Back to Search Start Over

Cross-Feature Transfer Learning for Efficient Tensor Program Generation.

Authors :
Verma, Gaurav
Raskar, Siddhisanket
Emani, Murali
Chapman, Barbara
Source :
Applied Sciences (2076-3417); Jan2024, Vol. 14 Issue 2, p513, 20p
Publication Year :
2024

Abstract

Tuning tensor program generation involves navigating a vast search space to find optimal program transformations and measurements for a program on the target hardware. The complexity of this process is further amplified by the exponential combinations of transformations, especially in heterogeneous environments. This research addresses these challenges by introducing a novel approach that learns the joint neural network and hardware features space, facilitating knowledge transfer to new, unseen target hardware. A comprehensive analysis is conducted on the existing state-of-the-art dataset, TenSet, including a thorough examination of test split strategies and the proposal of methodologies for dataset pruning. Leveraging an attention-inspired technique, we tailor the tuning of tensor programs to embed both neural network and hardware-specific features. Notably, our approach substantially reduces the dataset size by up to 53% compared to the baseline without compromising Pairwise Comparison Accuracy (PCA). Furthermore, our proposed methodology demonstrates competitive or improved mean inference times with only 25–40% of the baseline tuning time across various networks and target hardware. The attention-based tuner can effectively utilize schedules learned from previous hardware program measurements to optimize tensor program tuning on previously unseen hardware, achieving a top-5 accuracy exceeding 90%. This research introduces a significant advancement in autotuning tensor program generation, addressing the complexities associated with heterogeneous environments and showcasing promising results regarding efficiency and accuracy. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
20763417
Volume :
14
Issue :
2
Database :
Complementary Index
Journal :
Applied Sciences (2076-3417)
Publication Type :
Academic Journal
Accession number :
175058177
Full Text :
https://doi.org/10.3390/app14020513