• 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.

Discussion RDNA4 + CDNA3 Architectures Thread

Page 119 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
DisEnchantment

DisEnchantment

Golden Member
1655034287489.png
1655034259690.png

1655034485504.png

With the GFX940 patches in full swing since first week of March, it is looking like MI300 is not far in the distant future!
Usually AMD takes around 3Qs to get the support in LLVM and amdgpu. Lately, since RDNA2 the window they push to add support for new devices is much reduced to prevent leaks.
But looking at the flurry of code in LLVM, it is a lot of commits. Maybe because US Govt is starting to prepare the SW environment for El Capitan (Maybe to avoid slow bring up situation like Frontier for example)

See here for the GFX940 specific commits
github.com

History for llvm/lib/Target/AMDGPU - llvm/llvm-project

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. - History for llvm/lib/Target/AMDGPU - llvm/llvm-project
github.com github.com
Or Phoronix

More AMD "GFX940" Enablement Work Landing In LLVM - Phoronix

www.phoronix.com www.phoronix.com

There is a lot more if you know whom to follow in LLVM review chains (before getting merged to github), but I am not going to link AMD employees.

I am starting to think MI300 will launch around the same time like Hopper probably only a couple of months later!
Although I believe Hopper had problems not having a host CPU capable of doing PCIe 5 in the very near future therefore it might have gotten pushed back a bit until SPR and Genoa arrives later in 2022.
If PVC slips again I believe MI300 could launch before it :grimacing:

This is nuts, MI100/200/300 cadence is impressive.

1655034362046.png

Previous thread on CDNA2 and RDNA3 here

Question - Speculation: RDNA3 + CDNA2 Architectures Thread

Man I have been dying to make this one for a while now. First rumours for RDNA3 are here so new thread time! Just going to start off with this one for now: kopite7kimi on Twitter: "@VideoCardz Ah, I mean a simple mcm design with 10240 cores is not enough. Because the lift from RDNA2 to RDNA3...
forums.anandtech.com forums.anandtech.com
 
Last edited:
SolidQ said:
Mindfactory. Seems a lot 6800 still..
8b6d5804725644b7efba53f828cdc3a0.png


If 8600XT with 12GB for 300-330 with same perf as 6800. Would be nice.

P.S Gonna be interesting how people react, if AMD gonna sell 8700 non XT for 400$ with much better RT than 7800XT
Click to expand...

I was looking at 7700 XT's last night. Then I saw, why bother? The 7800 XT is not much more and then I saw the vanillia 6800. I'm not really looking to buy but a 6800 is attractive at its price. If only Anandtech still reviewed GPU's.
 
Last edited:
Thunder 57 said:
The 7800 XT is not much more and then I saw the vanillia 6800. I'm not really looking to buy but a 6800 is attractive at its price.
Click to expand...
For me the 7900 GRE is a no-brainer coz it's so close to the 7800 XT where I live (Abu Dhabi). I think the shopkeepers decided to use their super brains and figured that since 7900 GRE is the Chinese edition, it must be inferior compared to the 7800 XT so not charging a premium for that.

But at this point, I would wait a few months for RDNA4 unless I find RDNA3 at HALF price 😛
 
igor_kavinski said:
Yeah except when their "best" product malfunctions (like some repair shops getting 200 4090s to repair per month). But people who want bragging rights appear to put themselves through any suffering.
Click to expand...
Yeah, well, and none of those Radeons have hot spot issues...
 
Tup3x said:
Yeah, well, and none of those Radeons have hot spot issues...
Click to expand...
It was a limited initial run of 7900 XTX cards. You don't see a thread on these forums where Radeon users are complaining about hotspots, do you? But the 12VHPWR connector fiasco threads are here, two at least I think.
 
Are you referring to the QC issue with some of the reference coolers? That issue didn't even affect any cards with non reference coolers. But yes, there were some early 7900XTX reference batches that had an issue with the vapor chamber I believe.
 
Before, people "hoped" that the new AMD card with the next generation architecture would compete with Nvidia's best for the top.
Now people are "hoping" that that in the generation after that AMD will decide to compete with Nvidia's best for the top.
 
Shmee said:
Are you referring to the QC issue with some of the reference coolers? That issue didn't even affect any cards with non reference coolers. But yes, there were some early 7900XTX reference batches that had an issue with the vapor chamber I believe.
Click to expand...
No, third party coolers. Pump out effect can happen after few months and hot spot temps start to climb. At worst it leads to throttling and noisy cooler.
 
Panino Manino said:
Before, people "hoped" that the new AMD card with the next generation architecture would compete with Nvidia's best for the top.
Now people are "hoping" that that in the generation after that AMD will decide to compete with Nvidia's best for the top.
Click to expand...
In times of ATI, there used to be the x990 cards that had more power than a single Nvidia card. Microstutter killed it. If AMD cracks this problem with RDNA 5 then you might get big $$$$ AMD cards. Else the wait will continue to RDNA 6 or beyond
 
Tup3x said:
No, third party coolers. Pump out effect can happen after few months and hot spot temps start to climb. At worst it leads to throttling and noisy cooler.
Click to expand...
OK, I guess that's a fair point. Do AIBs spend more on cooling solutions for Geforce cards so it doesn't happen there?
 
By the way, people getting the 4060 in droves coz 4090 is the current fastest consumer card, makes absolutely no sense to me. It's like getting a Mac Mini coz Apple is topping the Geekbench ST charts at the moment. Yeah, great job folks. Now suffer the VRAM inadequacy on the former and literally nothing much to do other than basic stuff on the latter.
 
igor_kavinski said:
By the way, people getting the 4060 in droves coz 4090 is the current fastest consumer card, makes absolutely no sense to me. It's like getting a Mac Mini coz Apple is topping the Geekbench ST charts at the moment. Yeah, great job folks. Now suffer the VRAM inadequacy on the former and literally nothing much to do other than basic stuff on the latter.
Click to expand...
the shills.
Shill Foundry etc.
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top