Question Speculation: RDNA2 + CDNA Architectures thread

Page 74 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

uzzi38

Platinum Member
Oct 16, 2019
2,705
6,427
146
All die sizes are within 5mm^2. The poster here has been right on some things in the past afaik, and to his credit was the first to saying 505mm^2 for Navi21, which other people have backed up. Even still though, take the following with a pich of salt.

Navi21 - 505mm^2

Navi22 - 340mm^2

Navi23 - 240mm^2

Source is the following post: https://www.ptt.cc/bbs/PC_Shopping/M.1588075782.A.C1E.html
 

leoneazzurro

Golden Member
Jul 26, 2016
1,052
1,716
136
Ampere being better does not mean Turing is crap at that, especially the highest end card. In any way, if I had to buy an enthusiast card, i would like it to last the longest time possible, with good aging. And in that case a RDNA1 high end card would have been less competittive than in the mainstream segment, where updating happens more often.
 

Kuiva maa

Member
May 1, 2014
182
235
116
The reason why AMD didn't create a bigger RDNA1 chip is quite obvious if we see their post bulldozer practices. The last time radeon came up with a full GPU range for a new architecture was back in 2012 and GCN 1st gen. They had an entry level (cape verde,7750/7770), mainstream (pitcairn,7850/7870), high end (tahit,7950/7970) that corresponded to the full array of nvidia kepler chips. They also gave us 7790 and even GK110 with some delay got competition in the form of hawaii. This has never happened ever since. From that point onwards, AMD has only been bringing one or two GPUs per generation tops. Against maxwell they just rebranded their existing range (eg grenada etc), dished out a card out of Apple's Tonga rejects (R9 285), and eventually released Fiji (theri last enthusiast level chip). Against Pascal they only gave two Polaris gpus for the low and mainstream part of the market and near the end of that gen they also brought vega 10 at the high end,which served as a bridge vs Turing in a shrunk to 7nm version. Then after 10+ months after Turing arrived they brought two RDNA1 chips.
So the reason we saw no big RDNA1 chip was simply the fact that until a couple of years ago, AMD was cash starved and simply couldn't afford the resources to design it. They would gladly make one if they could afford it but they have been alternating between segments throughout the 2010s while nvidia was happily bringing several GPUs to cover the whole market every year almost.
With their resurgence in the CPU front and their economic situation being rather good I would assume that from now one we will be seeing a full range of products with every new gen once again.
 
Last edited:

moinmoin

Diamond Member
Jun 1, 2017
5,064
8,032
136
Nothing more then demand exceeding the sales predictions on certain sku's. When this happens you can't just whip up more, I believe it takes a few months from start to finish.

AMD estimates sales and produces what they think they'll need. Best to wait and see what happens. I believe AMD said Big Navi comes before the consoles. I'd guess availability should be close to the announcement as there really isn't much time in between it and PS5's release date. Availability ??? Most likely in stock longer then the 3080's. The good old supply and demand arguments will be fought at that time.
If AMD botched the orders the lead time to correct that at TSMC is reportedly up to half a year.

This may have gotten better by now, but AMD's estimates have to be spot on (they tend to err on the low side historically out of financial necessity) and capacity at TSMC has to be there. In foundry business there is no fast enough turnaround possible to directly react to supply shortages right as they happen.

My expectation is that with the console chips orders AMD reserved plenty capacity at TSMC which it'll opt to retain for its own chips once the console chips orders are fulfilled.
 

blckgrffn

Diamond Member
May 1, 2003
9,299
3,440
136
www.teamjuchems.com
AMD themselves stated they didn't expect the take rate to be so high given the $500 MSRP before tax.

Haha, which is sort of hilarious.

Because that means that type of SKU (in terms of competitive peformance and pricing) didn't exist for them before so their forecasting models were terrible.

"Wow, there is this much potential at this price point? Intel you've had this spot for the last decade?!? We can actually make money selling CPUs!"
 
  • Love
Reactions: lightmanek

moinmoin

Diamond Member
Jun 1, 2017
5,064
8,032
136
Haha, which is sort of hilarious.

Because that means that type of SKU (in terms of competitive peformance and pricing) didn't exist for them before so their forecasting models were terrible.

"Wow, there is this much potential at this price point? Intel you've had this spot for the last decade?!? We can actually make money selling CPUs!"
More like a sad reflection of AMD's business the decade before. It really had no worthwhile mass market consumer CPU product at that price point for that long (or even longer?).
 

Timorous

Golden Member
Oct 27, 2008
1,748
3,240
136
If AMD botched the orders the lead time to correct that at TSMC is reportedly up to half a year.

This may have gotten better by now, but AMD's estimates have to be spot on (they tend to err on the low side historically out of financial necessity) and capacity at TSMC has to be there. In foundry business there is no fast enough turnaround possible to directly react to supply shortages right as they happen.

