How GPU-Powered Analytics Improves Mail Delivery for USPS
Alex Woodie (25 July 2016)
Paper’s reference in the IEEE style?
“How GPU-Powered Analytics Improves Mail Delivery for USPS,” Datanami, 25-Jul-2016. [Online]. Available: https://www.datanami.com/2016/07/25/gpu-powered-analytics-improves-mail-delivery-usps/. [Accessed: 21-Aug-2016].
How did you find the paper?
If applicable, write a list of the search terms you used.
Was the paper peer reviewed? Explain how you found out.
No. Datanami is a news portal dedicated to providing insight, analysis and up-to-the-minute information about emerging trends and solutions in big data.
Does the author(s) work in a university or a government-funded research institute? If so, which university or research institute? If not, where do they work?
The author, Alex Woodie, is the managing editor at Datnami and is a journalist with experience in servers, ERP systems etc.
What does this tell you about their expertise? Are they an expert in the topic area?
The author is likely experience in reporting on technology but is not a technical subject matter expert.
What was the paper about?
The United States Postal Service (USPS) needed to implement a system to improve its operations and delivery logistics.
With a fleet of 215,000 vehicles and 600,000 employees, the USPS is the largest logistic business in the USA.
In order to improve performance, the USPS implemented a system to emit the geographic coordinates of each vehicle every minute. In order to analyse this amount of data, USPS implemented a distributed in memory GPU based database (GPUdb) from Kinetica.
A cluster of 150-200 nodes, each node is a single X86 blade server with 0.5-1.0 TB RAM and up to two NVIDIA GPUs.
The cluster can server up to 15,000 simultaneous sessions to service managers and analysts
If applicable, is this paper similar to other papers you have read for this assignment? If so, which papers and why?
This paper is similar to previous papers reviewed, and explores the use of GPUs to rapidly and cost effectively analyse big data.
If applicable, is this paper different to other papers you have read for this assignment? If so, which papers and why?
What do these similarities and differences suggest? What are your observations? Do you have any new ideas? Do you have any conclusions?
The use of big data and data analytics is continuing to be utilised in large enterprise and, more recently, the use of GPU clusters to facilitate this analysis at scale and at lower costs is further increasing its use.
This question is to be answered after your critical analysis is completed. Which sections (if any) of your critical analysis was this paper cited in?