5 papers
LEO: Tracing GPU Stall Root Causes via Cross-Vendor Backward Slicing
Yuning Xia, John Mellor-Crummey
More than half of the Top 500 supercomputers employ GPUs as accelerators. On GPU-accelerated platforms, developers face a key diagnostic gap: profilers show source lines where stal…
Matrix-Free Finite Volume Kernels on a Dataflow Architecture
Ryuichi Sai, Francois P. Hamon, John Mellor-Crummey +1
Fast and accurate numerical simulations are crucial for designing large-scale geological carbon storage projects ensuring safe long-term CO2 containment as a climate change mitigat…
Priority Sampling of Large Language Models for Compilers
Dejan Grubisic, Chris Cummins, Volker Seeker +1
Large language models show great potential in generating and optimizing code. Widely used sampling methods such as Nucleus Sampling increase the diversity of generation but often p…
A Portable Framework for Accelerating Stencil Computations on Modern Node Architectures
Ryuichi Sai, John Mellor-Crummey, Jinfan Xu +1
Finite-difference methods based on high-order stencils are widely used in seismic simulations, weather forecasting, computational fluid dynamics, and other scientific applications.…
LoopTune: Optimizing Tensor Computations with Reinforcement Learning
Dejan Grubisic, Bram Wasti, Chris Cummins +2
Advanced compiler technology is crucial for enabling machine learning applications to run on novel hardware, but traditional compilers fail to deliver performance, popular auto-tun…