Zobrazeno 1 - 10
of 66
pro vyhledávání: '"Alexander Heinecke"'
Autor:
Evangelos Georganas, Dhiraj Kalamkar, Sasikanth Avancha, Menachem Adelman, Deepti Aggarwal, Cristina Anderson, Alexander Breuer, Jeremy Bruestle, Narendra Chaudhary, Abhisek Kundu, Denise Kutnick, Frank Laub, Vasimuddin Md, Sanchit Misra, Ramanarayan Mohanty, Hans Pabst, Brian Retford, Barukh Ziv, Alexander Heinecke
Publikováno v:
Frontiers in Applied Mathematics and Statistics, Vol 8 (2022)
During the past decade, novel Deep Learning (DL) algorithms, workloads and hardware have been developed to tackle a wide range of problems. Despite the advances in workload and hardware ecosystems, the programming methodology of DL systems is stagnan
Externí odkaz:
https://doaj.org/article/0ca258dcbf0f493b97c2c2aef3829f43
Autor:
Rui Ma, Evangelos Georganas, Alexander Heinecke, Sergey Gribok, Andrew Boutros, Eriko Nurvitadhi
Publikováno v:
IEEE Computer Architecture Letters. 21:49-52
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f95be76d6fdc5d451ec40815961dc000
https://doi.org/10.1109/lca.2022.3189207
https://doi.org/10.1109/lca.2022.3189207
Autor:
Narendra Chaudhary, Sanchit Misra, Dhiraj Kalamkar, Alexander Heinecke, Evangelos Georganas, Barukh Ziv, Menachem Adelman, Bharat Kaul
Publikováno v:
2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::327367015c55d8b68223f1412c7e9a3d
https://doi.org/10.1109/ipdpsw55747.2022.00042
https://doi.org/10.1109/ipdpsw55747.2022.00042
Autor:
Alexander Heinecke, Evangelos Georganas, Nesreen K. Ahmed, Dhiraj D. Kalamkar, Vasimuddin, Sasikanth Avancha, Sanchit Misra, Guixiang Ma, Ramanarayan Mohanty
Publikováno v:
SC
Full-batch training on Graph Neural Networks (GNN) to learn the structure of large graphs is a critical problem that needs to scale to hundreds of compute nodes to be feasible. It is challenging due to large memory capacity and bandwidth requirements
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::68b9efba91450ff8075b812045822ddf
https://doi.org/10.1145/3458817.3480856
https://doi.org/10.1145/3458817.3480856
Autor:
Menachem Adelman, Narendra Chaudhary, Dhiraj D. Kalamkar, Barukh Ziv, Bharat Kaul, Sanchit Misra, Alexander Heinecke, Evangelos Georganas
Identifying accessible chromatin regions is a fundamental problem in epigenomics with ATAC-seq being a commonly used assay. Exponential rise in single cell ATAC-seq experiments has made it critical to accelerate processing of ATAC-seq data. ATAC-seq
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a2881cf74d8f1fb3a0dc7ee5bae7313
https://doi.org/10.1101/2021.09.28.462099
https://doi.org/10.1101/2021.09.28.462099
Autor:
Alexander Heinecke, Evangelos Georganas, Sudarshan Srinivasan, Mikhail Shiryaev, Jianping Chen, Dhiraj D. Kalamkar
Publikováno v:
SC
During the last two years, the goal of many researchers has been to squeeze the last bit of performance out of HPC system for AI tasks. Often this discussion is held in the context of how fast ResNet50 can be trained. Unfortunately, ResNet50 is no lo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f0a65805ffc730b5cd6f843ddb44f0b3
https://doi.org/10.1109/sc41405.2020.00047
https://doi.org/10.1109/sc41405.2020.00047
Autor:
Kunal Banerjee, Dhiraj D. Kalamkar, Anand Venkat, Alexander Heinecke, Evangelos Georganas, Sasikanth Avancha, Hans Pabst, Greg Henry, Michael J. Anderson
Publikováno v:
IPDPS
Deep learning (DL) is one of the most prominent branches of machine learning. Due to the immense computational cost of DL workloads, industry and academia have developed DL libraries with highly-specialized kernels for each workload/architecture, lea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8c68182cbd124066c14b7ce4228fcbf
https://doi.org/10.1109/ipdps47924.2020.00032
https://doi.org/10.1109/ipdps47924.2020.00032
Autor:
Kunal Banerjee, Alexander Heinecke, Evangelos Georganas, Dhiraj D. Kalamkar, Barukh Ziv, Cristina S. Anderson, Eden Segal
Publikováno v:
Supercomputing Frontiers and Innovations. 6
Recurrent neural network (RNN) models have been found to be well suited for processing temporal data. In this work, we present an optimized implementation of vanilla RNN cell and its two popular variants: LSTM and GRU for Intel Xeon architecture. Typ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6de19692848930d014bd19b6a9d61f18
https://doi.org/10.14529/jsfi190304
https://doi.org/10.14529/jsfi190304
Autor:
Srinivas Sridharan, Kunal Banerjee, Alexander Heinecke, Evangelos Georganas, Sudarshan Srinivasan, Mikhail E. Smorkalov, Dhiraj D. Kalamkar, Cong Xu
Publikováno v:
CLUSTER
Google’s neural machine translation (GNMT) is state-of-the-art recurrent neural network (RNN/LSTM) based language translation application. It is computationally more demanding than well-studied convolutional neural networks (CNNs). Also, in contras
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7defbfd348ceae64409843479d3aa2ec
https://doi.org/10.1109/cluster.2019.8891019
https://doi.org/10.1109/cluster.2019.8891019
Publikováno v:
ARITH
In recent years fused-multiply-add (FMA) units with lower-precision multiplications and higher-precision accumulation have proven useful in machine learning/artificial intelligence applications, most notably in training deep neural networks due to th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::196d32e095f39fb06edb7b3a9afbc31b
https://doi.org/10.1109/arith.2019.00019
https://doi.org/10.1109/arith.2019.00019