Discussion RDNA4 + CDNA3 Architectures Thread

Page 37 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

DisEnchantment

Golden Member
Mar 3, 2017
1,623
5,894
136





With the GFX940 patches in full swing since first week of March, it is looking like MI300 is not far in the distant future!
Usually AMD takes around 3Qs to get the support in LLVM and amdgpu. Lately, since RDNA2 the window they push to add support for new devices is much reduced to prevent leaks.
But looking at the flurry of code in LLVM, it is a lot of commits. Maybe because US Govt is starting to prepare the SW environment for El Capitan (Maybe to avoid slow bring up situation like Frontier for example)

See here for the GFX940 specific commits
Or Phoronix

There is a lot more if you know whom to follow in LLVM review chains (before getting merged to github), but I am not going to link AMD employees.

I am starting to think MI300 will launch around the same time like Hopper probably only a couple of months later!
Although I believe Hopper had problems not having a host CPU capable of doing PCIe 5 in the very near future therefore it might have gotten pushed back a bit until SPR and Genoa arrives later in 2022.
If PVC slips again I believe MI300 could launch before it

This is nuts, MI100/200/300 cadence is impressive.



Previous thread on CDNA2 and RDNA3 here

 
Last edited:

Ajay

Lifer
Jan 8, 2001
15,628
7,955
136
Trying to patiently wait thru 1H24 to see all the goodies were are talking about in CPUs & GPUs to be released.
I really do miss the roughly annual releases we used to have 20-25 years ago.
 

GodisanAtheist

Diamond Member
Nov 16, 2006
6,938
7,356
136
The long wait between hardware does make each release and the lead up to it feel like more of an event though.

I enjoy the hype train ramp up and derails, all the theorycrafting, the techtube leaker garbage. All of it just feeds into the long ramp up to a proper launch.
 

Trovaricon

Member
Feb 28, 2015
28
43
91
Distance from the object (screen) and dimension of the screen are two of three variables (third being resolution) that have to be part of any enough/not enough pixels.
Screen dimension and resolution can be expressed also by a single variable pixels-per-inch.
12k "eye resolution" from what? 10cm or 1m? 12k pixels on a surface of what 1cm2 or 1m2?
 

blackangus

Member
Aug 5, 2022
70
95
51
Ahh the never ending discussion, here is a chart from RTINGS:


I sit roughly 25" from my 32" monitor, by this chart I am very near the point of diminishing returns for greater than 4k. Could likely see a difference with 8k but only by a very tiny margin, and with my eyes not even that is likely lost.
IMHO one of the most lacking things isn't resolution IMHO, its texture resolution. A poor texture is going to look bad no matter the physical resolution.
Starfield and CP2077 both benefit greatly from the high resolution texture pack mods.
 
Last edited:

Heartbreaker

Diamond Member
Apr 3, 2006
4,237
5,244
136
I mean, it's weird to argue with detailed scientific studies by quoting "no because", but go ahead.

Yes it is weird. So the question is. Why are you doing that?

Human vision can differentiate a certain angular feature size, typically around 63 pixels/degree. From there you can calculate the distance when any screens size/resolution combination exceeds human ability to differentiate.

That was the technical basis for Apples original "Retina" marketing, and for viewing distance charts like the post above mine. It's a sound basis.

Typical home most likely has a 55" or smaller TV, at 8 to 10 feet, at which point, it's really only in the 1080p zone. Making even 4K TV overkill in for most people.

8K TVs will be nothing more than pure marketing excess...
 
Reactions: Tlh97 and Mopetar
Jul 27, 2020
16,816
10,755
106
8K TVs will be nothing more than pure marketing excess...
When 8K TVs become commonplace, our eyes might adapt to the higher resolution and might detect the inferiority of 4K TVs much more easily. It's always been like this. I remember never thinking that TV looked bad. Then I saw Full HD and it became apparent how bad the lower resolutions looked. Same thing happened when I moved to 4K TV. Suddenly, I could see the pixels on 55 inch Full HD TVs and they just looked awful and distracting. I'm sure that once I get used to 8K, my brain will concoct plenty of reasons to tell me that I'm not getting the best visual experience.