My expectation is that with the console chips orders AMD reserved plenty capacity at TSMC which it'll opt to retain for its own chips once the console chips orders are fulfilled.

Isn't that the lead time to get more wafers rather than the lead time to change the product mix on wafers you have ordered but that have not been manufactured yet.
 

blckgrffn

Diamond Member
May 1, 2003
9,299
3,440
136
www.teamjuchems.com
More like a sad reflection of AMD's business the decade before. It really had no worthwhile mass market consumer CPU product at that price point for that long (or even longer?).

Ha, right?

I can laugh, you can cry, but that's exactly it.

Even the 8xxx bulldozer chips were relegated to "super value sub i5" pricing basically from the jump.

Man, I bet there were a lot of very unfun tense meetings at AMD over the last decade I am very glad that I was not a part of.
 
Last edited:

moinmoin

Diamond Member
Jun 1, 2017
5,064
8,032
136
Isn't that the lead time to get more wafers rather than the lead time to change the product mix on wafers you have ordered but that have not been manufactured yet.
That's what I think too, which is why I wrote that I expect AMD to retain the capacity at TSMC for its own chips after the console chips orders for which it was originally reserved are fulfilled. External obligations, like those console chips orders, always come first though.
 

A///

Diamond Member
Feb 24, 2017
4,351
3,158
136
Haha, which is sort of hilarious.

Because that means that type of SKU (in terms of competitive peformance and pricing) didn't exist for them before so their forecasting models were terrible.

"Wow, there is this much potential at this price point? Intel you've had this spot for the last decade?!? We can actually make money selling CPUs!"
That's what I don't get. I forget if it was Forest who said that or Papermaster. It amounted to "Because of how the competition prices similar hardware and what we estimated they move each month, we did not expect such an enthusiastic take rate."

What was the ASP for a 12 core Intel at the time? $1,200?
 
  • Like
Reactions: Tlh97 and blckgrffn

DJinPrime

Member
Sep 9, 2020
87
89
51
3) The RX 5700 XT already had a high TDP and AMD is done playing that game.
So, not scalable at higher speed or core counts or both then. It was a small chip on 7nm from tsmc, I don't remember hearing yield issues.

Navi was by design targeting the mid-range performance level. Simple economics as greater sales are to be had in the lower to mid-range vs the higher end market. Putting Big Navi on the back burner doesn't mean they couldn't have made it earlier if it made sense at the time to do so. It was in AMD's best interest to use their resources and wafer supply for their other offerings and commitments at that time.
Also not scalable then, since it was only designed for mid range performance. If you believe that, then it means there's something about the design that doesn't work at high performance. But that's not how historically GPU have been design. All the lower tiers are basically the big chip with clusters removed, there's not a whole lot of difference in design. Whatever is their biggest chip is their best chip. Where the performance lands is what it is.
Let's do some simple math, including all the cost of the card, 5700 ended up selling for $400. So, you think that basically having the same board and maybe add another 4GB of memory and have a 50% bigger chip that sells for $800-$1000 wouldn't have bigger margins? And it's not like you're wasting the chip, bin the bad ones down to 5700 and 5500. If that's really how it is, no wonder NV is on top, AMD is not even trying. I prefer to think that AMD tried but could not scale up for some technical reason. No shame there, sometime things just didn't work the way you expected and the next version will be better. Also, I hope you're wrong about the wafer availability, cause there's tons more pressure now at 7nm. New xbox, ps5, zen 3, new iphones. If they have the same mentality, how many big Navi will we even be made?
Why bother even, with the price of 3070 and 3080, might as well not even make any big Navi. /s
 

Hitman928

Diamond Member
Apr 15, 2012
6,186
10,693
136
So, not scalable at higher speed or core counts or both then. It was a small chip on 7nm from tsmc, I don't remember hearing yield issues.


Also not scalable then, since it was only designed for mid range performance. If you believe that, then it means there's something about the design that doesn't work at high performance. But that's not how historically GPU have been design. All the lower tiers are basically the big chip with clusters removed, there's not a whole lot of difference in design. Whatever is their biggest chip is their best chip. Where the performance lands is what it is.
Let's do some simple math, including all the cost of the card, 5700 ended up selling for $400. So, you think that basically having the same board and maybe add another 4GB of memory and have a 50% bigger chip that sells for $800-$1000 wouldn't have bigger margins? And it's not like you're wasting the chip, bin the bad ones down to 5700 and 5500. If that's really how it is, no wonder NV is on top, AMD is not even trying. I prefer to think that AMD tried but could not scale up for some technical reason. No shame there, sometime things just didn't work the way you expected and the next version will be better. Also, I hope you're wrong about the wafer availability, cause there's tons more pressure now at 7nm. New xbox, ps5, zen 3, new iphones. If they have the same mentality, how many big Navi will we even be made?
Why bother even, with the price of 3070 and 3080, might as well not even make any big Navi. /s

