Check out the High-performance computing SKUs in the Azure Government Virginia region

The HPC SKUs (HBv2 and HC) are now generally available in the Azure Government Virginia region. Customers can leverage this new capability for any unclassified workload including ITAR and FedRAMP High. These are designed to deliver cutting-edge performance for complex engineering and scientific workloads.

HBv2-series

HBv2-series VMs are optimized for applications driven by memory bandwidth, such as fluid dynamics, explicit finite element analysis, and weather modeling. HB VMs feature 120 AMD EPYC™ 7002-series CPU cores, 4 GB of RAM per CPU core, and no hyperthreading. HBv2-series VMs provide up to 350 GB/sec of memory bandwidth, which is 45-50 percent faster than x86 alternatives and 3x faster than what most HPC customers have in their data centers today. HBv2-series VMs also feature 200 Gb/sec HDR InfiniBand from our technology partners Mellanox.

‘r’ denotes support for RDMA. ‘s’ denotes support for Premium SSD disks.

HC-series

HC-series VMs are optimized for applications driven by dense computation, such as implicit finite element analysis, reservoir simulation, and computational chemistry. HC VMs feature 44 Intel Xeon Platinum 8168 processor cores, 8 GB of RAM per CPU core, and no hyperthreading. HC-series VMs support Intel’s rich ecosystem of software tools such as the Intel Math Kernel Library and feature an all-cores clock speed greater than 3 GHz for most workloads. HC-series VMs also feature 100 Gb/sec EDR InfiniBand with support for standard Mellanox OFED drivers and all MPI types and versions.

‘r’ denotes support for RDMA. ‘s’ denotes support for Premium SSD disks.

Customers can accelerate their HC/HBv2 deployments with a variety of resources optimized and pre-configured by the Azure HPC team. Our pre-built HPC image for CentOS is tuned for optimal performance and bundles key HPC tools like various MPI libraries, compilers, and more. The AzureHPC Project helps customers deploy an end-to-end Azure HPC environment reliably and quickly, and includes deployment scripts for setting up building blocks for networking, compute, schedulers, and storage. Also included is a growing list of tutorials for running HPC applications themselves.

For customers familiar with HPC schedulers and who would like to use these with HBv2/HC Virtual Machines, Azure CycleCloud is the simplest way to orchestrate autoscaling clusters. Azure CycleCloud supports schedulers such as Slurm, PBSPro, LSF, GridEngine, and HTCondor, and enables hybrid deployments for customers wishing to pair HBv2/HC Virtual Machines with their existing on-premises clusters. The new H-series Virtual Machines will also be supported by Azure Batch for cloud-native batch processing. HBv2/HC Virtual Machines will be available to all Azure platform partners.

You can also use this learning module that can guide you on how to choose the right SKU for your HPC workload and optimize your tightly coupled jobs on Azure.

Azure is the only cloud platform that offers VM instances with InfiniBand-enabled hardware. This provides a significant performance advantage. Below you can find some of the published performance results using the HBv2/HC:

Azure HBv2 Virtual Machines eclipse 80,000 cores for MPI HPC

Azure HBv2 joins Graph500 Top 20 list

Run WRF v4 on Azure HBv2 Virtual Machines

Azure HC Virtual Machines crosses 20,000 cores for HPC workloads

If you’re a current customer interested in using our new VMs to run your HPC workloads, you can request a H-Series quota via the Azure Government portal.

To explore Azure Government, request your free 90-day trial today.