Amir Yazdanbakhsh

GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimation

Oct 11, 2022
Ondrej Sykora, Phitchaya Mangpo Phothilimthana, Charith Mendis, Amir Yazdanbakhsh

Figure 2 for GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimation

Figure 3 for GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimation

Figure 4 for GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimation

* 13 pages; 5 figures; published at IISWC 2022; Included IEEE copyright;

Access Paper or Ask Questions

Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango

Sep 16, 2022
Aman Madaan, Amir Yazdanbakhsh

Figure 2 for Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango

Figure 3 for Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango

Figure 4 for Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango

* 115 pages, 15 figures, and 84 tables. The authors contributed equally. Work done when Aman Madaan was a student researcher at Google Research, Brain Team

Access Paper or Ask Questions

Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask

Sep 15, 2022
Sheng-Chun Kao, Amir Yazdanbakhsh, Suvinay Subramanian, Shivani Agrawal, Utku Evci, Tushar Krishna

Figure 2 for Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask

Figure 3 for Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask

Figure 4 for Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask

* 11 pages, 2 figures, and 9 tables. Published at the ICML Workshop on Sparsity in Neural Networks Advancing Understanding and Practice, 2022. First two authors contributed equally

Access Paper or Ask Questions

Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation

Sep 01, 2022
Amir Yazdanbakhsh, Ashkan Moradifirouzabadi, Zheng Li, Mingu Kang

Figure 2 for Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation

Figure 3 for Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation

Figure 4 for Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputation

* 15 pages; 14 figures; published at MICRO 2022; First three authors contributed equally

Access Paper or Ask Questions

Accelerating Attention through Gradient-Based Learned Runtime Pruning

Apr 15, 2022
Zheng Li, Soroush Ghodrati, Amir Yazdanbakhsh, Hadi Esmaeilzadeh, Mingu Kang

Figure 2 for Accelerating Attention through Gradient-Based Learned Runtime Pruning

Figure 3 for Accelerating Attention through Gradient-Based Learned Runtime Pruning

Figure 4 for Accelerating Attention through Gradient-Based Learned Runtime Pruning

* First three authors contributed equally; published at ISCA 2022

Access Paper or Ask Questions

Data-Driven Offline Optimization For Architecting Hardware Accelerators

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

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 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 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 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

1

2

>>