand those graphs and decide what parts of the pipeline are executed where. Further, to perform these and other operations, Intercept logic will also decode what requests are included as part of the requests.
As will be understood, the previously discussed functionality (e.g., for Broker requests, for Load Balancing requests, for failover, resiliency and reliability, and for executing parts of the workloads) are particularly relevant for use by the present techniques for managing workload processing using distributed IPUs.
Resource Management
A distributed network processing configuration may enable IPUs to perform important role for managing resources of edge appliances. As further shown in FIG. 6 , the functional components of an IPU can operate to perform these and similar types of resource management functionalities.
As a first example, an IPU can provide management or access to external resources that are hosted in other locations and expose them as local resources using constructs such as Compute Express Link (CXL). For example, the IPU could potentially provide access to a remote accelerator that is hosted in a remote system via CXL.mem/cache and IO. Another example includes providing access to remote storage device hosted in another system. In this later case the local IPU could work with another IPU in the storage system and expose the remote system as PCIE VF/PF (virtual functions/physical functions) to the local host.
As a second example, an IPU can provide access to IPU-specific resources. Those IPU resource may be physical (such as storage or memory) or virtual (such as a service that provides access to random number generation).
As a third example, an IPU can manage local resources that are hosted in the system where it belongs. For example, the IPU can manage power of the local compute platform.
As a fourth example, an IPU can provide access to other type of elements that relate to resources (such as telemetry or other types of data). In particular, telemetry provides useful data for something that is needed to decide where to execute things or to identify problems.
I/O Management. Because the IPU is acting as a connection proxy between the external peers (compute systems, remote storage etc.) resources and the local compute, the IPU can also include functionality to manage I/O from the system perspective.
Host Virtualization and XPU Pooling. The IPU includes Host Virtualization and XPU Pooling logic responsible to manage the access to resources that are outside the system domain (or within the IPU) and that can be offered to the local compute system. Here, “XPU” refers to any type of a processing unit, whether CPU, GPU, VPU, an acceleration processing unit, etc. The IPU logic, after discovery and attestation, can agree with other systems to share external resources with the services running in the local system. IPUs may advertise to other peers available resources or can be discovered during discovery phase as introduced earlier. IPUs may request to other IPUS to those resources. For example, an IPU on system A may request access to storage on system B manage by another IPU. Remote and local IPUs can work together to establish a connection between the target resources and the local system.
Once the connection and resource mapping is completed, resources can be exposed to the services running in the local compute node using the VF/PF PCIE and CXL Logic. Each of those resources can be offered as VF/PF. The IPU logic can expose to the local host resources that are hosted in the IPU. Examples of resources to expose may include local accelerators, access to services, and the like.
Power Management. Power management is one of the key features to achieve favorable system operational expenditures (OPEXs). IPU is very well positioned to optimize power consumption that the local system is consuming. The Distributed and local power management unit: Is responsible to meter the power that the system is consuming, the load that the system is receiving and track the service level agreements that the various services running in the system are achieving for the arriving requests. Likewise, when power efficiencies (e.g., power usage effectiveness (PUE)) are not achieving certain thresholds or the local compute demand is low, the IPU may decide to forward the requests to local services to other IPUs that host replicas of the services. Such power management features may also coordinate with the Brokering and Load Balancing logic discussed above. As will be understood, IPUs can work together to decide where requests can be consolidated to establish higher power efficiency as system. When traffic is redirected, the local power consumption can be reduced in different ways. Example operations that can be performed include: changing the system to C6 State; changing the base frequencies; performing other adaptations of the system or system components.
Telemetry Metrics. The IPU can generate multiple types of metrics that can be interesting from services, orchestration or tenants owning the system. In various examples, telemetry can be accessed, including: (i) Out of band via side interfaces; (ii) In band by services running in the IPU; or (iii) Out of band using PCIE or CXL from the host perspective. Relevant types of telemetries can include: Platform telemetry; Service Telemetry; IPU telemetry; Traffic telemetry; and the like.
System Configurations for Distributed Processing
Further to the examples noted above, the following configurations may be used for processing with distributed IPUs:
1) Local IPUs connected to a compute platform by an interconnect (e.g., as shown in the configuration of FIG. 4 );
2) Shared IPUs hosted within a rack/physical network—such as in a virtual slice or multi-tenant implementation of IPUs connected via CXL/PCI-E (local), or extension via Ethernet/Fiber for nodes within a cluster;
3) Remote IPUs accessed via an IP Network, such as within certain latency for data plane offload/storage offloads (or, connected for management/control plane operations); or
4) Distributed IPUs providing an interconnected network of IPUs, including as many as hundreds of nodes within a domain.
Configurations of distributed IPUs working together may also include fragmented distributed IPUs, where each IPU or pooled system provides part of the functionalities, and each IPU becomes a malleable system. Configurations of distributed IPUs may also include virtualized IPUs, such as provided by a gateway, switch, or an inline component (e.g., inline between the service acting as IPU), and in some examples, in scenarios where the system has no IPU.
Other deployment models for IPUs may include IPU-to-IPU in the same tier or a close tier; IPU-to-IPU in the cloud (data to compute versus compute to data); integration in small device form factors (e.g., gateway IPUs); gateway/NUC+IPU which connects to a data center; multiple GW/NUC (e.g. 16) which connect to one IPU (e.g. switch); gateway/NUC+IPU on the server; and GW/NUC and IPU that are connected to a server with an IPU.