Similarly, when I saw my first CD video, I thought it was the best quality ever. Then DVD made that look inferior. Then Bluray made DVD look like CD. UHD Blurays are not that much better in quality but if you spend a lot of time looking at 4K Blurays, you might start noticing that 1080p Blurays lack a bit of sharpness.
 
Reactions: Tlh97

Ajay

Lifer
Jan 8, 2001
15,628
7,955
136
The long wait between hardware does make each release and the lead up to it feel like more of an event though.

I enjoy the hype train ramp up and derails, all the theorycrafting, the techtube leaker garbage. All of it just feeds into the long ramp up to a proper launch.
Guess I reach a point, which is now, when I really only care about hard infos from the the respective semiconductor designers, manufacturers and board partners. I’ll still participate, looking, but the endless bogus leaks are getting on my nerves.
 
Reactions: Saylick

dr1337

Senior member
May 25, 2020
344
598
106
At any reasonable distance, 8K is overkill, let alone 12K.

Even 4K at typical living room distance and TV size is overkill.
The only person that would say this is someone that's never used 4k as their main display. Maybe you watch 1080p TV on a 4k screen and as such aren't impressed, but the difference is huge with native/real time content regardless of display size. I've used 4k screen at 17" all the way to 75" and have never had an issue seeing the difference between 1080p and actual 4k at any distance. To me its always obvious because many intro clips, ads, menu screens, ect aren't native, and you can just see the image get so much sharper when it changes to real 4k.

Seriously you guys need to go get your eyes checked if you can't see a difference. Otherwise the only rational explanation is that a lot of you are fooling yourselves with media that isn't actually native resolution.
 
Reactions: Tlh97

Heartbreaker

Diamond Member
Apr 3, 2006
4,237
5,244
136
... never had an issue seeing the difference between 1080p and actual 4k at any distance.

This is obvious nonsense. Distance is a vital parameter. Physics doesn't lie. You can only see so many pixels/degree, and the further the distance, the fewer the degrees involved, so the less effective resolution delivered for any screen.

Anyone can test it on any screen. Just take a full screen video, and produce half resolution version (but at high bit rate). Start viewing them at various distances. You will very quickly discover the become indistinguishable. If you are deep in the placebo zone, you may need someone to randomize for you...
 
Last edited:

dr1337

Senior member
May 25, 2020
344
598
106
Anyone can test it on any screen. Just take a full screen video, and produce half resolution version (but at high bit rate). Start viewing them at various distances. You will very quickly discover the become indistinguishable. If you are deep in the placebo zone, you may need someone to randomize for you...
This is something I doubt you've done yourself but even 10ft across the room I can see the difference night and day between 720p, 1080p, 1440p, and 4k in videogames. Something ya know that renders in real time and has no bitrate problem (and hence why it matters so much for next gen GPUS). I'm sure you own at least one game that lets you change the render resolution, right? But sure yeah lemme go throw a bluray rip into resolve to prove something to myself that I've already seen time and time again. I doubt you even have anything high enough bitrate yourself let alone at 4k.

Physics don't lie but assuming a chart made by a random person with unsubstantial data is gospel is silly. You're telling me to go do this test when I actually have done it before and you literally haven't, I don't see why you're trying to gaslight me.
 
Reactions: DaaQ

dr1337

Senior member
May 25, 2020
344
598
106

Go ahead and try this out, see how far away you have to back away from your display for the aliasing to disappear. And if you can't see the aliasing, then its time for glasses.

This concept applies to the entire image quality.
 
Reactions: DaaQ

gdansk

Platinum Member
Feb 8, 2011
2,212
2,836
136
The difference in the map between 2160 vertical lines compared to 1440 vertical lines in e.g. Crusader Kings is noticeable from any reasonable distance away.

What im saying is it depends on the type of game too You shouldn't simply say 'a gamer will not notice the difference between the two resolutions' when in fact it really does depend on the game. Slowly panning maps with plenty of tool tips and text to read? You're going to benefit from higher DPI.
 

