Bondrewd
Veteran
Yeah, both in client and DC.So AMD are finally breaking the 64 CU "barrier"?
Arcturus is whopping 8 SEs.
Last edited:
Yeah, both in client and DC.So AMD are finally breaking the 64 CU "barrier"?
The logical CU count is 2*Navi10 => 80 CUs with both frontend and backend scaled proportionally. Also finally a truly historical moment - more than 64 ROPs for AMD!More.
Because when you're smashing some heads, only the best can do.
N21 also has weird stuff like xGMI on it so that eats area, too.
They can do weird shit too.The logical CU count is 2*Navi10 => 80 CUs with both frontend and backend scaled proportionally
True that.Also finally a truly historical moment - more than 64 ROPs for AMD!
No.Can the xGMI be a simple copy&paste from compute cards aimed to produce a gimmick like "Cross Fire Reloaded"?
Not entirely, no.Navi 21 is a consumer oriented chip.
N21 also has weird stuff like xGMI on it so that eats area, too.
Just throw more cores.Something in the consumer gaming PC space will need to compensate for the embedded hardware decompressors in next-gent consoles.
Throwing more cores is worthless.Just throw more cores.
Something in the consumer gaming PC space will need to compensate for the embedded hardware decompressors in next-gent consoles.
I.e. we should all want GPUs with NVMe slots in 2021. It might be the best case scenario.
Yeah but we can get plenty.Decompression isn't infinitely parallel
Not coming in client for a god damn while due to PCB material reqs.Or just wait for PCIe5 to blow everything away.
Lower end of the Radeon Instant product stack for running inference, perhaps. Parity in xGMI across the lineup probably enables direct mGPU interconnect, as MI60 already does but only with its own kind.Just throw more cores.
Also idunno how that relates to N21 having xGMI.
You can just get a MI100, it's fairly cheap should you be annoying enough.Lower end of the Radeon Instant product stack for running inference, perhaps.
NVMe slots on GPU's won't get around the need to decompress the output from the SSD in realtime.
If you're talking about plenty of threads for decompression, then we really can't..Yeah but we can get plenty.
I think shader based decompression is more of a method to offload the CPU than to achieve higher performance (due to low thread counts). Bigger installs alone don't solve the I/O throughput limit.Either shader based texture decompression or less compression with bigger installs are the answer to that.
https://coreteks.tech/articles/index.php/2020/07/29/big-navi-not-so-big/Reports from sources in Asia indicate AMD has started sharing details with partners about the upcoming RDNA2 based gaming GPUs.
Unfortunately for us PC enthusiasts it seems the news aren’t great regarding the so-called “NVidia Killer”. The performance level of the high-end GPUs based on the codenamed Sienna Cichlid ASICs is around the same as NVidia’s last-gen top SKU, the 2080ti, according to these reports. A best case scenario supposedly shared by AMD is that at most gamers should expect to get about 15% over the 2080ti in a select AMD “optimized” titles. According to the same sources AMD is aiming to launch the “Big Navi” as a direct competitor to the soon to be launched RTX 3080, and not as a competitor to NVidia’s highest performing part as has been widely reported (let alone beat it). Some have suggested that “Big Navi” would be up to 50% faster in traditional rasterization than the RTX 2080ti but according to AMD’s partners that will not be the case.
It's all so tiresome, yes.So it's Vega and 5700xt all over again ?
Of course, they're just generating clicks and covering all the bases.That rumor sounds kinda silly
This, Rome/Milan orders are big enough for AMD to pretend dGPUs don't exist for at least the next 2Q.I'm more concerned about TSMC capacity and what the availability will be like.
if the price is right it wont matter much.So it's Vega and 5700xt all over again ?
Of course, they're just generating clicks and covering all the bases.
N21 perf now ranges from 2080ti to 2080ti+50%.
No tier left behind!
This, Rome/Milan orders are big enough for AMD to pretend dGPUs don't exist for at least the next 2Q.
Maybe even into Q1'21.