Smart NIC Application Deployment Across Computing Domains
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As the complexity of applications and the number of interconnected devices increase, implementing a high-performance, highly available, and secure client-server architecture with intermediary computing devices becomes challenging.
Innovation Solution
The technology enables application deployment across multiple computing domains using smart network interface cards (NICs) and programmable accelerators, allowing applications to be executed simultaneously on multiple virtual machines in distinct subdomains without modification, and leveraging orchestration logic for configuration and management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If applications are deployed across multiple computing domains using smart NICs and programmable accelerators, then scalability and availability are improved, but device complexity increases
Solution Approach 1:
The patent segments the computing architecture into distinct computing domains (host domain, smart NIC domain, accelerator domain) with clear boundary definitions. Each domain has dedicated resources and communication pathways, allowing independent deployment and management while improving overall system availability through domain-level fault isolation.
Solution Approach 2:
The patent introduces domain controllers and communication interfaces as intermediary components between different computing domains. These intermediaries manage the complexity of inter-domain communication, resource allocation, and coordination, enabling scalable deployment without proportionally increasing operational complexity.
2Productivity
If applications are executed simultaneously on multiple virtual machines in distinct subdomains, then productivity and scalability are improved, but ease of operation deteriorates
Solution Approach 1:
The patent implements a universal deployment framework that can execute the same application code across multiple virtual machines in different subdomains without modification. The framework provides unified resource management, consistent communication protocols, and standardized monitoring mechanisms that simplify operations despite the distributed nature of the system.
Solution Approach 2:
The patent enables dynamic configuration of virtual machines and their resource allocations through parameter changes in the deployment manifest. Operators can modify resource distributions, communication parameters, and execution configurations without redeploying the application logic, maintaining ease of operation while achieving high productivity through parallel execution.
3Object-affected harmful factors
If network traffic management computing devices are added between client devices and application servers, then security and performance are improved, but device complexity increases
Solution Approach 1:
The patent extracts security and traffic management functions from traditional centralized network devices and distributes them across multiple computing domains. Smart NICs and accelerators perform security functions locally at the edge, reducing the complexity burden on centralized management systems while maintaining comprehensive security coverage.
Solution Approach 2:
The patent adds a new dimensional layer to the architecture by introducing programmable accelerators and smart NICs as intermediate computing domains between traditional network devices and application servers. This additional dimension enables security functions to be implemented through software programming rather than hardware complexity, improving security while managing device complexity through software abstraction.
Data Source
AI summary
Technology related to application deployment across network devices including smart network interface cards. In one example, a method includes distributing an application across a plurality of locally connected computing subdomains. The subdomains can include a mixture of general and special purpose computing subdomains, such as for example, a main computer and an associated smart network interface devices or systems, such as for example a smart network interface card (NIC). The subdomains can each run hypervisors that are bridged to allow a single virtual machine to operate across the subdomains. The application can include multiple portions. For example, an application can be split by different functionalities. The application portions can be tagged to indicate which subdomain they are to be executed within. If the chosen subdomain has available the requisite resources, the application can be detached and distributed to the chosen subdomain.


