Home
Creators
Search Recent Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register Favorites Keys Review DMs Logout
Community
Telegram ThePornDude
Home Creators Posts Import Register Favorites Logout

Discussing Computex, Zen 6 / 7, RDNA 4, and Nvidia's War on Reviewers w/ Level1Techs (Guest Telegrams) (Patreon)

Published:
2025-05-23 18:13:10
Imported:
2026-06
Tags:

Content

As previously announced, the next episode of Broken Silicon will see Wendell from Level1Techs join us yet again to discuss everything Computex, CPU, and GPU! Wendell is someone who can uniquely speak on more technical subjects, and has a real wealth of knowledge when it comes to all things semiconductors - so don't miss this chance to influence a BS conversation with this much promise. At a minimum, we plan to discuss:

Everything Computex

Nvidia CPUs (Tom knows more...)

Nvidia's War on Reviewers & Truth

RX 9060 XT & RDNA 4

AMD Zen 6 & Zen 7

Intel's Future

You have ~48 hours to submit below!

Last Episode Wendell was on: https://youtu.be/ZK6jAc8LY48?si=1vvzX-EIYOae7wND

Check out Level1Techs Videos: https://www.youtube.com/@Level1Techs/videos

Zen 6 Specs: https://youtu.be/970JyCapx8A?si=HXCgYsM6UPY-IGK1

Zen 6 LP: https://youtu.be/CcXN9xoXwns?si=BAvViKT0a0T0zYYB

Zen 7 Leak: https://youtu.be/bvHrJzB4-MQ?si=m1-iTiSLztuTJQMi

RTX 5080 SUPER 24 GB Leak: https://youtu.be/Z-29AJ5nCyw?si3KQ7qd-TpMdXsC

https://www.theverge.com/pc-gaming/672637/nvidia-rtx-5060-review-meddling-gamersnexus-wake-up-call

Comments

Lo_Res_Gamer

Greetings: I have two Computex questions: 1) Was there any discussion at Computex about how companies have changed or delayed their strategies due to the US tariff situation? 2) For Wendell, one thing I appreciate about the Level1Techs channel is how you highlight upcoming technologies that most tech-tubers aren't paying attention to yet, such as memory over PCIe in years past. Did you see anything that might fit that category of important but overlooked by the media at Computex?

FloridaMan

Hey Wendell, what do you look forward to most for enterprise tech distilling down to consumer platforms?

AI-Soldier789

Hello Wendell and Tom, Intel seems to seek a buyer for their Network department. The explanation is that markets dominated by broadcom can not be accessed. Will a short term cash boost help Intel more then the constant an solid profits.

Timo H

On behalf of Raptor Lake Matt, how screwed are intel cpus with hardware degradation now in 13th and 14th gen? Do you have better understanding than oodle team debugging their hardware from blackbox? Bonus: could Zen7 introduce something similar? AMD has had similar flaws in at least IOD piece. Modern hardware is so complex it is miracle no flaws are anywhere.

xz

Hi Tom and Wendell, hope you’re having a great day. Tom you had mentioned rumour of a “navi 48 ultimate”, anything technical you can share of what’s happening behind the scenes to make this navi 48 ultimate. Also do you think AMD will keep it in the bank to counter Blackwells Super refresh or launch asap if they manage to get it ready.

Cleansweep

Hello Wendell and Tom, Are there any products that you expected to at least get a mention at Computex that didn't show up at all? Obvious shout out to the B770, but also the 9000G AM5 APUs.

Lucas

Hi Wendell & Tom. I was wondering if you see any chance of consumer mainboards getting more pcie lanes in the foreseeable future? Is there a technical reason we're still limited this way or is it just market segmentation? AMD has no reason to move on this right now, happy as they are to sell you Threadripper, but Intel has no workstation product to protect. Might they make a move here to differentiate?

Prior is the theme 999

Another year another big promise of a ROCm support push from AMD. It feels like every year they promise said support but it never happens. With the 60 class launching in a few weeks the true “marketshare” gpu how much of a missed opportunity would it be if they once again fail to deliver on ROCm while radeons worth is so high right now.

