Top AMD RDNA4 Part Could Offer RX 7900 XTX Performance at Half its Price and Lower Power

[Chrispy_]

the right way to count how old a product is to count the time between its set-in-stone, tape-out, or set-in-stone decision / feature set.

Your insanity and delusional nonsense continue to entertain.

Tape-out and product launch are at a bare minimum, 6 months apart and have been 2+ years on several notable occasions where redesigns were required after the initial tape-out. Tape-out is one of the product development phases, but there's no way to know if any tape-out will be final until the silicon is received back and tested months later. Saying that a tape-out is the time at which a product is set-in-stone proves that you have absolutely no idea what you're talking about.

By your metrics, Nvidia Blackwell GPUs, slated to launch in early 2025 are already 18 months old!

Here's another shovel if you want to keep digging...

 

[AusWolf]

Wrong. AMD's market share is close to non-existent in the OEMs market, which means that while the products do indeed physically work, they are market failures.

88% of all GPU shipments are nvidia, the rest is AMD and intel.

View attachment 360544

Shipments of graphics add-in boards decline in Q1 of 24 as the market experiences a return to seasonality

Quarter to quarter, graphics add-in board shipments decreased by -7.9% and increased by 39.2% year to year.

www.jonpeddie.com

What has the age of RDNA 3 got to do with market share?

Also, what's this big deal about market share imparity with Nvidia? Why do you think that a much smaller company should equal out a much bigger one in market share?

 

[Vayra86]

The one spouting nonsense is you.
You in a wrong way count the period between a product going in the wild and the present moment, when the right way to count how old a product is to count the time between its set-in-stone, tape-out, or set-in-stone decision / feature set. Because between that moment in time, and the physical release to the wild, there can be multiple other milestones happening, feature set updates, etc.



Wrong. AMD's market share is close to non-existent in the OEMs market, which means that while the products do indeed physically work, they are market failures.

88% of all GPU shipments are nvidia, the rest is AMD and intel.

View attachment 360544

Shipments of graphics add-in boards decline in Q1 of 24 as the market experiences a return to seasonality

Quarter to quarter, graphics add-in board shipments decreased by -7.9% and increased by 39.2% year to year.

www.jonpeddie.com

Wow. This has to be the most blatant attempt at twisting facts in plain sight ever. Do you even know what a tape out means bruv.. maybe you should just disconnect for a couple of years to regain sanity.

"The world is wrong and Im right"... lmao

 

[Zach_01]

I think 7900XTX performance with half the price is too good to be true. I really hope I'm wrong...
I mean raster performance, yeah but at 450~500? I can't see it going under 600 at best if not more.
It will depend a lot on RTX5000 perf/prices and how its going to compete to them (raster/RTRT).

-------------------------------------------

Your insanity and delusional nonsense continue to entertain.

Tape-out and product launch are at a bare minimum, 6 months apart and have been 2+ years on several notable occasions where redesigns were required after the initial tape-out. Tape-out is one of the product development phases, but there's no way to know if any tape-out will be final until the silicon is received back and tested months later. Saying that a tape-out is the time at which a product is set-in-stone proves that you have absolutely no idea what you're talking about.

By your metrics, Nvidia Blackwell GPUs, slated to launch in early 2025 are already 18 months old!

Here's another shovel if you want to keep digging...
View attachment 360563

What has the age of RDNA 3 got to do with market share?

Also, what's this big deal about market share imparity with Nvidia? Why do you think that a much smaller company should equal out a much bigger one in market share?

Wow. This has to be the most blatant attempt at twisting facts in plain sight ever. Do you even know what a tape out means bruv.. maybe you should just disconnect for a couple of years to regain sanity.

"The world is wrong and Im right"... lmao

I dont know guys...

Seems like this one is on a constant campaign of shoveling dirt and mud all over AMD.
Almost every post on every thread is on the same direction. Twisting facts, cropping screenshots and many more just to prove how bad AMD is on everything.