The preceding distributed IPU functionality may be implemented among a variety of types of computing architectures, including one or more gateway nodes, one or more aggregation nodes, or edge or core data centers distributed across layers of the network (e.g., in the arrangements depicted in FIGS. 2 and 3 ). Accordingly, such IPU arrangements may be implemented in an edge computing system by or on behalf of a telecommunication service provider (“telco”, or “TSP”), internet-of-things service provider, cloud service provider (CSP), enterprise entity, or any other number of entities. Various implementations and configurations of the edge computing system may be provided dynamically, such as when orchestrated to meet service objectives. Such edge computing systems may be embodied as a type of device, appliance, computer, or other “thing” capable of communicating with other edge, networking, or endpoint components.
FIG. 7 depicts a block diagram of example components in a computing device 750 which can operate as a distributed network processing platform. The computing device 750 may include any combinations of the components referenced above, implemented as integrated circuits (ICs), as a package or system-on-chip (SoC), or as portions thereof, discrete electronic devices, or other modules, logic, instruction sets, programmable logic or algorithms, hardware, hardware accelerators, software, firmware, or a combination thereof adapted in the computing device 750, or as components otherwise incorporated within a larger system. Specifically, the computing device 750 may include processing circuitry comprising one or both of a network processing unit 752 (e.g., an IPU or DPU, as discussed above) and a compute processing unit 754 (e.g., a CPU).
The network processing unit 752 may provide a networked specialized processing unit such as an IPU, DPU, network processing unit (NPU), or other “xPU” outside of the central processing unit (CPU). The processing unit may be embodied as a standalone circuit or circuit package, integrated within an SoC, integrated with networking circuitry (e.g., in a SmartNIC), or integrated with acceleration circuitry, storage devices, or AI or specialized hardware, consistent with the examples above.
The compute processing unit 754 may provide a processor as a central processing unit (CPU) microprocessor, multi-core processor, multithreaded processor, an ultra-low voltage processor, an embedded processor, or other forms of a special purpose processing unit or specialized processing unit for compute operations.
Either the network processing unit 752 or the compute processing unit 754 may be a part of a system on a chip (SoC) which includes components formed into a single integrated circuit or a single package. The network processing unit 752 or the compute processing unit 754 and accompanying circuitry may be provided in a single socket form factor, multiple socket form factor, or a variety of other formats.
The processing units 752, 754 may communicate with a system memory 756 (e.g., random access memory (RAM)) over an interconnect 755 (e.g., a bus). In an example, the system memory 756 may be embodied as volatile (e.g., dynamic random access memory (DRAM), etc.) memory. Any number of memory devices may be used to provide for a given amount of system memory. A storage 758 may also couple to the processor 752 via the interconnect 755 to provide for persistent storage of information such as data, applications, operating systems, and so forth. In an example, the storage 758 may be implemented as non-volatile storage such as a solid-state disk drive (SSD).
The components may communicate over the interconnect 755. The interconnect 755 may include any number of technologies, including industry-standard architecture (ISA), extended ISA (EISA), peripheral component interconnect (PCI), peripheral component interconnect extended (PCIx), PCI express (PCIe), Compute Express Link (CXL), or any number of other technologies. The interconnect 755 may couple the processing units 752, 754 to a transceiver 766, for communications with connected edge devices 762.
The transceiver 766 may use any number of frequencies and protocols. For example, a wireless local area network (WLAN) unit may implement Wi-Fi® communications in accordance with the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, or a wireless wide area network (WWAN) unit may implement wireless wide area communications according to a cellular, mobile network, or other wireless wide area protocol. The wireless network transceiver 766 (or multiple transceivers) may communicate using multiple standards or radios for communications at a different range. A wireless network transceiver 766 (e.g., a radio transceiver) may be included to communicate with devices or services in the edge cloud 110 or the cloud 130 via local or wide area network protocols.
The communication circuitry (e.g., transceiver 766, network interface 768, external interface 770, etc.) may be configured to use any one or more communication technology (e.g., wired or wireless communications) and associated protocols (e.g., a cellular networking protocol such a 3GPP 4G or 5G standard, a wireless local area network protocol such as IEEE 802.11/Wi-Fi®, a wireless wide area network protocol, Ethernet, Bluetooth®, Bluetooth Low Energy, an IoT protocol such as IEEE 802.15.4 or ZigBee®, Matter®, low-power wide-area network (LPWAN) or low-power wide-area (LPWA) protocols, etc.) to effect such communication. Given the variety of types of applicable communications from the device to another component or network, applicable communications circuitry used by the device may include or be embodied by any one or more of components 766, 768, or 770. Accordingly, in various examples, applicable means for communicating (e.g., receiving, transmitting, etc.) may be embodied by such communications circuitry.
The computing device 750 may include or be coupled to acceleration circuitry 764, which may be embodied by one or more AI accelerators, a neural compute stick, neuromorphic hardware, an FPGA, an arrangement of GPUs, one or more SoCs, one or more CPUs, one or more digital signal processors, dedicated ASICs, or other forms of specialized processors or circuitry designed to accomplish one or more specialized tasks. These tasks may include AI processing (including machine learning, training, inferencing, and classification operations), visual data processing, network data processing, object detection, rule analysis, or the like. Accordingly, in various examples, applicable means for acceleration may be embodied by such acceleration circuitry.
The interconnect 755 may couple the processing units 752, 754 to a sensor hub or external interface 770 that is used to connect additional devices or subsystems. The devices may include sensors 772, such as accelerometers, level sensors, flow sensors, optical light sensors, camera sensors, temperature sensors, global navigation system (e.g., GPS) sensors, pressure sensors, pressure sensors, and the like. The hub or interface 770 further may be used to connect the edge computing node 750 to actuators 774, such as power switches, valve actuators, an audible sound generator, a visual warning device, and the like.