Webby

Hi Wendell and Tom! I'd love hear your thoughts on Strix halo and how similar chips will shake things up going forward. Any chance we might get a socketed version? Is the unified memory going to make lower end discreet GPUs obsolete?

Christopher Mullins

Tom and Wendell, do you believe that the public perception of these companies would be better if they increased prices a bit but also provided adequate VRAM for all gpu tiers? For example a 9060 xt 16gb @ $379 and 9060 nonXT 12gb (96bit) @279 and no more 8gb gpus or fake msrps. Do they not see the value in gaining trust and respect of the community?

Woody Chang

Hi Tom and Wendell, At this point, what is Intel's play to stabilize their business, aside from delivering on schedule? People in the past bought Intel because of the highest gaming performance or because "no one got fired buying Intel" but given the degradation issues, less than stellar GPU launch, and not much interest in their mobile offerings, I'm not seeing an obvious avenue for Intel to attack. Thanks!

Dark Helmet

What do you think of Intel's foundry prospects while not being a fully separate company? What can they do to gain the trust of their prospective customers?

LargeCheeseGrater

Hi Tom and wendll, i'd like to hear your thoughts on steam os, and do you think somthing like a AMD LP core can make the diffrence in performance between native windows and linux with proton negligible.

Kiln God

Wendell, how do you feel about ROCm coming to Windows? Personally I'm excited to wrap ROCm in C# for GPU acceleration with C# other than CUDA. When will you be publishing pytorch and other benchmarks of ROCm vs CUDA on Windows?

Batty251

Good morning/afternoon Wendell and Tom, With the upcoming launch of the new Intel Arc Pro B50 and B60 for workstations and AI workloads, do you think we’ll see an increase in the adoption of dual GPU cards, particularly for AI tasks? Or do you believe dual GPUs are more of a niche solution and won’t significantly impact heavy AI workloads?

coltmarshmallow

Good evening, With the steam app coming to Xbox is that a win for valve or Microsoft? Does this have any impact on steamOS coming to desktop?

Prior is the theme 999

How are the nvidia drivers fairing up with professional work? Gaming side it seems like it’s been a mess recently, has that been the same for other applications? Is the ROCm push arriving at the best possible time?

kwerboom

Hi, Wendell and Tom. To Wendell, when you and Steve over at Gamers Nexus made the bold statement about the x86 architecture being on a doomed trajectory compared ARM, how certain is that outcome? Do you have any whispers on the replacement for the x86S initiative? Alternatively, if x86S doesn’t happen, is the future of the PC really Qualcomm, Nvidia Project Digits, and AMD Sound Wave?

kwerboom

Hi, Wendell and Tom. Back about 2005, I started dual booting Windows XP and Ubuntu because Windows XP was a security hazard and the ‘Year of Linux’ was any day now. When Vista came out in 2007, I triple booted Windows XP, Windows Vista, and Ubuntu. When Windows 7 came out in 2009, I just switched back to only Windows because Windows 7 had a good enough experience. I had wanted to give Linux a chance. I’d switched from Internet Explorer 6 to Firebird/Firefox in 2004. The Linux experience at that time was, generously speaking, an uneven experience with the Linux OS having good quality of life features, the productivity applications having features but lacking compatibility with commercial file formats, and the gaming experience being at best not mentioned. I’ve seen that things have recently started to improve with Valve getting involved with SteamOS and the Proton compatibility layer. How much closer are we to the point where a Windows user like me with a Steam account and a GOG Galaxy account being able to seriously consider Linux again?

kwerboom

Hi, Wendell and Tom. As of recent I’ve started to think about Microsoft getting out of the OS business without giving up on Windows. What would it take for Microsoft to take the Window Subsystem for Linux and dump it into the System Folder using shim code between the current front end and the new kernel with a Windows Subsystem for NTFS to cover the proprietary bits Linux can’t replicate? It wouldn’t be the first time Microsoft did something like this. Windows XP is just the Windows 2000 NTFS kernel with the 16-bit subsystem from WinDOS (Windows 95/Windows 98 SE) to run stubbornly outdated games and software. Also, recently Microsoft dumped support for the EdgeHTML engine in Microsoft Edge and replaced it with Chromium based Blink engine.

