CSE IITK PROSPAR Research Group

Research

Our group works on research problems to help build efficient and correct parallel software. We work on problems ranging from static and dynamic program analysis for correctness of multithreaded programs to automated checking for performance problems on CPU, GPU, and heterogeneous architectures. Our work involves applying concepts at the interface of Programming Languages, Compilers and Runtime systems, Program Analysis, Operating Systems, and Computer Architecture, and involves building prototypes to demonstrate the feasibility of our ideas.

Our group is looking for good PhD/MS(R) students who are motivated to do research in the general area of programming languages and parallel software systems.

Recent Publications

MICRO 2024 Leveraging Cache Coherence to Detect and Repair False Sharing On-the-fly
EMSOFT 2022 An MILP Encoding for Efficient Verification of Quantized Deep Neural Networks
PMAM 2022 Efficient Data Race Detection of Async-Finish Programs Using Vector Clocks
arXiv 2021 Predictive Data Race Detection for GPUs
EMSOFT 2021 Thermal-aware Adaptive Platform Management for Heterogeneous Embedded Systems
DUAC 2021 Explaining the Performance of Supervised and Semi-Supervised Methods for Automated Sparse Matrix Format Selection
arXiv 2021 Neat: Low-Complexity, Efficient On-Chip Cache Coherence

Click here to see a detailed list of publications.

Current Members

    PhD     MTech/Dual Degree     MS(R)

Click here to know more about our group members.

Funding

Our student members have been awarded scholarships like TCS RSP and QIF Fellowship.