In some optional examples, various input/output (I/O) devices may be present within or connected to, the edge computing node 750. For example, a display or other output device 784 may be included to show information, such as sensor readings or actuator position. An input device 786, such as a touch screen or keypad may be included to accept input. An output device 784 may include any number of forms of audio or visual display, including simple visual outputs such as LEDs or more complex outputs such as display screens (e.g., LCD screens), with the output of characters, graphics, multimedia objects, and the like being generated or produced from the operation of the edge computing node 750.
A battery 776 may power the edge computing node 750, although, in examples in which the edge computing node 750 is mounted in a fixed location, it may have a power supply coupled to an electrical grid, or the battery may be used as a backup or for temporary capabilities. A battery monitor/charger 778 may be included in the edge computing node 750 to track the state of charge (SoCh) of the battery 776. The battery monitor/charger 778 may be used to monitor other parameters of the battery 776 to provide failure predictions, such as the state of health (SoH) and the state of function (SoF) of the battery 776. A power block 780, or other power supply coupled to a grid, may be coupled with the battery monitor/charger 778 to charge the battery 776.
In an example, the instructions 782 on the processing units 752, 754 (separately, or in combination with the instructions 782 of the machine-readable medium 760) may configure execution or operation of a trusted execution environment (TEE) 790. In an example, the TEE 790 operates as a protected area accessible to the processing units 752, 754 for secure execution of instructions and secure access to data. Other aspects of security hardening, hardware roots-of-trust, and trusted or protected operations may be implemented in the edge computing node 750 through the TEE 790 and the processing units 752, 754.
The computing device 750 may be a server, appliance computing devices, and/or any other type of computing device with the various form factors discussed above. For example, the computing device 750 may be provided by an appliance computing device that is a self-contained electronic device including a housing, a chassis, a case, or a shell.
In an example, the instructions 782 provided via the memory 756, the storage 758, or the processing units 752, 754 may be embodied as a non-transitory, machine-readable medium 760 including code to direct the processor 752 to perform electronic operations in the edge computing node 750. The processing units 752, 754 may access the non-transitory, machine-readable medium 760 over the interconnect 755. For instance, the non-transitory, machine-readable medium 760 may be embodied by devices described for the storage 758 or may include specific storage units such as optical disks, flash drives, or any number of other hardware devices. The non-transitory, machine-readable medium 760 may include instructions to direct the processing units 752, 754 to perform a specific sequence or flow of actions, for example, as described with respect to the flowchart(s) and block diagram(s) of operations and functionality discussed herein. As used herein, the terms “machine-readable medium”, “machine-readable storage”, “computer-readable storage”, and “computer-readable medium” are interchangeable.
In further examples, a machine-readable medium also includes any tangible medium that is capable of storing, encoding, or carrying instructions for execution by a machine and that cause the machine to perform any one or more of the methodologies of the present disclosure or that is capable of storing, encoding or carrying data structures utilized by or associated with such instructions. A “machine-readable medium” thus may include but is not limited to, solid-state memories, and optical and magnetic media. The instructions embodied by a machine-readable medium may further be transmitted or received over a communications network using a transmission medium via a network interface device utilizing any one of a number of transfer protocols (e.g., HTTP).
A machine-readable medium may be provided by a storage device or other apparatus which is capable of hosting data in a non-transitory format. In an example, information stored or otherwise provided on a machine-readable medium may be representative of instructions, such as instructions themselves or a format from which the instructions may be derived. This format from which the instructions may be derived may include source code, encoded instructions (e.g., in compressed or encrypted form), packaged instructions (e.g., split into multiple packages), or the like. The information representative of the instructions in the machine-readable medium may be processed by processing circuitry into the instructions to implement any of the operations discussed herein. For example, deriving the instructions from the information (e.g., processing by the processing circuitry) may include: compiling (e.g., from source code, object code, etc.), interpreting, loading, organizing (e.g., dynamically or statically linking), encoding, decoding, encrypting, unencrypting, packaging, unpackaging, or otherwise manipulating the information into the instructions.
In an example, the derivation of the instructions may include assembly, compilation, or interpretation of the information (e.g., by the processing circuitry) to create the instructions from some intermediate or preprocessed format provided by the machine-readable medium. The information, when provided in multiple parts, may be combined, unpacked, and modified to create the instructions. For example, the information may be in multiple compressed source code packages (or object code, or binary executable code, etc.) on one or several remote servers.
In further examples, a software distribution platform (e.g., one or more servers and one or more storage devices) may be used to distribute software, such as the example instructions discussed above, to one or more devices, such as example processor platform(s) and/or example connected edge devices noted above. The example software distribution platform may be implemented by any computer server, data facility, cloud service, etc., capable of storing and transmitting software to other computing devices. In some examples, the providing entity is a developer, a seller, and/or a licensor of software, and the receiving entity may be consumers, users, retailers, OEMs, etc., that purchase and/or license the software for use and/or re-sale and/or sub-licensing.
