Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Alexander Heinecke

Alexander Heinecke
Alert button

FP8 Formats for Deep Learning


Sep 12, 2022
Paulius Micikevicius, Dusan Stosic, Neil Burgess, Marius Cornea, Pradeep Dubey, Richard Grisenthwaite, Sangwon Ha, Alexander Heinecke, Patrick Judd, John Kamalu, Naveen Mellempudi, Stuart Oberman, Mohammad Shoeybi, Michael Siu, Hao Wu

Add code
Alert button

Figure 1 for FP8 Formats for Deep Learning
Figure 2 for FP8 Formats for Deep Learning
Figure 3 for FP8 Formats for Deep Learning
Figure 4 for FP8 Formats for Deep Learning

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

FPGA-based AI Smart NICs for Scalable Distributed AI Training Systems


Apr 22, 2022
Rui Ma, Evangelos Georganas, Alexander Heinecke, Andrew Boutros, Eriko Nurvitadhi

Add code
Alert button

Figure 1 for FPGA-based AI Smart NICs for Scalable Distributed AI Training Systems
Figure 2 for FPGA-based AI Smart NICs for Scalable Distributed AI Training Systems
Figure 3 for FPGA-based AI Smart NICs for Scalable Distributed AI Training Systems
Figure 4 for FPGA-based AI Smart NICs for Scalable Distributed AI Training Systems
* 5 pages, 4 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks


Apr 16, 2021
Vasimuddin Md, Sanchit Misra, Guixiang Ma, Ramanarayan Mohanty, Evangelos Georganas, Alexander Heinecke, Dhiraj Kalamkar, Nesreen K. Ahmed, Sasikanth Avancha

Add code
Alert button

Figure 1 for DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks
Figure 2 for DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks
Figure 3 for DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks
Figure 4 for DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Efficient and Generic 1D Dilated Convolution Layer for Deep Learning


Apr 16, 2021
Narendra Chaudhary, Sanchit Misra, Dhiraj Kalamkar, Alexander Heinecke, Evangelos Georganas, Barukh Ziv, Menachem Adelman, Bharat Kaul

Add code
Alert button

Figure 1 for Efficient and Generic 1D Dilated Convolution Layer for Deep Learning
Figure 2 for Efficient and Generic 1D Dilated Convolution Layer for Deep Learning
Figure 3 for Efficient and Generic 1D Dilated Convolution Layer for Deep Learning
Figure 4 for Efficient and Generic 1D Dilated Convolution Layer for Deep Learning

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning Workloads


Apr 14, 2021
Evangelos Georganas, Dhiraj Kalamkar, Sasikanth Avancha, Menachem Adelman, Cristina Anderson, Alexander Breuer, Narendra Chaudhary, Abhisek Kundu, Vasimuddin Md, Sanchit Misra, Ramanarayan Mohanty, Hans Pabst, Barukh Ziv, Alexander Heinecke

Add code
Alert button

Figure 1 for Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning Workloads
Figure 2 for Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning Workloads
Figure 3 for Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning Workloads
Figure 4 for Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning Workloads

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives


Jun 02, 2020
Sanket Tavarageri, Alexander Heinecke, Sasikanth Avancha, Gagandeep Goyal, Ramakrishna Upadrasta, Bharat Kaul

Add code
Alert button

Figure 1 for PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives
Figure 2 for PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives
Figure 3 for PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives
Figure 4 for PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives
* arXiv admin note: substantial text overlap with arXiv:2002.02145 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Optimizing Deep Learning Recommender Systems' Training On CPU Cluster Architectures


May 10, 2020
Dhiraj Kalamkar, Evangelos Georganas, Sudarshan Srinivasan, Jianping Chen, Mikhail Shiryaev, Alexander Heinecke

Add code
Alert button

Figure 1 for Optimizing Deep Learning Recommender Systems' Training On CPU Cluster Architectures
Figure 2 for Optimizing Deep Learning Recommender Systems' Training On CPU Cluster Architectures
Figure 3 for Optimizing Deep Learning Recommender Systems' Training On CPU Cluster Architectures
Figure 4 for Optimizing Deep Learning Recommender Systems' Training On CPU Cluster Architectures

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

PolyScientist: Automatic Loop Transformations Combined with Microkernels for Optimization of Deep Learning Primitives


Feb 06, 2020
Sanket Tavarageri, Alexander Heinecke, Sasikanth Avancha, Gagandeep Goyal, Ramakrishna Upadrasta, Bharat Kaul

Add code
Alert button

Figure 1 for PolyScientist: Automatic Loop Transformations Combined with Microkernels for Optimization of Deep Learning Primitives
Figure 2 for PolyScientist: Automatic Loop Transformations Combined with Microkernels for Optimization of Deep Learning Primitives
Figure 3 for PolyScientist: Automatic Loop Transformations Combined with Microkernels for Optimization of Deep Learning Primitives
Figure 4 for PolyScientist: Automatic Loop Transformations Combined with Microkernels for Optimization of Deep Learning Primitives

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>