 

[Vayra86]

I think 7900XTX performance with half the price is too good to be true. I really hope I'm wrong...
I mean raster performance, yeah but at 450~500? I can't see it going under 600 at best if not more.
It will depend a lot on RTX5000 perf/prices and how its going to compete to them (raster/RTRT).

-------------------------------------------




I dont know guys...

Seems like this one is on a constant campaign of shoveling dirt and mud all over AMD.
Almost every post on every thread is on the same direction. Twisting facts, cropping screenshots and many more just to prove how bad AMD is on everything.

I've stopped trying to wrap my mind around this fellow honestly. Any attention given is really far too much already

 

[RJARRRPCGP]

Following this absurd logic, every single API feature developed in the past 20 years is a con, since you can get 70% of the job done with DirectX 9.0c anyway

Yep, because Gearbox Halo Custom Edition 1.0.10, can do a lot already with Direct X 9. It's surprising how much it can look like the very-late-Halos.

 

[Dr. Dro]

Yep, because Gearbox Halo Custom Edition 1.0.10, can do a lot already with Direct X 9. It's surprising how much it can look like the very-late-Halos.

Borderlands 2 and Pre-Sequel, DirectX 9.0c games as well. Really. No need to buy anything newer than a 8800 GTX. That DX10 support's luxury enough, even that is already being conned by Big Graphics and nGreedia's evil

 

[LabRat 891]

Borderlands 2 and Pre-Sequel, DirectX 9.0c games as well. Really. No need to buy anything newer than a 8800 GTX. That DX10 support's luxury enough, even that is already being conned by Big Graphics and nGreedia's evil

NGL...
if graphics processors could be 'stacked' with >50% performance gains for each GPU added,
I'd probably rock multiple G80s or G92s, for the lulz.

 

[Noci]

Despite all speculations and some bickering, Q4-2024 is on the verge of becoming reality, but I've seen no Red or Green camp hard release dates announcements yet (or I just missed it ).

I'd love to see some real representative reviews when both camps have launched their cards and shows where their new products stand in the picking order as well as pricewise. Would give me some food for thoughts on the possible upgrade path.

 

[Dr. Dro]

Despite all speculations and some bickering, Q4-2024 is on the verge of becoming reality, but I've seen no Red or Green camp hard release dates announcements yet (or I just missed it ).

I'd love to see some real representative reviews when both camps have launched their cards and shows where their new products stand in the picking order as well as pricewise. Would give me some food for thoughts on the possible upgrade path.

That's because no announcements have been made. But what's the rush? Battlemage isn't ready. RDNA 4 is out of the performance race. The RTX 4090 remains the undisputed king far ahead of the pack (despite being an horribly cutdown version of AD102, which makes matters eve worse), and if all we know thus far is to be believed, it's already faster than both BMG-G10 (supposed to be the big chip/Arc B770?) and N48 (purported RDNA 4 flagship/8900 XTX?).

Truth be told, if Nvidia decided to release a complete AD102 chip today (with all 144 SMs and 96 MB of cache enabled) and upgrade it with the 24 Gbps G6X chips used on 4080 and 4080S, with board designs simply reusing parts from existing RTX 4090 assembly lines, they'd achieve something that could be considered equivalent to a full generational uplift by simply releasing something that isn't cutdown. Yet there is no reason, or incentive to do even that, regardless of branding or positioning. They even played with the idea around, there are reports of "Titan Ada" engineering samples having been built, they just never released that (at 48 GB config) or 4090 Ti (24 GB config).

 

[Noci]

That's because no announcements have been made. But what's the rush? Battlemage isn't ready. RDNA 4 is out of the performance race. The RTX 4090 remains the undisputed king far ahead of the pack (despite being an horribly cutdown version of AD102, which makes matters eve worse), and if all we know thus far is to be believed, it's already faster than both BMG-G10 (supposed to be the big chip/Arc B770?) and N48 (purported RDNA 4 flagship/8900 XTX?).

