Two weeks ago, we reported on Nova Reel 1.1, an AI model by Amazon, available through AWS, that lets you generate videos up to two minutes long, and Sonic, a unified speech model Amazon says outperforms rivals from OpenAI and Google. Now, Amazon is back with some hardware news for its cloud computing platform.
Amazon Elastic Compute Cloud (EC2) is getting three new instance families powered by the latest AWS Graviton4 processors. These are the compute optimized C8gd, general purpose M8gd, and memory optimized R8gd instances, and they all come with NVMe-based SSD local storage.
Amazon says that these instances offer some solid performance gains over the previous Graviton3-based instances. For general compute tasks, Amazon claims up to 30 percent better performance. For database workloads that hit the storage hard, Amazon is reporting up to 40 percent higher performance. If you are doing real-time data analytics that are I/O intensive, Amazon suggests you could see query results come back up to 20 percent faster.
These new instances are bigger across the board, too. You can get up to three times more vCPUs, maxing out at 192. Memory also triples, going up to 1.5 TiB. Local storage is up to three times larger as well, offering up to 11.4TB of NVMe SSD storage. Memory bandwidth is 75 percent higher, and there is twice as much L2 cache compared to the Graviton3 versions. All this extra capacity helps you handle bigger data loads and scale up your applications.
Network bandwidth is now up to 50 Gbps, and Amazon Elastic Block Store (EBS) bandwidth goes up to 40 Gbps, which is a big jump from the Graviton3 instances. Amazon also gives you the ability to tweak network and EBS bandwidth allocation by up to 25 percent using a bandwidth weighting configuration, letting you fine tune performance for specific workloads.
Amazon is positioning these Graviton4 instances as a good fit for storage intensive Linux based applications, like those built with containers and microservices using tools like Amazon Elastic Kubernetes Service (EKS) or Docker.
Applications written in popular programming languages such as C/C++, Java, Python, and others should also run well. Amazon specifically mentioned that the Graviton4 processors themselves are up to 30 percent faster for web applications, 40 percent faster for databases, and 45 percent faster for large Java applications than Graviton3 processors.
The new instances are built on the AWS Nitro System, which uses dedicated hardware and software to offload virtualization, storage, and networking tasks for better performance and security. On the security front, Graviton4 processors encrypt all high-speed physical hardware interfaces.
These instances are available in 10 different sizes for each family, plus two bare metal configurations. Here is a look at the specs:
| Instance Name | vCPUs | Memory (GiB) (C8gd/M8gd/R8gd) | Storage (GB) | Network Bandwidth (Gbps) | EBS Bandwidth (Gbps) |
|---|---|---|---|---|---|
| medium | 1 | 2/4/8 | 1 x 59 | Up to 12.5 | Up to 10 |
| large | 2 | 4/8/16 | 1 x 118 | Up to 12.5 | Up to 10 |
| xlarge | 4 | 8/16/32 | 1 x 237 | Up to 12.5 | Up to 10 |
| 2xlarge | 8 | 16/32/64 | 1 x 474 | Up to 15 | Up to 10 |
| 4xlarge | 16 | 32/64/128 | 1 x 950 | Up to 15 | Up to 10 |
| 8xlarge | 32 | 64/128/256 | 1 x 1900 | 15 | 10 |
| 12xlarge | 48 | 96/192/384 | 3 x 950 | 22.5 | 15 |
| 16xlarge | 64 | 128/256/512 | 2 x 1900 | 30 | 20 |
| 24xlarge | 96 | 192/384/768 | 3 x 1900 | 40 | 30 |
| 48xlarge | 192 | 384/768/1536 | 6 x 1900 | 50 | 40 |
| metal-24xl | 96 | 192/384/768 | 3 x 1900 | 40 | 30 |
| metal-48xl | 192 | 384/768/1536 | 6 x 1900 | 50 | 40 |
The M8gd, C8gd, and R8gd instances are available now in the US East (N. Virginia, Ohio) and US West (Oregon) Regions. You can buy them using On-Demand instances, Savings Plans, Spot instances, or as Dedicated instances or Dedicated hosts. If you want to try them out, you can launch them through the AWS Management Console, CLI, or SDKs.
0 Comments - Add comment