GPUs are AMD's least profitable 7nm product. Priority was given to more profitable product lines both in terms of development funding and wafer supply. AMD's GPU group had been stripped down to a bare bones operation to give more funding to the Zen team and the graphics team are only recently seeing significant increases in funding. Without the required funding, AMD decided to focus on the higher volume segments to try and stay relevant in regards to market share. Now that they have more funding they are expanding to a full product lineup. That's it, it's not that complicated.

Ongoing wafer availability is a concern and no one knows how many wafers AMD has purchased/is purchasing for RDNA2. It might be tight for a bit with Zen3, RDNA2, and consoles all launching at the same time, but with mobile chips migrating to 5 nm, that should free up a lot of space for the medium to long term until AMD makes the move to 5 nm as well.
 

Olikan

Platinum Member
Sep 23, 2011
2,023
275
126
Hmm, is he referring to this patent?

ADAPTIVE CACHE RECONFIGURATION VIA CLUSTERING

That's quite a big change to cache subsytem
There is crazy impressive research from AMD, that pretty much IS this patent....


Just a quote:
"We extensively evaluate our proposal across 28 GPGPU applications. Our dynamic scheme boosts performance by 22% (up to 52%) and energy efficiency by 49% for the applications that exhibit high data replication and cache sensitivity without degrading the performance of the other applications. This is achieved at a modest
area overhead of 0.09 mm2/core."
 

Hitman928

Diamond Member
Apr 15, 2012
6,186
10,693
136
There is crazy impressive research from AMD, that pretty much IS this patent....


Just a quote:
"We extensively evaluate our proposal across 28 GPGPU applications. Our dynamic scheme boosts performance by 22% (up to 52%) and energy efficiency by 49% for the applications that exhibit high data replication and cache sensitivity without degrading the performance of the other applications. This is achieved at a modest
area overhead of 0.09 mm2/core."

I'm assuming by core they mean compute unit? If it's stream processor, that modest overhead is not so modest, lol.
 
Last edited:

eek2121

Diamond Member
Aug 2, 2005
3,100
4,398
136
GPUs are AMD's least profitable 7nm product. Priority was given to more profitable product lines both in terms of development funding and wafer supply. AMD's GPU group had been stripped down to a bare bones operation to give more funding to the Zen team and the graphics team are only recently seeing significant increases in funding. Without the required funding, AMD decided to focus on the higher volume segments to try and stay relevant in regards to market share. Now that they have more funding they are expanding to a full product lineup. That's it, it's not that complicated.

Ongoing wafer availability is a concern and no one knows how many wafers AMD has purchased/is purchasing for RDNA2. It might be tight for a bit with Zen3, RDNA2, and consoles all launching at the same time, but with mobile chips migrating to 5 nm, that should free up a lot of space for the medium to long term until AMD makes the move to 5 nm as well.

I would ignore him, he is just trolling people.
 

Krteq

Senior member
May 22, 2015
993
672
136
There is crazy impressive research from AMD, that pretty much IS this patent....


Just a quote:
"We extensively evaluate our proposal across 28 GPGPU applications. Our dynamic scheme boosts performance by 22% (up to 52%) and energy efficiency by 49% for the applications that exhibit high data replication and cache sensitivity without degrading the performance of the other applications. This is achieved at a modest
area overhead of 0.09 mm2/core."
Nice

But after some research I assume both patents are more related to CDNA then RDNA
 

blckgrffn

Diamond Member
May 1, 2003
9,299
3,440
136
www.teamjuchems.com
Do you really consider it a loss? I paid $800 for my 1080ti and I hope to retire it this year, but it won’t be a loss at all for me. I got my money’s worth out of it, and I can’t even sell it (it is going in another PC).

That's fair to ask - but if I could sell today and get nearly $400 and then in a five weeks there is such a bountiful crop of AMD Navi cards that I lose ~$200 on resale then that seems like lost money to me. Like deciding when to sell a stock...

And I've got a years use out of this thing, so I could look it at is as ~no cost per month of usage (sell now) or ~$20 per month (sell post launch) OR just pass it down to my son like I intended to and like you just get years of functional use out of it.

If used GPU prices hadn't been so crazy last year I probably would have tried to find a Vega 56 or something to nurse myself into RDNA2. I was so close to buying a Fury Nano on eBay for ~$105 shipped - I am kind of annoyed I didn't because of how niche that card was :tearsofjoy: (I put in an offer for $100 and he countered at $105 and I let it expire)