Sunday, May 24th 2020
AMD RDNA2 "Navi 21" GPU to Double CU Count Over "Navi 10"
AMD's RDNA2 graphics architecture, which sees real-time ray-tracing among other DirectX 12 Ultimate features, could see the company double the amount of stream processors generation-over-generation, according to a specs leak by _rogame. The increase in stream processors would fall in line with AMD's effort to increase performance/Watt by 50%. It may appear like the resulting SKUs finally measure up to the likes of the RTX 2080 Ti, but AMD has GeForce "Ampere" in its competitive calculus, and should the recent specs reveal hold up, the new "Navi 21" could end up being a performance-segment competitor to GeForce graphics cards based on the "GA104" ("TU104" successor), rather than a flagship-killer.
The RDNA2-based "Navi 21" GPU allegedly features 80 RDNA2 compute units amounting to 5,120 stream processors. AMD might tap into a refined 7 nm-class silicon fabrication node by TSMC to build these chips, either N7P or N7+. The die-size could measure up to 505 mm², and AMD could aim for a 50% performance/Watt gain over the "Navi 10." AMD could carve out as many as 10 SKUs out of the "Navi 21," but only three are relevant to the gamers. The SKU with the PCI device ID "0x731F: D1" succeeds the RX 5700 XT. The one bearing "0x731F: D3" succeeds the RX 5700, with a variant name "Navi 21 XL." The "Navi 21 XE" variant has a PCI ID of "0x731F: DF," and succeeds the RX 5600 XT.
Among the other variants are the "Navi 21 XTX," with PCI ID "0x731F: D0," which could be a limited edition SKU succeeding the slightly beefed up RX 5700 XT 50th Anniversary Edition; the Navi 21 Pro XT and Navi 21 Pro XL with PCI IDs "0x731F:10" and "0x731F:12," marking Radeon Pro W5700X and W5700 successors, respectively. There are also four Apple-exclusive SKUs, the "Navi 21 XTA" and "Navi 21 XLA" client-segment chips targeting next-generation iMac and iMac Pro desktops, and their Pro variants targeting future Mac Pro workstations.
The first-gen RDNA may not ride into the sunset, as AMD is planning to refresh them. The company is probably porting the "Navi 10" silicon to TSMC N7P, to come up with new mainstream SKUs that lack ray-tracing, but will occupy mid-range price-points. This would be similar to NVIDIA positioning half its "Turing" product-stack without ray-tracing, under the GTX 16-series, occupying sub-$300 price-points. The resulting ASICs are the "Navi 10+," "Navi 10 XM+," and "Navi 10 XTE+."
Source:
Hardware Leaks (by _rogame)
The RDNA2-based "Navi 21" GPU allegedly features 80 RDNA2 compute units amounting to 5,120 stream processors. AMD might tap into a refined 7 nm-class silicon fabrication node by TSMC to build these chips, either N7P or N7+. The die-size could measure up to 505 mm², and AMD could aim for a 50% performance/Watt gain over the "Navi 10." AMD could carve out as many as 10 SKUs out of the "Navi 21," but only three are relevant to the gamers. The SKU with the PCI device ID "0x731F: D1" succeeds the RX 5700 XT. The one bearing "0x731F: D3" succeeds the RX 5700, with a variant name "Navi 21 XL." The "Navi 21 XE" variant has a PCI ID of "0x731F: DF," and succeeds the RX 5600 XT.
The first-gen RDNA may not ride into the sunset, as AMD is planning to refresh them. The company is probably porting the "Navi 10" silicon to TSMC N7P, to come up with new mainstream SKUs that lack ray-tracing, but will occupy mid-range price-points. This would be similar to NVIDIA positioning half its "Turing" product-stack without ray-tracing, under the GTX 16-series, occupying sub-$300 price-points. The resulting ASICs are the "Navi 10+," "Navi 10 XM+," and "Navi 10 XTE+."
51 Comments on AMD RDNA2 "Navi 21" GPU to Double CU Count Over "Navi 10"
AMD are aware of this and they are trying hard to change things, but they are a smaller company than Intel and Nvidia, so they have to pick their fights more carefully. I think they wanted to go for the crown with graphic cards this fall, but Nvidia won't get caught with their pants down like Intel. So we'll see a higher-end GPU from AMD this fall, just that it won't be enough to take the crown from the biggest Nvidia die.
In the laptop market, you don't see any 4900HS with RTX 2080, the best video card you see the 4900HS paired with is 2060. This, in spite of the fact that the 4900HS is smashing Intel processors in performance, power consumption, and price. The 2070s and the 2080s are paired with Intel instead. Why? Brand awareness, intel sells better in high-end laptops, because buyers in that market are looking for that blue logo.
Last time AMD tried to fight Nvidia by throwing shaders at the problem, they ended up with an architecture they couldn't actually fully feed (Polaris). I hope they learned their lesson.
Something something, but it's only 30%+ faster than 2080Ti, something.
Oh well.Lol.A kindergarden take on a techie forum, color me surprised.Or for other reasons that we have seen about 2 decades ago.
I mean, "brand awareness" is one hell of an argument, given what AMD is doing with Intel in DIY market.
Excited for Navi21 XT! I remember the days when AMD was touting "RADEON FURY, HUNTING TITANS", maybe this time AMD could say that again, fingers crossed!
I'm quite sure that Nvidia's spying services and general market forecasts already know what is coming with Navi 2X.
But it'd be against their interest to do anything proactively, so would like to keep the status quo as it is as longer as possible.
This said - it's perfect timing for AMD to begin releasing benchmarks, so we see anyways what is coming, and the general public knows it with certain.
Personally, I would love to see 2080 performance for $200-300, but I think we all know that's not very realistic. Still, whatever the improvements, 4k or high refresh gaming will be one step closer to the mainstream.
Hmm, Vega 20 is just 331 sq. mm with (most probably) 64 compute units and 4096 shaders.
www.techpowerup.com/gpu-specs/radeon-vii.c3358
First, Nvidia do not mind at all pairing their GPU's with AMD CPU's, if that allows them to sell more products and make more money. The simplest example in that direction is that the latest Ampere compute cards are paired with AMD Rome CPU's, and they are built by Nvidia themselves this way because this will allow them to make more money.
Second, Nvidia is not blocking the OEM from pairing their GPU's with AMD CPU's, hence you have laptops with 4000 Ryzen and Nvidia graphics (1660Ti or 2060 series). Nvidia sells the cards to the OEM and the OEM assemble them as they deem better.
Third, it's the OEM themselves that prefer to pair the higher-end Nvidia cards with Intel CPU's, and that,s because in the >2k USD laptop segment, the blue logo sells better, or at least that is what the OEM think. This is the brand awareness part, and this changes very slowly, since many people in that market segment never heard of Techpowerup, or gamer's nexus, etc. in their life.
This
is
Pascal!
Sorry I couldn't contain myselfYou seem new here, can you get a room? Two week quarantine, its contagious