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 Amir Yazdanbakhsh

Amir Yazdanbakhsh

Data-Driven Offline Optimization For Architecting Hardware Accelerators


Oct 20, 2021
Aviral Kumar, Amir Yazdanbakhsh, Milad Hashemi, Kevin Swersky, Sergey Levine

Figure 1 for Data-Driven Offline Optimization For Architecting Hardware Accelerators
Figure 2 for Data-Driven Offline Optimization For Architecting Hardware Accelerators
Figure 3 for Data-Driven Offline Optimization For Architecting Hardware Accelerators
Figure 4 for Data-Driven Offline Optimization For Architecting Hardware Accelerators
* First two authors contributed equally 
  Access Paper or Ask Questions

An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks


Feb 20, 2021
Amir Yazdanbakhsh, Kiran Seshadri, Berkin Akin, James Laudon, Ravi Narayanaswami

Figure 1 for An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks
Figure 2 for An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks
Figure 3 for An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks
Figure 4 for An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks
* 11 pages, 15 figures, submitted to ISCA 2021 
  Access Paper or Ask Questions

Rethinking Co-design of Neural Architectures and Hardware Accelerators


Feb 17, 2021
Yanqi Zhou, Xuanyi Dong, Berkin Akin, Mingxing Tan, Daiyi Peng, Tianjian Meng, Amir Yazdanbakhsh, Da Huang, Ravi Narayanaswami, James Laudon

Figure 1 for Rethinking Co-design of Neural Architectures and Hardware Accelerators
Figure 2 for Rethinking Co-design of Neural Architectures and Hardware Accelerators
Figure 3 for Rethinking Co-design of Neural Architectures and Hardware Accelerators
Figure 4 for Rethinking Co-design of Neural Architectures and Hardware Accelerators

  Access Paper or Ask Questions

Apollo: Transferable Architecture Exploration


Feb 02, 2021
Amir Yazdanbakhsh, Christof Angermueller, Berkin Akin, Yanqi Zhou, Albin Jones, Milad Hashemi, Kevin Swersky, Satrajit Chatterjee, Ravi Narayanaswami, James Laudon

Figure 1 for Apollo: Transferable Architecture Exploration
Figure 2 for Apollo: Transferable Architecture Exploration
Figure 3 for Apollo: Transferable Architecture Exploration
Figure 4 for Apollo: Transferable Architecture Exploration
* 10 pages, 5 figures, Accepted to Workshop on ML for Systems at the 34th Conference on Neural Information Processing Systems (NeurIPS 2020) 
  Access Paper or Ask Questions

Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation


Jan 23, 2020
Byung Hoon Ahn, Prannoy Pilligundla, Amir Yazdanbakhsh, Hadi Esmaeilzadeh

Figure 1 for Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
Figure 2 for Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
Figure 3 for Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
Figure 4 for Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
* Published as a conference paper at ICLR 2020. arXiv admin note: text overlap with arXiv:1905.12799 
  Access Paper or Ask Questions

ReLeQ: An Automatic Reinforcement Learning Approach for Deep Quantization of Neural Networks


Dec 10, 2018
Amir Yazdanbakhsh, Ahmed T. Elthakeb, Prannoy Pilligundla, FatemehSadat Mireshghallah, Hadi Esmaeilzadeh

Figure 1 for ReLeQ: An Automatic Reinforcement Learning Approach for Deep Quantization of Neural Networks
Figure 2 for ReLeQ: An Automatic Reinforcement Learning Approach for Deep Quantization of Neural Networks
Figure 3 for ReLeQ: An Automatic Reinforcement Learning Approach for Deep Quantization of Neural Networks
Figure 4 for ReLeQ: An Automatic Reinforcement Learning Approach for Deep Quantization of Neural Networks

  Access Paper or Ask Questions

ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks


Nov 05, 2018
Ahmed T. Elthakeb, Prannoy Pilligundla, Amir Yazdanbakhsh, Sean Kinzer, Hadi Esmaeilzadeh

Figure 1 for ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
Figure 2 for ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
Figure 3 for ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
Figure 4 for ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks

  Access Paper or Ask Questions

GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks


May 10, 2018
Amir Yazdanbakhsh, Hajar Falahati, Philip J. Wolfe, Kambiz Samadi, Nam Sung Kim, Hadi Esmaeilzadeh

Figure 1 for GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks
Figure 2 for GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks
Figure 3 for GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks
Figure 4 for GANAX: A Unified MIMD-SIMD Acceleration for Generative Adversarial Networks
* Proceedings of the 45th International Symposium on Computer Architecture (ISCA), 2018 
  Access Paper or Ask Questions