Overview

Heterogeneous computing assigns work across different resources—such as CPUs, GPUs, NPUs, FPGAs, and processing-in-memory devices—whose strengths and constraints vary. Common approaches include task and graph scheduling, workload partitioning, pipeline parallelism, compiler and kernel optimization, and joint hardware-runtime design; reinforcement learning and analytical cost models help make these decisions adaptive. Applications range from edge inference and robotics to large-model training and serving across distributed clusters. A central challenge is balancing computation against data movement, contention, and power while preserving accuracy and meeting latency targets, with solutions often depending on the specific hardware and workload.

Latest papers

CardsList

89 papers8 papers in the last four weeks, down 33% on the four weeks before. 0.1% of all new papers.

  1. Performance-Portable Exact Gaussian Process Regression in Python via SYCL and oneMath

    Nov 12, 2026Alexander Strack, Marcel Graf, Alexander Van Craen +1GPU AccelerationGaussian Process Regression

  2. DataHelix: A CPU-GPU Co-Scheduling Data Plane for Multimodal Model Training

    Nov 6, 2026Yuanhe Li, Jiazhen Wu, Dian Ding +2Heterogeneous Computing

  3. More with Less: Efficient Parallel Scientific Code Translation via an Agent-Skill Workflow

    Nov 6, 2026Jianuo Shen, Pengyi Xu, Bo ZhangCode TranslationLLM Agent Workflow Optimization

  4. TileWeave: Heterogeneous Tiling for Sparse Prefill on Mobile SoCs

    Oct 30, 2026Wentao Ni, Hong Cai, Mingu Lee +7LLM Inference AccelerationOn-Device Language Model Inference

  5. Heterogeneous Space Data Centers: A Key Paradigm for Future Non-Terrestrial and In-Orbit Services

    Oct 23, 2026Peng Hu, Mustafa Alhassan, Amjad IqbalHeterogeneous ComputingLEO Satellite Networks

  6. AgentDP: Towards Automated Model Deployment for Heterogeneous Embedded AI Applications

    Oct 22, 2026Leming Shen, Qiang Yang, Xinyu Huang +2MLOpsOn-Device Inference

  7. One Communicator, Three Vendors: Extending the MoA Predictive Theory to a Real NVIDIA+AMD+CPU MPI Ensemble

    Oct 16, 2026Lenore Mullin, Gaetan HainsHigh-Performance ComputingHeterogeneous Computing

  8. ETH: Data-Balanced Heterogeneous Pipeline Parallelism for Training Large Models

    Oct 15, 2026Mianjie Yu, Zhongmin Zhao, Zizhao Mo +9Distributed TrainingPipeline Parallelism

  9. MoSAIC: Learning DAG Scheduling Heuristics from Optimal Schedules through Motif-Aware Recovery and LLM-Guided Reasoning

    Oct 10, 2026Shiva Ahir, Hashmath Shaik, Alex Doboli +2Automated Heuristic DesignLearning to Optimize

  10. LLM-Augmented Bayesian Optimization with Adaptive Policies for Chiplet Design Space Exploration

    Oct 10, 2026Hang Liu, Zhengfei Chen, Zhengrui Chen +3Large Language Model-Guided OptimizationElectronic Design Automation

  11. Rethinking Streaming-Perception Evaluation on Heterogeneous Edge Platforms

    Oct 4, 2026Misun Yu, Jinyoung Moon, Jemin LeeEdge InferenceHeterogeneous Computing

  12. EdgeAgent: Orchestrating On-Device LLM inference for End-User Multi-Agent Systems on CPU-GPU Unified Memory Architectures

    Oct 2, 2026Yuhai Long, Yuanxin Wei, Kai Wu +3On-Device InferenceLLM Inference Scheduling

  13. HAPMoE: Heterogeneity-Aware Automatic Parallelism Planning for Mixture-of-Experts Models Training

    Sep 30, 2026Mengyuan Fan, Peizhuang Cong, Zixiao Huang +7Expert ParallelismHeterogeneous Computing

  14. Kafila: Serving Large Language Models on a Trusted Set of Heterogeneous Commodity Machines

    Sep 28, 2026Murtaza Rangwala, Richard O. Sinnott, Rajkumar BuyyaLLM InferenceLLM Inference Scheduling

  15. Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scale

    Sep 18, 2026Hao Fu, Jichao Sun, Baiting Zhu +15Information RetrievalHybrid Retrieval

  16. HiGFRL: Hierarchical Graph Fusion-Driven Reinforcement Learning for Dependency-Aware Task Scheduling in Heterogeneous Cloud

    Sep 14, 2026Tiangang Li, Shi Ying, Xiangbo TianReinforcement LearningHeterogeneous Computing

  17. Physically Partitioned KVCache Format for CPU--GPU Load Balancing in MoE Inference

    Sep 13, 2026Enda Yu, Dezun Dong, Xiangke LiaoKV-Cache ManagementKV-Cache Offloading

  18. OpWeave: Flexible Operator Disaggregation for Heterogeneous LLM Serving

    Sep 13, 2026Zikun Li, Yixuan Mei, Shiqi Pan +9Disaggregated LLM ServingCost-Aware Inference

  19. Partition-Aware Scheduling for Mobile Heterogeneous Inference Co-Execution

    Sep 13, 2026Zhuojin Li, Marco Paolieri, Leana GolubchikOn-Device InferenceHeterogeneous Computing

  20. Rethinking Heterogeneous System Disaggregation for Subquadratic Attention

    Sep 11, 2026Arya Tschand, Yaosheng Fu, Vikram Sharma Mailthody +6Disaggregated LLM ServingLLM Inference Acceleration

  21. Fidelity-Aware Scheduling of Quantum Circuits on Multi-QPU Systems

    Sep 9, 2026Innocenzo Fulginiti, Antonio Tudisco, Salvatore Zammuto +7High-Performance ComputingHeterogeneous Computing

  22. Diamond Agent: Agentic Control of Federated HPC Resources as a Service

    Sep 5, 2026Haotian Xie, Junlin Chen, Mingkai Zheng +9High-Performance ComputingAgentic Workflows

  23. Para-Pipe: Exploiting Hierarchical Operator Parallelism of ML Computational Graphs on SoCs

    Sep 3, 2026Yujie Zhang, Huiying Lan, Ehsan Aghapour +5Efficient Neural Network InferenceEnergy-Efficient ML