My research interests lie in Computing systems, including high-performance computing and compiler design and their applications in scientific computing, machine learning, data analytics, and numerical optimization. My research focuses on these topics and their real-world applications. I collaborate with my students to design and build computing systems that are efficient and fast for various types of processors, from low-end embedded processors to high-end supercomputers. We also investigate numerical optimization methods and how to scale them up using program and data characteristics.
Kazem Cheshmi is an assistant professor in Electrical and Computer Engineering at McMaster University. He received his B.Eng. degree in computer engineering from the Ferdowsi University of Mashad, an M.A.Sc in computer engineering from the University of Tehran, and a Ph.D. in computer science from the University of Toronto.
Kazem has worked as a researcher at several prestigious institutions, including Microsoft Research, Adobe Research, Concordia University, and Rutgers University. He has received many awards and honors for his research, such as the ACM-IEEE CS George Michael Memorial HPC Fellowship 2020, the grand final award of the 2017 ACM Student Research Competitions, honorable mention in the ACM SIG-HPC 2022 doctoral dissertation award, the Wolfund Fellowship 2019, and the Adobe Fellowship 2018.
High-performance computing; code and loop optimization; performance analysis; compilers and basic code analysis; vectorization; code specialization and irregular computing; parallelism in CPU and GPUs; cache-aware and cache-oblivious algorithms; and runtime systems Three lectures, one tutorial, one lab every other week, first term Prerequisite(s): COMPENG 2SI3, enrolment in Computer Engineering or with permission of the instructor
High-performance computing; code and loop optimization; performance analysis; compilers and basic code analysis; vectorization; code specialization and irregular computing; parallelism in CPU and GPUs; cache-aware and cache-oblivious algorithms; and runtime systems Three lectures, one tutorial, one lab every other week, first term Prerequisite(s): COMPENG 2SI3, enrolment in Computer Engineering or with permission of the instructor
High-performance computing; code and loop optimization; performance analysis; compilers and basic code analysis; vectorization; code specialization and irregular computing; parallelism in CPU and GPUs; cache-aware and cache-oblivious algorithms; and runtime systems Three lectures, one tutorial, one lab every other week, first term Prerequisite(s): COMPENG 2SI3, enrolment in Computer Engineering or with permission of the instructor
This special topic course explores the computational challenges in hyperdimensional computing
Instructor
Dr. Kazem Cheshmi
A computer engineering design and implementation project of reasonable complexity to be completed by small groups of students; oral presentations and written reports. Two lectures, one lab, one tutorial/design studio 1 hour, second term Prerequisite(s): COMPENG 2DX4 or 2DX3, COMPENG 3DQ5, ELECENG 3EJ4, 3TP3 Antirequisite(s): COMPENG 3DR4, ELECENG 3EY4 Co-requisite(s): ELECENG 3CL4, 3TR4
