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
7 papers · 2 filters
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…
High-Performance and Power-Efficient Emulation of Matrix Multiplication using INT8 Matrix Engines
Yuki Uchino, Katsuhisa Ozaki, Toshiyuki Imamura
Recent architectures integrate high-performance and power-efficient matrix engines. These engines demonstrate remarkable performance in low-precision matrix multiplication, which i…
Bine Trees: Enhancing Collective Operations by Optimizing Communication Locality
Daniele De Sensi, Saverio Pasqualoni, Lorenzo Piarulli +5
Communication locality plays a key role in the performance of collective operations on large HPC systems, especially on oversubscribed networks where groups of nodes are fully conn…
RAPTOR: Practical Numerical Profiling of Scientific Applications
Faveo Hoerold, Ivan R. Ivanov, Akash Dhruv +4
The proliferation of low-precision units in modern high-performance architectures increasingly burdens domain scientists. Historically, the choice in HPC was easy: can we get away…
A Unifying Framework to Enable Artificial Intelligence in High Performance Computing Workflows
Jens Domke, Mohamed Wahib, Anshu Dubey +2
Current trends point to a future where large-scale scientific applications are tightly-coupled HPC/AI hybrids. Hence, we urgently need to invest in creating a seamless, scalable fr…
Balanced and Elastic End-to-end Training of Dynamic LLMs
Mohamed Wahib, Muhammed Abdullah Soyturk, Didem Unat
To reduce the computational and memory overhead of Large Language Models, various approaches have been proposed. These include a) Mixture of Experts (MoEs), where token routing aff…