Alert button
Picture for Vivek Sarkar

Vivek Sarkar

Alert button

Advanced Graph-Based Deep Learning for Probabilistic Type Inference

Sep 13, 2020
Fangke Ye, Jisheng Zhao, Vivek Sarkar

Figure 1 for Advanced Graph-Based Deep Learning for Probabilistic Type Inference
Figure 2 for Advanced Graph-Based Deep Learning for Probabilistic Type Inference
Figure 3 for Advanced Graph-Based Deep Learning for Probabilistic Type Inference
Figure 4 for Advanced Graph-Based Deep Learning for Probabilistic Type Inference
Viaarxiv icon

MISIM: An End-to-End Neural Code Similarity System

Jun 15, 2020
Fangke Ye, Shengtian Zhou, Anand Venkat, Ryan Marcus, Nesime Tatbul, Jesmin Jahan Tithi, Paul Petersen, Timothy Mattson, Tim Kraska, Pradeep Dubey, Vivek Sarkar, Justin Gottschlich

Figure 1 for MISIM: An End-to-End Neural Code Similarity System
Figure 2 for MISIM: An End-to-End Neural Code Similarity System
Figure 3 for MISIM: An End-to-End Neural Code Similarity System
Figure 4 for MISIM: An End-to-End Neural Code Similarity System
Viaarxiv icon

Context-Aware Parse Trees

Mar 24, 2020
Fangke Ye, Shengtian Zhou, Anand Venkat, Ryan Marcus, Paul Petersen, Jesmin Jahan Tithi, Tim Mattson, Tim Kraska, Pradeep Dubey, Vivek Sarkar, Justin Gottschlich

Figure 1 for Context-Aware Parse Trees
Figure 2 for Context-Aware Parse Trees
Figure 3 for Context-Aware Parse Trees
Figure 4 for Context-Aware Parse Trees
Viaarxiv icon

MARVEL: A Decoupled Model-driven Approach for Efficiently Mapping Convolutions on Spatial DNN Accelerators

Feb 18, 2020
Prasanth Chatarasi, Hyoukjun Kwon, Natesh Raina, Saurabh Malik, Vaisakh Haridas, Tushar Krishna, Vivek Sarkar

Figure 1 for MARVEL: A Decoupled Model-driven Approach for Efficiently Mapping Convolutions on Spatial DNN Accelerators
Figure 2 for MARVEL: A Decoupled Model-driven Approach for Efficiently Mapping Convolutions on Spatial DNN Accelerators
Figure 3 for MARVEL: A Decoupled Model-driven Approach for Efficiently Mapping Convolutions on Spatial DNN Accelerators
Figure 4 for MARVEL: A Decoupled Model-driven Approach for Efficiently Mapping Convolutions on Spatial DNN Accelerators
Viaarxiv icon