Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore advanced GPU kernel optimization strategies for high-performance finite element computations in this technical workshop presentation from the MFEM community workshop. Discover how to leverage MFEM's GPU abstraction layer to achieve optimal performance on both AMD and NVIDIA GPUs, with practical insights drawn from the Cascadia application code development process. Learn specific techniques for navigating compiler possibilities and unlocking architectural opportunities to enhance computational efficiency in scientific simulations. Gain understanding of the collaborative optimization journey that transforms finite element method implementations for high-performance computing environments, featuring real-world examples and performance enhancement strategies developed through joint research efforts across multiple institutions.