Josue Garcia

Hi Tom and Wendell, Do you guys that that intel will go full IGPU and abandon their consumer gpu or at least make them more AI driven and have you heard of the performance of panther lake igpu Xe3 architecture

CRCV

Hi Tom and Wendel. I have two questions themes for you. The first one concerns computex. Have you seen any thing that cought your attention for business clients and data center ? Or interesting stuff for homelabs and data hoarder ? The second is on the usage of local AI workload. From what I gather, the current main bottleneck in LLM inference (for CPU) is the memory bandwith. Will we need to wait for DDR6 to see large improvement in CPU inference speed ? Is there any reason why NPU could help on that too (i.e. is there operations they can do more efficiently) ? Or are they still to weak to be of any use in those kind of workload ? Finally, it seems (from my experience) that context length is quite important for letting local llm crunch data. However, I don’t see a lot of improvement on that angle. In your experiences, is it more due to hardware limitation, or software ? Thank you all for your good work.

Prior is the theme 999

Valve looks to be goin all out with steamOS and handing it out to other handhelds. All I do is game on my pc so the moment they make a desktop version capable of having discord and browser functionalities like YouTube, I’ll definitely at the minimum have a separate boot drive with it installed and only use windows for games not capable of running Linux. Do you think this will light a fire under Microsoft? They don’t even have to do much but the minimum which is make sure windows is a working enjoyable experience, but that seems to be hard.

Prior is the theme 999

I get that Microsoft cannot accommodate for every piece of hardware combination possible, but they set the minimum requirements for their operating system. Knowing that, windows should not be this bad. It’s actually comical now I laugh at how much it doesn’t make sense. If the problem truly is ancient code then why was windows 11 not the “new” os without all the bloat considering windows 10 was supposedly the “last windows” I know it technically wasn’t Microsoft who made that claim, but they sure rode it and never disputed or said “no this statement from our dev isn’t true”. Supporting two OS’s is something I know a 3 trillion dollar company can do since they’ve done it every new OS launch.

Prior is the theme 999

What do you think of the new 32gb AI card coming out? We don’t know how ROCm will turn out but being a gamer I don’t know if it’s interesting to someone it’s targeting. Quick shoutout to the naming, AI PRO R9700, that truly is a name of all names. I just know they wanted to add some X’s but felt it would be a mouthful.

Prior is the theme 999

Wendell what are your thoughts on AMD going all out going forward? 2nm for zen 6, 1.4nm for zen 7 and impressive designs like zen 7 3D cores even on Radeon’s side with RDNA 4 which appears to be a design win over Blackwell.

Prior is the theme 999

The AI PRO R9700 according to tech Powerup looks to have a decent jump in things like shaders and clocks over the 9070’s. Is there a possibility we could get the infamously fabled and gloriously rumored 9070xtx with 32gb that will beat the 7900xtx ;).

crumbling_earthblocks

Greetings from Sweden! What are there any news regarding RDNA4 mobile? I am very interested in buying a laptop that finally let's me play Witcher 3 class games in 4k90 (yes, I know it's old) and am wondering if those machines will be cheaper or more expensive than a Strix Halo device? Any other predictions how Radeon might fare this time in the mobile segment?

KingKoro

Greetings Tom and Wendell, what do you think about the Intel Arc Pro B60 and do you think it will cause AMD or Nvidia to respond with some low-priced higher VRAM SKU for AI? Also, have you heard anything about Radeon AI Pro R9700 pricing?

KingKoro

Hi Tom and Wendell, with some Strix Halo Mini PCs starting at 1500-2000€ now and with 128GB of RAM, would you recommend these for starting with local LLM testing? I would expect something like Nvidia Spark to be a lot faster (at double the price), but I assume due to the same LPDDR5X bandwith bottleneck, it would probably not make a big difference on large models. Clustering these Mini PCs with USB4 also sounds interesting.

