GBCMG meets in various locations around the Boston area. The meetings consist of presentations on computer systems capacity, performance, and management issues in the mainframe and open-systems areas. Topics cover a broad range of subjects including systems, storage, networks and applications.

Fall 2017 Meeting

Date and Time Friday, September 22, 2017, 8:30am – 5:00pm
Sponsors Premier Sponsor:
Location 228 South Street, Hopkinton, MA (Classroom A&B near the cafeteria)
Cost $25 registration per person.

Click here to register
Directions Exit 21b off I-495, right at the end of the ramp, left onto South Street (1st light if southbound on I-495, 2nd light if northbound on I-495; “228 South Street” has its own entrance off South Street.
Parking Use a visitors space in front of the building or park in any undesignated space further away from the building.
Agenda NOTE: Scroll down for abstracts of the presentations

Start Agenda Item Author (Affiliation)
8:30 Registration & breakfast
9:00 Introduction and presentation by Dell/EMC Yaron Dar (Dell/EMC)
10:00 Performance Management for Cloud Applications (1) Priyanka Arora (MUFG APM)
11:00 Benchmarking Machine Learning (2) Rohith Bakkannagari (Mathworks)
12:00 Lunch
1:00 A framework for Capacity Analysis (3) Debbie Sheetz (MBI Solutions)
2:00 Dynatrace journey from monolithic application to Cloud native application (4) Asad Ali (Dynatrace)
3:00 Can a robot read your performance reports? Deep learning and machine learning for Performance and Capacity Engineers (5) Anoush Najarian (Mathworks)
4:30 Concluding Remarks GBCMG Committee

Abstracts

(1) Performance Management for Cloud Applications

Cloud adoption rate continues to trend upward as providers mature towards offering more Hybrid solutions allowing organizations to keep one foot on the ground. Despite the abundance of providers and variety of offerings, organizations face significant challenges and require careful planning in moving towards Cloud solutions.

(2) Benchmarking Machine Learning

How to measure performance and scalability of key use cases: prediction and training from scratch, for Deep Learning frameworks: MATLAB, TensorFlow, MXNet, Caffe, and Theano. We will share performance metrics we obtained, and what we learned from this effort.

(3) A framework for Capacity Analysis

What are the essential steps of a Capacity Analysis? This is an introduction to the topic, focusing on the required elements. We begin with defining the purpose of the capacity study, analyze historical measurements, proceed to the ‘what-if’ phase, and report our results.

(4) Dynatrace journey from monolithic application to Cloud native application

Actual capacity study content is used to illustrate the principles described.
With the adoption of cloud in application deployment and extensive use of IoT devices across the industry, Dynatrace built cloud ready application from the ground up to meet the customer and the market demand. In order to support monitoring of microservices applications that generate tons of metrics, Dynatrace not only designed the newer architecture of the offering to support thousands of application nodes but also built industry first Artificial Intelligence into the product to identify the performance root cause with one click. Learn about Dynatrace’s journey into cloud ready architecture to support dynamic applications and IoT devices.

(5) Can a robot read your performance reports? Deep learning and machine learning for Performance and Capacity Engineers

We show how to apply deep learning and machine learning for performance performance testing, data analysis, and modeling.