AMD in its post Q1-2020 earnings release disclosures stated that the company is "on track" to launching its next-generation "Zen 3" CPU microarchitecture and RDNA2 graphics architecture in late-2020. The company did not reveal in what shape or form the two will debut. AMD is readying "Zen 3" based EPYC "Milan" enterprise processors, "Vermeer" Ryzen desktop processors, and "Cezanne" Ryzen mobile APUs based on "Zen 3," although there's no word on which product line the microarchitecture will debut with. "Zen 3" compute dies (CCDs) are expected to do away with the quad-core compute complex (CCX) arrangement of cores, and are expected to be built on a refined 7 nm-class silicon fabrication process, either TSMC N7P or N7+.
The only confirmed RDNA2 based products we have as of now are the semi-custom SoCs that drive the Sony PlayStation 5 and Microsoft Xbox Series X next-generation consoles, which are expected to debut by late-2020. The AMD tweet, however, specifies "GPUs" (possibly referring to discrete GPUs). Also, with AMD forking its graphics IP to RDNA (for graphics processors) and CDNA (for headless compute accelerators), we're fairly sure AMD is referring to a Radeon RX or Radeon Pro launch in the tweet. Microsoft's announcement of the DirectX 12 Ultimate logo is expected to expedite launch of Radeon RX discrete GPUs based on RDNA2, as the current RDNA architecture doesn't meet the logo requirements.
46 Comments on AMD Confirms Zen 3 and RDNA2 by Late-2020
Just because the upcoming May 14th reveal of server/AI/Datacenter cards have obvious 'Ampere' focused hints, what's stopping the gaming side of things being the same?
They can both use the same code name but have different derivatives of that base architectures?
If Nvidia show off their next gen GPU architecture that's gaming focused then awesome!!! But I'm not going to hype myself up for it.
www.pcgamesn.com/nvidia/ampere-release-date-specs-performance-rumours
Realistically we don't really know, we just know next gen is on 7nm (or something like it) and it will have to improve on Turing. Which is really all you need to know. Nvidia isn't really surprising when it comes to GPU releases... ~30% bump across the stack, and if its more, a mark up on price to go with it.
Might sound boring, but it really is :D
wccftech.com/amd-radeon-big-navi-21-gpu-505-mm-die/
APUs are a different branch and if you follow Ryzen 9 4900HS, you will see how much more efficient and better it is than the desktop versions.
Despite AMD's Technologically superior CPU designs versus Intel, they don't hold the majority of market share. Even though Intel fell flat on its face, they remain the leader, die to past market share they've gained throughout AMDs lacking Bulldozer CPU era. AMDs mobile parts better be more efficient, can't compare desktop CPUs with mobile parts. They are both different animals. Not to mention, ZEN2 mobile just got released, that gave AMD ample more time to enhance ZEN2 versus the desktop models.
So far there are no signs Intel is radically throwing things around to make a dent. In fact with all these designs I get the impression they dig themselves an even deeper hole, hoping to weather the storm until they have volume production on a better node.
I mean, this here below, is just armageddon.
www.techpowerup.com/265241/amd-ryzen-9-4900hs-torpedoes-intels-core-i9-mobile-lineup-fastest-mobile-processor?cp=7
And CUDA isn't the only GPU acceleration available, what about AMDs' Direct Compute? Is it really THAT inferior to CUDA? < Question, I'm not sure, please enlighten me here.