Accelerator-optimized machine family

Accelerator-optimized virtual machine (VM) instances featuring NVIDIA's new Ampere A100 GPUs are a new machine family available on Compute Engine that are optimized for massively parallelized Compute Unified Device Architecture (CUDA) workloads, such as machine learning (ML) and high performance computing (HPC).

Machine Workloads
A2 VMs
  • CUDA-enabled ML training and inference
  • HPC
  • Massive parallelized computation

Each A2 VM has a fixed number of A100 GPUs that offers up to 10x improvements in computing speed when compared to previous generation NVIDIA V100 GPUs.

In summary, A2 VMs provide the following features:

  • Industry-leading NVLink scale that provides peak GPU to GPU NVLink bandwidth of 600 Gbps. For example, systems with 16 GPUs have an aggregate NVLink bandwidth of up to 9.6 Terabytes per second. These 16 GPUs can be used as a single high performance accelerator with unified memory space to deliver up to 10 petaFLOPS of compute power and up to 20 petaFLOPS of inference compute power that can be used for artificial intelligence, deep learning, and machine learning workloads.
  • Next generation NVIDIA A100 GPUs. A100 GPU provides 40 GB of GPU memory—ideal for large language models, databases, and HPC.
  • High performance network bandwidth of up to 100 Gbps.
  • Virtualization optimizations.
  • Optional local SSD support—you can get up to 3 TB of Local SSD with A2 VMs. This can be used as fast scratch disks or for feeding data into the A100 GPUs while preventing I/O bottlenecks.

A2 VMs

A2 VMs come in different machine types ranging from 12 to 96 vCPUs, and offer up to 1360 GB of memory. You can attach up to 257 TB of local storage to these VMs for applications that require higher storage performance.

Machine types vCPUs* Memory (GB) Max number of persistent disks (PDs) Max total PD size (TB) Local SSD Maximum egress bandwidth (Gbps)
a2-highgpu-1g 12 85 128 257 Yes 24
a2-highgpu-2g 24 170 128 257 Yes 32
a2-highgpu-4g 48 340 128 257 Yes 50
a2-highgpu-8g 96 680 128 257 Yes 100
a2-megagpu-16g 96 1360 128 257 Yes 100

*A vCPU is implemented as a single hardware hyper-thread on one of the available CPU platforms.
Persistent disk usage is charged separately from machine type pricing.
Maximum egress bandwidth cannot exceed the number given. Actual egress bandwidth depends on the destination IP address and other factors. See Network bandwidth.

Limitations

  • A2 VMs are only available in certain regions and zones.
  • a2-megagpu-16g machine types are not supported on Windows operating systems. When using Windows operating systems, choose a different machine type.
  • A2 VMs are only available on the Cascade Lake platform.

What's next