Partition-Aware Scheduling for Mobile Heterogeneous Inference Co-Execution

• URL: http://arxiv.org/abs/2609.14213v1
• Date: Sun, 13 Sep 2026 00:44:37 GMT
• Title: Partition-Aware Scheduling for Mobile Heterogeneous Inference Co-Execution
• Abstract summary: We consider the problem of partition-aware DAG scheduling for mobile heterogeneous inference.<n>We propose an online iterative search framework, which decomposes large DAGs into stages, focuses search on critical operators, and uses latency predictors to estimate partitioned execution.
• Score: 1.3356260369011272
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Modern mobile inference runs on heterogeneous platforms combining mobile GPUs with multiple CPU core clusters. Existing optimizations typically exploit either inter-operator parallelism, by assigning entire operators to CPU cores or to the GPU, or intra-operator parallelism, by partitioning each operator for CPU-GPU co-execution. We consider these two forms of parallelism together, to improve inference latency of tasks that can be represented by a static DAG of operators with predefined input/output tensor shapes (e.g., CNNs or vision transformers). We define the problem of partition-aware DAG scheduling for mobile heterogeneous inference, illustrating that the best strategy depends on the structure of the inference DAG, thus motivating a joint formulation capturing operator partition choices, device assignment, and execution order. We propose an online iterative search framework, which decomposes large DAGs into stages, focuses search on critical operators, and uses latency predictors to estimate partitioned execution without exhaustive profiling. Across representative mobile inference workloads, our approach achieves latency close to an offline solution while keeping scheduling overhead to a fraction of the model initialization cost, allowing platform-specific scheduling at deployment time.

Related papers

• Para-Pipe: Exploiting Hierarchical Operator Parallelism of ML Computational Graphs on SoCs [22.6523068033902]
  Para-Pipe is a hierarchical mapping framework that integrates intra- and inter-stage operator parallelism within a pipelined architecture.<n>Para-Pipe navigates the trade-off between throughput and latency by selectively fine-tuning parallelism levels within and across pipeline stages.
  arXiv  Detail & Related papers  (2026-09-03T17:53:44Z)
• Fine-Grain GPU Parallelization of the Generalized Partition Crossover for Large-Scale Traveling Salesman Problems [1.160208922584163]
  The Traveling Salesman Problem (TSP) is one of the most extensively studied NP-hard optimization problems.<n>The proposed approach reformulates GPX as a graph-parallel problem using coalesced memory layouts, ghost-node transformations, and connected-node analysis.<n>The proposed GPU achieves speedups between 48x and 625x while significantly reducing memory overhead.
  arXiv  Detail & Related papers  (2026-08-21T15:42:05Z)
• Event Tensor: A Unified Abstraction for Compiling Dynamic Megakernel [17.931727429220874]
  Event Compiler (ETC) applies static and dynamic scheduling to generate high-performance persistent kernels.<n>ETC achieves state-of-the-art serving latency while significantly reducing warmup overhead.
  arXiv  Detail & Related papers  (2026-04-14T22:19:51Z)
• Para-B&B: Load-Balanced Deterministic Parallelization of Solving MIP [50.917107318582715]
  Mixed-integer programming (MIP) extends linear programming by incorporating both continuous and integer decision variables.<n>This paper presents the first fully open-source implementation of deterministic parallel branch-and-bound for HiGHS, a high-performance MIP solver.<n>Our approach introduces a novel data-parallel architecture ensuring strict determinism by replicating complete solver state across worker threads.
  arXiv  Detail & Related papers  (2026-02-10T14:17:53Z)
• Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs [61.953548065938385]
  We introduce the ''Three Taxes'' (Bulk Synchronous, Inter- Kernel Data Locality, and Kernel Launch Overhead) as an analytical framework.<n>We propose moving beyond the rigid BSP model to address key inefficiencies in distributed GPU execution.<n>We observe a 10-20% speedup in end-to-end latency over BSP-based approaches.
  arXiv  Detail & Related papers  (2025-11-04T01:15:44Z)
• Intra-DP: A High Performance Collaborative Inference System for Mobile Edge Computing [67.98609858326951]
  Intra-DP is a high-performance collaborative inference system optimized for deep neural networks (DNNs) on mobile devices.<n>It reduces per-inference latency by up to 50% and energy consumption by up to 75% compared to state-of-the-art baselines.<n>The evaluation demonstrates that Intra-DP reduces per-inference latency by up to 50% and energy consumption by up to 75% compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-07-08T09:50:57Z)
• Optimizing Multi-DNN Inference on Mobile Devices through Heterogeneous Processor Co-Execution [39.033040759452504]
  Deep Neural Networks (DNNs) are increasingly deployed across diverse industries, driving demand for mobile device support.<n>Existing mobile inference frameworks often rely on a single processor per model, limiting hardware utilization and causing suboptimal performance and energy efficiency.<n>We propose an Advanced Multi-DNN Model Scheduling (ADMS) strategy for optimizing multi-DNN inference on mobile heterogeneous processors.
  arXiv  Detail & Related papers  (2025-03-27T03:03:09Z)
• FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression [55.992528247880685]
  Decentralized training faces significant challenges regarding system design and efficiency. We present FusionLLM, a decentralized training system designed and implemented for training large deep neural networks (DNNs) We show that our system and method can achieve 1.45 - 9.39x speedup compared to baseline methods while ensuring convergence.
  arXiv  Detail & Related papers  (2024-10-16T16:13:19Z)
• Harnessing Deep Learning and HPC Kernels via High-Level Loop and Tensor Abstractions on CPU Architectures [67.47328776279204]
  This work introduces a framework to develop efficient, portable Deep Learning and High Performance Computing kernels. We decompose the kernel development in two steps: 1) Expressing the computational core using Processing Primitives (TPPs) and 2) Expressing the logical loops around TPPs in a high-level, declarative fashion. We demonstrate the efficacy of our approach using standalone kernels and end-to-end workloads that outperform state-of-the-art implementations on diverse CPU platforms.
  arXiv  Detail & Related papers  (2023-04-25T05:04:44Z)
• Gradient Coding with Dynamic Clustering for Straggler-Tolerant Distributed Learning [55.052517095437]
  gradient descent (GD) is widely employed to parallelize the learning task by distributing the dataset across multiple workers. A significant performance bottleneck for the per-iteration completion time in distributed synchronous GD is $straggling$ workers. Coded distributed techniques have been introduced recently to mitigate stragglers and to speed up GD iterations by assigning redundant computations to workers. We propose a novel dynamic GC scheme, which assigns redundant data to workers to acquire the flexibility to choose from among a set of possible codes depending on the past straggling behavior.
  arXiv  Detail & Related papers  (2021-03-01T18:51:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.