HPCA/CGO/PPoPP/CC 2026 (series) / PPoPP 2026 (series) / Main Conference /
Faster and Cheaper: Pushing the Sequence Alignment Throughput with Commercial CPUs
This paper proposes FastAlign, a faster, cheaper, and practical end-to-end solution for sequence alignment using commercial CPUs. It introduces two key innovations: a multi-stage seeding algorithm that improves search performance while maintaining low memory consumption, and an intra-query parallel seed-extension algorithm that eliminates redundancy and increases SIMD utilization. Evaluation results show that FastAlign achieves 2.27$\times$ $\sim$ 3.28$\times$ throughput speedup and 2.54$\times$ $\sim$ 5.65$\times$ cost reduction compared to state-of-the-art CPU and GPU baselines while guaranteeing 100% identical output to the de facto software BWA-MEM. FastAlign is open-sourced at https://github.com/zzhofict/BWA-FastAlign.git.
Tue 3 FebDisplayed time zone: Hobart change
Tue 3 Feb
Displayed time zone: Hobart change
14:10 - 15:30 | |||
14:10 20mTalk | Pipelonk: Accelerating End-to-End Zero-Knowledge Proof Generation on GPUs for PLONK-Based Protocols Main Conference Zhiyuan Zhang Shandong University, Yanxin Cai Shandong University, Wenhao Yin Shandong University, Xueyu Wu The University of Hong Kong, Yi Wang Shenzhen University, Lei Ju Shandong University, Zhuoran Ji Shandong University DOI | ||
14:30 20mTalk | ParDiff: Efficiently Parallelizing Reverse-Mode Automatic Differentiation with Direct Indexing Main Conference Shuhong Huang Tsinghua University, Shizhi Tang Qingcheng.AI, Yuan Wen University of Aberdeen, Huanqi Cao Tsinghua University, Ruibai Tang Tsinghua University, yidong chen , Jiping Yu Tsinghua University, Yang Li Lenovo Research, Chao Jiang Lenovo Research, Limin Xiao Lenovo Research, Jidong Zhai Tsinghua University DOI | ||
14:50 20mTalk | Faster and Cheaper: Pushing the Sequence Alignment Throughput with Commercial CPUs Main Conference Zhonghai Zhang Institute of Computing Technology, Chinese Academy of Sciences / University of Chinese Academy of Sciences, Yewen Li The Hong Kong University of Science and Technology, Ke Meng Chinese Academy of Sciences, Chunming Zhang Institute of Computing Technology, Chinese Academy of Sciences, Guangming Tan University of Chinese Academy of Sciences DOI | ||
15:10 20mTalk | PIM-zd-tree: A Fast Space-Partitioning Index Leveraging Processing-in-Memory Main Conference Yiwei Zhao Carnegie Mellon University, Hongbo Kang Tsinghua University, Ziyang Men University of California, Riverside, Yan Gu University of California, Riverside, Guy E. Blelloch Carnegie Mellon University, Laxman Dhulipala University of Maryland, College Park, Charles McGuffey Reed College, Phil Gibbons Carnegie Mellon University DOI | ||