Intel announced that Amazon Web Services (AWS) has just launched its new processor-powered Amazon EC2 I4i instances 3rd Generation Intel Xeon Scalable, i.e. the Ice Lake architecture at 10 nm. As revealed, thanks to Turbo frequencies of 3.50 GHz for all cores, it will be offered a 30% increase in performance Compared to I3 instances, in addition to reducing I/O storage latencies by up to 60%, the variability of said storage latency is reduced by 75%.
These instances are offered with a maximum configuration of 128 hearts (vCPU) with access to 1024 GB of RAM (twice compared to instance I3), 30,000 GB of NVMe storage @ 22,400 MB/s read, access up to 75 Gbps network speed and 40 Gbps bandwidth to Amazon Elastic Block Store.
Amazon Web Services (AWS) has announced the general availability of Amazon EC2 I4i instances powered by 3rd Generation Intel® Xeon® Scalable processors (codenamed Ice Lake).
Along with the recently announced Amazon EC2 I4i instances and Amazon EC2 X2idn and X2iedn instances, 3rd Generation Intel Xeon Scalable processors now power 48 AWS instances across workloads and marketplaces.
Designed for storage I/O-intensive workloads such as databases, data analytics, and search engines, and with a 3.5 GHz turbo frequency on all cores, Amazon announced that EC2 I4i instances offer up to 30% better compute price performance than I3 instances and always-on memory encryption using Intel Total Memory Encryption (TME).
I4i instances offer up to 30 terabytes of NVMe storage from AWS Nitro SSDs. According to Amazon, I4i instances offer up to 60% lower storage I/O latency and 75% lower storage I/O latency variability compared to I3 instances. These instances offer the highest local storage performance within Amazon EC2 and are designed for databases including MySQL, Oracle DB, and Microsoft SQL Server, and NoSQL databases including MongoDB, Couchbase, Aerospike, and Redis, where storage is needed. NVMe to meet application SLAs. Based on the AWS Nitro system, a combination of bare metal and lightweight hypervisor, I4i instances provide virtually all of the host hardware’s compute and memory resources to the instances.
To meet customer demands for greater scalability, I4i instances provide a new instance size (i4.32xlarge) with 128 vCPUs and 1024 gigabytes of memory, which is double the largest I3 instance. I4i instances offer customers up to 75 Gbps of network speed and 40 Gbps of bandwidth to Amazon Elastic Block Store.
EC2 I4i instances are now generally available in AWS Regions: US East (N. Virginia, Ohio), US West (Oregon), and Europe (Ireland).