Intel is also adding a new VT (threshold voltage) pair to its lineup. Typically, we see four flavors of VT pairs: HVT, SVT, LVT, and ULVT, noting high, standard, low, and ultra-low threshold voltage, respectively. The lower the threshold voltage, the less power a transistor needs to activate, and therefore the more power it leaks. So, ULVT transistors are the most performant, but they leak the most power, while HVT transistors are the least performant but leak the least amount of power. Chip designers need to balance these different flavors of threshold voltage for their application.
The new VT pair adds another option: ULVTLL, or Ultra-Low Voltage Threshold Low Leakage. It lives between ULVT and LVT, offering better performance than LVT but lower leakage than ULVT. Like the new transistor design, it gives designers more flexibility when designing a chip for 18A-P.
In addition to the expanding 18A-P’s capabilities, Intel says the revision comes with a 20% to 40% improvement in thermal resistance, as well as a 10% to 30% improvement in via resistance at “perf critical layers.” The reduction in thermal resistance comes from grinding the wafer down with advanced EDA tools for better thermal conductivity.
Intel 18A is currently ramping in two U.S. fabs, and although the company has taken some heat for poor 18A yields , Intel says that defect rates continue to drop along with its expectations. 18A is being used already in Panther Lake and Xeon 6+, and Intel is reportedly in talks with Apple and Nvidia to build on 18A, as well.
(Image credit: Intel) (Image credit: Intel) (Image credit: Intel) (Image credit: Intel) (Image credit: Intel) (Image credit: Intel) (Image credit: Intel) (Image credit: Intel) (Image credit: Intel) (Image credit: Intel) (Image credit: Intel) (Image credit: Intel) (Image credit: Intel) (Image credit: Intel)
Follow Tom's Hardware on Google News , or add us as a preferred source , to get our latest news, analysis, & reviews in your feeds.
Jake Roach is the Senior CPU Analyst at Tom\u2019s Hardware, writing reviews, news, and features about the latest consumer and workstation processors. ","collapsible":{"enabled":true,"maxHeight":250,"readMoreText":"Read more","readLessText":"Read less"}}), "https://slice.vanilla.futurecdn.net/13-4-24/js/authorBio.js"); } else { console.error('%c FTE ','background: #9306F9; color: #ffffff','no lazy slice hydration function available'); } Jake Roach Social Links Navigation Senior Analyst, CPUs Jake Roach is the Senior CPU Analyst at Tom’s Hardware, writing reviews, news, and features about the latest consumer and workstation processors.
thestryker The characteristics they've targeted for improvement with 18A-P is really making me wonder if DMR was originally supposed to be 18A and the delays are to get volume set for 18A-P. I'm betting there are still fab volume concerns which will prevent client processors from utilizing the new node any time soon but the improvements seem like exactly what you'd want for desktop parts. Reply
JRStern Intel says that defect rates continue to drop along with its expectations. Huh? Perhaps you mean "drop as expected". Also, defect rate is not quite the same thing as yield. Reply
IntelUser2000 The 9% perf improvement is something we used to gain with a LOT less work with small modifications. When these guys tell you "14A" or "A14" it really is marketing. Because while the numbers show you a full node gain, they are fraction of what it was just few years ago. 14A is just 30% density over 18A, while still taking 2 years to arrive. We used to get 2x easy. 14A in original terms is 16A. 18A would have been called 24A. Intel 4 is intel 5. Note that "7 or N7" is also a diluted meaning, as TSMC N7 is equal to Intel 7, which is a renamed, enhanced Intel 10nm. So really if we bring things back to reality the actual numbers are like the following: -Marketing calls it 7, 3, 18A and 14A -It's 10nm, 8nm, 6.6nm, 5nm Note that density-wise, it's even worse. I'm giving above names taking performance into account, as the gains there have been less pathetic. 14A/5nm should have been 4x the density of 10nm, but it's actually less than 3x. So density wise, "14A" would be 6nm. It would take 8 years to go from Intel 7 to 14A. Intel's 14nm brought the same density gain in a SINGLE generation over 22nm(specialized cases like E cores and GPUs but still). It gets worse after 14A. The only "density gains" are coming from stacking dies, which means the cost per transistor barely goes down, as now you need two complex silicon dies. And power density would multiply as you need to stack them. Reply
Stomx Since 14A name now comes from the transistor gate length 1.4nm and not from the transistor size there is no shrink scaling like it was before. The transistor size still is at its enormous 40-55nm scale Reply
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/tech-industry/semiconductors/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/semiconductors/intels-performance-enhanced-18a-p-process-enters-risk-production-enhanced-node-promises-9-percent-performance-improvement-at-iso-power#main
- https://www.tomshardware.com/membership
- U.S. gov't asks court to dismiss NAACP lawsuit against Elon Musk's xAI over use of unpermitted gas turbines — DOJ says Grok model running at Colossus 2 ‘support
- NVIDIA, KRAFTON, NC and Reigning ‘League of Legends’ Champions T1 Celebrate RTX Spark at Korea’s PC Bangs
- Get an RTX 5090 gaming laptop for less than $3,000 — Acer's 16-inch Predator with 2TB of storage and 32GB of RAM is now $500 off
- Cooler Master MasterHUB review: A modular stream deck with potential
- Dell's $699 XPS 13 laptop is now available with the MacBook Neo in its sights — entry-level XPS design comes with Wildcat Lake, 8GB of RAM, and a 512GB SSD
Informational only. No financial advice. Do your own research.