AMD RDNA4 Architecture Speculation

[Picao84]

Reference is 2x8-pin.
To quote TPU, "The card calls for three 8-pin PCIe power connectors. We've only seen one other custom RX 9070 XT come with three connectors, and that is the XFX RX 9070 XT Merc 319 Black. ... Most other cards, including the PowerColor Red Devil, come with just two 8-pin connectors (375 W)"
Yes, there's cards (more than those 2 they had seen at that point) with 3x, but there's nothing new in AIBs putting extra power connectors, heck, there's even one with 12V-2x6, but it doesn't mean the card is drawing 600W

What's the point of putting 3 8 pin connectors if one of pins is not required? If OC versions really need a 3rd pin then it either clocks like a champ or there is something really wrong with it's efficiency. I guess we'll know soon.

 

[Kaotik]

What's the point of putting 3 8 pin connectors if one of pins is not required? If OC versions really need a 3rd pin then it either clocks like a champ or there is something really wrong with it's efficiency. I guess we'll know soon.

No, it doesn't mean either of those. We have countless examples from previous generations of cards with extra power connectors that offer no discernible benefits over default. Most likely it's just PR department telling engineers MOAR POWAH sells even when it does nothing.

 

[Kaotik]

According to IGN RX 9070 (non-XT) reaches 99 FPS in COD: Black Ops 6 at 4K Extreme settiings without FSR.

I Benchmarked the AMD Radeon RX 9070 - IGN

Everything we know so far about the newest graphics cards from AMD.

www.ign.com

 

[DegustatoR]

According to IGN RX 9070 (non-XT) reaches 99 FPS in COD: Black Ops 6 at 4K Extreme settiings without FSR.

I Benchmarked the AMD Radeon RX 9070 - IGN

Everything we know so far about the newest graphics cards from AMD.

www.ign.com

Not a very representative benchmark but puts it above 7970XTX.

Probably not a good idea to read much into it.

 

[Erinyes]

Well they'd better be looking to price the 9070XT at $399, $450 max. Honestly I don't see how anyone with a 6800XT or higher could even consider it. That's a huge chunk of their previous buyers with no upgrade path without going Nvidia.

If it essentially gives you the performance of a 7900XT, which was going for ~$650 I think at it's lowest, why would you think they need to price it that low? It isn't a huge upgrade from a 6800XT yes but not everyone upgrades that often. The 7900XTX is still an option if someone really wants to go AMD.

That's how I'm interpreting this as well. If they were confident in having decided on some 'aggressive' pricing, they wouldn't have held off. They probably got word of Nvidia's 50 series pricing, and then realized they were not nearly as well positioned as they thought they'd be.

It's telling that in their interviews they did after the event, it really sounded like their talk of the importance of good pricing and learning lessons and all that was all in relation to their competition. That's probably obvious from a business standpoint, but from a consumer standpoint, that's still very much a "We're not really trying to provide great standalone value, only make it seem like good value when compared against our super high priced competition" giveaway here, and goes against what consumers are thinking when we talk about aggressive pricing.

Given that Nvidia is the market leader, naturally they can dictate pricing and AMD has almost no option but to follow. If AMD had announced a price and then had to announce a price cut due to Nvidia's aggressive pricing for the 5070, it would have been even worse.

Besides, they actually had great products in Kracken Point, Strix Halo and 9950X3D where they have leadership performance to talk about. I think they'd rather get more positive spin out of those than the slight negative spin RDNA4 might have gotten them.

That would be strange.

Navi 32 with 60CU's had total die area of 346mm², and that obviously included four 6nm MCD's totaling about 146mm².

Navi 48 is supposed to be 64CU's, but there should be die savings from moving to 4nm and putting the memory bus and L3 IC on the main 4nm die as well(scaling here isn't great, but it's still something).

Perhaps 64CU is wrong and they actually upped CU count a fair bit instead of going for narrow+faster clockspeeds? Or maybe RDNA4 CU's are a really sizeable chunk wider to accommodate better RT/AI? I dont know, but that doesn't strike me as the sort of architectural or area efficiency gains they'd have liked, especially if the aim is to be able to price this GPU more aggressively.

I agree, the die size does seem too large, even if they beefed up the RT and ML hardware. The rumours were sub 300mm2 die. Let's wait for official news from AMD before we jump to any conclusions but it does seem larger than expected.

Not a very representative benchmark but puts it above 7970XTX.

Probably not a good idea to read much into it.

Yea too many variables to read into it. They might have used a totally different scene than TPU. And the CPU used is a 9950X3D vs what I think is a 13900K for TPU.

 

[LordEC911]

https://videocardz.com/newz/amd-nav...rx-9070-pictured-may-exceed-nvidia-ad103-size

~390mm2 ? Quite chunky

Some others have measured with different known references and got < 350mm2.
Hard to get solid measurements on such a wide picture at an angle, you can easily be off +10% on each side.
I would guess around 320-330mm2.

They supposedly doubled up RT and went to 4SE/128ROPs.
N31, and to some degree N32, were shader heavy designs.
N48 seems to be much better balanced, at least on paper.

Edit- Found your original post(from April '24) with the silly season die sizes from twitter for N48 and N44.
Going off my post/response, N48 was rumored to be ~240mm2 and N44 was ~120mm2 (i think).

Even then I thought ~280-320mm2 for N48 and ~140-150mm2 for N44 made more sense.