In some examples, the instructions are stored on storage devices of the software distribution platform in a particular format. A format of computer readable instructions includes, but is not limited to a particular code language (e.g., Java, JavaScript, Python, C, C#, SQL, HTML, etc.), and/or a particular code state (e.g., uncompiled code (e.g., ASCII), interpreted code, linked code, executable code (e.g., a binary), etc.). In some examples, the computer readable instructions stored in the software distribution platform are in a first format when transmitted to an example processor platform(s). In some examples, the first format is an executable binary in which particular types of the processor platform(s) can execute. However, in some examples, the first format is uncompiled code that requires one or more preparation tasks to transform the first format to a second format to enable execution on the example processor platform(s). For instance, the receiving processor platform(s) may need to compile the computer readable instructions in the first format to generate executable code in a second format that is capable of being executed on the processor platform(s). In still other examples, the first format is interpreted code that, upon reaching the processor platform(s), is interpreted by an interpreter to facilitate execution of instructions.
Management of Application States with Distributed Network Processing Units
Edge services typically have different requirements based on the time of day. For instance, during vehicle traffic rush hours, safety and security video analytics are more relevant and will require lower latency to perform compute operations. Similarly, throughout any given day, an edge service will encounter fluctuations of more or less workloads and service density. Variation in service needs, traffic, and load is common for a variety of types of edge computing services and workloads.
One of the typical challenges that edge computing will encounter is how to decide (or forecast) where edge services will be—or should be—executed. Some of the metrics that are often used to decide a location of execution are based on some combination of: (1) latency (or geographic distance) between the device and a possible location of execution; (2) compute resources available or forecasted at the location of execution; (3) network congestion at the location of execution; and (4) the service requirements (e.g., an SLO) that are defined for the service.
Additionally, there are varying priorities for services that depend on context including location, time of day, or historical context. For example, it may be possible to forecast events based on historic data having a higher priority at certain geographic locations. For example, consider a scenario of processing data at a street corner in smart cities at nighttime (from 10 pm to 5 am). In this scenario, a street corner in the city may be a more dangerous area for vehicle collisions, and it is more likely that vehicle accidents will occur at this particular location. Based on forecasted usage, some services may be identified as critical in these and other particular areas.
A further complication is that edge computing often operates in a resource constrained environment. It may be necessary to conserve power at resources that provide edge computing services (e.g., solar and battery-powered roadside units), while at the same time, there are real-time requirements and deadlines for services which use such resources.
Existing approaches in data centers and edge computing locations have not fully addressed these issues. For instance, priority-based flow control schemes in data center network (DCN) architectures have not been very effective due to a high propensity for head-of-line blocking, unfairness, and even deadlocks. Likewise, there are no fully effective mechanisms for edge architectures to evaluate all—or even a large number—of processing considerations. As a result, existing systems are unable to determine how traffic requests can be shaped and mapped onto diverse hardware capabilities, from cores, to accelerators like Intel® data streaming accelerator (DSA) units, to memory resources.
Thus, an overall technical problem in the edge is that there may be a set of resources that may or may not be available, with compute cores that may or may not be active, with connectivity provided at different rates and at different locations, and with requests being infrequent yet often coming in at high speeds. These and other limitations can be addressed with the use of a distributed IPU architecture, and the following configurations.
FIG. 8 depicts an example arrangement of distributed processing provided at an edge computing network layer, using a distributed infrastructure processing unit mesh network. Specifically, FIG. 8 depicts a computing operations coordinated among a user layer 810, an edge layer 820, and a cloud layer 830. Consistent with the examples discussed above (e.g., with reference to FIGS. 1 to 3 ), edge computing operations may be performed at the edge layer 820 based on requests from client devices or consumers at the user layer 810, such as from one or more heterogenous networks 812, a vehicular network 814, a machine-to-machine (M2M) or device-to-device (D2D) network (not shown), or other network arrangements. The edge layer 820 may further invoke a cloud layer 830 and cloud services 832 to perform further data processing or data retrieval (e.g., at one or more remote data centers or offices).
A variety of disaggregated resources available in the edge layer 820 may be combined, pooled, or coordinated in order to perform tasks for clients and other consumers. For instance, resources at a first base station 822A, including compute resources 842A, may be coordinated with the compute resources 842B at a second base station 822B. Other types of resources, not shown, may include communication resources, storage and caching resources, and the like, provided among a variety of devices or nodes. The resources may be arranged into compute pools, memory pools, or storage pools, coordinated via various interconnects and network protocols.
The use of a distributed IPU mesh network 840 enables a variety of coordinated and distributed workload processing operations. For instance, a first IPU (e.g., IPU 844A) at a first node or system (e.g., base station 822A) may invoke additional compute resources at a second node or system (e.g., compute resources 842B at base station 822) based on communications to a second IPU (e.g., IPU 844B). Thus, workloads, workload tasks, processing operations, and other related concepts may be distributed across the IPU mesh network 840 based on the performance characteristics and coordination properties discussed herein.
A variety of use cases exist for the distributed IPU mesh 840 and other IPUs involved in the edge layer 820. IPUs may operate together to create as many streams as possible and pool resources, to meet real-time high-demand requirements. Multiple IPUs can factor in real time usage, and operate various aspects of core services and congestion control. For instance, concerning core services, logic implemented among multiple IPUs can migrate workloads or resources, and selectively deploy or control instances to be activated or not activated (e.g., due to power aspects). For example, in a power constrained environment, certain power-sensitive resources can be turned off as much as possible to offload to power-available locations. Thus, IPUs in the mesh network 840, acting together, can act as an organized overall entity to obtain and process requests and map the correct requests to the appropriate resources.
