Close

Request a demo

CliQr's groundbreaking technology makes it fast and efficient for businesses to move, manage and secure applications onto any private, public or hybrid cloud environment.

CliQr is now part of Cisco Learn More About Cisco
Request a Demo

Blog

Benchmark: #Google #Cloud Platform instance types for #HPC workloads

When choosing an instance size for your high CPU workload, you have an important decision to make.  Do you want speed or low price or a combination of the two?  How do you find all that out?  Benchmarking.

Benchmarking 16 Task Blender on GCP

As an example, we decided to test out Google Cloud Platform high CPU workloads using Blender, the popular open source high resolution graphics and animation engine.  Specifically, we used a test workload with 16 different .blend files containing data used for the 3D rendering of animated houses.  We deployed this on a single node and spun up 16 tasks per node in an attempt to take better advantage of multiple processors available on a given VM.

Here’s how those results played out, both in graphical and tabular form with on demand pricing used:

16TaskBlenderGCP

 

Instance Name

vCPU

RAM

Time (hrs)

Cost Per Job

n1-standard-2

2

7.5

2.92

$0.41

n1-standard-4

4

15

1.30

$0.36

n1-standard-8

8

30

0.73

$0.41

 

Analyzing Results

Similar to what we saw in our AWS analysis recently, Google does a great job pricing their instance types.  Since we segmented our workload across 16 processes, you’d expect the completion time to roughly half each time you double the number of CPUs and that’s exactly what we see here.  Since Google doubles the price of the instances as those CPUs double, the price to complete the job is essentially the same after the slight speedy variance seen in the n1-standard-4 across the three trials conducted for each instance type.

It is worth noting, however, that on a batch workload like this is where Google’s per minute billing really shines.  With this cost structure, you pay for exactly the time you need for the job and can save money that can add up over large volumes.

In the end, this is exactly the type of raw data an organization needs to make instance type decisions when running HPC workloads on public clouds.  Only through benchmarking that considers both price AND performance can you get what you need to make an informed decision.  At that point, you can take the specifics of your situation into account and decide for yourself

Leave a Reply

Your email address will not be published. Required fields are marked *


− 2 = four

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>

Stay Informed

Subscribe to our email list for company updates.

CliQr Technologies, CliQr CloudCenter and CloudBlades are trademarks of CliQr Technologies, Inc. All other registered or unregistered trademarks are the sole property of their respective owners.