December 1, 2022
Amazon Web Services, a leading provider of cloud computing services, is rolling out its new ARM-based Graviton3E chips for high-performance workloads, including tasks like weather forecasting and gene sequencing. AWS customers can rent the high-performance computing (HPC) power to take advantage of “performance gains and cost savings” as a result of making its own chips, Amazon says. The move makes AWS something of a competitor to other top chipmakers, including Intel, AMD and Nvidia, who continue to be among Amazon’s major chip suppliers. Amazon says it will continue to offer HPC services that rely on third-party chips.
The Graviton3E is “a springboard” for making HPC “more readily available,” Bloomberg writes, calling the new chip “the latest piece of Amazon’s effort to build more of the hardware that fills the massive data centers that power AWS.”
In an interview with Bloomberg, AWS engineering senior VP Peter DeSantis said the Graviton3E will ultimately make AWS’s HPC services more affordable. In 2015, Amazon acquired fabless chipmaker Annapurna Labs to support AWS’ in-house chip designs.
Although AWS didn’t specify when the Graviton3E will be deployed, it did reveal the new iteration “will have twice the ability of current versions in one type of calculations needed by high-performance computers,” according to Bloomberg and “when combined with other AWS technology, the new offering will be 20 percent better than the previous one.”
“The reason that high-performance computing isn’t big is it’s hard,” DeSantis told Bloomberg, adding, “it’s hard to get capacity, it’s hard to get time on that supercomputer. What we’re excited about is bringing the capabilities of high-performance computing to more workloads.”
The HPC push was a focal point of the AWS re:Invent expo, running Monday through Friday (with many sessions available on-demand). The Inferentia chip, which draws inferences from huge volumes of data, saw the Inferentia2 introduced at the show, where AWS CEO Adam Selipsky talked-up its efficient handling of larger data sets for tasks like software-generated images and interpreting or detecting human speech.
AWS VP and chief evangelist Jeff Barr collects the top announcements of re:Invent in a blog post.
“For Intel fans, there are also new Ice Lake-based Xeon-based machines,” TechCrunch reports, noting “all of these new instances will make use of AWS’s new Nitro 5 hardware hypervisor,” which the company also announced at re:Invent. (Hypervisors are programs that can run multiple virtual machines on individual servers).
“Nitro v5 promises significantly improved latency, up to 40 percent better performance per watt, and 60 percent higher PPS,” TechCrunch writes, explaining “the AWS team made this possible by roughly doubling the number of transistors in the custom Nitro chips.”
Amazon Introduces AWS Supply Chain to Help Bring Order to Supply Chain Chaos, TechCrunch, 11/29/22