The video prioritizes sensationalist rumors over grounded engineering, turning speculative roadmaps into click-driven hype. It’s a classic example of the tech leak cycle valuing engagement more than verifiable technical substance.
Deep Dive
Prerequisite Knowledge
- No data available.
Where to go next
- No data available.
Deep Dive
INSANITY: Next Gen Ryzen Core Counts & IPC Revealed! Intel Gaming GPUs Aren't Dead??Added:
AMD's next generation of Ryzen processors powered by Zen 6 will increase core counts by 50%. That's a pretty big increase over the 16 cores that we've been enjoying since the Ryzen 3000 series launched way back in the midst of time. But the rumor is that AMD are not going to be stopping there. Oh no. And potentially we could see up to 72 cores for Ryzen not too distant future for the highest end configurations anyway. And that may sound kind of bonkers, but given what we know about Intel's Nova Lake as well as subsequent processors, NovaLink, just so you remember, is 52 cores for this highest end configuration, it makes a lot of sense. But cores alone aren't enough, of course. They also need to have high performance per core. And the good news is IPC, clock frequencies, and lots of other stuff really seems to be coming together for the next generation of Ryzen and Zenbased CPUs. So, we've got a lot of stuff to talk about here.
I've also been speaking to my sources.
Plus, also Intel's discrete GPU plans, at least for gamers, don't seem to be dead. There is some hope and we're going to be talking about that as well. So, with that said, let's jump into this, shall we? So, AMD's Zen 7 Florence, and this is from Moore is dead. Of course, I will leave an article link as well as a link to the video in the description, but I have also reached out to a couple of my own sources about this because it's actually quite interesting. And honestly, some of the stuff here does sound quite insane, but um yeah, I really do think that AMD are going to be pulling out all of the stops. Now, just as a very quick reminder, the next generation of processors from Intel again with Novalink is going to go up to 52 cores, but it does seem that this is a product which is going to be I wouldn't say segmented, but it's certainly going to be aimed at high-end enthusiasts.
Now, that's obviously because it's going to be quite expensive. It's going to be very power hungry and all of that stuff, but um from my understanding, and I leaked this back in, uh when was this, sorry, uh late December, and I've spoken about this a couple of times now, but other sources like JK are also starting to say the same thing. So, I'm pretty certain it's um pretty confident, excuse me, that it's accurate. But basically, from what I'm hearing, Razer Lake is still going to keep the same core count as Nova Lake, but they're going to be a lot more ambitious on the core and really start to focus on IPC and improvements of clock frequency. Now, I've spoken to a few sources as well.
Uh, slightly off topic. I know I'm kind of going around the bush here, but I do think this is really important for context, guys. And basically, there is a lot of debate online. Um, you've seen rumors of course that AMD's higher clock frequency is going to be a big thing with Zen 6, but Intel may have have the IPC gain. Again, that was a leak I put out and then others are starting to say the same thing. So, it's quite interesting because I'm hearing a lot of conflicting information. Actually, one of my sources very recently said that they are actually very confident AMD are going to win very, very comfortably in single thread performance, particularly for gaming. I'm just going to wait and see because at the end of the day, uh, the processors obviously we're not looking at final retail configuration and well, we're just going to have to wait and see just how much room is left in the tank, final clock frequencies, improvements for BIOS, and that's to say nothing of stuff like software optimization. But this now probably gets you into a pretty good understanding of where we're at because Zen 7 is looking at a 15 to 25% IPC uplift over Zen 6. Now, I just want to repeat that one more time. One more time, Cal.
Um, sorry.
Uh, 15 to 25% IPC gain over Zen 6. That is absolutely crazy. But for my from my understanding, I've spoken to multiple sources about this. Now, it's not that Zen 6 sucks. I just want to be very clear, but Zen 7 is pretty much a groundup redesign. It's not to say that nothing of the original design remains, but it is going to be a much bigger redesign across the entire processor.
