Publications

(For a full list see below or go to Google Scholar, dblp)

PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives

Sanket Tavarageri, Alexander Heinecke, Sasikanth Avancha, Gagandeep Goyal, Ramakrishna Upadrasta, Bharat Kaul

arXiv2020

arXiv    

PolyScientist: Automatic Loop Transformations Combined with Microkernels for Optimization of Deep Learning Primitives

Sanket Tavarageri, Alexander Heinecke, Sasikanth Avancha, Gagandeep Goyal, Ramakrishna Upadrasta, Bharat Kaul

arXiv2020

arXiv    

IR2Vec: A Flow Analysis based Scalable Infrastructure for Program Encodings

S. VenkataKeerthy, Rohit Aggarwal, Shalini Jain, Maunendra Desarkar, Ramakrishna Upadrasta and Y. N. Srikant

ACM Transactions on Architecture and Code Optimization (TACO)2020

arXiv    

LLOV: A Fast Static Data-Race Checker for OpenMP Programs

Utpal Bora, Santanu Das, Pankaj Kukreja, Saurabh Joshi, Ramakrishna Upadrasta, Sanjay Rajopadhye

ACM Transactions on Architecture and Code Optimization (TACO)2020

arXiv     Github

Some Improvements to Branch Probability Information (BPI)

Akash Banerjee, Rohit Aggarwal, S. VenkataKeerthy and Ramakrishna Upadrasta

Poster in European LLVM Developers’ Meeting2020

LLOV: A Fast Static Data-Race Checker for OpenMP Programs

Utpal Bora, Santanu Das, Pankaj Kukreja, Saurabh Joshi, Ramakrishna Upadrasta and Sanjay Rajopadhye

Technical talk in the Fourth LLVM Performance Workshop at CGO2020

Slides    

An analysis of executable size reduction by LLVM passes

Shalini Jain, Utpal Bora, Prateek Kumar, Vaibhav B Sinha, Suresh Purini and Ramakrishna Upadrasta

CSI Transactions on ICT2019

Paper    

Polyhedral Model Guided Automatic GPU Cache Exploitation Framework

Abhishek A Patwardhan & Ramakrishna Upadrasta

17th International Conference on High Performance Computing & Simulation (HPCS 2019) Special CADO session, Dublin, Ireland2019

  Github

Some Efficient Algorithms for the Tightest UTVPI Polyhedral Over-Approximation Problem

Abhishek A Patwardhan & Ramakrishna Upadrasta

9th International Workshop on Polyhedral Compilation Techniques In conjunction with HiPEAC 2019 Valencia, Spain2019

Paper     Github

Exploting GPU caches By Polyhedral Compilation

Abhishek A Patwardhan & Ramakrishna Upadrasta

Talk in OMASE 2019 (co-located with CGO 2019), Washington DC, USA (Virtual/online talk was given)2019

P4LLVM: An LLVM Based P4 Compiler

Tharun Kumar. D, S. VenkataKeerthy and Ramakrishna Upadrasta

P4WE workshop in International Conference on Network Protocols (ICNP)2018

Paper     Github

ISL Memory Management Using Clang Static Analyzer

Malhar Thakkar, Ramakrishna Upadrasta

Lightning talk in US LLVM Developers’ Meeting2018

Video    

An LLVM based Loop Profiler

Shalini Jain, Kamlesh Kumar, Suresh Purini, Dibyendu Das and Ramakrishna Upadrasta

Poster and Lightning talk in US LLVM Developers’ Meeting2017

Video   Slides  

When Polyhedral Optimizations Meet Deep Learning Kernels

Hrishikesh Vaidya, Akilesh B, Abhishek A Patwardhan, Ramakrishna Upadrasta

Poster in IEEE International Conference on High Performance Computing, Jaipur, India2017

Won best poster award

Paper    

Enabling Polyhedral optimizations in TensorFlow through Polly

Annanay Agarwal, Michael Kruse, Brian Retford, Tobias Grosser and Ramakrishna Upadrasta

Lightning talk in US LLVM Developers’ Meeting2017

Improved Loop Distribution in LLVM using Polyhedral Dependences

Tharun Kumar Dangeti, Utpal Bora, Santanu Das, Tobias Grosser and Ramakrishna Upadrasta

Lightning talk in Workshop on the LLVM Compiler Infrastructure in HPC (in SC 2017)2017

Slides    

Implementation of a Cache Miss Calculator in LLVM/Polly

Keyur Joshi, Ramakrishna Upadrasta, and Albert Cohen

Lightning talk in Workshop on the LLVM Compiler Infrastructure in HPC (in SC 2017)2017

Slides    

Texturizing PPCG: Supporting Texture Memory in a Polyhedral Compiler

Abhishek A Patwardhan & Ramakrishna Upadrasta

Poster in IEEE International Conference on High Performance Computing, Hyderabad, India2016

Won best poster award

Paper    

A Comparative Study of Vectorization in Compilers

Santanu Das, D. Tharun Kumar, Utpal Bora, Ramakrishna Upadrasta

Poster in IEEE International Conference on High Performance Computing, Hyderabad, India2016

Won best poster award

Slides    

Polly as an Analysis pass in LLVM

Utpal Bora, Johannes Doerfert, Tobias Grosser,Venugopal Raghavan and Ramakrishna Upadrasta

Poster and Lightning talk in US LLVM Developers’ Meeting2016

Slides    

Reducing the Computational Complexity of RegionInfo

Nandini Singhal, Pratik Bhatu, Aditya Kumar, Tobias Grosser, Ramakrishna Upadrasta

Poster and Lightning talk in US LLVM Developers’ Meeting2016

Video   Slides