.png){kind=icon}
返回
OpBench: an operator-level GPU benchmark for deep learning
.png){kind=icon}
PRE
AI
DOI：10.1007/s11432-023-3989-3.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Operators (such as Conv and ReLU) play an important role in deep neural networks. Every neural network is composed of a series of differentiable operators. However, existing AI benchmarks mainly focus on accessing model training and inference performance of deep learning systems on specific models. To help GPU hardware find computing bottlenecks and intuitively evaluate GPU performance on specific deep learning tasks, this paper focuses on evaluating GPU performance at the operator level. We statistically analyze the information of operators on 12 representative deep learning models from six prominent AI tasks and provide an operator dataset to show the different importance of various types of operators in different networks. An operator-level benchmark, OpBench, is proposed on the basis of this dataset, allowing users to choose from a given range of models and set the input sizes according to their demands. This benchmark offers a detailed operator-level performance report for AI and hardware developers. We also evaluate four GPU models on OpBench and find that their performances differ on various types of operators and are not fully consistent with the performance metric FLOPS (floating point operations per second).
Keyword:
deep learning
operator benchmark
model benchmark
GPU performance analysis
deep neural networks
期刊
IF:
7.6
论文数:
4.9K
被引数:
8.9K
机构
引用论文
Jittor: a novel deep learning framework with meta-operators and unified graph executionJittor: 一种具有元运算符和统一图执行的新型深度学习框架
PREAI
分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏Natural language processing: state of the art, current trends and challenges自然语言处理: 最新技术，当前趋势和挑战
OAAI
OAAI分享收藏
没有更多内容
没有更多内容