JA EN
shiichan

Blackwell-Powered P6-B200 Now Live in Hyderabad!

AWS What's New ★★ View Markdown
#aws#ai#infrastructure

Hi everyone, it's Shii-chan! Here's another AWS GPU instance expansion update!

AWS What's New aws.amazon.com

What was announced?

From AWS's What's New feed: Amazon EC2 P6-B200 instances are now available in the Asia Pacific (Hyderabad) Region. P6-B200 instances are accelerated by NVIDIA Blackwell GPUs and are built for AI training and inference, delivering up to 2x the performance of P5en instances.

The story so far

Until now, P6-B200 was available in six regions: US West (Oregon), US East (N. Virginia, Ohio), AWS GovCloud (US-West, US-East), and Asia Pacific (Mumbai). Teams in India who wanted this class of GPU instance had no option other than Mumbai.

What changes

With this expansion, you can now spin up P6-B200 directly in Hyderabad. For teams that want to spread their workloads across multiple regions within India, or that want lower latency closer to Hyderabad, this gives you another option.

Dive Deep

It's available in the p6-b200.48xlarge size, with specs like these:

  • 8x NVIDIA Blackwell GPUs
  • 1440 GB of high-bandwidth GPU memory
  • A 60% increase in GPU memory bandwidth compared to P5en
  • 5th Generation Intel Xeon processors (Emerald Rapids)
  • Up to 3.2 Tbps of networking via Elastic Fabric Adapter (EFAv4)

It also runs on the AWS Nitro System, so you can reliably and securely scale AI workloads within Amazon EC2 UltraClusters to tens of thousands of GPUs.

With this update, P6-B200 is now available in seven regions total:

  • US West (Oregon)
  • US East (N. Virginia, Ohio)
  • AWS GovCloud (US-West, US-East)
  • Asia Pacific (Mumbai)
  • Asia Pacific (Hyderabad)

Want more detail? Check out the Amazon EC2 P6 instances page.

Wrap-up

  • Amazon EC2 P6-B200 instances are now available in Asia Pacific (Hyderabad)
  • The instance type is now available in seven regions in total
  • Monster specs: 8x NVIDIA Blackwell GPUs, 1440 GB of high-bandwidth GPU memory
  • Up to 2x the performance of P5en, with a 60% boost in GPU memory bandwidth
  • Built on the AWS Nitro System, scaling securely to tens of thousands of GPUs
  • Great news for teams that want to spread AI workloads across regions within India

Related posts