Follow Tom's Hardware on Google News , or add us as a preferred source , to get our latest news, analysis, & reviews in your feeds.
Anton Shilov is a contributing writer at Tom\u2019s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends. ","collapsible":{"enabled":true,"maxHeight":250,"readMoreText":"Read more","readLessText":"Read less"}}), "https://slice.vanilla.futurecdn.net/13-4-22/js/authorBio.js"); } else { console.error('%c FTE ','background: #9306F9; color: #ffffff','no lazy slice hydration function available'); } Anton Shilov Social Links Navigation Contributing Writer Anton Shilov is a contributing writer at Tom’s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends.
beyondlogic Admin said: Intel details improvements of 18A-P that include higher performance, lower power, reduced variability, improved yields, and more. Intel details 18A-P process node, touts higher performance, lower power, and better thermals — 9% more performance, thermal conductivity improved b… : Read more Good if it's true real world will tell. Reply
garbilkee When was the last time Intel actually delivered on something they said they would. Exactly. Reply
usertests new types of gate-all-around RibbonFET transistors That's a mouthful. It looks nice, especially the efficiency improvement on a design compatible tweaked node. This is perhaps why Apple and other fabless chip designers are rumored to be considering using 18A-P. Intel makes sharp reversal, is 'going big time into 14A,' says CEO Lip-Bu Tan — 'serve the customer well' remark hints at external client I thought the energy was behind pitching 14A for external customers. Maybe the supply desperation is reaching new heights. Reply
JRStern But does this change anything about 18a in regards to YIELD? And now what about 14a, is there going to be a 14a+ also, before it's even begin? This may be good news, even if it's multiplying work in progress, increasing capex costs, delaying delivery, crushing demand for the unoptimized process, etc. Reply
Gururu They seem to be having a lot of success around this process node. The contract buzz has the valuation sky high right now (record levels). Just about everything reported for their 18A production last year was doom and gloom, now squeaky quiet. Not seeing too much negative coverage on the 14A progress right now. Its either straight to the moon or to hell. Fun to watch. Reply
bit_user usertests said: I thought the energy was behind pitching 14A for external customers. They don't have enough fab capacity for that. Not since they started delaying the buildout of their new fabs, would they have had enough capacity to ramp it up for a meaningful amount of external business, I think. JRStern said: But does this change anything about 18a in regards to YIELD? Yeah, their statements all seem very carefully worded to highlight positive aspects, but I'm not sure the reality is quite as good as their pitch makes it sound. Gururu said: Just about everything reported for their 18A production last year was doom and gloom, now squeaky quiet. Not seeing too much negative coverage on the 14A progress right now. What I find telling is how they said 14A is yielding better than 18A did, at the same point. But, 18A had a rough ramp, so that's really not saying much. Reply
Lorguid Admin said: Intel details improvements of 18A-P that include higher performance, lower power, reduced variability, improved yields, and more. Intel details 18A-P process node, touts higher performance, lower power, and better thermals — 9% more performance, thermal conductivity improved b… : Read more I imagine that "18A-P is a heavily optimized version of 18A-P" was meant without the "-P" at the second occurrence of the process name. Reply
thestryker This mostly looks like exactly what one would expect from a node revision. I think the most notable thing here is the work on parametric yield as this is something rather important for outside customers and less so for Intel. Historically Intel has used one die for the majority of the SKUs in any given segment so significantly cutting down a chip isn't as important (for example: RPL and ARL 8/16 die were cut all the way down to 6/4). As for the yields conversation they improve over time or nodes get completely abandoned (see Samsung 3nm) and since there's no sign of the latter it's a safe bet the former is happening (albeit at a slower rate than they'd like). A node revision by itself isn't going to improve yields unless there's a specific change intended for that exact reason which there doesn't appear to be here. Reply
usertests thestryker said: This mostly looks like exactly what one would expect from a node revision. IMO the 18% efficiency improvement at same performance is better than a typical node revision. And I find this part important: To achieve these improvements, Intel introduced new types of gate-all-around RibbonFET transistors, including high-performance devices with enhanced contacts as well as new low-power devices. Designers can now push higher frequencies on critical paths and reduce power consumption in less demanding regions, which greatly improves overall performance efficiency. It reminds me of TSMC's FinFlex. Good to have, great for some of Intel's own heterogeneous processors. Does anyone know the current relationship between 18A, 18A-P, and backside power delivery? I thought it was optional and not playing a role with any of the stated improvements here. Reply
thestryker usertests said: IMO the 18% efficiency improvement at same performance is better than a typical node revision. Depends on what you're looking at since if I'm remembering correctly that's what Intel 4 to Intel 3 was. Keep in mind that 18A has more limited voltage than prior nodes which is also a place being improved. This is not to say 18% is anything to scoff at just that it's not an anomaly. usertests said: Does anyone know the current relationship between 18A, 18A-P, and backside power delivery? I thought it was optional and not playing a role with any of the stated improvements here. While it's supposed to be optional I think it's safe to say Intel is always going to be putting their best foot forward and unless stated it's included. I haven't heard of another iteration of PowerVia yet. Hopefully next month when VLSI happens more details will be publicly released. 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/intel-details-18a-p-process-node-touts-higher-performance-lower-power-and-better-thermals-9-percent-more-performance-thermal-conductivity-improved-by-50-percent#main
- https://www.tomshardware.com
- Microsoft now recommends 32GB of RAM as the future-proof 'no worries' config for gaming — 16GB becomes the new 'practical starting point' during the RAMageddon
- Tag, You’re It: GeForce NOW Levels Up Game Discovery With Xbox Game Pass and Ubisoft+ Labels
- NVIDIA and Google Cloud Collaborate to Advance Agentic and Physical AI
- NVIDIA and Google Cloud Collaborate to Advance Agentic and Physical AI
- Japan is deploying ultra-cheap cardboard drones built for swarm warfare and expendable combat missions — $2,000 expendable combat drones cost less than some gam
Informational only. No financial advice. Do your own research.