AMD Execution Thread [2024]

If they shift their messaging and product lineup to best value similar to early Zen generations they can generate a lot of positive buzz and sales momentum.
That's a big "if".

This statement:
So, my number one priority right now is to build scale, to get us to 40 to 50 percent of the market faster. Do I want to go after 10% of the TAM [Total Addressable Market] or 80%? I’m an 80% kind of guy because I don’t want AMD to be the company that only people who can afford Porsches and Ferraris can buy. We want to build gaming systems for millions of users.
Makes it sound like Nvidia, Intel and other GPU makers somehow only target the "10% of the TAM" and produce only "Porsches and Ferraris" which is essentially completely false. The "80%" is the most competitive part of the market with the lowest margins which coincidentally is why all chip makers want to target those "10%" as much as they could.

So yeah, I think this is just PR preparation for another AMD generation without proper high end part, little more.
 
A little creative reading inbetween the lines here; sounds like that they are prepping for some sort of cloud play for xbox/MS to 2in1 their service.

So, going forward, we’re thinking about not just RDNA 5, RDNA 6, RDNA 7, but UDNA 6 and UDNA 7. We plan the next three generations because once we get the optimizations, I don't want to have to change the memory hierarchy, and then we lose a lot of optimizations. So, we're kind of forcing that issue about full forward and backward compatibility. We do that on Xbox today; it’s very doable but requires advanced planning. It’s a lot more work to do, but that’s the direction we’re going.

PA: When you bring this back to a unified architecture, this means, just to be clear, a desktop GPU would have the same architecture as an MI300X equivalent in the future? Correct?

JH: It's a cloud-to-client strategy. And I think it will allow us to be very efficient, too. So, instead of having two teams do it, you have one team. It’s not doing something that's that crazy, right? We forked it because we wanted to micro-optimize in the near term, but now that we have scale, we have to unify back, and I believe it's the right approach. There might be some little bumps.
 

This is interesting. They admit some mistakes with their current strategy.

we made some mistakes with the RDNA side; each time we change the memory hierarchy, the subsystem, it has to reset the matrix on the optimizations. I don't want to do that

So, going forward, we’re thinking about not just RDNA 5, RDNA 6, RDNA 7, but UDNA 6 and UDNA 7. We plan the next three generations because once we get the optimizations, I don't want to have to change the memory hierarchy, and then we lose a lot of optimizations. So, we're kind of forcing that issue about full forward and backward compatibility. We do that on Xbox today; it’s very doable but requires advanced planning. It’s a lot more work to do, but that’s the direction we’re going.

They are probably bringing tensors to their consumer GPUs.
 
Previously CDNA-specific HW like the matrix cores coming to consumer GPUs is the natural implication, but is the opposite true as well? Will RDNA-specific HW like ray tracing units come to datacenter GPUs?
 
Previously CDNA-specific HW like the matrix cores coming to consumer GPUs is the natural implication, but is the opposite true as well? Will RDNA-specific HW like ray tracing units come to datacenter GPUs?
Probably not. If it's anything like what Nvidia is doing then despite the basic architecture being similar if not the same the balancing of units and caches/memory and the provision of some features will be different depending on the target market.
 
What else could it be though? AMD roadmap architecture not currently in any other AMD GPU...that has to be the next iteration of RDNA.
 
What else could it be though? AMD roadmap architecture not currently in any other AMD GPU...that has to be the next iteration of RDNA.
It's possible that Sony may be using something even more advanced than what will be a part of RDNA4 lineup. This possibility is low though I'd say.
 
It's possible that Sony may be using something even more advanced than what will be a part of RDNA4 lineup. This possibility is low though I'd say.

If that was the case AMD themselves would be using it in RDNA4 wouldn't they?

There have been leaks all year long, the PS5 Pro basically has an RDNA 3.5 based GPU with RDNA4 Raytracing enhancements.
 
A number of insiders at Microsoft have been mentioning performance issues with $AMD's MI300. Below are the comments from a recent interview which gave quite some detail. Basically there are a number of issues with the MI300, so they had to alter workloads as the chips were underperforming. As a result, they pushed out some orders for the MI300, but that being said, given that inference demand is so high, they might have to pull in those orders again. So net-net, could still be positive for AMD given the massive end demand from external customers. Although AMD might have to offer better pricing given the lower performance of their chips. Performance per dollar spent, the MI300 is still better than the $NVDA H200 for inference workloads, but just less than expected.

 
Last edited:
AMD’s laptop OEMs decry poor support, chip supply, and communication — OEM complains the company has "left billions of US dollars lying around" due to poor execution.

 
Ray Tracing Animated Displaced Micro-Meshes

So that's how AMD sold Microsoft on 2026 RDNA5 gaming machines and "biggest tech leap ever" or wtfever the quote was. RT Xbox AI 1080 incoming circa 2026

The next gen was earlier expected in the 2027 to 2028 timeframe but given the fall off in Xbox sales, MS might well be incentivized to launch earlier. And given they've chosen not to do a mid-gen upgrade like Sony, I think they will have to try and launch next gen first. Late 2026 works well for a Zen 6 and RDNA5 based APU.

AMD’s laptop OEMs decry poor support, chip supply, and communication — OEM complains the company has "left billions of US dollars lying around" due to poor execution.


This is true unfortunately. AMD has pretty much had the best laptop chips since Zen 2 but havent been able to capture more market share. Seemingly they were trying to turn this around with Strix Point but that remains to be seen.
 
Q2 2024 dGPUs results are in, AMD remains at 12%, NVIDIA is at 88%. Both managed to increase their shipments year over year, AMD only by 3% and NVIDIA by a huge 60%!

AIB_PR_Q224_001.png


 
Back
Top