Deep Learning Model Deployment in Multiple Cloud Providers: an Exploratory Study Using Low Computing Power Environments
This incremental work addresses cost barriers for resource-constrained users like startups by demonstrating affordable cloud-based deep learning inference without GPUs.
The study explored deploying a deep learning model for grammatical error correction across three major cloud platforms, finding that GPU solutions had 300% higher costs than CPU-based ones and that optimizing processor cache could reduce costs by over 50% compared to GPUs.
The deployment of Machine Learning models at cloud have grown by tech companies. Hardware requirements are higher when these models involve Deep Learning (DL) techniques and the cloud providers' costs may be a barrier. We explore deploying DL models using for experiments the GECToR model, a DL solution for Grammatical Error Correction, across three of the major cloud platforms (AWS, Google Cloud, Azure). We evaluate real-time latency, hardware usage and cost at each cloud provider by 7 execution environments with 10 experiments reproduced. We found that while GPUs excel in performance, they had an average cost 300% higher than solutions without GPU. Our analysis also identifies that processor cache size is crucial for cost-effective CPU deployments, enabling over 50% of cost reduction compared to GPUs. This study demonstrates the feasibility and affordability of cloud-based DL inference solutions without GPUs, benefiting resource-constrained users like startups.