Agastya Seth
  • Blog
  • Resume
  • About Me

Home

The answer to life, universe and everything is 42.14378291...

RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing

Paper Review

Posted on March 18, 2024

RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing [Read More]
Tags: Machine Learning Acceleration Personalized Recommendation Software-Hardware Codesign DNN

Centaur: A Chiplet-based, Hybrid Sparse-Dense Accelerator for Personalized Recommendations

Paper Review

Posted on March 18, 2024

Centaur: A Chiplet-based, Hybrid Sparse-Dense Accelerator for Personalized Recommendations [Read More]
Tags: Machine Learning Acclerator Design Personalized Recommendation FPGA Software-Hardware Codesign DNN

HyPar: Towards Hybrid Parallelism for Deep Learning Accelerator Array

Paper Review

Posted on February 26, 2024

HyPar: Towards Hybrid Parallelism for Deep Learning Accelerator Array [Read More]
Tags: ML Acceleration Deep Learning Parallel Computing Distributed Processing

Distributed Deep Learning Using Synchronous Stochastic Gradient Descent

Paper Review

Posted on February 26, 2024

Distributed Deep Learning Using Synchronous Stochastic Gradient Descent [Read More]
Tags: ML Acceleration SGD Deep Learning CNN Distributed Processing

SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning

Paper Review

Posted on February 17, 2024

SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning [Read More]
Tags: ML Acceleration NLP Transformers Attention Deep Learning
  • Older Posts →
  • RSS
  • Email me
  • LinkedIn
  • GitHub
  • Soundcloud
  • Facebook
  • Twitter
  • Spotify

Agastya Seth  •  2025