Heartbreaker

Diamond Member
Apr 3, 2006
4,237
5,244
136
This is something I doubt you've done yourself but even 10ft across the room I can see

I tested this with video, and the distances work out much as predicted by ubiquitous viewing distance charts.

But no doubt you are the "golden eye" visual equivalent, of the "golden ear" audiophiles who can hear the difference between different speaker wires... Until someone independently tests them...
 

blackangus

Member
Aug 5, 2022
70
95
51
It feels like there are two items being talked about that are actually very separate:
1. How far away must a display be to be indistinguishable from the next resolution hop for the exact same content?
2. When does display of native resolution become indistinguishable between native resolution steps?

For 1 there is a very strong scientific way to quantify that, as your eyes can only resolve a some number of pixels (at a given dot pitch) per some coverage unit at some distance. (Yes, of course some people will resolve more or less)
For 2 its more complex. High resolution content may still look better than native when displayed
Example:
Two images are create from the same source where the source native is larger than 8K
1080P image
8k image
Display 1080p
Display both at the same physical resolution device.... which will look better? Even tho the display is only 1080P the content displayed that is from the 8k image still likely look better than the native 1080p image.

While its likely there is some outer limit on number 2 where content differences cant be seen past some distance, I doubt than 1 and 2 have the same thresholds and the 2 is a longer distance by quite a bit.
 
Last edited:

Mopetar

Diamond Member
Jan 31, 2011
7,936
6,233
136
I think 8K will be a big step up for projectors. Maybe TVs will manage to get even more inexpensive to the point where I can get an okay 10' display for $500 on Black Friday, but when I have an even bigger wall I can project on to, then the resolution becomes more important.

Although modern 4k TVs look better I think most of the jump in quality is due to better colors and HDR as opposed to the resolution increase. Better blacks from OLED as well, and I had a plasma prior to getting an OLED so for anyone coming from an LCD it was a massive upgrade. The resolution increase was noticeable, but not as big as the jump from SD to HD. 8K will have diminishing returns for most people.

I think people do sit closer to their TVs than in the past, even though they're much, much larger. Growing up we had a TV in the living room that was maybe 24" or slightly larger. I thought it was pretty huge and probably sat over 12' away when watching it. Now I have a 4k that's ~2.5x the size and sit around 7' from it. I almost think that the sitting distance is adjusted to where pixelation doesn't become apparent and the whole screen can be seen without having to turn one's head. It fits the chart at any rate.
 
Mar 11, 2004
23,099
5,578
146
I think you guys are looking the wrong direction. It'll be people using much much much smaller screens, much much much closer to their eyes.

All the benefits of projectors, all the benefits over projectors of self lit pixels, with added bonuses of being more portable and usable in ways those aren't.

You might balk at the price, but True 4K projectors are more expensive than Apple's Vision Pro right now. And there will basically guaranteed to be cheaper options and that stuff will continue to evolve. In 5 years we might be looking at 8K per eye resolution, possibly MicroLED (or maybe NanoLED or whatever term will describe the needed even tinier non-organice LED tech).
 
Reactions: Heartbreaker

maddie

Diamond Member
Jul 18, 2010
4,772
4,739
136
I think you guys are looking the wrong direction. It'll be people using much much much smaller screens, much much much closer to their eyes.

All the benefits of projectors, all the benefits over projectors of self lit pixels, with added bonuses of being more portable and usable in ways those aren't.

You might balk at the price, but True 4K projectors are more expensive than Apple's Vision Pro right now. And there will basically guaranteed to be cheaper options and that stuff will continue to evolve. In 5 years we might be looking at 8K per eye resolution, possibly MicroLED (or maybe NanoLED or whatever term will describe the needed even tinier non-organice LED tech).

Yes. That research finding on extremely high DPI needed came from VR headset research AFAIK.
 