BespokeEP

Good day gentlemen, I guess this is more a question for Tom, but I’d love to hear both your inputs. Have you heard or do you think any or all of the FSR Redstone update will be included in the “PSSR 2” update coming early next year? According to Cerny the TOPS performance of the PS5 Professional is similar to the 9070, so in theory it should be possible

Gregory S Acker

Hi Tom and Wendell Based on the current hate Nvidia has deservedly heaped on itself with poor pricing and even poorer excecutuion of the last few GPU launches, I'd like to pose a question. They have already achieved major victories in dropping performance per tier while at the same time raising pricing per tier Let's say, hypothetically, that all the consumer pressure works on Nvidia...finally? They relent and start doing exactly what the minority of gamers have been screaming for, while at the same time they continue to reap massive profits from the AI bubble they are propping up. What does "Malicious Compliance" Nvidia look like? Or is that who we have already been dealing with? What kind of products do they try to sell us if they don't have to keep two fingers crossed behind their back as they make gaming products? Will they still continue to keep two fingers back there...?

Chris Rijk

A year ago, Raptor Lake servers were dropping like flies and AMD suddenly launched the EPYC 4004 series, which is physically the same as desktop Zen 4. It’s now a year later and AMD have launched the EPYC 4005 series, which seems to have very wide-spread support on day 1 amongst OEMs. This suggests to me that there’s been a big shift to AMD for low-end servers. What have you seen happen in this market and are Raptor Lake servers still failing a lot?

KarbinCry

If you are asking two questions, please send each separately.

Chris Rijk

Let’s say that Nvidia launches an APU using ARM and GeForce and on day 1 it can run 90% of all games on Steam. Do you think that would be good enough for gamers to switch in volume? Would Nvidia need to undercut x86 with GeForce laptops in pricing? What should Intel and AMD do to counter Nvidia?

KarbinCry

If you are asking two questions, please send each separately.

MarvoloRiddle

This is a fairly long one; Hi Tom and Wendell I came across this fantastic analysis of the 9950x vs the M4Ultra and MAX which confirmed some of my suspicions about bandwidth and compute on some modern CPU's. It compared workloads that are bandwidth limited vs compute limited. It seems the 9950x is quite bandwidth starved for comparison the theoretical bandwidth of the m4 max is equal to the EPYC 9655 which launched at an MSRP of $11852 it makes the launch price of $1999 of the mac studio seem like a bargain even if the bandwidth is shared with the GPU as long as you are running a tasks that stress both. The conclusion he came to which I also agree with is that the Ryzen CPU's (And Intel's but who's counting? lol jk) are WAY overbuilt for their theoretical memory bandwidth we have a GFLOPS/Memory bandwidth of 1946/89.6 for the 9950x and 747/546 for the M4 Max 21.7 vs 1.37 roughly 16x higher. For tasks that have a low operational intensity defined as FLOPS/Byte of DRAM on the low end at about 0.125 to about 1.0 or so in this example, the Apple chip can see up to a 5.6x theoretical advantage and a lot of tasks people do in day to day do might stand to benefit more from the bandwidth than that peak GFLOPS, we need to go all the way to a complexity of about 12.0 FLOPS/BYTE to see the Ryzen match the performance of the m4 Max for example. TLDR: Modern AMD and Intel chips seem to be either very bandwidth constrained for a the amount of peak compute on hand OR have way too much compute for the bandwidth offered depending on your outlook, at least for less complex tasks. Why do you think this is? And will AMD address this issue? Link to the video in question here : https://www.youtube.com/watch?v=dwYaFlnrFgA

Fipa

Hi Tom and Wendell. This is a question about Linux binary compatibility and viability for native Linux games. There is a great article from JengaFX, creators of EmberGen, called "The Atrocious State Of Binary Compatibility on Linux and How To Address It". Too keep it short, they state: 1. Containerization (like Flatpack) is not feature ready for pro tools and games 2. That GLIBC (pronounced g-lib-c) is a massive, monolithic system that handles too much. With the GNOME Foundation not caring about breaking compatability with older versions, causing software build years back to stop working. What are your thoughts? Is there any hope for native Linux games to be able to run years after they have been released, without needing to use containerization?