Modern LLVM mapping of sequential code to task-/data-flow models

The high-level goal is to develop technology to enable more C++ applications to run well on many-core architectures such as recent AMD CPUs, GPUs, and combinations thereof (APUs). We expect to improve the capabilities of compilers like clang/LLVM to identify task-level parallelization opportunities that are not able to be identified today.

Faculty Supervisor:

Angela Demke Brown

Student:

Partner:

AMD Canada

Discipline:

Computer science

Sector:

Manufacturing; Professional, scientific and technical services

University:

University of Toronto

Program:

Accelerate

Current openings

Find the perfect opportunity to put your academic skills and knowledge into practice!

Find Projects