---
title: "GraphPerf-RT: Graph-Driven Performance Modeling with Calibrated Uncertainty for OpenMP Scheduling on Heterogeneous Embedded SoCs"
authors:
  - "Mohammad Pivezhandi"
  - "Mahdi Banisharif"
  - "Saeed Bakhshan"
  - "Abusayeed Saifullah"
  - "Ali Jannesari"
doi: "10.24963/ijcai.2026/722"
url: "https://ijcai.org/proceedings/2026/722"
pdf: "https://ijcai.org/proceedings/2026/0722.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6491-6499"
track: "AI4Tech: AI Enabling Technologies"
keywords:
  - "Advanced AI4Tech: AI4Tech foundations"
  - "Advanced AI4Tech: Deep AI4Tech"
  - "Advanced AI4Tech: Data-driven AI4Tech"
---

# GraphPerf-RT: Graph-Driven Performance Modeling with Calibrated Uncertainty for OpenMP Scheduling on Heterogeneous Embedded SoCs

Mohammad Pivezhandi, Mahdi Banisharif, Saeed Bakhshan, Abusayeed Saifullah, Ali Jannesari

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6491-6499. DOI: [10.24963/ijcai.2026/722](https://doi.org/10.24963/ijcai.2026/722)

## Abstract

Autonomous AI agents on embedded platforms require real-time, risk-aware scheduling under resource and thermal constraints. Classical heuristics struggle with workload irregularity, tabular regressors discard structural information, and model-free reinforcement learning (RL) risks overheating. We introduce GraphPerf-RT, an AI technology achieving deep learning accuracy at heuristic speeds (2-7ms). GraphPerf-RT is, to our knowledge, the first graph-grounded infrastructure unifying task DAG topology, CFG-derived code semantics, and runtime context (per-core DVFS, thermal state, utilization) in a heterogeneous graph with typed edges encoding precedence, placement, and contention. The architecture supports multi-task evidential heads with Normal-Inverse-Gamma uncertainty; we validate on makespan prediction for risk-aware scheduling. Experiments on three ARM platforms (Jetson TX2, Orin NX, RUBIK Pi) achieve R^2 = 0.81 on log-transformed makespan with Spearman rho = 0.95 and conservative uncertainty calibration (PICP = 99.9% at 95% confidence). Integration with four RL methods demonstrates that multi-agent model-based RL with GraphPerf-RT as the world model achieves 66% makespan reduction and 82% energy reduction versus model-free baselines, with zero thermal violations.