In the following, the IPUs in a meshed distributed network are arranged to perform multiple functions with distributed intelligence and logic. In some nodes, the IPUs act with the use of scheduling intelligence. In other nodes, the IPUs act with the use of processing intelligence. In both cases, the IPUs may consider network and processing telemetry, gathered data, work queues, and available conditions, and each type of actor can provide information on the current view from one IPU to another. In addition to ensuring that processing can successfully occur, this information can also be used to prevent network congestion deadlock.
The IPUs may aggregate overall network information to identify an appropriate mapping of resources. Even if one node is short on resources, a particular IPU may use the network information to identify which of the other nodes are fully occupied, which of the other nodes are only partially occupied and available for usage (and, what level of usage is available). As a result, the IPU can ask for help and offload tasks based on distance, usage, availability, scheduling, and a number of other relevant factors.
FIG. 9 depicts an example arrangement of processing use cases for IPUs, involving logic for core usage (e.g., core set usage sensing and core set activation logic 910), accelerator usage (e.g., accelerator usage sensing and activation logic 920), and network usage (e.g., congestion control, task deadline/priority analysis, and traffic flow reshaping logic 930). Such logic may be coordinated to determine the location of execution for workloads or various portions of workloads from requests 940A, 940B, 940C, 940D, including the usage of compute cores (e.g., core sets 1-N at location 912A, core sets 1-N at location 912B, core set 1-N at location 912C, and core set 1-N at location 912D) or accelerators (e.g., accelerators 1-N at location 922A, accelerators 1-N at location 922B, accelerators 1-N at location 922C, accelerators 1-N at location 922D). Other resources such as storage and memory (not shown) may also be coordinated. In an example, this logic is provided in a peer-to-peer configuration between respective IPUs, and the functions and usage discussed herein need not be implemented in networking equipment.
The arrangement of FIG. 9 shows an example deployment of IPUs, such as IPUs 944A, 944B, 944C, 944D operating in a group of gateway nodes connected to respective base stations 822A, 822B, 822C, 822D. The IPUs 944A, 944B, 944C, 944D coordinate with other IPUs at different servers or nodes such as IPUs 942A, 942B, 942C, 942D located at the respective base stations, on-premise hardware, edge servers, or the like. Here, the IPUs 942A, 942B, 942C, 942D obtain relevant telemetry and metrics from associated hardware and servers, and can provide the relevant telemetry and metrics to the other IPUs 944A, 944B, 944C, 944D elsewhere in the network.
In this configuration, the IPUs 942A, 942B, 942C, 942D use the telemetry information to maintain a view of compute nodes within the network, while also maintaining a macro-level view of the overall network. For instance, a particular IPU at this level operates as a controller of multiple nodes and can be provided with a full view of network activities and congestion. Additionally, the particular IPU can also ping other IPUs which manage other resources, to provide the IPUs with information regarding network usage and congestion. The IPUs on target computer systems, for example, can evaluate utilization information and ongoing telemetry to not overload any particular system. The IPUs can also evaluate such utilization information and telemetry to produce relevant predictions of system and network usage.
Various usage examples can be provided based on the coordination of traffic logic (e.g., logic 930), accelerator logic (e.g., logic 920), and compute logic (e.g., logic 910). In a first example, IPUs include or interface with various logic to track the availability (e.g., a heat map) of the infrastructure characteristics, using logic 910 and 920. This may be provided as a heat map (or a derivative or alternate representation of the heat map) that is maintained or stored in or at the IPU itself. This heat map may be used to provide a micro batch of interrupts to activate compute entities (e.g., among accelerators 922A, 922B, 922C, or 922D, or among core sets 912A, 912B, 912C, 912D). Workload analysis 934A, 934B, 934C may be performed based on characteristics such as deadlines, roundtrip times, and priority, in addition to information from the IPUs provided as outputs 946A, 946B, 946C, 946D. Additionally, power analysis 932 can be performed based on actual, scheduled, or forecasted usage of these compute entities. In particular, because power usage and availability is often critical to the availability of the processing resources (e.g., how many accelerators or cores can be used, or what speed the accelerators or cores can be used at), logic coordinated by the IPUs can be used to balance or minimize power usage and track the overall load on system resources.
As a second example, the IPUs are used at different network and hardware locations (e.g., the base stations 822A, 822B, 822C, 822D) to provide congestion control and network flow reshaping with the logic 910, 920 and 930. For example, consider a scenario where there are three accelerators in use by a workload, and a system is waiting for one of the accelerator tasks to finish before a fourth task can be deployed. In this scenario, workload tasks can be modeled at the IPU as a decision model or graph, including the modeling of dependencies among tasks. This modeling may be useful to verify when tasks are a precondition to other tasks, or are dependent waiting tasks, to ensure that deadlocks can be avoided and wait time reduced. Further, congestion avoidance can be used in such modeling while considering workload deadlines.
As a third example, the IPUs are deployed to perform specialized processing with one or more accelerators with the logic 920 and 930. Accelerators are useful for performing specialized operations in a very fast manner Here, the IPUs can weight the use of such accelerators versus the usage of power from such accelerators. The IPUs can also consider the ongoing amount of usage of the accelerators, the ongoing usage and scheduling of the accelerators, and the possibility of deadlocked operations if accelerators are not used.
With such deployments of IPUs, edge infrastructure capabilities may enable distributed load shaping and handling for bursts of traffic. As an example, tasks assigned to one base station can be moved to another base station. Such assigned tasks may be based on an observation of how infrastructure handles tasks and construction of test cases to decode scheduling. In contrast, in existing hardware configurations, most of the decisions are taken either in isolation in each of the tiers or are taken by software entities such as orchestrators. The use of software entities such as orchestrators that run on top of the architecture makes them slow to respond, while lacking visibility on the whole system at the granularity that is needed.
