MetaDSE: A Few-shot Meta-learning Framework for Cross-workload CPU Design Space Exploration
By: Runzhen Xue , Hao Wu , Mingyu Yan and more
Potential Business Impact:
Teaches computers to design faster chips.
Cross-workload design space exploration (DSE) is crucial in CPU architecture design. Existing DSE methods typically employ the transfer learning technique to leverage knowledge from source workloads, aiming to minimize the requirement of target workload simulation. However, these methods struggle with overfitting, data ambiguity, and workload dissimilarity. To address these challenges, we reframe the cross-workload CPU DSE task as a few-shot meta-learning problem and further introduce MetaDSE. By leveraging model agnostic meta-learning, MetaDSE swiftly adapts to new target workloads, greatly enhancing the efficiency of cross-workload CPU DSE. Additionally, MetaDSE introduces a novel knowledge transfer method called the workload-adaptive architectural mask algorithm, which uncovers the inherent properties of the architecture. Experiments on SPEC CPU 2017 demonstrate that MetaDSE significantly reduces prediction error by 44.3\% compared to the state-of-the-art. MetaDSE is open-sourced and available at this \href{https://anonymous.4open.science/r/Meta_DSE-02F8}{anonymous GitHub.}
Similar Papers
OneDSE: A Unified Microprocessor Metric Prediction and Design Space Exploration Framework
Hardware Architecture
Designs faster computer chips more easily.
Intelligent4DSE: Optimizing High-Level Synthesis Design Space Exploration with Graph Neural Networks and Large Language Models
Machine Learning (CS)
Makes computer chips design faster and better.
DiffAxE: Diffusion-driven Hardware Accelerator Generation and Design Space Exploration
Hardware Architecture
Finds best computer chips for AI faster.