Skip to main content

High-End Application Execution Middleware (HEAppE Middleware)

HPC-as-a-Service is a well known term in the area of high performance computing. It enables users to access an HPC infrastructure without a need to buy and manage their own physical servers or data centre infrastructure. Through this service small and medium enterprises (SMEs) can take advantage of the technology without an upfront investment in the hardware. This approach further lowers the entry barrier for users and SMEs who are interested in utilizing massive parallel computers but often do not have the necessary level of expertise in this area.

To provide this simple and intuitive access to the supercomputing infrastructure an in-house application framework called HEAppE has been developed. This framework is utilizing a mid-layer principle, in software terminology also known as middleware. Middleware manages and provides information about submitted and running jobs and their data between the client application and the HPC infrastructure. HEAppE is able to submit required computation or simulation on HPC infrastructure, monitor the progress and notify the user should the need arise. It provides necessary functions for job management, monitoring and reporting, user authentication and authorization, file transfer, encryption, and various notification mechanisms.

HEAppE

Use-Cases

HPC-as-a-Service​

HEAppE acts as a unified abstraction layer over the underlying cluster resource managers. While HPC centers commonly utilize complex workload managers, HEAppE simplifies the interaction by translating generic API requests into the specific dialect required by the scheduler.

  • Scheduler Support: The middleware fully supports industry-standard workload managers, specifically Slurm and PBS Pro.
  • Job Lifecycle Management: Users do not need to manually interact with the CLI. Instead, the middleware handles the creation, submission and monitoring of batch jobs (handling sbatch or qsub commands internally).
  • Abstraction: Users define job parameters via the HEAppE API, and the middleware automatically constructs the submission script, executes the submission, and subsequently manages the job state.
  • Portability: This abstraction allows applications to be portable across different HPC centers regardless of whether the underlying hardware is managed by Slurm or PBS.

Inference Server (Interactive Access)​

Beyond standard batch processing, HEAppE supports long-running interactive services, such as AI Inference Servers, visualization tools, or Jupyter Lab instances running on compute nodes.

  • Connectivity: Since compute nodes generally reside on a private network without direct internet access, HEAppE manages secure SSH tunneling.
  • Mechanism: When an inference server is started on a compute node, HEAppE establishes a secure tunnel from the outside world (or the client application) through the login nodes to the specific port on the allocated compute node/s.
  • Security: This enables users to interact with running services in real-time without compromising the security policies of the HPC network or requiring complex VPN configurations.
  • HTTP Request Proxying: HEAppE facilitates direct application interaction via dedicated API endpoints that support HTTP GET and POST methods. This feature allows clients to transmit structured data (e.g., JSON payloads) which HEAppE securely proxies to the target application's listening socket or web server interface running on the compute node.

Quantum Scheduling (Quantum-as-a-Service)​

As High-Performance Computing evolves into hybrid classical-quantum workflows, HEAppE serves as the primary interface for a dedicated Quantum-as-a-Service (QaaS) Scheduler.

  • QaaS Integration: HEAppE leverages a specialized QaaS Scheduler to bridge the gap between users and quantum resources. By acting as a sophisticated intermediary, it abstracts the complexities of various quantum providers (such as IQM) and their respective software stacks, ensuring a hardware-agnostic approach.

  • Hybrid Middleware and Orchestration: HEAppE acts as the master middleware for modern research. It seamlessly manages the submission of classical pre-processing jobs to standard HPC nodes while simultaneously dispatching quantum tasks to the QaaS Scheduler, enabling perfectly synchronized hybrid workflows.

  • Job Lifecycle Management: From the user’s perspective, executing a quantum algorithm is as seamless as submitting a standard simulation. HEAppE autonomously handles authentication, secure data staging, and real-time status monitoring, delivering unified results through a single, consistent workflow.