Reproduce “Characterizing CPU-GPU Memory Sharing over Unified Memory Architecture” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jinrong Yang, Zimeng Wang, Rong Chen, Haibo Chen
The authors introduce libumsh, a library that tests CPU–GPU shared-memory protocols across four platforms and selects cache and coherence settings for data transfers and coordination. On Arrow, direct access for PyTorch model loading reduced elapsed time by 75% and memory use by half; Transparent Huge Pages cut loading time a further 5%. These results are platform- and workload-specific, not universal.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.