arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.03060cs.DCcs.LG
收藏

推理加速器对硬件选择的影响

Impact of Inference Accelerators on hardware selection

GE Healthcare(GE医疗)

Dibyajyoti Pati, Caroline Favart, Purujit Bahl, Vivek Soni, Yun-chan Tsai, Michael Potter, Jiahui Guan, Xiaomeng Dong, V. Ratna Saripalli

摘要:

随着人工智能辅助医疗保健的机会稳步增长,由于行业的具体特点,模型部署面临挑战。生产设备的配置选择可能会影响模型性能,同时影响运营成本。此外,在医疗保健中,某些情况可能需要快速但不是实时的推断。我们研究了不同的配置,并进行了成本性能分析,以确定优化的硬件部署的模型受到医疗领域的限制。我们观察到,一个天真的性能比较可能不会导致最佳的配置选择。事实上,考虑到现实的域约束,CPU执行可能比GPU加速器更可取。因此,预先定义模型部署的精确期望至关重要。

英文摘要:

As opportunities for AI-assisted healthcare grow steadily, model deployment faces challenges due to the specific characteristics of the industry. The configuration choice for a production device can impact model performance while influencing operational costs. Moreover, in healthcare some situations might require fast, but not real time, inference. We study different configurations and conduct a cost-performance analysis to determine the optimized hardware for the deployment of a model subject to healthcare domain constraints. We observe that a naive performance comparison may not lead to an optimal configuration selection. In fact, given realistic domain constraints, CPU execution might be preferable to GPU accelerators. Hence, defining beforehand precise expectations for model deployment is crucial.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