Publications

Publications

1. AI Powered Compiler Techniques for DL Code Optimization [paper]

   • Sanket Tavarageri, Gagandeep Goyal, Sasikanth Avancha, Bharat Kaul, Ramakrishna Upadrasta arXiv:2104.05573, April 2021

2. PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives [paper][talk]

   • Sanket Tavarageri, Alexander Heinecke, Sasikanth Avancha, Bharat Kaul, Gagandeep Goyal, Ramakrishna Upadrasta In ACM Transactions on Architecture and Code Optimization (TACO). Presented at High Performance and Embedded Architecture and Compilation (HiPEAC) conference, January 2021

3. Automatic Model Parallelism for Deep Neural Networks with Compiler and Hardware Support [paper]

   • Sanket Tavarageri, Srinivas Sridharan, Bharat Kaul arXiv:1906.08168, June 2019

4. Categorization of Program Regions for Agile Compilation using Machine Learning and Hardware Support [paper]

   • Sanket Tavarageri arXiv:1905.12292, May 2019

5. A Data Analytics Framework for Aggregate Data Analysis [paper]

   • Sanket Tavarageri, Nag Mani, Anand Ramasubramanian, Jaskiran Kalsi arXiv:1809.05877, September 2018

6. A Medical Price Prediction System using Hierarchical Decision Trees [paper][talk]

   • Anuja Tike, Sanket Tavarageri In the IEEE International Conference on Big Data (Big Data), December 2017, Boston, MA

7. Compiler Support for Software Cache Coherence [paper][talk]

   • Sanket Tavarageri, Wooil Kim, Josep Torrellas, P Sadayappan In the IEEE International Conference on High Performance Computing, Data, and Analytics (HiPC), December 2016, Hyderabad, India

8. Architecting and Programming an Incoherent Multiprocessor Cache Hierarchy [paper]

   • Wooil Kim, Sanket Tavarageri, P Sadayappan, Josep Torrellas In the International Parallel and Distributed Processing Symposium (IPDPS), May 2016, Chicago, IL

9. Automatic Code Generation for an Asynchronous Task-based Runtime [paper]

   • Muthu Baskaran, Benoit Meister, Tom Henretty, Sanket Tavarageri, Benoit Pradelle, Athanasios Konstantinidis, and Richard Lethin In the workshop on Runtime Systems for Extreme Scale Programming Models and Architectures (RESPA), November 2015, Austin, TX

10. Automatic Cluster Parallelization and Minimizing Communication via Selective Data Replication [paper][talk]

    • Sanket Tavarageri, Benoît Meister, Muthu Baskaran, Benoît Pradelle, Tom Henretty, Athanasios Konstantinidis, Ann Johnson, Richard Lethin In IEEE High Performance Extreme Computing Conference (HPEC), September 2015, Waltham, MA

11. A Tale of Three Runtimes [paper]

    • Nicolas Vasilache, Muthu Baskaran, Tom Henretty, Benoît Meister, M. Harper Langston, Sanket Tavarageri, Richard Lethin arXiv:1409.1914, September 2014

12. PWCET: Power-Aware Worst Case Execution Time Analysis

    • Wenlei Bao, Sanket Tavarageri, Fusun Ozguner, P Sadayappan In the International Conference on Parallel Processing Workshops (ICCPW), Septem- ber 2014, Minneapolis, MN

13. Compiler-Assisted Detection of Transient Memory Errors [paper][talk]

    • Sanket Tavarageri, Sriram Krishnamoorthy, P. Sadayappan In the ACM SIGPLAN conference on Programming Language Design and Implementation (PLDI), June 2014, Edinburgh, UK

14. A Compiler Analysis to Determine Useful Cache Size for Energy Efficiency [paper][talk]

    • Sanket Tavarageri, P. Sadayappan In the Workshop on High-Performance, Power-Aware Computing (HPPAC), May 2013, Boston, MA

15. Adaptive Parallel Tiled Code Generation and Accelerated Auto-tuning [preprint]

    • Sanket Tavarageri, J. Ramanujam, P. Sadayappan In the International Journal of High Performance Computing Applications (IJHPCA 2013)

16. Dynamic Selection of Tile Sizes [paper][talk]

    • Sanket Tavarageri, Louis-Noel Pouchet, J. Ramanujam, Atanas Rountev, P. Sadayappan In the International Conference on High Performance Computing (HiPC), December 2011, Bangalore, India

17. Parametric Tiling of Affine Loop Nests [paper][talk]

    • Sanket Tavarageri, Albert Hartono, Muthu Baskaran, Louis Noel Pouchet, J. Ramanujam and P. Sadayappan In the Workshop on Compilers for Parallel Computing (CPC), July 2010, Vienna, Austria

18. Parameterized Tiling Revisited [paper][talk]

    • Muthu Manikandan Baskaran, Albert Hartono, Sanket Tavarageri, Tom Henretty, J. Ramanujam, P. Sadayappan In the International Symposium on Code Generation and Optimization (CGO), April 2010, Toronto, Canada

Ph.D Thesis

• Compiler Techniques for High Performance Computing, Energy Efficiency, and Resilience [pdf][talk]

  • PhD thesis, The Ohio State University, 2014