Heartbreaker

Diamond Member
Apr 3, 2006
4,237
5,244
136
I think you guys are looking the wrong direction. It'll be people using much much much smaller screens, much much much closer to their eyes.

All the benefits of projectors, all the benefits over projectors of self lit pixels, with added bonuses of being more portable and usable in ways those aren't.

You might balk at the price, but True 4K projectors are more expensive than Apple's Vision Pro right now. And there will basically guaranteed to be cheaper options and that stuff will continue to evolve. In 5 years we might be looking at 8K per eye resolution, possibly MicroLED (or maybe NanoLED or whatever term will describe the needed even tinier non-organice LED tech).

Agreed VR/AR headsets are one area where 8K would benefit. You have a much larger FOV than any TV/Monitor, so you are spreading those pixels over more degrees, and thus you have much less pixels/degree.
 

MrTeal

Diamond Member
Dec 7, 2003
3,578
1,725
136
I think people do sit closer to their TVs than in the past, even though they're much, much larger. Growing up we had a TV in the living room that was maybe 24" or slightly larger. I thought it was pretty huge and probably sat over 12' away when watching it. Now I have a 4k that's ~2.5x the size and sit around 7' from it. I almost think that the sitting distance is adjusted to where pixelation doesn't become apparent and the whole screen can be seen without having to turn one's head. It fits the chart at any rate.
LOL.. Maybe for TV, but gaming was a whole other realm. The cords on a Genesis controller were so short your nose was damn near touching the TV to play. Nintendo was a lot better, but it's still nothing like you get with modern console and wireless controllers.
 

DaaQ

Golden Member
Dec 8, 2018
1,333
957
136
At any reasonable distance, 8K is overkill, let alone 12K.

Even 4K at typical living room distance and TV size is overkill.
DLSS vX
Yes it is weird. So the question is. Why are you doing that?

Human vision can differentiate a certain angular feature size, typically around 63 pixels/degree. From there you can calculate the distance when any screens size/resolution combination exceeds human ability to differentiate.

That was the technical basis for Apples original "Retina" marketing, and for viewing distance charts like the post above mine. It's a sound basis.

Typical home most likely has a 55" or smaller TV, at 8 to 10 feet, at which point, it's really only in the 1080p zone. Making even 4K TV overkill in for most people.

8K TVs will be nothing more than pure marketing excess...
Because DLSS vX is utmost priority.


I mean c'mon, you were voraciously arguing about no DLSS in Starfield. Now 4k is overkill? Think I am going to check to see if there is a sig rig labeled.
You argue some of the weirdest things. No offense meant.
 

rtxtwt

Senior member
Jul 2, 2018
319
505
136
This.
Gossip just suggest one of the model(possible to be "flagship") just a bit smaller than N31(529 mm2), between N32(346 mm2) & N31 but closer to N31.
Title : "Just now, I told you that the small core ratio of the next generation is larger than 32 and is close to 31". (they were shocked that such size is not a small chip/mid-end anymore)
Most of those comments under that topic were speculation. And most important information is within the title: "next gen" "larger than 32 and is close to 31". No codename like N43/42/41 being confirmed.

looks like some dudes also had similar confirmations about this mysterious next-gen RDNA GPU:




edit: ouch nobody pointed out my mistake of posting wrong X(twitter) link lol. but yeah OTOH the X links seem don't work well since X changed the policy.
 
Last edited:
Reactions: Tlh97

Heartbreaker

Diamond Member
Apr 3, 2006
4,237
5,244
136
DLSS vX

Because DLSS vX is utmost priority.


I mean c'mon, you were voraciously arguing about no DLSS in Starfield. Now 4k is overkill? Think I am going to check to see if there is a sig rig labeled.
You argue some of the weirdest things. No offense meant.

Reading comprehension issue?

I said "Even 4K at typical living room distance and TV size is overkill"

If you are sitting 10+ feet away from a 55" TV, then you aren't seeing 4K. You are barely in the 1080p zone. My point is that distance matters. This was in response to someone claiming we needed 12K...

Distance matters.

 
Reactions: Joe NYC and DaaQ
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |