• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Rumor: AMD Rembrandt APUs to Feature Zen3+, RDNA2 Architectures - Up to 12 CUs

Raevenlord

News Editor
Joined
Aug 12, 2016
Messages
3,755 (1.18/day)
Location
Portugal
System Name The Ryzening
Processor AMD Ryzen 9 5900X
Motherboard MSI X570 MAG TOMAHAWK
Cooling Lian Li Galahad 360mm AIO
Memory 32 GB G.Skill Trident Z F4-3733 (4x 8 GB)
Video Card(s) Gigabyte RTX 3070 Ti
Storage Boot: Transcend MTE220S 2TB, Kintson A2000 1TB, Seagate Firewolf Pro 14 TB
Display(s) Acer Nitro VG270UP (1440p 144 Hz IPS)
Case Lian Li O11DX Dynamic White
Audio Device(s) iFi Audio Zen DAC
Power Supply Seasonic Focus+ 750 W
Mouse Cooler Master Masterkeys Lite L
Keyboard Cooler Master Masterkeys Lite L
Software Windows 10 x64
A fresh rumor straight from the rumor mill paints AMD's next APU iterations as being updated to the latest and greatest architectures the company has to offer. The rumor comes from ExecutableFix via Twitter, a leaker who has a relatively proven track record on being right regarding upcoming hardware releases. This rumor can lay some credence to others, painting AMD's Ryzen 7000 series as being the first AMD APU-only release since they began their journey with the Zen architecture - it makes sense for the company to integrate their latest architectures in the mobile-geared Rembrandt first, working out some possible interaction quirks that might arise between the two architectures when deployed in the same package.

The leaker further affirms that the Rembrandt APUs will feature up to 12 RDNA2 CUs, which would amount to 768 stream processors on-chip - a marked increase from the current-generation 8 CUs based on the Vega architecture on their Ryzen 4000 mobile series. The leaker also discloses that AMD's Warhol seems to be MIA in recent AMD documentation and planning when it comes to the deployment of Zen3+, and that Rembrandt should be the one to carry that particular architecture refinement through to the 6 nm process. It would seem that AMD's Vega would "finally" see its demise, bringing about some much-needed performance improvements to counter Intel's investments in GPU performance with Xe.



View at TechPowerUp Main Site
 
Imagine AMD will someday build a microarchitecture to rival Intel's AVX512 aspirations with its own heterogeneous APU architecture and you would scale your gpu performance by upgrading memory sticks - what a future it would be for DIY enthusiasts!
 
it won't be in stock, so what's the point.
 
One question - why?
Because AVX512 is more ambitious, but AMD already has the framework laid out.
A single pipeline's power rail is easier to anticipate. Seperate units don't mix and match instead of a single device that does everything in its own power gating profile.
The FPU will become APU which is the radeon GPU we take for granted. GPU≡APU as they develop more dynamic workloads in my opinion.
 
1620593570960.png


*Nods in approval*

Guy's even wearing a red shirt for the occasion.
 
I'm waiting for the Bob Ross architecture :)
 
I'm waiting for the Bob Ross architecture :)

Im waiting for the Rolf Harris architecture. I hope it comes bundled with a cooler that makes wobbly board sounds
 
I'm waiting for the Bob Ross architecture :)
You know a certain Austrian was a good painter too. Chances of AMD naming anything after him are zero, though. :D

Because AVX512 is more ambitious, but AMD already has the framework laid out.
A single pipeline's power rail is easier to anticipate. Seperate units don't mix and match instead of a single device that does everything in its own power gating profile.
The FPU will become APU which is the radeon GPU we take for granted. GPU≡APU as they develop more dynamic workloads in my opinion.
AVX512 are far too niche to waste so much silicon on it. For every AVX512 workload that is needed enough, a good solution without using AVX512 will be found.
 
AVX512 are far too niche to waste so much silicon on it. For every AVX512 workload that is needed enough, a good solution without using AVX512 will be found.
Exactly my point. Yet, I don't approach it from the silicon side. The silicon is secondary to the power requirement. Longer instructions have their limits.
 
I do hope this is true. If this iGPU with will be able to push up to 120 or better, even 160fps for modern titles with low/medium. lt will be golden and GPU makers will need to think something to offer better deal for people. But as it is AMD i doubt they will cripple their market in gpu... and because of that it will be maybe x2 better than best iGPU from AMD. Let's wait and see :).
 
So Zen3+ isn't cancelled. Please make up your mind.
Zen 3+ may not be cancelled in a sense that will end up being an APU, and not a CPU only solution. Its almost like when AMD launched Ryzen 3xxxG with Zen+ series while the CPU only variant runs on Zen 2. So it is possible that may happen based on this article. I think it may be a good idea to combat the shortage of GPUs in the market, at least for the coming year or so. This is especially beneficial for OEMs/ PC makers because they can't sell an AMD system without GPU.
 
"Up to 12 CUs"

Waiting for an APU with 20 CUs.............mmmmmmmmmmmmmmmmmm
 
Zen 3+ may not be cancelled in a sense that will end up being an APU, and not a CPU only solution. Its almost like when AMD launched Ryzen 3xxxG with Zen+ series while the CPU only variant runs on Zen 2. So it is possible that may happen based on this article. I think it may be a good idea to combat the shortage of GPUs in the market, at least for the coming year or so. This is especially beneficial for OEMs/ PC makers because they can't sell an AMD system without GPU.
But the premise for the headlines saying it was cancelled had to do with global ship shortages, that doesn't change whether it instead ends up in an APU rather than a CPU. The point is no one knows and Zen3+ is not even something AMD has ever mentioned. So headlines talking about Zen3+ being cancelled are quite ridiculous when it has never even been confirmed.
 
You guys think adding AMD's Infinity cache into their APU's would remedy the issue that they've been having since they first launched, memory bandwidth?
 
You know a certain Austrian was a good painter too. Chances of AMD naming anything after him are zero, though. :D


AVX512 are far too niche to waste so much silicon on it. For every AVX512 workload that is needed enough, a good solution without using AVX512 will be found.
the fourth rei- generation architecture.
I don't like Apple but least M1 name is simple, M and 1. Intel has many lakes and wells and those get messy, NVidia and AMD keeps attaching their product with (influential)people and places, at some point it all looks like marketing ploy.
 
View attachment 199802

*Nods in approval*

Guy's even wearing a red shirt for the occasion.
He's also holding a graphics card that most certainly isn't green.

the fourth rei- generation architecture.
I don't like Apple but least M1 name is simple, M and 1. Intel has many lakes and wells and those get messy, NVidia and AMD keeps attaching their product with (influential)people and places, at some point it all looks like marketing ploy.
You're reading it wrong. It's i5 or Ryzen 5 against Firestorm+Icestorm.
 
Back
Top