Optimal Kernel Orchestration for Tensor Programs with Korch

Muyan Hu, Ashwin Venkatram, Shreyashri Biswas, Balamurugan Marimuthu, Bohan Hou, Gabriele Oliaro, Haojie Wang, Liyan Zheng, Xupeng Miao, Jidong Zhai
University of Illinois at Urbana-Champaign, Urbana-Champaign, IL, USA
arXiv:2406.09465 [cs.DS], (13 Jun 2024)


   series={ASPLOS ’24},

   title={Optimal Kernel Orchestration for Tensor Programs with Korch},



   booktitle={Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3},


   author={Hu, Muyan and Venkatram, Ashwin and Biswas, Shreyashri and Marimuthu, Balamurugan and Hou, Bohan and Oliaro, Gabriele and Wang, Haojie and Zheng, Liyan and Miao, Xupeng and Zhai, Jidong and Jia, Zhihao},



   collection={ASPLOS ’24}


Kernel orchestration is the task of mapping the computation defined in different operators of a deep neural network (DNN) to the execution of GPU kernels on modern hardware platforms. Prior approaches optimize kernel orchestration by greedily applying operator fusion, which fuses the computation of multiple operators into a single kernel, and miss a variety of optimization opportunities in kernel orchestration. This paper presents Korch, a tensor program optimizer that discovers optimal kernel orchestration strategies for tensor programs. Instead of directly fusing operators, Korch first applies operator fission to decompose tensor operators into a small set of basic tensor algebra primitives. This decomposition enables a diversity of fine-grained, inter-operator optimizations. Next, Korch optimizes kernel orchestration by formalizing it as a constrained optimization problem, leveraging an off-the-shelf binary linear programming solver to discover an optimal orchestration strategy, and generating an executable that can be directly deployed on modern GPU platforms. Evaluation on a variety of DNNs shows that Korch outperforms existing tensor program optimizers by up to 1.7x on V100 GPUs and up to 1.6x on A100 GPUs. Korch is publicly available.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: