7 papers
Interactive and Urgent HPC: State of the Research
Albert Reuther, William Arndt, Johannes Blaschke +10
When we think of how we use smartphones, e-commerce, collaboration platforms, LLMs, etc., most of our interactions with computers are interactive and often urgent. Similar trends o…
Lincoln AI Computing Survey (LAICS) and Trends
Albert Reuther, Peter Michaleas, Michael Jones +2
In the past year, generative AI (GenAI) models have received a tremendous amount of attention, which in turn has increased attention to computing systems for training and inference…
Scaling Performance of Large Language Model Pretraining
Alexander Interrante-Grant, Carla Varela-Rosa, Suhaas Narayan +2
Large language models (LLMs) show best-in-class performance across a wide range of natural language processing applications. Training these models is an extremely computationally e…
Performance and Numerical Aspects of Decompositional Factorizations with FP64 Floating-Point Emulation in INT8
Piotr Luszczek, Vijay Gadepally, LaToya Anderson +18
Mixing precisions for performance has been an ongoing trend as the modern hardware accelerators started including new, and mostly lower-precision, data formats. The advantage of us…
DBOS Network Sensing: A Web Services Approach to Collaborative Awareness
Sophia Lockton, Jeremy Kepner, Michael Stonebraker +26
DBOS (DataBase Operating System) is a novel capability that integrates web services, operating system functions, and database features to significantly reduce web-deployment effort…
Easy Acceleration with Distributed Arrays
Jeremy Kepner, Chansup Byun, LaToya Anderson +20
High level programming languages and GPU accelerators are powerful enablers for a wide range of applications. Achieving scalable vertical (within a compute node), horizontal (acros…