AMD rising and Arm Macs: How Intel’s endless 10nm struggles cost it so much
By Brad Chacos
PCWorldOct 9, 2020 11:24 am PDT
Image: Gordon Mah Ung/IDG
Intel’s endless 10nm nightmare has cost it so, so much.
It all started on September 5, 2014. That’s the day Intel introduced 5th-gen Core M chips based on “Broadwell,” the company’s first processors built using the 14-nanometer manufacturing process. Despite some manufacturing woes that pushed Broadwell back from its expected 2013 release, Intel’s offering served as the vanguard of processor technology. AMD remained stuck on the 28nm process with its abysmal Bulldozer architecture. A mere month later, the Apple iPad Air 2 launched with a custom A8X chip that couldn’t quite hang with Intel’s older Haswell CPUs in Geekbench—but it was getting close.
The death of Intel’s vaunted “tick-tock” manufacturing process served as the canary in the coal mine. For years, Intel’s processors followed the tick-tock cadence, releasing upgraded CPUs with a smaller manufacturing process one generation, then a new microarchitecture built on the smaller process the following year. Tick-tock; tick-tock. The relentless innovation must have sounded like the doomsday clock to then-floundering AMD.
The troublesome 10nm process killed it. In early 2016, Intel confirmed that tick-tock was dead, adding a third leg to the process dubbed “optimization.” Intel’s 7th-gen “Kaby Lake” processors were flagged as the first “optimization” architecture in 2017, another 14nm chip following the releases of Broadwell and then Skylake. Considering that Intel still has yet to release 10nm desktop processors, it comes at no surprise that neither tick-tock nor tick-tock-optimization has been mentioned since.
Tick-tock’s demise obviously delayed 10nm’s arrival. Originally slated for a 2016 launch, by early that year Intel said that its first 10nm would be “Cannon Lake” in the second half of 2017, a die-shrink of the optimized Kaby Lake architecture. It wouldn’t launch until mid-2018, and only then in a handful of low-end systems with integrated graphics disabled. Later that year, we said “Cannon Lake is barely squeaked out in any reasonable volume.” The release went so poorly that when Intel previewed 10nm “Sunny Cove” cores to the press in December 2018, it also vowed to decouple its architecture and IP from manufacturing process as much as possible to prevent stalls like this from happening again.
The 10nm question occurs at 17:30 in the video above.
Intel CEO Bob Swan blamed the delays on sheer ambition at Fortune’s Brainstorm Tech Conference in mid-2019, citing the company’s history of “defying odds.” “At a time when it was getting harder and harder, we set a more and more aggressive goal. From that, it just took us longer… We prioritized performance at a time when predictability was really important,” he said. “The short story is we learned from it and we’ll get our 10nm node out this year. Our 7nm node will be out in two years and it will be a 2.0x scaling, so back to the historical Moore’s Law curve.”
Our performance analysis declared that Ice Lake’s true appeal lay in its vastly upgraded graphics chops. “Our general takeaway is that the CPU is on a par with, or somewhat faster than, today’s laptops in most conventional applications that don’t touch the special sauce of improved encryption, AI or encoding features,” we said. “In applications that touch those features, though, it’s a major upgrade over existing 14nm chips.” It’s telling, however, that Intel’s “10th-gen” Comet Lake H gaming processors continue to use the 14nm process and its higher clock speeds. Newer 11th-gen, 10nm “Tiger Lake” chips deliver much bigger single-threaded performance gains in small laptops thanks to improvements like an innovative “SuperFIN” transistor design, but remain restricted mostly to ultra-thin laptops at the moment.
Intel hasn’t sat still for half a decade; it’s been fine-tuning the performance of its 14nm processors, introducing features like AVX-512 instructions, Thunderbolt 3, Wi-Fi 6, and greatly enhanced integrated graphics.
Intel’s also been pushing what’s possible with 14nm hard to keep up with the competitive landscape. While the 14nm Core i7-6700K debuted with four cores and 4.2 GHz Turbo speeds, the new 10-core, 20-thread Core i9-10900K can hit up to 5.3GHz under optimal conditions. That might be why we haven’t seen 10nm processors hit desktops yet. Intel’s tuned the 14nm architectures so finely that it’s hard to imagine newer 10nm coming anywhere close to the same raw speeds.
Intel’s 10nm struggles have opened the doors for its rivals.