This is uh of course I mean actually uh Tom here does point out that around 8% of the uplift is just from the cache alone. And again this is not including things like improvements in floatingoint units, integer branch prediction, all the other crap that goes into actually a processor going bro. So my point is that you know what I do think that uh this is going to be a really really big deal. So 16 to 20%. Now again that's in non-gaming applications. And of course one of the big points about all of this is that AMD are going to be doubling down on the cache structure as well. And he basically goes on to say that theoretically this could mean a Zen7 desktop processor could go up to 72 cores with 504 megabytes of L3 cache. Now that's if AMD decides to go absolutely balls to the wall. I think it's very likely that we will see increases in core count. We've seen 32 cores leaked before, of course, for AMD's future plans, and I really do think it's quite likely they may push the boat boat out higher. basically Intel's road map. Nova Lake I do think is going to be pretty good. I do think that Nova Lake is going to be good, but um you can check out this article.
Basically, it's a little old now.
There's a couple of small updates here and there, but basically from my understanding, Intel are going to be going absolutely crazy and eventually they will move to that unified design.
It's a lot more Intel-like actually in its approach. Um sorry, or rather a lot more AMD like I can't speak apparently.
Um, so what they're going to do essentially is adjust things based on power targets of the chip, sorry, of the of the core. They're going to adjust like, you know, specifically the various instructions it can support, the cache configurations and lots of other stuff.
But ultimately, it's going to be based on ecores or at the very least an evolution of the ecores. So I think that Intel are going to be extremely um competitive going forward and the rumor well at least Intel's own reports should I say seem to indicate that their um that the own internal yeah we've heard this before but apparently the own fabs are doing quite well and yields a lot better. Um, I haven't read a huge amount on that recently, but it's going to be very interesting to see exactly what happens with their product cycle. Obviously, I mean, from my perspective, and this is just my personal opinion. I think that more competition or the very least not everyone being completely reliant on, let's say, TSMC. That's only ever a good thing. But yeah, um, going back to what Tom was saying though, basically this thing is going to be absolutely monstrous and I truly believe that these processors will be insane. Now, the question is, is it going to be on AM5?
Now, Tom does think that AM5 will be used for Zen 7. I've mentioned several times that I've heard that AM5 is in contention for some processors or some variants, but I've heard that Zen AM6, excuse me, could be for the higherend Zen CPUs or whatever, you know, the Ryzen iteration is going to be called like Ryzen 11000 or whatever. Um, what of course the big question is how are they going to feed the bandwidth beast? Like I've said a billion times, I'm going to be very curious to see how mobile with the 52 cores manages to hold out. Um, obviously 52 cores, yes, it can handle 8,000 MTS, but um, yeah, I I I mean to be fair, it might even go higher if you're willing to overclock and stuff like that, but it's going to be extremely interesting. The real question of course is what is the pricing and power targets for these things. Hopefully at this point um memory prices will start to crash. There is you know some um evidence that they will. I think it was in Japan recently there's reports that memory prices are starting to become a lot more stable. Uh in Europe in the UK it's not quite as bad like in the US you guys seem to be getting absolutely hammered. I'm not 100% certain why certain regions are so much worse than others. Um, and probably should do a bit more uh um digging into that to be honest with you. But um I want to now switch to something quite interesting. Um again, if you're a regular viewer, you'll know that I've been saying that I don't think Intel Arc is dead. I think Intel are going to continue it. And there is actually a lot of evidence of this. I mean, the fact that they are still doing a lot of work on XCSS and other things.
Um, but according to Jake and there's actually a lot of gold here, by the way, if you're interested in server stuff.
Um, but basically Kepler L2 asked 16 hours ago, Celestial Druid Gaming DGPUs are dead. Celestial variants were canned a long time ago. Druid is up in the air.
And uh, he then adds a little bit more information here. Um uh this is a different um a different uh um part of the thread. Excuse me, I can't speak apparently. No discrete GPUs by late.
