一句话：提出面向高瘦矩阵乘的 I/O 分析，并据此设计长序列精确自注意力加速器 AttenIO，实现显著加速。
随着 GPU 等加速器普及，片上与片外存储之间的 I/O 优化愈发关键，但系统化 I/O 分析仍具挑战。本文研究如何利用 I/O 分析加速精确的长序列自注意力。作者首先提出针对高瘦矩阵乘的 I/O 分析，用以刻画长序列自注意力中主导的数据移动行为；在该分析指导下设计 AttenIO 加速器，包含三项优化：分析推导的 I/O 最优分块与调度、细粒度三级通信—计算重叠，以及高效并行 softmax。评估显示，AttenIO 相比当前最优方案取得 1.6×–8.8× 的加速，并展示了 I/O 分析作为高性能 I/O 优化原则性基础的更广泛潜力。
As GPUs and other accelerators become increasingly popular, optimizing I/O operations between on-chip and off-chip memory is increasingly critical. I/O analysis, however, is complex, requiring a deep understanding of application dataflow and memory hierarchy. Developing a practical I/O analysis methodology remains a timely challenge. Self-attention is employed extensively in transformer models, but its quadratic memory complexity poses significant challenges to modern memory systems. In this study, we explore how to use I/O analysis to develop optimal solutions for accelerating exact long-sequence self-attention. We first introduce a novel I/O analysis for tall-and-skinny matrix-matrix multiplication, which captures the dominant data movement behavior of long-sequence self-attention. Guided by systematic I/O analysis, we develop AttenIO, an I/O-driven accelerator for exact long-sequence self-attention with three key optimizations: (1) an analytically derived I/O-optimal tiling and scheduling to minimize I/O operations, (2) fine-grained three-level communication-computation overlapping to hide I/O stalls, and (3) parallel execution patterns for efficient softmax. Our evaluation shows that AttenIO achieves a 1.6×-8.8× speedup over the state-of-the-art solutions. Although AttenIO is designed for self-attention, it also highlights the broader potential of I/O analysis as a principled foundation for guiding high-performance I/O optimizations.
@inproceedings{LuL00S26,
title = {I/O Analysis is All You Need: An I/O Analysis for Long-Sequence Attention},
author = {Xiaoyang Lu and Boyu Long and Xiaoming Chen and Yinhe Han and Xian-He Sun},
booktitle = {ASPLOS},
year = {2026},
doi = {10.1145/3779212.3790174}
}