After the disastrous Bulldozer, AMD struck back big-time with its new Ryzen processors, built using TSMC’s most advanced processing nodes. Ryzen debuted in 2017 as a core-loaded 14nm monster that slaughtered Intel in multi-threaded tasks and overall value, but lagged in gaming performance. Lower prices and significant IPC improvements helped 2nd-gen Ryzen supplant Intel’s 8th-gen Core i7 as our recommended flagship processor. Then, with Intel mired at 14nm, AMD took the technological lead with 3rd-gen Ryzen CPUs built using an advanced 7nm process with support for blazing-fast PCIe 4.0 storage. (Intel’s latest 10th-gen chips remain on PCIe 3.0.)
Mentioned in this article
AMD Ryzen 9 3900X 12-core, 24-Thread Unlocked Desktop Processor with Wraith Prism LED Cooler
Ryzen processors dominate our list of the best CPUs, and AMD’s taking full advantage. The company’s gained market share for 10 straight quarters, hitting nearly 20 percent of total desktop pie for the first time since 2013. Ryzen desktop CPUs accounted for 86 percent of sales at Germany’s enthusiast-focused Mindfactory this past February, and they’ve remained atop Amazon’s CPU bestseller list for years now. “In desktop, overall demand for our latest Ryzen 3000 and prior generation Ryzen 2000 processor families were strong, both of which continue to top retailer bestseller lists and have more than 50-percent share of premium processor sales at many top global etailers,” CEO Lisa Su said to investors in April.
On November 5, AMD plans to complete its coup with Ryzen 5000 processors that outpunch their Core rivals in gaming performance on the back of a massive 19 percent IPC uplift. Throughout AMD’s desktop resurgence, top-notch gaming performance helped Intel stay competitive. If Ryzen 5000 manages to seize that crown, Intel’s desktop prospects look bleak in the near future, even with 11th-gen “Rocket Lake” CPUs coming sometime in the first quarter of 2021. Leakersexpect Rocket Lake to remain on the 14nm process, though it may switch away from Intel’s ancient Skylake-based cores for the newer microarchitecture.
Making matters worse for Intel, 7nm Ryzen 4000 mobile chips introduced in 2020 enable performance that all but the highest-end Intel-based systems just can’t match (though Intel’s new 10nm “Tiger Lake” chips excel in small, portable laptops). “To put AMD’s Ryzen 4000 in perspective, you have to understand that in AMD’s 50-year history, it has never beaten Intel in laptops,” we said in our review. “…AMD’s Ryzen 4000 can spar with laptops that weigh two to even three times as much. This is something we frankly didn’t expect. Ryzen 4000 is without a doubt the most game-changing performance laptop CPU we’ve seen in years.”
Laptops remained a key bastion for Intel, but AMD’s knocking. Notebooks like the Asus ROG Zephyrus G14, Acer Swift 3, and the Dell G5 15 SE deliver killer performance at killer prices. AMD expects over 100 laptops with Ryzen 4000 to launch in 2020.
Keep reading to learn how Apple just dealt Intel another crushing blow.
Apple historically has little patience with partners that fail to meet expectations. The company’s leadership can’t be happy that Intel’s processors have largely stalled in performance upgrades over the last half-decade.
During that time, Apple’s own hardware team has kept the pedal to the medal. Ars Technica’s testing shows that the A12Z Bionic inside the new iPad Pro delivers GeekBench scores higher than the Core i5 inside the 2020 MacBook in both single-core and multi-core tests. It actually comes closer to the Core i9 inside the 2019 MacBook Pro in single-thread performance despite the iPad Pro’s tighter thermal constraints.
GeekBench is just a single benchmark, and usurping the Intel Xeon chips inside the higher-end MacBook Pros will be a difficult challenge. Still, Apple obviously feels its future is more secure in its own hands rather than Intel’s. The transition from Intel to ARM will be painful for Mac users, but it should be fun to see what Apple’s engineers can whip up now that the chains are off.
Either way, it’s yet another in a series of body blows for Intel. NetMarketShare puts MacOS at about 10 percent of the total PC market, and analyst firms place quarterly sales for Macs in roughly the same ballpark. Losing 10 percent of the valuable laptop market hurts, especially when you consider that AMD’s hoovering up more customers in the desktop and server markets, and making serious inroads on laptop integrations too. All those small losses start to feel mighty big when you add them together.
Intel’s endless 10nm nightmare has cost it so, so much—but Chipzilla’s fought back from behind before. After AMD stunned the world by beating Intel with Athlon 64 nearly 15 long years ago, Intel responded with the stunningly successful Core architecture that heralded over a decade of unrivaled dominance. It could happen again, but the odds of success seem far less likely this time around. AMD’s firing on all cylinders, and Apple’s not coming back. After a half-decade of stagnation, Intel has a fierce fight on its hands.