Presentation
Crop: An Analytical Cost Model for Cross-Platform Performance Prediction of Tensor Programs
DescriptionLearn-based cost models used for tensor compiler auto-tuning often suffer from poor performance when trained on one hardware platform and applied to another. This issue necessitates collecting performance data for each potential platform during model deployment, incurring significant overhead.
We propose Crop, a comprehensive and universal analytical cost model designed for cross-platform performance prediction of tensor programs. Crop decouples program features and hardware features, gathering hardware-independent program features on one platform and predicts their performance based on parametric hardware features for given platforms. Crop achieves comparable levels of prediction accuracy to that of a learn-based cost model while ensuring portability.
We propose Crop, a comprehensive and universal analytical cost model designed for cross-platform performance prediction of tensor programs. Crop decouples program features and hardware features, gathering hardware-independent program features on one platform and predicts their performance based on parametric hardware features for given platforms. Crop achieves comparable levels of prediction accuracy to that of a learn-based cost model while ensuring portability.
Event Type
Research Manuscript
TimeTuesday, June 254:45pm - 5:00pm PDT
Location3001, 3rd Floor
AI
AI/ML Application and Infrastructure