Nitro and Graviton Chips
People often ask how AWS innovates at such a rapid clip, and Jassy puts it to two reasons: AWS Nitro System, which is AWS’ underlying platform for its next generation of EC2 instances, and its Graviton chips.
AWS spent five years rebuilding the virtualization layer in its compute platform and launched Nitro in 2017.
“We took the virtualization of the security, networking and storage off of the main server chip, and we put that on their own Nitro chips,” Jassy said. “It meant that you got all the CPU to run your instances, so you get performance that’s indistinguishable from bare metal, but at a lower price. It also meant you got a stronger security posture, because it used to be that when you had to troubleshoot VMs, you had to worry about whether somebody would do something to the main server with your instances. But because the security now is on that separate Nitro chip, you don’t have to worry about that.”
“What it did for us was, because we broke out a bunch of those pieces into separable cards or chips, it meant we didn’t have to make changes in making all these different things change and evolve in lockstep, which allows us to innovate at a much faster clip,” Jassy said. “What that means for you is that…instead of every two to three years, you get innovative, brand-new, change-the-game-types of instances in months. That’s a big difference.”
AWS’ work on chips also has allowed AWS to innovate at a rapid clip, according to Jassy.
“We have a deep relationship with both Intel and AMD, and we will for the foreseeable future,” he said.
But AWS realized a few years ago that if it wanted to continue to push the envelope of price performance -- which customers had asked it to do -- it had to develop some of its own chips.
“So we acquired a company called Annapurna (Labs in 2015), who were sophisticated and very experienced chip designers and builders, and we put them to work,” Jassy said. “We tried to pick chips that would allow you to get the most done and have the most impact for your business.”
AWS started with generalized compute and had its team build a chip on top of Arm that it calls Graviton, which first manifested itself in A1 instances.
“They were really for scale-out workloads -- things like web-tier workloads,” Jassy said. “And people loved them. They used them a lot quicker than we ever imagined. And they said, ‘Gosh, if you would make the chip more powerful, so we could use it for more of our workloads, that would really change the game for us.’”
Graviton2, AWS’ second version of the Graviton chip, gives customers 40 percent better price performance than the most recent generations of the x86 processors from other providers, Jassy noted. Those manifest themselves on C6g, M6g, R6g and T4g instances.
“That is a big deal,” Jassy said. “Think about what you can do for your business if you have 40 percent better price performance on your compute. Customers have loved this. We have a large number of customers who are already using it, from Nielsen to Netflix to Snap and Lyft and Next Roll. And we have, announcing today, a brand new Graviton2 instance, which is going to be the C6gn instance, which is our compute-heavy and network-heavy instance with 100 gigabits per second that will come in the next week or two.”
“We are not close to being done investing and inventing with Graviton,” Jassy said. “People are seeing a big difference.”