The IPU deployments in this architecture also address edge scale. The architecture also enables improved device to cloud flow. It allows to provide better continuum between the different tiers. Accordingly, with the proposed architecture, a distributed computing environment is much more capable to scale and opportunistically find new resources that can be used, merge and combine requests, and the like. This provides much more de-centralized scalability improving overall total cost of ownership (TCO).
The IPU deployments in this architecture also address a variety of power considerations. For example, a system may prolong CPU sleep states by having IPUs redirect micro-batches of interrupts to a local or remote “CPU of first resort,” and bringing local CPUs out of sleep states when some activity meets or exceeds a threshold.
The IPU deployments in this architecture also address reliability aspects. In addition to the use of service level features (e.g., SLAs), scenarios may occur to require to re-launch a task because of poor performance or because the task is not responding to another IPU. Reliability considerations may be used to ensure that not only the new task is launched, but also that the original task is terminated (e.g., when decision is made for failover, or later when the system becomes available).
The arrangement of accelerator logic 920 and compute logic 910 may enable further coordination with compute operations that can be performed in the IPUs themselves. For instance, the IPU deployments may invoke accelerators such as DSA units to do bulk value range checking under IPU control, with varying levels of precision and reporting a bit map vector through a memory range mapped across CPUs, IPUs, and other xPUs.
Likewise, the IPU deployments in this architecture may enable congestion control based on a number of schemes and algorithms. For instance, congestion control schemes driven by explicit congestion notifications from receiving side (such as RTT based, as described by TIMELY, R. Mittal et. al., “Timely: Rtt-based congestion control for the datacenter”, ACM SIGCOMM, 2015, or Swift-based, as described by G. Kumar, et. al., “Swift: Delay is Simple and Effective for Congestion Control in the Datacenter”, SIGCOMM 2020) have proved to be very effective. The multi-path adaptive scheme for distributed IPUs may integrate one or multiple congestion control schemes. For example, instead of high and low priorities, a different weight can be attached to lower priority requestors in weighing the round trip times, or setting delay targets.
FIG. 10 depicts a flowchart for an example method of workload processing in an edge computing arrangement. The method 1000 may be implemented by one or more networked processing units (e.g., IPUs) or other forms of processing circuitry, and instructions embodied thereon to be executed by the networked processing unit(s) (or processing circuitry), consistent with the examples and functionality of networked processing units, as discussed above.
At 1010, operations are performed to receive workload information for a workload, for a workload that includes respective tasks to be processed (e.g., executed) among distributed computing entities.
At 1020, operations are performed to analyze network conditions for a predicted execution of the workload, based on the received workload information. These network conditions may include network availability among the distributed computing entities, such as network availability as measured by a measurement, metric, or other observable value that relates to congestion, priority, and latency of network connections used among the distributed computing entities. In some examples, the network conditions are based on point-to-point or local network conditions (e.g., within a constrained environment) which directly affect performance such as latency, bandwidth, throughput, and other similar metrics.
At 1030, operations are performed to analyze compute conditions for a predicted execution of the workload, based on the received workload information. These compute conditions may include processing availability among the distributed computing entities, such as processing availability as measured by a measurement, metric, or other observable value that relates to compute resources located among the distributed computing entities. In specific examples, such compute resources include: at least a first plurality of central processing unit (CPU) cores located at a first computing node and at least a second plurality of CPU cores located at a second computing node; or at least a first plurality of accelerators located at a first computing node and at least a second plurality of accelerators located at a second computing node; or a combination of CPU and accelerator resources.
At 1040, operations are optionally performed to analyze power usage and power availability among the distributed computing entities, based on the predicted execution of the workload. If this power analysis is performed, then the following operations to identify the locations in the distributed computing entities to deploy the workload (at 1050) can be based on the analysis of power usage and power availability. Likewise, this power analysis may cause or trigger a change to at least one power state at the identified locations of the distributed computing entities during deployment of the workload.
At 1050, operations are performed to identify, select, or determine locations (e.g., resources) among the distributed computing entities to deploy the workload. Such locations may be represented by data values, a database, or ongoing set of data relationships which can be reviewed, accessed, queried, and retrieved. This is followed at 1060 with operations that are performed to activate (or, cause activation of) the identified locations of the distributed computing entities to enable execution of the workload. In specific examples, the analysis of network conditions and the analysis of compute conditions each include evaluation of at least one priority of the workload and evaluation of at least one characteristic of a service level agreement for the workload, and the resulting identification and activation operations are based on this at least one characteristic of a service level agreement. Such characteristics of a service level agreement may include or be associated with a variety of technical measurements, service objectives as represented by data, telemetry data values, and other representations in a computer system.
Other implementations and adaptations of the method 1000 may be provided consistent with the techniques and architectures discussed above. In a specific example, the method 1000 is performed by a networked processing unit in a network interface of a computing system, and the workload information is received via the network interface from another networked processing unit located at a base station, on-premises server, or data center server. Other combinations or scenarios may be provided.

