Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Gianinazzi, Lukas"'
Autor:
Besta, Maciej, Scheidl, Florian, Gianinazzi, Lukas, Klaiman, Shachar, Müller, Jürgen, Hoefler, Torsten
Higher-order graph neural networks (HOGNNs) are an important class of GNN models that harness polyadic relations between vertices beyond plain edges. They have been used to eliminate issues such as over-smoothing or over-squashing, to significantly e
Externí odkaz:
http://arxiv.org/abs/2406.12841
Autor:
Luczynski, Piotr, Gianinazzi, Lukas, Iff, Patrick, Wilson, Leighton, De Sensi, Daniele, Hoefler, Torsten
Efficient Reduce and AllReduce communication collectives are a critical cornerstone of high-performance computing (HPC) applications. We present the first systematic investigation of Reduce and AllReduce on the Cerebras Wafer-Scale Engine (WSE). This
Externí odkaz:
http://arxiv.org/abs/2404.15888
Autor:
Baumann, Yves, Ben-Nun, Tal, Besta, Maciej, Gianinazzi, Lukas, Hoefler, Torsten, Luczynski, Piotr
Publikováno v:
IEEE International Parallel and Distributed Processing Symposium, IPDPS 2024, San Francisco, CA, USA, May 27-31 (2024) 180-192
Contemporary accelerator designs exhibit a high degree of spatial localization, wherein two-dimensional physical distance determines communication costs between processing elements. This situation presents considerable algorithmic challenges, particu
Externí odkaz:
http://arxiv.org/abs/2404.12953
Autor:
Gianinazzi, Lukas, Ziogas, Alexandros Nikolaos, Huang, Langwen, Luczynski, Piotr, Ashkboos, Saleh, Scheidl, Florian, Carigiet, Armon, Ge, Chio, Abubaker, Nabil, Besta, Maciej, Ben-Nun, Tal, Hoefler, Torsten
Publikováno v:
PPoPP'24: Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (2024) 404-416
We propose a novel approach to iterated sparse matrix dense matrix multiplication, a fundamental computational kernel in scientific computing and graph neural network training. In cases where matrix sizes exceed the memory of a single compute node, d
Externí odkaz:
http://arxiv.org/abs/2402.19364
Autor:
Besta, Maciej, Memedi, Florim, Zhang, Zhenyu, Gerstenberger, Robert, Piao, Guangyuan, Blach, Nils, Nyczyk, Piotr, Copik, Marcin, Kwaśniewski, Grzegorz, Müller, Jürgen, Gianinazzi, Lukas, Kubicek, Ales, Niewiadomski, Hubert, O'Mahony, Aidan, Mutlu, Onur, Hoefler, Torsten
The field of natural language processing (NLP) has witnessed significant progress in recent years, with a notable focus on improving large language models' (LLM) performance through innovative prompting techniques. Among these, prompt engineering cou
Externí odkaz:
http://arxiv.org/abs/2401.14295
The generation of initial conditions via accurate data assimilation is crucial for weather forecasting and climate modeling. We propose DiffDA as a denoising diffusion model capable of assimilating atmospheric variables using predicted states and spa
Externí odkaz:
http://arxiv.org/abs/2401.05932
Autor:
Besta, Maciej, Catarino, Afonso Claudino, Gianinazzi, Lukas, Blach, Nils, Nyczyk, Piotr, Niewiadomski, Hubert, Hoefler, Torsten
Publikováno v:
Proceedings of Learning on Graphs (LOG), 2023
Many graph representation learning (GRL) problems are dynamic, with millions of edges added or removed per second. A fundamental workload in this setting is dynamic link prediction: using a history of graph updates to predict whether a given pair of
Externí odkaz:
http://arxiv.org/abs/2311.18526
Autor:
Besta, Maciej, Blach, Nils, Kubicek, Ales, Gerstenberger, Robert, Podstawski, Michal, Gianinazzi, Lukas, Gajda, Joanna, Lehmann, Tomasz, Niewiadomski, Hubert, Nyczyk, Piotr, Hoefler, Torsten
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence 2024 (AAAI'24)
We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts (ToT). The key idea and primary advantage of GoT is
Externí odkaz:
http://arxiv.org/abs/2308.09687
Execution graphs of parallel loop programs exhibit a nested, repeating structure. We show how such graphs that are the result of nested repetition can be represented by succinct parametric structures. This parametric graph template representation all
Externí odkaz:
http://arxiv.org/abs/2307.08420
Dataflow devices represent an avenue towards saving the control and data movement overhead of Load-Store Architectures. Various dataflow accelerators have been proposed, but how to efficiently schedule applications on such devices remains an open pro
Externí odkaz:
http://arxiv.org/abs/2306.02730