Blah blah blah. In December, Battle Mage will be 2 years old. No gaming GPUs. Arc is dead. Arc is fine, but the XC3 P installment was cancelled. It's only a snapshot that spans a year or two. It's a drop in the bucket of the ocean. So, yes, the next generation. Um, honestly, I I kind of thought I mean, maybe I'm maybe I was just missing something, but I honestly did think that um people knew this like it was kind of an old rumor that was circulating quite some time ago. The XC3P variants were cancelled for um the next generation of uh um gaming GPUs.
So, I have reached out to a lot of people. Um, and honestly, the information does seem at this point to be very inconclusive with what's going on with ARC. It generally, however, does seem that Intel does not want to give up on gaming GPUs. If I had to take a guess at this point, the big problem that everyone in the industry is obviously having is that no one's 100% certain of what's going on with the supply chains.
My personal opinion is that Intel really do want to keep on with gaming GPUs because I just think it makes a ton of sense. Not to mention the fact that obviously that research, yes, obviously not all of it is going to be uh directly transferable to say the data center, but they also want of course to have their own iGPUs. They are, as you probably know at this point, they're doing a tie-up of course with Nvidia uh for certain variants as I reported here. I think it's um you know quite well known at this point. Where are we?
Yeah, I was talking about Titan uh sorry, Serpent Lake, excuse me, not Titan Lake. Um and obviously that's Nvidia GPU, but they also want their own uh product IPS as well. So, I do think it's a very good chance that ARC is not dead. I think at this point however they they just don't want to release a product and then obviously it comes out and then they have to charge incredibly high prices because obviously you know memory and everything else is just absolutely nuts at this point. So my personal opinion is that they'd rather get it right at a price which makes sense. Um, I mean, there's a reason, well, again, the rumors, but there's a reason that, uh, you know, Nvidia, uh, rumored to have canled RTX um, super refresh. Um, you know, it does seem like that was going to happen, but at the end of the day, Nvidia didn't confirm that they were going to release it, so you have to report it as a rumor. Um, and it looks like there's a possibility, of course, RTX 50, uh, sorry, 60 is delayed beyond the initial release date, but it's very difficult to know. At the end of the day, we have snapshots of road maps and you have to kind of guess is the road map even fake or you know, have they is it just like one possible plan.
But I do think that um it's very likely that arc is going to continue and quite frankly I think that the market um this is one of those things where the more competition that we have the better. Um so with any luck RDNA5 is also incredibly competitive. like it does seem to be coming on quite well uh from all of the you know the information that we've managed to piece together as well and obviously because RDNA 5 is going to be part of the consoles um it doesn't look like there's going to be much customization if any for the Xbox and possibly even the same for the PlayStation 6. So that's probably going to be good for a lot of developers in terms of optimization. Obviously, for example, the PlayStation is probably going to have its own APIs and stuff like that, but ultimately much of it is going to be transferable, so that's going to be good. With that said, guys, hopefully you have enjoyed the video. If you did, well, it's YouTube. You know what to do. Take care of yourselves.
Have an amazing day. Bye for now.
Related Videos
Agentforce NOW AMA: Build with React and Salesforce Multi-Framework
SalesforceDevs
490 views•2026-05-28
How agent o11y differs from traditional o11y — Phil Hetzel, Braintrust
aiDotEngineer
450 views•2026-05-28
WEB TECHNOLOGIES UNIT-2 | Degree 4th sem BCOM Computers web technologies unit-2 full explanation💯✅
LearnwithSahera
1K views•2026-05-29
More tests are always better? How to use AI to identify tests that bring little value
Alliance4Qualification
335 views•2026-05-29
Search Algorithms Explained in 60 Seconds! 🤖💨
samarthtuliofficial
218 views•2026-06-01
People of Game of Thrones using JavaScript DOM
AltCampus
296 views•2026-05-30
Introduction to Problem Solving Part - 1 | Lecture 1 | Intermediate DSA
ascensionix
107 views•2026-05-29
🚀 BCS613C Compiler Design | Module 1 to 5 Schema Evaluation 🔥 | VTU 6th Sem 💯 #VTU #bcs613c #exam
Pranavaa-y4y
104 views•2026-06-02











