I am a PhD student candidate at ParaMathics lab, Rutgers university University of Toronto, working under supervision of Prof. Maryam Mehri Dehnavi. My research area includes numerical methods, compiler optimization, sparse computations, and parallel programming.
"NASOQ: Numercally Accurate Sparsity-Oriented QP Solver" is accepted in SIGGRAPH20 pre-print.
Our work titled "Decoupling Structure Analysis in Hierarchical Matrix Approximations" will be presented in 2020 SIAM conference on Parallel Processing for Scientific Computing SIAM-PP'20.
I have been awarded the Platform Computing Graduate Fellowship in Computer Science.
Our paper titled "MatRox: Modular approach for improving data locality in Hierarchical Matrix AppRoximation" is accepted in PPoPP'20.
recieved SIGPLAN PAC Grants to attend PLDI 2019.
Will do an internship in Microsoft research, WA this summer.
Our paper titled "Sparse Computation Data Dependence Simplification for Efficient Compiler-Generated Inspectors" is accepted in PLDI'19
Compiler optimization and domain specific languages.
Numerical methods and sparse computations.
Parallel programming and architectures.
Formal verification methods.
“You can do anything you set your mind to.” - Benjamin Franklin
K. Cheshmi, S. Kamil, M. M. Strout, and M. M. Dehnavi, "Sympiler: Transforming Sparse Matrix Codes by Decoupling Symbolic Analysis," In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC'17). (First place in ACM SRC Grand Finals)BibTex Code Presentation
Kazem Cheshmi, Danny M. Kaufman, Shoaib Kamil, and Maryam Mehri
Dehnavi. 2020. NASOQ: Numerically Accurate Sparsity-Oriented QP Solver.
ACM Transactions on Graphics (SIGGRAPH'20). Code
K. Cheshmi, S. Kamil, M. M. Strout, and M. M. Dehnavi, "ParSy: inspection and transformation of sparse matrix computations for parallelism," In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC'18). BibTex Code Presentation
Bangtian Liu, Kazem Cheshmi, Saeed Soori, Michelle Mills Strout, Maryam Mehri Dehnavi, "MatRox: Modular approach for improving data locality in Hierarchical (Mat) rix App (Rox) imation," In Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP'20). (Co-first author) BibTex Code
Mahdi Soltan Mohammadi, Tomofumi Yuki, Kazem Cheshmi, Eddie C Davis, Mary Hall, Maryam Mehri Dehnavi, Payal Nandy, Catherine Olschanowsky, Anand Venkat, Michelle Mills Strout, "Sparse computation data dependence simplification for efficient compiler-generated inspectors," In Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI'19). BibTex Code