• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Question Speculation: RDNA2 + CDNA Architectures thread

Page 82 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
True, I checked It once more using the measured average clockspeed from the review and It's almost linear in 4K.

edit:
I checked also Polaris RX 460 vs RX 470 and there we can see a difference. Vega doesn't have a halved version.
ASUS Radeon RX 460 STRIX OC 4GB Review vs ASUS Radeon RX 470 STRIX OC 4 GB Review
Specs:
TFLOPs: 2.262Tflops vs 4.706Tflops (+108%)
Clockspeed: 1262Mhz vs 1149Mhz (-9%)
CU: 14 vs 32 (+129%)
ROP: 16 vs 32 (+100%)
Bandwidth: 112GB/s vs 211GB/s (+88%)

Performance difference:
FullHD: +79%
WQHD: +82%
4k: +76%
 
Last edited:
Of course, another issue with prediction is that there will be for sure changes in the architecture that may affect performance in a positive or negative way. I.e. the rumors about a narrow bus may point to a negative factor, utlization in a CU should increase, and there was a rumor about a complete overhaul of RBEs
 
Well not only that, there was Katcorgi or Rogame (sorry, I don't remember who) saying Big Navi had 128 ROPs with fewer RBE partitions... Pointing to something fishy going on on that side
 
Now that the 3090 reviews are out, it looks like straight doubling of 5700xt performance will put AMD in a competitive position with NV's entire stack for 1080 and 1440p at least, and within striking distance of the 3090 at 4k (although falling a bit short).

If Navi21 has right at 2x Navi10's 4k performance, it will be less than 2x on 1440 and 1080.
 
If Navi21 has right at 2x Navi10's 4k performance, it will be less than 2x on 1440 and 1080.

- The 5700xt experienced some non-linear performance drop off at 4K resolutions. My expectation/hope is that we see double performance at 1080/1440 and *better* than double performance at 4K as big-navi becomes less CPU bound.

This would not be unlike what we see with the 3080/3090 that really start stretching their legs at the 4K res.

AMD is just starting from so much further behind, which makes it less believable/likely to happen...
 
- The 5700xt experienced some non-linear performance drop off at 4K resolutions. My expectation/hope is that we see double performance at 1080/1440 and *better* than double performance at 4K as big-navi becomes less CPU bound.

This would not be unlike what we see with the 3080/3090 that really start stretching their legs at the 4K res.

AMD is just starting from so much further behind, which makes it less believable/likely to happen...
Yeah, it'll be more than 2x 5700XT performance at 4k.
 
- The 5700xt experienced some non-linear performance drop off at 4K resolutions. My expectation/hope is that we see double performance at 1080/1440 and *better* than double performance at 4K as big-navi becomes less CPU bound.

This would not be unlike what we see with the 3080/3090 that really start stretching their legs at the 4K res.

AMD is just starting from so much further behind, which makes it less believable/likely to happen...

Is it really much further behind when they are starting with a 10.3B transistor die and RDNA performance per transistor is similar to Turing?
 
I am really starting to wonder If the info about 505mm2 and 80CU is actually correct. For 80CU, 128ROPs and 512bit Rdna1 GPU I got only 461mm2 and that is with the same transistor density.
I personally don't believe density will stay the same so either die size is wrong or the number of CU.
 
Back
Top