AI News, Machine learning benchmarks: Hardware providers (part 1)
- On Sunday, September 30, 2018
- By Read More
Machine learning benchmarks: Hardware providers (part 1)
The rise of machine learning as a discipline brings new demands for number crunching and computing power.
With easily accessible and cheap hardware resources, one has to pick the right platform to run the experiments and model training on.
With no clear benchmark to address the practical aspects of choosing a hardware and software platform for ML, individuals and small companies like to go ahead with the popular choice.
This is part one in a blog post series by our Incubator student Shiva Manne compares machine learning frameworks and hardware platforms from practical aspects, such as their ease of use, cost, stability, scalability and performance.
This categorisation of machines is based on their cost ($/hr) which, for this CPU intensive benchmark, is primarily dependent on the total number of CPU cores it contains.
This wasn’t as easy with Google’s product – with GCE, I had to spend around 15 minutes pondering over the numerous mandatory fields (like private keys, firewall rules, subnets etc.).
Dedicated servers come out on top when comparing prorated costs (even though these are charged on a monthly basis and have no hourly option) against virtual machines by a huge margin.
They also keep expenses in check better than others by offering features such as no upfront costs, per-second billing and automatic sustained use discounts.
The price gap between Softlayer and AWS is not enormous but the costs for AWS eclipses all the other platforms completely, telling us that the high prices charged by AWS for premium instances are not backed by expected performance speedups, at least for these kind of intense number-crunching tasks.
Softlayer is also the only platform that allows the provisioning of bare metal servers amongst the 3 cloud service providers, which might be useful under security or compliance constraints.
GCE allow you to custom configure instances, which aids in keeping the costs low while AWS customers are required to choose from a predefined set of instances and then over-provision resources (CPUs &
Additionally, we had a serious issue with Softlayer where the price would not update properly for weeks, showing an outdated monthly cost that caused us to overshoot our monthly budget.
It becomes apparent from the above plot that barring original C, all the other software frameworks cost more to train on hardware instances with better configs and that the expected decrease in training time (owing to more CPU cores) does not justify the price of these extra resources.
- On Saturday, March 23, 2019
Cloud Cost Calculator Demo
This video contains a short demo on how to use AppScale's Cloud Cost Calculator. The Cloud Cost Calculator is a tool that enables people and companies with ...
CostStorage.com ☁ Cloud Storage Pricing Calculator
Demonstrate CostStorage.com Compare online storage pricing for Amazon AWS S3, Microsoft Azure, Google Cloud Storage, BackBlaze B2, IBM Softlayer and ...
Akasia Webinar Cost Modeling for AWS
Understanding the costs and options for moving existing applications or workloads to the public cloud is a complex and "moving target" problem. Akasia ...
DEMO: IBM Cloud AMM Migration Service for SoftLayer
Watch this demo of IBM Cloud Automated Modular Management (AMM), a migration service specifically designed to streamline workload migration onto ...
How to Run Amibroker in Amazon AWS Cloud
This Video Tutorial Explains How to Run Amibroker Software in Amazon Cloud more tutorials at
CloudCenter with AWS
Automate application deploy and manage on Amazon Web Services and reduce cloud costs with Cisco CloudCenter. Request a CloudCenter demo now: ...
IBM Cloud AMM: Migration Service Portal
AMM migration service is designed to streamline the time and costs of workload migrations onto SoftLayer. The offering provides a self-service dashboard to ...
IBM- OpenStack for Beginners
Are you still evaluating your cloud strategy or determining how best to apply OpenStack in your company? Is this your first OpenStack Summit? Come hear what ...
Migrating your Virtual Machine to Google Compute Engine
In this 10 minute video, Brian Stark, a product manager for Google Compute Engine, discusses how to move your virtual machine into the cloud. The reasons ...
Amazon Web Services (AWS) 100$ Promotional Code Auto Generate Script
Amazon Web Services provides hackers with low cost, easy to use infrastructure needed to build and scale their hacks. Some of the world's hottest startups ...