VEXIR2Vec: An Architecture-Neutral Embedding Framework for Binary Similarity

no code implementations • 1 Dec 2023 • S. VenkataKeerthy, Yashas Andaluri, Sayan Dey, Soumya Banerjee, Ramakrishna Upadrasta

We show results on several standard projects and on real-world vulnerabilities.

The Next 700 ML-Enabled Compiler Optimizations

1 code implementation • 17 Nov 2023 • S. VenkataKeerthy, Siddharth Jain, Umesh Kalvakuntla, Pranav Sai Gorantla, Rajiv Shailesh Chitale, Eugene Brevdo, Albert Cohen, Mircea Trofin, Ramakrishna Upadrasta

There is a growing interest in enhancing compiler optimizations with ML models, yet interactions between compilers and ML frameworks remain challenging.

POSET-RL: Phase ordering for Optimizing Size and Execution Time using Reinforcement Learning

no code implementations • 27 Jul 2022 • Shalini Jain, Yashas Andaluri, S. VenkataKeerthy, Ramakrishna Upadrasta

We observe that the proposed model based on ODG outperforms the current Oz sequence both in terms of size and execution time by 6. 19% and 11. 99% in SPEC 2017 benchmarks, on an average.

reinforcement-learning Reinforcement Learning (RL)

RL4ReAl: Reinforcement Learning for Register Allocation

no code implementations • 5 Apr 2022 • S. VenkataKeerthy, Siddharth Jain, Anilava Kundu, Rohit Aggarwal, Albert Cohen, Ramakrishna Upadrasta

We aim to automate decades of research and experience in register allocation, leveraging machine learning.

Hierarchical Reinforcement Learning Multi-agent Reinforcement Learning +2

IR2Vec: LLVM IR based Scalable Program Embeddings

1 code implementation • 13 Sep 2019 • S. VenkataKeerthy, Rohit Aggarwal, Shalini Jain, Maunendra Sankar Desarkar, Ramakrishna Upadrasta, Y. N. Srikant

As our infrastructure is based on the Intermediate Representation (IR) of the source code, obtained embeddings are both language and machine independent.

Representation Learning