Truth be told, if Nvidia decided to release a complete AD102 chip today (with all 144 SMs and 96 MB of cache enabled) and upgrade it with the 24 Gbps G6X chips used on 4080 and 4080S, with board designs simply reusing parts from existing RTX 4090 assembly lines, they'd achieve something that could be considered equivalent to a full generational uplift by simply releasing something that isn't cutdown. Yet there is no reason, or incentive to do even that, regardless of branding or positioning. They even played with the idea around, there are reports of "Titan Ada" engineering samples having been built, they just never released that (at 48 GB config) or 4090 Ti (24 GB config).

There's no rush and the RTX 4090 being the performance king is undisputed also I believe you when you say it can even be better with the existing hardware if artificial limitations are lifted.

But I was just wondering when the new lower tier products were coming out with more convinient prices to the average Joe, as Q4-2024 seemed to be the starting season of new products. Does make sense from a marketing point of view, and these companies are always keen on making the most out of these months. Also curious if AMD catches up with RT and ARC closing in on the competition, would be nice (maybe just whisful thinking) .

 

[AusWolf]

There's no rush and the RTX 4090 being the performance king is undisputed also I believe you when you say it can even be better with the existing hardware if artificial limitations are lifted.

But I was just wondering when the new lower tier products were coming out with more convinient prices to the average Joe, as Q4-2024 seemed to be the starting season of new products. Does make sense from a marketing point of view, and these companies are always keen on making the most out of these months. Also curious if AMD catches up with RT and ARC closing in on the competition, would be nice (maybe just whisful thinking) .

If I remember right, Nvidia said that they'll only release the 5080/5090 this year, and target the midrange in the first half of next year. To me, that means that AMD and Intel are in no rush, either.

 

[Chrispy_]

I've stopped trying to wrap my mind around this fellow honestly. Any attention given is really far too much already

I just enjoy calling out lies and BS when it's *that* easy to disprove.
I usually bring popcorn.

There's no rush and the RTX 4090 being the performance king is undisputed also I believe you when you say it can even be better with the existing hardware if artificial limitations are lifted.

But I was just wondering when the new lower tier products were coming out with more convinient prices to the average Joe, as Q4-2024 seemed to be the starting season of new products. Does make sense from a marketing point of view, and these companies are always keen on making the most out of these months. Also curious if AMD catches up with RT and ARC closing in on the competition, would be nice (maybe just whisful thinking) .

I suspect both AMD and Nvidia will stagger their launches from the top down, for profitability reasons. Sell the highest margin SKUs to those with fat wallets and the least patience first, while shifting old inventory at more affordable tiers before updating SKUs lower down the product stack.

For people looking for midrange GPU upgrade, I think were going to see very little of value from AMD until after Christmas and Nvidia's 5060Ti or whatever they call it will probably be Summer 2025. I'd like to be wrong, but that just seems to be the way the last few generations have played out.

 

[TeamMe]

TBH don’t have much time to play games, 7900XT perf for £500-600 sounds good. Went from a 1070 to 6900XT, I probably get something like 9900 non XT…

 

[ARF]

There is now a question mark next to the new generation RX 8**** series branding.

Maybe the new Navi 48 and Navi 44 powered graphics cards will be called something else?!
What about Radeon AI 170 Ultra?

The L3 caches will remain rather small - 48 or 64 MB...

AMD RDNA4 GPUs to feature 48 to 64MB of Infinity Cache - VideoCardz.com

Kepler_L2 reveals RDNA4 Infinity Cache sizes The new GPUs are said to feature either 48MB or 64MB. It looks like the past few days are finally giving us a glimpse of what to expect from RDNA4, AMD’s next-gen GPU architecture. While it’s well known that this architecture won’t expand its presence...

videocardz.com

 

[Chrispy_]

There is now a question mark next to the new generation RX 8**** series branding.

