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

arXiv:2609.04168 · cs.DC, cs.LG, cs.PF · Submitted 2026-09-03 · Read on arXiv

cs.DC, cs.LG, cs.PF

Submitted: 2026-09-03

Updated: 2026-09-03

Code: https://github.com/ssvb/tinymembench

Terminology

• Energy Efficiency — 47× in this paper · explained in 3 episodes
• Core — 14× in this paper · explained in 2 episodes
• Transformer — 8× in this paper · explained in 2 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Communication Overhead — 4× in this paper · explained in 2 episodes
• Bayesian Optimization — 2× in this paper · explained in 3 episodes
• Black Sesame Technology — 2× in this paper
• Edge Devices — 2× in this paper · explained in 2 episodes
• Objective Function — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Directed Acyclic Graph — 1× in this paper
• Integer Linear Programming — 1× in this paper
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• Model Parallelism on Distributed Infrastructure: A Literature Review from Theory to LLM Case-Studies

Related papers

• iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
• SAMM: Sharded Automated Market Maker
• InferScale: GPU-Native KV Injection for Personalized LLM Serving
• Vigil: Accountable Liveness against Selective Silence
• Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
• Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing