提出高效内存分配方案，解决百万缓冲区静态内存规划难题。
Futureproof Static Memory Planning
- 采用低碎片化设计，优化百万级缓冲区的内存分配
- 在硬核测试集上优于四个主流实现，兼顾效率与稳定性
- 适合深度学习等静态架构场景的内存优化需求
将一组已知大小和生命周期的缓冲区分配偏移量以最小化总内存使用，这一组合优化问题被称为动态存储分配（DSA），属于NP完全问题。现有实现因性能或可扩展性限制，要么采用快速但浪费内存的启发式方法，要么无法扩展到超过千个缓冲区。随着深度神经网络的静态架构与‘AI内存墙’问题凸显，对高效DSA的需求再度兴起。本文提出idealloc，一种专为百万级缓冲区实例设计的低碎片、高性能DSA方案。在多个领域构建的新颖难题基准测试中，idealloc在综合有效性和鲁棒性指标上领先于四个生产级实现。
原文摘要 · Abstract (English)
The NP-complete combinatorial optimization task of assigning offsets to a set of buffers with known sizes and lifetimes so as to minimize total memory usage is called dynamic storage allocation (DSA). Existing DSA implementations bypass the theoretical state-of-the-art algorithms in favor of either fast but wasteful heuristics, or memory-efficient approaches that do not scale beyond one thousand buffers. The "AI memory wall", combined with deep neural networks' static architecture, has reignited interest in DSA. We present idealloc, a low-fragmentation, high-performance DSA implementation designed for million-buffer instances. Evaluated on a novel suite of particularly hard benchmarks from several domains, idealloc ranks first against four production implementations in terms of a joint effectiveness/robustness criterion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。