Antoine Buttier
I'm a student at the École Polytechnique Fédérale de Lausanne (EPFL). I'm currently pursuing a Master's degree in Data Science with a minor in Computational Science and Engineering. I use Julia to support research and prototype new techniques in high-performance computing and graph analysis.
Session
07-24
14:40
15min
GraphBLAS and Sparse Computation on GPUs: Limits and Progress
Antoine Buttier
GPU-accelerated sparse operations are notoriously difficult to implement efficiently. In addition, the GraphBLAS standard requires modularity as users can provide custom operators to use in the matrix multiplication, which usually doesn't mix well with handwritten GPU kernels. Leveraging KernelAbstractions.jl, we took a novel approach by JIT-compiling customized kernels for any user-defined operation while making it compatible cross-platform.
Sparse & Graph Computing in Julia
Main Room 3