Selected Talks

1. (De/Re)-Composition of Data-Parallel Computations via Multi-Dimensional Homomorphisms
   ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2024); Copenhagen, Denmark
   Slides

2. Linalg vs MDH: A Comparison of two MLIR Dialects
   European LLVM Developers’ Meeting (EuroLLVM 2024); Vienna, Austria
   Slides

3. Code Generation & Optimization for Deep-Learning Computations via Multi-Dimensional Homomorphisms
   Compilers for Machine Learning (C4ML 2024); Edinburgh, Scotland
   Slides

4. Array Programming via Multi-Dimensional Homomorphisms
   ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2023); Orlando FL, USA
   Slides Talk

5. (De/Re)-Compositions Expressed Systematically via MDH-Based Schedules
   ACM SIGPLAN International Conference on Compiler Construction (CC 2023); Montreal, Canada
   Slides

6. Auto-Tuning Framework (ATF)
   Generic Autotuning Technology for GPU Applications (Lorentz Center 2022); Leiden, Netherlands
   Slides

7. Efficient Auto-Tuning of Parallel Programs with Interdependent Tuning Parameters via Auto-Tuning Framework (ATF)
   International Conference on High-Performance Embedded Architectures and Compilers (HiPEAC 2021); online event
   Slides Talk

8. Using MLIR for Multi-Dimensional Homomorphisms
   Google SIG MLIR Open Design Meeting 2020; online event
   Slides Talk

9. md_stencil: High-Performance Stencil Computations on CPU and GPU via Multi-Dimensional Homomorphisms
   International Conference on Parallel Architectures and Compilation Techniques (PACT 2020); online event
   Slides Talk

10. Multi-Dimensional Homomorphisms and Their Implementation in OpenCL
    NVIDIA Deep Learning Compiler Team 2020; online event
    Slides

11. md_poly: A Performance-Portable Polyhedral Compiler Based on Multi-Dimensional Homomorphisms
    IEEE/ACM International Symposium on Code Generation and Optimization (CGO 2020); San Diego CA, USA
    Slides

12. md_poly: A Performance-Portable Polyhedral Compiler Based on Multi-Dimensional Homomorphisms
    International Workshop on Polyhedral Compilation Techniques (IMPACT 2020); Bologna, Italy
    Slides

13. Performance, Portability, and Productivity for Data-Parallel Applications on Multi- and Many-Core Architectures
    The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2019); Denver CO, USA
    Slides

14. Performance, Portability, and Productivity for Data-Parallel Applications on Multi- and Many-Core Architectures
    ACM SIGPLAN conference on Systems, Programming, Languages, and Applications: Software for Humanity (SPLASH 2019); Athens, Greece
    Slides

15. Generating Portable High-Performance Code via Multi-Dimensional Homomorphisms
    International Conference on Parallel Architectures and Compilation Techniques (PACT 2019); Seattle WA, USA
    Slides

16. OCAL: An Abstraction for Host- Code Programming with OpenCL and CUDA
    IEEE International Conference on Parallel and Distributed Systems (ICPADS 2018); Singapore
    Slides

17. High-Performance Probabilistic Record Linkage via Multi-Dimensional Homomorphisms
    ACM/SIGAPP Symposium On Applied Computing (SAC 2018); Limassol, Cyprus
    Slides

18. ATF: A Generic Auto-Tuning Framework
    International Symposium on High-Level Parallel Programming and Applications (HLPP 2017); Valladolid, Spain
    Slides

19. ATF: A Generic Auto-Tuning Framework
    IEEE International Conference on High Performance Computing and Communications (HPCC 2017); Bangkok, Thailand
    Slides

20. Multi-Dimensional Homomorphisms and Their Implementation in OpenCL
    International Symposium on High-Level Parallel Programming and Applications (HLPP 2016); Muenster, Germany
    Slides