Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.23988 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917195354734592 |
|---|---|
| author | Lemos, Elayne Oliveira, Rodrigo Rodrigues, Jairson Neto, Rosalvo F. Oliveira |
| author_facet | Lemos, Elayne Oliveira, Rodrigo Rodrigues, Jairson Neto, Rosalvo F. Oliveira |
| contents | The deployment of Machine Learning models in the cloud has grown among tech companies. Hardware requirements are higher when these models involve Deep Learning techniques, and the cloud providers' costs may be a barrier. We explore deploying Deep Learning models, using for experiments the GECToR model, a Deep Learning solution for Grammatical Error Correction, across three of the major cloud providers (Amazon Web Services, Google Cloud Platform, and Microsoft Azure). We evaluate real-time latency, hardware usage, and cost at each cloud provider in 7 execution environments with 10 experiments reproduced. We found that while Graphics Processing Units (GPUs) excel in performance, they had an average cost 300% higher than solutions without a GPU. Our analysis also suggests that processor cache memory size is a key variable for CPU-only deployments, and setups with sufficient cache achieved a 50% cost reduction compared to GPU-based deployments. This study indicates the feasibility and affordability of cloud-based Deep Learning inference solutions without a GPU, benefiting resource-constrained users such as startups and small research groups. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23988 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Learning Model Deployment in Multiple Cloud Providers: an Exploratory Study Using Low Computing Power Environments Lemos, Elayne Oliveira, Rodrigo Rodrigues, Jairson Neto, Rosalvo F. Oliveira Distributed, Parallel, and Cluster Computing Artificial Intelligence Performance 68T07, 68U01 C.4; I.2.0; B.8.2 The deployment of Machine Learning models in the cloud has grown among tech companies. Hardware requirements are higher when these models involve Deep Learning techniques, and the cloud providers' costs may be a barrier. We explore deploying Deep Learning models, using for experiments the GECToR model, a Deep Learning solution for Grammatical Error Correction, across three of the major cloud providers (Amazon Web Services, Google Cloud Platform, and Microsoft Azure). We evaluate real-time latency, hardware usage, and cost at each cloud provider in 7 execution environments with 10 experiments reproduced. We found that while Graphics Processing Units (GPUs) excel in performance, they had an average cost 300% higher than solutions without a GPU. Our analysis also suggests that processor cache memory size is a key variable for CPU-only deployments, and setups with sufficient cache achieved a 50% cost reduction compared to GPU-based deployments. This study indicates the feasibility and affordability of cloud-based Deep Learning inference solutions without a GPU, benefiting resource-constrained users such as startups and small research groups. |
| title | Deep Learning Model Deployment in Multiple Cloud Providers: an Exploratory Study Using Low Computing Power Environments |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Performance 68T07, 68U01 C.4; I.2.0; B.8.2 |
| url | https://arxiv.org/abs/2503.23988 |