惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Martin Fowler
Martin Fowler
博客园 - 三生石上(FineUI控件)
WordPress大学
WordPress大学
博客园_首页
宝玉的分享
宝玉的分享
S
SegmentFault 最新的问题
Jina AI
Jina AI
Hugging Face - Blog
Hugging Face - Blog
V
Visual Studio Blog
美团技术团队
IT之家
IT之家
罗磊的独立博客
Blog — PlanetScale
Blog — PlanetScale
Google DeepMind News
Google DeepMind News
月光博客
月光博客
Microsoft Azure Blog
Microsoft Azure Blog
H
Help Net Security
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Last Week in AI
Last Week in AI
博客园 - 叶小钗
M
MIT News - Artificial intelligence
B
Blog RSS Feed
有赞技术团队
有赞技术团队
Y
Y Combinator Blog

cs.DC updates on arXiv.org

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models Efficient, VRAM-Constrained xLM Inference on Clients Folding Tensor and Sequence Parallelism for Memory-Efficient Transformer Training & Inference DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving RaMP: Runtime-Aware Megakernel Polymorphism for Mixture-of-Experts Spark Policy Toolkit: Semantic Contracts and Scalable Execution for Policy Learning in Spark Internet of Everything in the 6G Era: Paradigms, Enablers, Potentials and Future Directions PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations ITAS: A Multi-Agent Architecture for LLM-Based Intelligent Tutoring Latency and Cost of Multi-Agent Intelligent Tutoring at Scale TACO: Efficient Communication Compression of Intermediate Tensors for Scalable Tensor-Parallel LLM Training FreeScale: Distributed Training for Sequence Recommendation Models with Minimal Scaling Cost CommFuse: Hiding Tail Latency via Communication Decomposition and Fusion for Distributed LLM Training A Taxonomy and Resolution Strategy for Client-Level Disagreements in Federated Learning Usable Agent Discovery for Decentralized AI Systems Cloud to Edge: Benchmarking LLM Inference On Hardware-Accelerated Single-Board Computers Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy Shard the Gradient, Scale the Model: Serverless Federated Aggregation via Gradient Partitioning Promoting Simple Agents: Ensemble Methods for Event-Log Prediction GraphLeap: Decoupling Graph Construction and Convolution for Vision GNN Acceleration on FPGA AGNT2: Autonomous Agent Economies on Interaction-Optimized Layer 2 Infrastructure FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels Stream-CQSA: Avoiding Out-of-Memory in Attention Computation via Flexible Workload Scheduling A Delta-Aware Orchestration Framework for Scalable Multi-Agent Edge Computing Federated Learning over Blockchain-Enabled Cloud Infrastructure Optimal Routing for Federated Learning over Dynamic Satellite Networks: Tractable or Not? Sherpa.ai Privacy-Preserving Multi-Party Entity Alignment without Intersection Disclosure for Noisy Identifiers
Demand-driven Inlining in a Region-based Optimizer for IL...
Thomas P. Way, Lori L. Pollock · 2006-04-11 · via cs.DC updates on arXiv.org

Region-based compilation repartitions a program into more desirable compilation units using profiling information and procedure inlining to enable region formation analysis. Heuristics play a key role in determining when it is most beneficial to inline procedures during region formation. An ILP optimizing compiler using a region-based approach restructures a program to better reflect dynamic behavior and increase interprocedural optimization and scheduling opportunities. This paper presents an interprocedural compilation technique which performs procedure inlining on-demand, rather than as a separate phase, to improve the ability of a region-based optimizer to control code growth, compilation time and memory usage while improving performance. The interprocedural region formation algorithm utilizes a demand-driven, heuristics-guided approach to inlining, restructuring an input program into interprocedural regions. Experimental results are presented to demonstrate the impact of the algorithm and several inlining heuristics upon a number of traditional and novel compilation characteristics within a region-based ILP compiler and simulator.