Additional Examples

Additional examples of the presently described method, system, and device embodiments include the following, non-limiting implementations. Each of the following non-limiting examples may stand on its own or may be combined in any permutation or combination with any one or more of the other examples provided below or throughout the present disclosure.
Example 1 is a method for workload processing in an edge computing arrangement, comprising: receiving, from a networked processing unit, workload information for a workload, the workload including respective tasks to be processed among distributed computing entities; performing an analysis of network conditions for a predicted execution of the workload, based on the workload information, to analyze network availability among the distributed computing entities; performing an analysis of compute conditions for the predicted execution of the workload, based on the workload information, to analyze processing availability among the distributed computing entities; and identifying locations of the distributed computing entities to deploy the workload, based on the analysis of network conditions and the analysis of compute conditions.
In Example 2, the subject matter of Example 1 optionally includes causing activation of the identified locations of the distributed computing entities to enable execution of the workload.
In Example 3, the subject matter of any one or more of Examples 1-2 optionally include subject matter where the network availability relates to a measurement of congestion, priority, and latency of network connections used among the distributed computing entities.
In Example 4, the subject matter of any one or more of Examples 1-3 optionally include subject matter where the processing availability relates to a measurement of compute resources located among the distributed computing entities.
In Example 5, the subject matter of Example 4 optionally includes subject matter where the compute resources include: at least a first plurality of central processing unit (CPU) cores located at a first computing node and at least a second plurality of CPU cores located at a second computing node.
In Example 6, the subject matter of any one or more of Examples 4-5 optionally include subject matter where the compute resources include: at least a first plurality of accelerators located at a first computing node and at least a second plurality of accelerators located at a second computing node.
In Example 7, the subject matter of any one or more of Examples 1-6 optionally include performing an analysis of power usage and power availability among the distributed computing entities; wherein identifying the locations in the distributed computing entities to deploy the workload is further based on the analysis of power usage and power availability.
In Example 8, the subject matter of Example 7 optionally includes causing a change to at least one power state at the identified locations of the distributed computing entities during deployment of the workload.
In Example 9, the subject matter of any one or more of Examples 1-8 optionally include subject matter where the analysis of network conditions and the analysis of compute conditions each include evaluation of at least one priority of the workload and evaluation of at least one characteristic of a service level agreement for the workload.
In Example 10, the subject matter of any one or more of Examples 1-9 optionally include subject matter where the method is performed by a networked processing unit in a network interface of a computing system, and wherein the workload information is received via the network interface from another networked processing unit located at a base station, on-premises server, or data center server.
In Example 11, the subject matter of Example 10 optionally includes providing commands to cause a network switch or gateway to control network traffic to the identified locations of the distributed computing entities during deployment of the workload.
Example 12 is a device, comprising: a networked processing unit; and a storage medium including instructions embodied thereon, wherein the instructions, which when executed by the networked processing unit, configure the networked processing unit to: receive, from another networked processing unit, workload information for a workload, the workload including respective tasks to be processed among distributed computing entities; perform an analysis of network conditions for a predicted execution of the workload, based on the workload information, to analyze network availability among the distributed computing entities; perform an analysis of compute conditions for the predicted execution of the workload, based on the workload information, to analyze processing availability among the distributed computing entities; and identify locations of the distributed computing entities to deploy the workload, based on the analysis of network conditions and the analysis of compute conditions.
In Example 13, the subject matter of Example 12 optionally includes subject matter where the instructions further configure the networked processing unit to: cause activation of the identified locations of the distributed computing entities to enable execution of the workload.
In Example 14, the subject matter of any one or more of Examples 12-13 optionally include subject matter where the network availability relates to a measurement of congestion, priority, and latency of network connections used among the distributed computing entities.
In Example 15, the subject matter of any one or more of Examples 12-14 optionally include subject matter where the processing availability relates to a measurement of compute resources located among the distributed computing entities.
In Example 16, the subject matter of Example 15 optionally includes subject matter where the compute resources include: at least a first plurality of central processing unit (CPU) cores located at a first computing node and at least a second plurality of CPU cores located at a second computing node.
In Example 17, the subject matter of any one or more of Examples 15-16 optionally include subject matter where the compute resources include: at least a first plurality of accelerators located at a first computing node and at least a second plurality of accelerators located at a second computing node.
In Example 18, the subject matter of any one or more of Examples 12-17 optionally include subject matter where the instructions further configure the networked processing unit to: perform an analysis of power usage and power availability among the distributed computing entities; wherein identifying the locations in the distributed computing entities to deploy the workload is further based on the analysis of power usage and power availability.
In Example 19, the subject matter of Example 18 optionally includes subject matter where the instructions further configure the networked processing unit to: cause a change to at least one power state at the identified locations of the distributed computing entities during deployment of the workload.
In Example 20, the subject matter of any one or more of Examples 12-19 optionally include subject matter where the analysis of network conditions and the analysis of compute conditions each include evaluation of at least one priority of the workload and evaluation of at least one characteristic of a service level agreement for the workload.
In Example 21, the subject matter of any one or more of Examples 12-20 optionally include subject matter where the networked processing unit is provided in a network interface of the device, and wherein the workload information is received via the network interface from another networked processing unit located at a base station, on-premises server, or data center server.
In Example 22, the subject matter of any one or more of Examples 12-21 optionally include subject matter where the instructions further configure the networked processing unit to: provide commands to cause a network switch or gateway to control network traffic to the identified locations of the distributed computing entities during deployment of the workload.
Example 23 is a machine-readable medium (e.g., a non-transitory storage medium) comprising information (e.g., data) representative of instructions, wherein the instructions, when executed by processing circuitry, cause the processing circuitry to perform, implement, or deploy any of Examples 1-22.
Example 24 is an apparatus of an edge computing system comprising means to implement any of Examples 1-23, or other subject matter described herein.
Example 25 is an apparatus of an edge computing system comprising logic, modules, circuitry, or other means to implement any of Examples 1-23, or other subject matter described herein.
Example 26 is a networked processing unit (e.g., an infrastructure processing unit as discussed here) or system including a networked processing unit, configured to implement any of Examples 1-23, or other subject matter described herein.
Example 27 is an edge computing system, including respective edge processing devices and nodes to invoke or perform any of the operations of Examples 1-23, or other subject matter described herein.
Example 28 is an edge computing system including aspects of network functions, acceleration functions, acceleration hardware, storage hardware, or computation hardware resources, operable to invoke or perform the use cases discussed herein, with use of any Examples 1-23, or other subject matter described herein.
Example 29 is a system to implement any of Examples 1-28.
Example 30 is a method to implement any of Examples 1-28.
Although these implementations have been described concerning specific exemplary aspects, it will be evident that various modifications and changes may be made to these aspects without departing from the broader scope of the present disclosure. Many of the arrangements and processes described herein can be used in combination or in parallel implementations that involve terrestrial network connectivity (where available) to increase network bandwidth/throughput and to support additional edge services. Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense. The accompanying drawings that form a part hereof show, by way of illustration, and not of limitation, specific aspects in which the subject matter may be practiced. The aspects illustrated are described in sufficient detail to enable those skilled in the art to practice the teachings disclosed herein. Other aspects may be utilized and derived therefrom, such that structural and logical substitutions and changes may be made without departing from the scope of this disclosure. This Detailed Description, therefore, is not to be taken in a limiting sense, and the scope of various aspects is defined only by the appended claims, along with the full range of equivalents to which such claims are entitled.
Such aspects of the inventive subject matter may be referred to herein, individually and/or collectively, merely for convenience and without intending to voluntarily limit the scope of this application to any single aspect or inventive concept if more than one is disclosed. Thus, although specific aspects have been illustrated and described herein, it should be appreciated that any arrangement calculated to achieve the same purpose may be substituted for the specific aspects shown. This disclosure is intended to cover any adaptations or variations of various aspects. Combinations of the above aspects and other aspects not specifically described herein will be apparent to those of skill in the art upon reviewing the above description.

Claims

What is claimed is:

1. A method for workload processing in an edge computing arrangement, comprising:

receiving, from a networked processing unit, workload information for a workload, the workload including respective tasks to be processed among distributed computing entities;

performing an analysis of network conditions for a predicted execution of the workload, based on the workload information, to analyze network availability among the distributed computing entities;

performing an analysis of compute conditions for the predicted execution of the workload, based on the workload information, to analyze processing availability among the distributed computing entities; and

identifying locations of the distributed computing entities to deploy the workload, based on the analysis of network conditions and the analysis of compute conditions.

2. The method of claim 1, further comprising:

causing activation of the identified locations of the distributed computing entities to enable execution of the workload.

3. The method of claim 1, wherein the network availability relates to a measurement of congestion, priority, and latency of network connections used among the distributed computing entities.

4. The method of claim 1, wherein the processing availability relates to a measurement of compute resources located among the distributed computing entities.

5. The method of claim 4, wherein the compute resources include: at least a first plurality of central processing unit (CPU) cores located at a first computing node and at least a second plurality of CPU cores located at a second computing node.

6. The method of claim 4, wherein the compute resources include: at least a first plurality of accelerators located at a first computing node and at least a second plurality of accelerators located at a second computing node.

7. The method of claim 1, further comprising:

performing an analysis of power usage and power availability among the distributed computing entities;

wherein identifying the locations in the distributed computing entities to deploy the workload is further based on the analysis of power usage and power availability.

8. The method of claim 7, further comprising:

causing a change to at least one power state at the identified locations of the distributed computing entities during deployment of the workload.

9. The method of claim 1, wherein the analysis of network conditions and the analysis of compute conditions each include evaluation of at least one priority of the workload and evaluation of at least one characteristic of a service level agreement for the workload.

10. The method of claim 1, wherein the method is performed by a networked processing unit in a network interface of a computing system, and wherein the workload information is received via the network interface from another networked processing unit located at a base station, on-premises server, or data center server.

11. The method of claim 10, further comprising:

providing commands to cause a network switch or gateway to control network traffic to the identified locations of the distributed computing entities during deployment of the workload.

12. A device, comprising:

a networked processing unit; and

a storage medium including instructions embodied thereon, wherein the instructions, which when executed by the networked processing unit, configure the networked processing unit to:

receive, from another networked processing unit, workload information for a workload, the workload including respective tasks to be processed among distributed computing entities;

perform an analysis of network conditions for a predicted execution of the workload, based on the workload information, to analyze network availability among the distributed computing entities;

perform an analysis of compute conditions for the predicted execution of the workload, based on the workload information, to analyze processing availability among the distributed computing entities; and

identify locations of the distributed computing entities to deploy the workload, based on the analysis of network conditions and the analysis of compute conditions.

13. The device of claim 12, wherein the instructions further configure the networked processing unit to:

cause activation of the identified locations of the distributed computing entities to enable execution of the workload.

14. The device of claim 12, wherein the network availability relates to a measurement of congestion, priority, and latency of network connections used among the distributed computing entities.

15. The device of claim 12, wherein the processing availability relates to a measurement of compute resources located among the distributed computing entities.

16. The device of claim 15, wherein the compute resources include: at least a first plurality of central processing unit (CPU) cores located at a first computing node and at least a second plurality of CPU cores located at a second computing node.

17. The device of claim 15, wherein the compute resources include: at least a first plurality of accelerators located at a first computing node and at least a second plurality of accelerators located at a second computing node.

18. The device of claim 12, wherein the instructions further configure the networked processing unit to:

perform an analysis of power usage and power availability among the distributed computing entities;

19. The device of claim 18, wherein the instructions further configure the networked processing unit to:

cause a change to at least one power state at the identified locations of the distributed computing entities during deployment of the workload.

20. The device of claim 12, wherein the analysis of network conditions and the analysis of compute conditions each include evaluation of at least one priority of the workload and evaluation of at least one characteristic of a service level agreement for the workload.

21. The device of claim 12, wherein the networked processing unit is provided in a network interface of the device, and wherein the workload information is received via the network interface from another networked processing unit located at a base station, on-premises server, or data center server.

22. The device of claim 12, wherein the instructions further configure the networked processing unit to:

provide commands to cause a network switch or gateway to control network traffic to the identified locations of the distributed computing entities during deployment of the workload.

23. A non-transitory machine-readable storage medium comprising information representative of instructions, wherein the instructions, when executed by a networked processing unit, cause the networked processing unit to:

24. The non-transitory machine-readable storage medium of claim 23, wherein the instructions further configure the networked processing unit to:

cause activation of the identified locations of the distributed computing entities to enable execution of the workload;

wherein the network availability relates to a measurement of congestion, priority, and latency of network connections used among the distributed computing entities; and

wherein the processing availability relates to a measurement of compute resources located among the distributed computing entities.

25. The non-transitory machine-readable storage medium of claim 24, wherein the compute resources include:

at least a first plurality of central processing unit (CPU) cores located at a first computing node and at least a second plurality of CPU cores located at a second computing node; or

at least a first plurality of accelerators located at the first computing node and at least a second plurality of accelerators located at the second computing node.