Intel Is Finally Shipping Ice Lake in Volume

Intel Is Finally Shipping Ice Lake in Book

This site may earn chapter commissions from the links on this page. Terms of use.

During Intel'southward quarterly conference call last calendar week, CEO Bob Swan confirmed that the company is, at long last, moving into volume production on 10nm. If you lot thought Intel had basically given up on scaling its procedure engineering into the new node, that's not the case.

Swan fabricated a number of comments related to 10nm during the call. Ice Lake servers accept been sampled to enterprise customers, with early production expected in 1H 2020 and volume production in the back half of the year. Cooper Lake (14nm) will share a platform with Ice Lake when those server parts launch in 2020. Regarding 10nm client launches, Swan said:

We began aircraft Water ice Lake clients in the 2nd quarter supporting systems on the shelf for the holiday selling season and wait to send Agilex, our first 10-nanometer FPGA later this year.

We now have ii factories in full product on 10-nanometer. We are as well on rail to launch vii-nanometer in 2021. With a roughly 2x improvement in density over 10-nanometer, our 7-nanometer procedure, which volition be comparable to competitors' five-nanometer nodes, and will put united states on step with historical Moore's Constabulary scaling.

Mobile in Q4 2019, Server in 2H 2020, Desktop …

Intel's electric current plans for Ice Lake/Sunny Cove in its desktop CPU SEEAMAZON_ET_135 See Amazon ET commerce product families are unclear. If a Dell roadmap that leaked earlier this year is accurate, Comet Lake will refresh Intel'southward product line through Q4 2020 with up to 10 cores, but all the same built on 14nm. We've seen various predictions virtually the state of Hyper-Threading; the most recent ones claimed Intel will reactivate it after removing it for the 9th Generation family. Restoring Hyper-Threading support would definitely improve performance compared with not-having information technology on various parts, merely whether Intel will actually take this step is even so uncertain.

Swan was actually rather open nearly expecting competitive force per unit area from AMD. While Intel has been talking a bully deal nigh the possibilities of a $300B expanded TAM (based on the total valuation of the spaces Intel competes in), he too took intendance to say that Intel expects to exist facing a reinvigorated AMD.

"Stepping back and just looking at the macro surroundings over the next several years and particularly in the 2d half of the year on the information middle side, what we've indicated is it will be a much more than competitive environment," Swan said. Later in the phone call, he spoke to the topic again:

And our expectations over time are to protect our market place share position, while continuing to invest in new prospects for growth… I'd say the competitive intensity on the PC side started probably in the first part of 2017. And during that time frame, we've either protect our position, while moving end customers up to higher performance products that generate higher ASPs and with that have the capacity likewise to fight back and run into comps in targeted areas, where we need to.

This is pretty frank talk, by Wall Street standards. The i thing Swan doesn't exercise is speak to when we might see Ice Lake/Sunny Cove CPUs on desktops. Right at present, it looks every bit though nosotros're nonetheless looking at a 2021 time frame for desktop 10nm, and 7nm chips are supposed to debut that year likewise, though Intel has committed to leading the 7nm accuse with GPUs, not CPUs.

Intel-Skylake-Summary

The Water ice Lake mobile CPUs that Intel has unveiled to appointment are reputed to exist up to 1.18x more efficient than Intel's old Sky Lake CPUs in terms of IPC, merely Intel has given back a great bargain of its clock speed gains over the by 4 years to deliver that improvement. The Skylake Core i7-6660U was a two.4GHz CPU with a 3.4GHz maximum clock speed. Ice Lake is one.18x faster in terms of IPC and runs at upward to 4.1GHz. The real-world gains should, therefore, be significantly larger, once clock and IPC are both factored in — except, Ice Lake is the follow-up to Whiskey Lake, and the improvements relative to that fleck are less certain. With a 4.8GHz single-core maximum, Whiskey Lake was clocked upwards to 1.41x faster than Skylake in the first place.

In brusk, information technology'south possible Ice Lake will exist much faster than Skylake but roughly on par with Whiskey Lake. Given that we take no idea what the operation or power characteristics of Intel's next-generation mobile GPU are, nosotros'd also need to know how its power consumption and capabilities cistron into Intel's maximum defined clock speeds. The GPU configuration is much wider on these new chips, and that could definitely be eating into the full headroom Intel gives these processors. 15W, afterwards all, is not a terribly large envelope.

With Intel's 10nm desktop chips nowhere in sight and AMD's latest Ryzen 3000 APUs SEEAMAZON_ET_135 See Amazon ET commerce nevertheless based on its 12nm 2d-generation Ryzen refresh, nosotros take an amusing situation to consider. Even in one case Intel has shipped 10nm chips, its 10nm fries will not compete against AMD'southward 7nm fries. That won't happen until either AMD ships 7nm mobile parts or Intel ships 10nm desktop and server parts. We haven't heard annihilation about a 7nm APU refresh in 2019. Bold AMD doesn't pull 1 of its hat, we may not see AMD 7nm confront-off with Intel 10nm until sometime between April and June 2020.

Granted, I don't remember AMD is going to complain about having room to stretch its metaphorical legs. But normally when 2 companies start talking about their cutting-border procedure node deployments, we await to actually encounter CPUs facing off against each other shortly thereafter.

At present Read: