In one of the X870/X870E motherboard previews (forgot which outlet covered it), when talking in a pre-event Q&A about the new mandatory 16x PCIE 5.0 GPU + PCIE 5.0 lanes for NVMe component, they said AMD hinted at "PCIE 5.0 GPUs" coming out "soon" (in the context that more 5.0 for GPU future...
Well, it's looking more and more like I predicted, that Zen5 will be more like Zen3 (a big core redesign) and Zen6 like Zen2 (a big die/packaging redesign).
Yeah given AMD's history, airing on a very conservative side in the runup (internal leaks or announcements) to a launch ("8%+" IPC for...
Anyone else think with the mid-gen console update/upgrade coming up pretty soon (which I'm almost sure might get memory pool bump), we're in for even more pain for VRAM-stricken GPUs next year and beyond?
I can see a 12GB redux of this thread not too far off lol
Not exactly an answer, but Eurogamer/DF claims AFMF/FSR3 runs on async compute engines and speculate that async compute heavy games may see less gains, but also the opposite.
Buying next year's version of "8GB 3070" and thinking you're better off? lol yeah no
Also, I think you're grotesquely overestimating how many people cared or even knew of such a thing called "N32 delayed to get fixed, just wait". I call it the "enthusiast/nerd bubble", or "forum bubble" if you...
Also the new Avatar game, a AMD sponsored title, advertises FSR (2 tho, FSR3 TBD) in it's PC features trailer, despite also launching with DLSS support as well.
I think some studios, partnered up with the GPU vendors or not, just don't bother with some of these features, particularly nVidia's...
I was far from ever considering 4070 (or any nVidia GPU for the foreseeable future), but this 7800XT price reveal sort of made my day, even tho it's stretching my budget a bit. Went from considering a 6650XT/7600 or the most basic/cheap 6700XT I can find to a full-blown "$500" card smh lol
The...
Based on this:
https://gpuopen.com/fsr3-announce/
It seems FSR3 has 2 main components, one is the frame generation (likely the only part most are thinking of) and the other is the upscaling. Which to me means that FSR3 also supersedes FSR v2.2.1 or whatever the last build of FSR2 was. Unlike...
Upselling go BRRRR
Based off of AMD's own data (website and press slides), 7800XT is 21% faster than 7700XT @1440p, they even admit the price/performance is skewed in 7800XT's favor with a slide.
They didn't tease just the imminent FSR3 and HYPR-RX BTW, they also showed Anti-Lag+ (RDNA3...
Completely irrelevant. AMD's own listing shows 2800MHz as well as third part tests of 7940HS show it clocks up to 2800MHz out of the box.
This is like people pointing to TPU for data, which is notoriously inaccurate. They still have R9 7040HS chips at 3000MHz, for example.
Or showing RTX 3070...
That's Red Dead Redemption 1(one)... on PS3... on PC through RPCS3 emulator...
...where you on some funny stuff when you wrote that?
I like how one low-key troll (usual suspect) placed a seed of doubt and now everyone is talking about how ETA Prime is or isn't some fake ass AMD shill or idiot...
AFAIK Phoenix also supports LPDDR5X-7500, some announced handhelds seemingly come with it, no idea on ultraportable laptops yet tho.
Judging by the frametime graph in those tests, which look way more spiky than 680M/RDNA2's.... 780M/iGPU RDNA3 is clearly still on early drivers in all these...
You're using SKU nomenclature for comparison in the first and die segmentation in the second and act like it's the same argument.
That's extremely flawed reasoning.
I could just as easily say the $999 MSRP 7900XTX (top N31 bin) was clearly priced lower than the $1099 6950XT (top N21 bin)
But...
So you're telling me the 7900 XTX announcement slide that showed it's up to(TM) 82% faster in ray tracing than 6950 XT pushed people into buying 4080s?
lol what a bizarre argument
IMHO MLID and his friend put it pretty well, AMD can't ask much more than $299 for a 7600XT that's probably close to but not quite a 6700XT in raster and maybe beyond a 6750XT in ray tracing, at a quite bit lower power envelope, BUT just 8GB of VRAM, considering there's already the 10GB 6700...
Maybe, but I'm not sure selling virtually none and having continuous oversupply problems on their hands is preferable.
Currently RDNA3 and RDNA2 SKUs don't really overlap in price categories, so that point is moot. And anyway, RDNA3 is far from selling terrible, all things like market slowdown...
Well, then there's the whole aspect of their oversupply of RDNA2 cards...
And right now they're selling very well, so I doubt AMD is hurting with this division too much.
That being said, still, I hope they also show something about N32/further cut N31 at Computex.
I wonder if Strix Point will have only 1 monolithic die (up to 4C+8c/16CU), or split into 2 like PHX. Same for Grey Hawk refresh.
Those, along with PHX2 and Mendocino may fit into fanless designs.
RDNA3+ is allegedly implementing the scalar arithmetic logic units planned for RDNA4 (Kepler...
Speak of the Devil...
https://www.igorslab.de/en/nvidia-stoppt-nicht-nur-die-belieferung-der-aic-mit-chips-fuer-die-geforce-rtx-4070-und-amd-zeigt-zur-computex-wohl-kleinere-karten/
4, PHX2 has 4 compute units. But 2 WGPs, tho Geekbench does not report WGPs AFAIK.
Either way, like I said, GB may not be the best source for obtaining concrete specs on unreleased products.
Well, that's unfortunate. I guess the alleged super-APU "Sarlak" will be RDNA3+ fastest incarnation then.
Will defo look into it if I have the cash on hand, will probably make for a helluva mini/micro desktop PC/gaming console!
There, that's the pretty good part. How exactly is that a bad...
We got burned with basing data on what GB says before. It does not have a authoritative hardware detection system, particularly on yet-to-be-released hardware. And it's just one data point anyway.
But we'll see, highly doubt that's the CU count tho.
From the recent potentially true MLID AMD APU info dump, Hawk Point potentially being a Phoneix+, Phoenix w/ RDNA3.5/RDNA3+ (same 6WGP config) in early 2024, along with virtually every other APU that year (including maybe the mainstream Zen5 IOD iGPU as well)... I see a tendency of AMD trying to...
Hence my bold text mentioning how there's loads of software (and the possible DDR5-5600 hardware) faults with this early preview. Not really worth basing much off of these numbers. We need post gold drivers/BIOS ones.
Seem the common denominator is DDR5 to me, but I may be wrong.
Yep. It's...
ETA Prime has a early preview of Phoenix R9 7940HS/Radeon 780M in a ASUS TUF design.
DO NOTE: Early drivers/BIOS, some performance is wildly inconsistent, also crashes while allowed to go to 80W.
Seems to clock at 2800MHz in Furmark at a 45W package and he also successfully overclocked it to...
Yep, people here seem quick to forget that Zen and Zen+, in most ways the same core designs, where on 2 different nodes. Or even worse, most recently, Zen3 and Zen3+/Cezanne and Rembrandt are also a similar story. So AMD is no stranger to this.
Even tho they'll likely make bigger...
Apparently the handheld PC industry is going full speed ahead, despite no OFFICIAL word from AMD on 7040U SKUs yet.
Base clock is apparently 3,3GHz (6800U and 7735U both have it at 2,7GHz), hence 5GHz boost or slightly higher seems very likely.
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.