Siddhisanket Raskar

Orcid: 0000-0002-4832-0834

According to our database1, Siddhisanket Raskar authored at least 15 papers between 2019 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Thorough Characterization and Analysis of Large Transformer Model Training At-Scale.
Proc. ACM Meas. Anal. Comput. Syst., 2024

2023
A Comprehensive Performance Study of Large Language Models on Novel AI Accelerators.
CoRR, 2023

Implementation of Dataflow Software Pipelining for Codelet Model.
Proceedings of the 2023 ACM/SPEC International Conference on Performance Engineering, 2023

Characterizing the Performance of Triangle Counting on Graphcore's IPU Architecture.
Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, 2023

Transfer Learning Across Heterogeneous Features For Efficient Tensor Program Generation.
Proceedings of the 2nd International Workshop on Extreme Heterogeneity Solutions, 2023

Towards Maximum Throughput of Dataflow Software Pipeline under Resource Constraints.
Proceedings of the 14th International Workshop on Programming Models and Applications for Multicores and Manycores, 2023

Codelet Pipe: Realization of Dataflow Software Pipelining for Extended Codelet Model.
Proceedings of the 52nd International Conference on Parallel Processing Workshops, 2023

TrainBF: High-Performance DNN Training Engine Using BFloat16 on AI Accelerators.
Proceedings of the Euro-Par 2023: Parallel Processing - 29th International Conference on Parallel and Distributed Computing, Limassol, Cyprus, August 28, 2023

Towards Fault Tolerance and Resilience in the Sequential Codelet Model.
Proceedings of the High Performance Computing - 10th Latin American Conference, 2023

2022

Throughput-oriented and Accuracy-aware DNN Training with BFloat16 on GPU.
Proceedings of the IEEE International Parallel and Distributed Processing Symposium, 2022

2020
DEMAC: A Modular Platform for HW-SW Co-Design.
Proceedings of the Fourth IEEE/ACM Annual Workshop on Emerging Parallel and Distributed Runtime Systems and Middleware, 2020

CODIR: Towards an MLIR Codelet Model Dialect.
Proceedings of the Fourth IEEE/ACM Annual Workshop on Emerging Parallel and Distributed Runtime Systems and Middleware, 2020

2019
Toward A High-Performance Emulation Platformfor Brain-Inspired Intelligent SystemsExploring Dataflow-Based Execution Model and Beyond.
Proceedings of the 43rd IEEE Annual Computer Software and Applications Conference, 2019

Position Paper: Extending Codelet Model for Dataflow Software Pipelining using Software-Hardware Co-Design.
Proceedings of the 43rd IEEE Annual Computer Software and Applications Conference, 2019


  Loading...