Cloud giant
Amazon Web Services, Inc. (AWS) has announced the launch of P3 instances for Amazon EC2. Part of the Amazon Group of companies, AWS has head offices in Seattle, Washington, United States. Recognized as the leader in the cloud arena, AWS' products and services extend to compute, storage, databases, analytics, networking, mobile, developer tools, management tools, the Internet of Things (IoT), security and enterprise applications. P3 instances represent "the next generation of Amazon Elastic Compute Cloud (Amazon EC2) GPU instances".
P3 instances are comprised of "up to eight NVIDIA Tesla V100 GPUs, provide up to one petaflop of mixed-precision, 125 teraflops of single-precision, and 62 teraflops of double-precision floating point performance, as well as a 300 GB/s second-generation NVIDIA NVLink interconnect that enables high-speed, low-latency GPU-to-GPU communication". They also feature "up to 64 vCPUs based on custom Intel Xeon E5 (Broadwell) processors, 488 GB of DRAM, and 25 Gbps of dedicated aggregate network bandwidth using the Elastic Network Adapter (ENA)." They are designed for applications that are compute-intensive and need "massive parallel floating point performance". Such applications might be used to manage "machine learning, computational fluid dynamics, computational finance, seismic analysis, molecular modeling, genomics, and autonomous vehicle systems". P3 instances enable AWS customers to "build and deploy advanced applications with up to 14 times better performance" than previous version of GPU compute instances. Additionally, they drastically reduce machine learning training times.
“When we launched our P2 instances last year, we couldn’t believe how quickly people adopted them,” explained Vice President of Amazon EC2, Matt Garman. “Most of the machine learning in the cloud today is done on P2 instances, yet customers continue to be hungry for more powerful instances. By offering up to 14 times better performance than P2 instances, P3 instances will significantly reduce the time involved in training machine learning models, providing agility for developers to experiment, and optimizing machine learning without requiring large investments in on-premises GPU clusters. In addition, high performance computing applications will benefit from up to 2.7 times improvement in double-precision floating point performance.”
Do you know of any other providers upgrading offerings? Let us know the details. Add your comments below.
