# Moses: Efficient Exploitation of Cross-device Transferable Features for Tensor Program Optimization

arXiv: https://arxiv.org/abs/2201.05752 · HTML: https://mlsanity.com/paper/2201.05752/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 15 Jan 2022.

## Builds on (most cited first, 10 of 10)

- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Ansor: Generating High-Performance Tensor Programs for Deep Learning](https://mlsanity.com/paper/2006.06762/) (2020)
- [Learning to Optimize Tensor Programs](https://mlsanity.com/paper/1805.08166/) (2018)
- [TVM: An Automated End-to-End Optimizing Compiler for Deep Learning](https://mlsanity.com/paper/1802.04799/) (2018)
- [A Deep Learning Based Cost Model for Automatic Code Optimization](https://mlsanity.com/paper/2104.04955/) (2021)
- [Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation](https://mlsanity.com/paper/2001.08743/) (2020)
- [Learning Transferable Parameters for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2108.06129/) (2021)
- [ProTuner: Tuning Programs with Monte Carlo Tree Search](https://mlsanity.com/paper/2005.13685/) (2020)
- [MetaTune: Meta-Learning Based Cost Model for Fast and Efficient Auto-tuning Frameworks](https://mlsanity.com/paper/2102.04199/) (2021)

## Built on by (most cited first, 3 of 3)

- [TLP: A Deep Learning-based Cost Model for Tensor Program Tuning](https://mlsanity.com/paper/2211.03578/) (2022)
- [CDMPP: A Device-Model Agnostic Framework for Latency Prediction of Tensor Programs](https://mlsanity.com/paper/2311.09690/) (2023)
- [FTuner: A Fast Dynamic Shape Tensors Program Auto-Tuner for Deep Learning Compilers](https://mlsanity.com/paper/2407.21418/) (2024)

## Abstract (arXiv)

Achieving efficient execution of machine learning models has attracted significant attention recently. To generate tensor programs efficiently, a key component of DNN compilers is the cost model that can predict the performance of each configuration on specific devices. However, due to the rapid emergence of hardware platforms, it is increasingly labor-intensive to train domain-specific predictors for every new platform. Besides, current design of cost models cannot provide transferable features between different hardware accelerators efficiently and effectively. In this paper, we propose Moses, a simple and efficient design based on the lottery ticket hypothesis, which fully takes advantage of the features transferable to the target device via domain adaptation. Compared with state-of-the-art approaches, Moses achieves up to 1.53X efficiency gain in the search stage and 1.41X inference speedup on challenging DNN benchmarks.