Maybe the new Navi 48 and Navi 44 powered graphics cards will be called something else?!
What about Radeon AI 170 Ultra?

The L3 caches will remain rather small - 48 or 64 MB...

View attachment 361046

AMD RDNA4 GPUs to feature 48 to 64MB of Infinity Cache - VideoCardz.com

Kepler_L2 reveals RDNA4 Infinity Cache sizes The new GPUs are said to feature either 48MB or 64MB. It looks like the past few days are finally giving us a glimpse of what to expect from RDNA4, AMD’s next-gen GPU architecture. While it’s well known that this architecture won’t expand its presence...

videocardz.com

There have been numerous articles here, VideoCardz, MLID, and plenty of other sources citing that the largest, Navi31 die configuration won't appear at RDNA4's launch, if at all - so don't go expecting 96MB or 80MB of Infinity cache.

The 8800XT (Navi 48) matches the approximate shader count, exact memory size, bus width, and cache size of the 7800XT so the cache size isn't really surprising or unexpected.

 

[ARF]

There have been numerous articles here, VideoCardz, MLID, and plenty of other sources citing that the largest, Navi31 die configuration won't appear at RDNA4's launch, if at all - so don't go expecting 96MB or 80MB of Infinity cache.

The 8800XT (Navi 48) matches the approximate shader count, exact memory size, bus width, and cache size of the 7800XT so the cache size isn't really surprising or unexpected.

Where is that rule which defines the relation between shaders quantity and L3 amount?
I think it's quite obvious that RDNA 3 would have been faster with more L3.
128 MB is needed for Navi 48.

 

[Chrispy_]

Where is that rule which defines the relation between shaders quantity and L3 amount?
I think it's quite obvious that RDNA 3 would have been faster with more L3.
128 MB is needed for Navi 48.

I don't think there is a rule.

RDNA2 had more L3, RDNA4 has the same L3 as RDNA3 and RDNA3.5

More L3 is always better but it's always about balancing cost vs performance. If it adds 15% to the cost and only brings 10% more performance, then it's not worth it.

 

[ARF]

More L3 is always better but it's always about balancing cost vs performance. If it adds 15% to the cost and only brings 10% more performance, then it's not worth it.

Isn't the cost always transferred to the users?
What's the cost difference in % between RX 7900 XTX and RTX 4090? One is 930 bucks, the other 1740 bucks.
Those missing % in performance would have made the whole lineup more interesting.

 

[Super XP]

nVidia Ray Tracing is a con I mean even Cyberpunk on a 4090 looks no where near as good as the CGI on old movie like Lord Of The Rings. AMD shouldn’t bother with Ray Tracing even on NVIDIA the performance degradation is too big. AMD should keep on being a Rasta man and use HDR like The Last of Us Part 1 PC. AMD should focus on getting higher polygon count models and more detailed textures…

I agree with 1 of your statements, Ray Tracing is nonsense and subjective. Personally I do not like how it looks. The performance hit is far too big, but maybe in the coming years it will even out and just be a regular option for gamers.

 

[TumbleGeorge]

I agree with 1 of your statements, Ray Tracing is nonsense and subjective. Personally I do not like how it looks. The performance hit is far too big, but maybe in the coming years it will even out and just be a regular option for gamers.

I'm willing to bet that the RTX 7000 series, in 2028-2029, will be crunching the rays for breakfast. Let's just survive until then.

 

[Noci]

A little bit off topic, but still related imo.

What was in the rumors earlier, about AMD not competing in the high-end consumer graphic cards segment in the near future is now confirmed, but with some nuances why this decision was made.

https://www.tomshardware.com/pc-com...ck-hyunh-talks-new-strategy-for-gaming-market

This combined with the newsflash about a 'change' of architecture ( https://www.techpowerup.com/326442/...ular-gpu-architecture-similar-to-nvidias-cuda ) makes me think not all hope is lost, but it will take time.

But with lot's of it depending on implementation by software developers, so still quite a big uncertainty factor.