Summary of Pruner: a Speculative Exploration Mechanism to Accelerate Tensor Program Tuning, by Liang Qiao et al.
Pruner: A Speculative Exploration Mechanism to Accelerate Tensor Program Tuning
by Liang Qiao, Jun Shi, Xiaoyu Hao, Xi Fang, Minfan Zhao, Ziqi Zhu, Junshi Chen, Hong An, Bing Li, Honghui Yuan, Xinyang Wang, Xulong Tang
First submitted to arxiv on: 4 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Deep learning models require efficient deployment on various hardware platforms. Search-based methods have shown promise in finding optimal programs for specific devices. However, this process can be slow and inefficient due to the reliance on an accurate but time-consuming learned cost model. Moreover, these models are not easily adaptable to new platforms, leading to “cross-platform online unawareness.” This paper proposes solutions to address these challenges by developing more efficient search strategies and learning algorithms that enable seamless adaptation across different hardware environments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Deep learning models need to work well on many devices. Right now, we use special methods to find the best way to make a model run fast on one device. But this process can take a long time because it relies on a complex computer program that takes a lot of computing power. Also, these programs aren’t good at adapting to new devices, which is a problem. |
Keywords
* Artificial intelligence * Deep learning
