Unified Kernel-Segregated Transpose Convolution Operation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913712502210560 |
|---|---|
| author | Tida, Vijay Srinivas Hossen, Md Imran Shan, Liqun Chilukoti, Sai Venkatesh Hsu, Sonya Hei, Xiali |
| author_facet | Tida, Vijay Srinivas Hossen, Md Imran Shan, Liqun Chilukoti, Sai Venkatesh Hsu, Sonya Hei, Xiali |
| contents | The optimization of the transpose convolution layer for deep learning applications is achieved with the kernel segregation mechanism. However, kernel segregation has disadvantages, such as computing extra elements to obtain the output feature map with odd dimensions while launching a thread. To mitigate this problem, we introduce a unified kernel segregation approach that limits the usage of memory and computational resources by employing one unified kernel to execute four sub-kernels. The findings reveal that the suggested approach achieves an average computational speedup of 2.03x (3.89x) when tested on specific datasets with an RTX 2070 GPU (Intel Xeon CPU). The ablation study shows an average computational speedup of 3.5x when evaluating the transpose convolution layers from well-known Generative Adversarial Networks (GANs). The implementation of the proposed method for the transpose convolution layers in the EB-GAN model demonstrates significant memory savings of up to 35 MB. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20493 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unified Kernel-Segregated Transpose Convolution Operation Tida, Vijay Srinivas Hossen, Md Imran Shan, Liqun Chilukoti, Sai Venkatesh Hsu, Sonya Hei, Xiali Machine Learning Artificial Intelligence The optimization of the transpose convolution layer for deep learning applications is achieved with the kernel segregation mechanism. However, kernel segregation has disadvantages, such as computing extra elements to obtain the output feature map with odd dimensions while launching a thread. To mitigate this problem, we introduce a unified kernel segregation approach that limits the usage of memory and computational resources by employing one unified kernel to execute four sub-kernels. The findings reveal that the suggested approach achieves an average computational speedup of 2.03x (3.89x) when tested on specific datasets with an RTX 2070 GPU (Intel Xeon CPU). The ablation study shows an average computational speedup of 3.5x when evaluating the transpose convolution layers from well-known Generative Adversarial Networks (GANs). The implementation of the proposed method for the transpose convolution layers in the EB-GAN model demonstrates significant memory savings of up to 35 MB. |
| title | Unified Kernel-Segregated Transpose Convolution Operation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2502.20493 |