TabConv: Low-Computation CNN Inference via Table Lookups

1 code implementation • 8 Apr 2024 • Neelesh Gupta, Narayanan Kannan, Pengmiao Zhang, Viktor Prasanna

TabConv preserves over 93% of the original model's performance while reducing arithmetic operations by 36. 5%, 25. 8%, and 99. 4% for ResNet-18 on CIFAR-10, CIFAR-100, and MNIST, respectively, 35. 6% and 99. 3% for ResNet-34 on CIFAR-10 and MNIST, and 98. 9% for NIN on MNIST, achieving low-computation inference.

PaCKD: Pattern-Clustered Knowledge Distillation for Compressing Memory Access Prediction Models

1 code implementation • 21 Feb 2024 • Neelesh Gupta, Pengmiao Zhang, Rajgopal Kannan, Viktor Prasanna

Deep neural networks (DNNs) have proven to be effective models for accurate Memory Access Prediction (MAP), a critical task in mitigating memory latency through data prefetching.

Image Classification Knowledge Distillation

Attention, Distillation, and Tabularization: Towards Practical Neural Network-Based Prefetching

no code implementations • 23 Dec 2023 • Pengmiao Zhang, Neelesh Gupta, Rajgopal Kannan, Viktor K. Prasanna

DART accelerates the large model inference by 170x and the distilled model by 9. 4x.