Reproduce “Gen-TAS: A Generative AI-Aided Hardware-Software Task Allocation Framework for FPGA-GPP Heterogeneous Systems” 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
Mary Kong, Yuqin Zhao, Semih Vazgecen, Cristian Sestito, Themis Prodromakis
Gen-TAS turns application stages and dependencies, user priorities, and historical implementation records into ranked processor/FPGA allocations. A designer selects a candidate, and a deterministic build-and-measurement flow implements it. Across two workloads and four objectives, the flow generated valid allocations on one platform. For CAMC, Gemini’s all-FPGA choice measured 0.351 ± 0.007 ms and 92.531 ± 1.757× speedup in the tested setting.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.