1.2k citations
- RIKENJP148 papers
- RIKEN Center for Emergent Matter ScienceJP121 papers
- The University of TokyoJP79 papers
- RIKEN Center for Quantum Computing45 papers
- Kobe UniversityJP40 papers
- Tokyo Institute of TechnologyJP39 papers
- University of TsukubaJP39 papers
- The University of OsakaJP36 papers
- Pioneer (Japan)JP35 papers
- University of EdinburghGB33 papers
- Tokyo University of ScienceJP32 papers
- Kyoto UniversityJP27 papers
34 papers · 1 filter
Multi-GPU Communication Schemes for Iterative Solvers: When CPUs are Not in Charge
Ismayil Ismayilov, Javid Baydamirli, Doğan Sağbili +2
This paper proposes a fully autonomous execution model for multi-GPU applications that completely excludes the involvement of the CPU beyond the initial kernel launch. In a typical…
LLMTailor: A Layer-wise Tailoring Tool for Efficient Checkpointing of Large Language Models
Minqiu Sun, Xin Huang, Luanzheng Guo +3
Checkpointing is essential for fault tolerance in training large language models (LLMs). However, existing methods, regardless of their I/O strategies, periodically store the entir…
Scrutinizing Variables for Checkpoint Using Automatic Differentiation
Xin Huang, Weiping Zhang, Shiman Meng +4
Checkpoint/Restart (C/R) saves the running state of the programs periodically, which consumes considerable system resources. We observe that not every piece of data is involved in…
Distributed Order Recording Techniques for Efficient Record-and-Replay of Multi-threaded Programs
Xiang Fu, Shiman Meng, Weiping Zhang +6
After all these years and all these other shared memory programming frameworks, OpenMP is still the most popular one. However, its greater levels of non-deterministic execution mak…
Learning-Augmented Performance Model for Tensor Product Factorization in High-Order FEM
Xuanzhengbo Ren, Yuta Kawai, Tetsuya Hoshino +4
Accurate performance prediction is essential for optimizing scientific applications on modern high-performance computing (HPC) architectures. Widely used performance models primari…
Emulation of Complex Matrix Multiplication based on the Chinese Remainder Theorem
Yuki Uchino, Qianxiang Ma, Toshiyuki Imamura +2
Modern computing architectures feature low-precision matrix multiplication units that achieve substantially higher throughput than their high-precision counterparts. Motivated by t…