Intel’s next generation of processors are designed to help you get things done as a streamer or creator without killing your laptop’s battery life. That’s part of the company’s efforts to improve the architecture of its processors, even as Moore’s law slows down and Intel is forced to find other ways to keep boosting performance every year.
We need larger displays because we’re getting so distracted from our tasks, said Becky Loop, Intel fellow and chief client CPU architect, in a recent press briefing. Improving the latest generation of processors on a faster basis is critical to Intel’s future, as it faces competitors on all sides, from Qualcomm, with its smartphone chips and Windows-based internet machines; Advanced Micro Devices, with its cleverly designed Zen family of processors; and Arm’s attack on both the server and internet of things markets.
Loop said that Intel’s architectural anchors for this generation — including a chip code-named Sunny Cove — include performance and responsiveness, artificial intelligence, form factor and integration, battery life, always fast and reliably connected, and security and cryptography. She said that the target for the next generation of CPUs is to enable laptops with 25 hours of battery life, rather than just 15.
I could use this. I’m at CES 2019, trying out a HP Spectre Folio laptop, and I’m running out of battery.
Intel’s new chips will also reduce the size of laptops, making them thinner, thanks to reducing the size of components that power things such as Thunderbolt 3 connectors. A 12-inch screen laptop could have a motherboard as thin as 7.5 millimeters. Intel is enabling smaller bezels on laptops as well, thanks to its miniaturization efforts.
At CES 2019, the big trade show in Las Vegas this week, Intel is showing off a bunch of new processors, from its Mobileye processors for smart cars to the latest processors for gaming PCs. The latest Intel chips at CES are based on the Sunny Cove chips coming this year. The chips will be used in everything from 2-in-1 laptop-tablet hybrids to liquid-cooled desktops.
“One thing I like about this job is the diversity of platforms,” said Loop. “What we are powering is every person’s greatest contribution.”
Having a larger display gives you an ability to create and to focus on what you’re doing, she said. But that larger display drains power, hurting battery life in a mobile device. The workforce has become transitory, with people like Lyft drivers doing their work on a phone. Writers and graphic artists and accountants and wedding photographers are sometimes just as mobile, but they can’t do their work on a phone. Intel is designing chips for these people, Loop said.
“We know we have to think about workers and our architecture very differently,” she said.
Laptop workers need the performance and responsiveness to edit videos, recognize objects, or parse speech. Sunny Cove will have some new instructions, Vector Neural Network Instructions (VNNI), to enable faster inferencing for artificial intelligence applications, Loop said. Sunny Cove will will also be able to handle cryptography calculations better, thanks to special instructions that enable faster compression — as much as 75 percent faster.
Sunny Cove is a next-generation CPU microarchitecture designed to increase performance per clock and power efficiency for general-purpose computing tasks. Sunny Cove includes new features to accelerate special-purpose computing tasks such as AI and cryptography. Intel has previously talked about 14-nanometer chips, like Cascade Lake and Cooper Lake. The first version of Sunny Cove at 10-nanometer will be Ice Lake.
Sunny Cove will be the basis for Intel’s next-generation server (Intel Xeon) and client (Intel Core) processors later next year. Sunny Cove features include improved designs that allow it to execute more operations at the same time, in parallel. Ronak Singhal, an Intel fellow, said that Sunny Cove finds ways to make processing wider, deeper, and smarter, with more work done in parallel and larger caches to improve latency.
It will also have new algorithms to reduce latency, or interaction delays; increased size of key buffers and caches to optimize data-centric workloads; and architectural extensions for specific use cases and algorithms. Sunny Cove has performance-boosting instructions for cryptography, such as vector AES and SHA-NI, and other critical use cases, like compression and decompression.
Loop said that Intel’s latest Gen11 integrated graphics will also be able to access LPDDR4X memory, which can provide faster bandwidth to feed the memory as graphics processors go to work on games or other 3D applications.
Intel unveiled new Gen11 integrated graphics with 64 enhanced execution units, more than double previous Intel Gen9 graphics (for some reason, the company didn’t compare it against Gen10), that are designed to break the teraflop barrier. The new integrated graphics will be delivered in 10-nanometer processors beginning in 2019.
The new integrated graphics architecture is expected to double the computing performance-per-clock compared to Intel Gen9 graphics. Integrated graphics aren’t high-end by any means, though — Intel noted that a billion consumers use Intel integrated graphics today.
The architecture challenge
There’s a subtext here.
Intel is eager to show it has recovered from a bad manufacturing misstep that caused it to fall off the regular cadence of manufacturing improvements. And so on Tuesday the company demoed a range of chips that were made with its new 10-nanometer (where the width between circuits is only 10 billionths of a meter wide) manufacturing process.
The aforementioned delay in moving to a new manufacturing technology was accompanied by the renewed competitiveness of Advanced Micro Devices, which has captured a higher share of the processor market with its Zen processor architecture.
With the slowing of Moore’s law (the famous prediction in 1965 made by Intel chairman emeritus Gordon Moore that the number of transistors on a chip will double every year), the design and architecture of processors will have to dramatically improve if the coming years are to bring the same pace of technological improvement as we’ve seen in the past 50 years. Intel’s recent slip has made people wonder if Moore’s law, limited by laws of physics for very small devices, is coming to an end.
There are some clever ways Intel is addressing these challenges. One is the Foveros 3D chip-stacking challenge, which is coming for chips debuting in the first half of 2019.
The technology provides tremendous flexibility as designers seek to “mix and match” intellectual property blocks with various memory and I/O elements in new device form factors. It will allow products to be broken up into smaller “chiplets,” where I/O, SRAM (a type of fast memory), and power delivery circuits can be fabricated in a base die and high-performance logic chiplets can be stacked on top.
Intel expects to launch a range of products using Foveros, beginning in the second half of 2019. The first such product will combine a high-performance 10-nanometer compute-stacked chiplet with a low-power base. It will enable the combination of world-class performance and power efficiency in a small form factor, Intel said.
Intel is also continuing to split its chip families into two categories, Core and Atom. While Sunny Cove is Core, Intel is continues to work on its low-end processor architecture, Atom, for devices that need good battery life. One Atom chip, Tremont, will debut in 2019. Another, Gracemont, is coming in 2021, and Nextmont should arrive in 2022 or 2023.
Intel is also building more hardware aimed at things like facial recognition or fingerprint identification, so that it’s easier to authenticate people at a time when 81 percent of cyber attacks are aimed at stealing passwords.