New Details Leak on Intel ‘Whiskey Lake’ 14nm Mobile CPUs
When Intel announced it would delay 10nm production, it also announced a new family of 14nm chips that would serve as a stop-gap replacement. We now know more about the CPUs themselves, thanks to disclosures from HP, Asus, and Synnex, and the new chips aren’t necessarily the warmed-over parts you’d expect from a point refresh on a mature process node. Intel has refused to comment on rumors and leaks, so we won’t be hearing their opinion on these new parts just yet.
Formal memory support bumps up to DDR4-2667 from DDR4-2400, though the performance advantage from the shift isn’t likely to be huge. At first glance, the huge kicks on turbo clocks are quite impressive, with gains of 15-20 percent and no change in TDP. But Intel’s TDP’s figures are calculated at base clock and refer to how much power the CPU’s cooling solution needs to be able to dissipate, not the power consumption of the chip.
The frequency gains are huge on paper but we don’t know anything about how well they translate into real-world performance. Intel no longer discloses its per-core boost clocks, meaning the new Core i7-8565U could have a huge single-core boost to give it a marketing shine, only to duplicate the clock behavior of the Core i7-8550U at every other point.
Of course, it’s also possible that the opposite is true. Intel could have tweaked these chips to be more aggressive about keeping their clock rates, in order to create a larger gulf between them and their predecessors. The company now offers OEMs a great deal of flexibility when setting clock speeds and skin temperature points. This can lead to erratic performance in some cases and to scenarios in which laptops throttle below their minimum advertised clocks in others and makes it even more difficult to determine when a product is or is not an upgrade.
There’s another wrench in the works, however, and it’s this: It’s been common short-hand to refer to Intel’s 8th Generation as being based on Coffee Lake, but that’s not strictly accurate. When Intel launched its 8th Generation a year ago, it told us that the new mobile chips were based on “Kaby Lake Refresh,” as opposed to Coffee Lake. That meant the Core i7-8650U, i7-8550U, i5-8350U, and i5-8250U are all built on Intel’s original 14nm refresh, 14nm+. Coffee Lake hit higher clocks than Intel’s first 14nm+ refresh, and those benefits could have carried over into mobile — but without knowing what turbo clocks Intel set for itself, we just don’t know. The higher turbo clocks should improve system responsiveness in short bursts, even if the overall clock frequencies haven’t been tweaked much beyond the single-core boost.
Continue reading
Intel Launches AMD Radeon-Powered CPUs
Intel's new Radeon+Kaby Lake hybrid CPUs are headed for store shelves. Here's how the SKUs break down and what you need to know.
RISC-V Tiptoes Towards Mainstream With SiFive Dev Board, High-Performance CPU
RISC V continues to make inroads across the market, this time with a cheaper and more fully-featured test motherboard.
VIA Technologies, Zhaoxin Strengthen x86 CPU Development Ties
VIA and Zhaoxin are deepening their strategic partnership with additional IP transfers, intended to accelerate long-term product development.
What Does It Mean for the PC Market If Apple Makes the Fastest CPU?
Apple's M1 SoC could have a profound impact on the PC market. After 25 years, x86 may no longer be the highest-performing CPU architecture you can practically buy.