Question Speculation: RDNA2 + CDNA Architectures thread

Page 68 - 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
 

EXCellR8

Diamond Member
Sep 1, 2010
3,982
839
136

blckgrffn

Diamond Member
May 1, 2003
9,298
3,440
136
www.teamjuchems.com
Yeah, wasn't that reported a month ago? I didn't think anything of it but I don't subscribe to Freight Life myself.

Maybe, I missed it. I thought there was something about how much that cost them back in the PS3 or PS4 days and they were committed to not doing that again. It's worse now that there are so few commercial flights to jam the bellies full on, I just brought in a pallet (~350 kg) and the surcharge was $5.80 per KG. Ouch. China is like $2 atm, which is way better but still bites when adding that to your BoM vs the comparatively free nature of 45' high cubes.
 

kurosaki

Senior member
Feb 7, 2019
258
250
86
What on earth are you basing that on? A 60/40 split is extremely unlikely given how much more air the back fan would move at similar power and noise levels. It wouldn't be as simple as stopping one fan and measuring GPU temperature, as that is not going to be the sole source of heat on the card. That, and even if you stop the front fan you might very well end up with a situation where the die remains cool connected to the back fin array with massive heatpipes, but the VRMs that rely on the front fan for cooling begin to overheat and throttle. If you really want to see how much each fan is exhausting in normal conditions, duct both IO and back exhaust through air velocity meters to measure CFM, and monitor intake and output temperatures to calculate the actual heat dissipated.

Haha!
I think we both can agree on that the cards ain't gonna survive on one fan only. To make the design depend on one fan to take 80% of the total needed dissipation isn't sound either. Makes for a too loud of a card. The best offload sound wise would be for the both fans to dissipate heat evenly. That's the dream scenario. My guess is that the back fan isn't doing quite as much as the "front"fan, to dissipate heat from the fins, but does a great job not circulating heat inside the case. It would just be asinine to put a fan on that realestate if it stood for 30% total cooling capacity or less.
 

MrTeal

Diamond Member
Dec 7, 2003
3,614
1,816
136
Haha!
I think we both can agree on that the cards ain't gonna survive on one fan only. To make the design depend on one fan to take 80% of the total needed dissipation isn't sound either. Makes for a too loud of a card. The best offload sound wise would be for the both fans to dissipate heat evenly. That's the dream scenario. My guess is that the back fan isn't doing quite as much as the "front"fan, to dissipate heat from the fins, but does a great job not circulating heat inside the case. It would just be asinine to put a fan on that realestate if it stood for 30% total cooling capacity or less.
Not at all, it can provide necessary cooling even if it's not moving a large portion of the heat. There's a lot of components in that front part of the card that require cooling, like the VRMs, inductors and RAM. Using a full coverage plate that ties into the main cooler is one way, but another is just to run air over them. An extreme example of something like this is cooling a card using something like a Kraken G10 bracket or one of the factory hybrid coolers. The vast majority of the cooling there is provided by the water cooling radiator, but the board still needs active airflow.

I disagree that the best arrangement soundwise is to have both fans dissipate heat evenly. Take a look at the cooler.
1600207975168.png
The front fins are tied into the vapour chamber, but the stack height is much smaller than the rear fan. Even if the airflow wasn't obstructed by the PCB, you would need greater airflow to provide the same cooling through the front fin array, which means more RPM and thus more noise. The airflow is obstructed by the PCB and the shroud though, and has to take a hard 90 and travel in that thin stack between the fan and the board, along all the high z-height components, and the up and around the HDMI ports and out the back. If you tried to provide equal cooling, the exhaust air will be a loud, high velocity turbulent mess and the fan will be spinning like a banshee trying to force it all through while the back fan spins slow and easy. The best compromise for low acoustics would be to have both fans run in a way that produces the same amount of noise, as long as thermal constraints on all the subsystems are met.

Really, this is an example of the entire reason people water cool and use big tower heatsinks on their CPUs. You take the high density heat and rather than try and deal with it in a compromised location, you use a high efficiency transport to bring it somewhere where you can use a nice big lowish density fin stack and a big fan to send low velocity laminar airflow through it. Low noise, good cooling.

So, back on track, AMD doesn't need a shrouded rear-exhaust card with axial fans, and I'm not really sure it's in their best interests to hire you as their thermal design engineering lead. :p
 

A///

Diamond Member
Feb 24, 2017
4,351
3,158
136
Jason has always been a whiny person.

Maybe, I missed it. I thought there was something about how much that cost them back in the PS3 or PS4 days and they were committed to not doing that again. It's worse now that there are so few commercial flights to jam the bellies full on, I just brought in a pallet (~350 kg) and the surcharge was $5.80 per KG. Ouch. China is like $2 atm, which is way better but still bites when adding that to your BoM vs the comparatively free nature of 45' high cubes.
Yeah. TBH, you either eat the loss now or forever delay or seek shipment via other methods that isn't as fast.
 

blckgrffn

Diamond Member
May 1, 2003
9,298
3,440
136
www.teamjuchems.com
Jason has always been a whiny person.


Yeah. TBH, you either eat the loss now or forever delay or seek shipment via other methods that isn't as fast.

I know man. I just wrote the check for $3,600 so I could have product now - not in mid November. It was worth it.

Plus that container has a duplicate of what I just had flown over, so I was able to actually get more stock total by mid November too.

Opportunity costs everywhere.
 

swilli89

Golden Member
Mar 23, 2010
1,558
1,181
136
Been looking over things and I am now super curious as to the die size big Navi is going to come in at. I think AMD actually built a chip larger than 500mm2 then it will match the 3080. Something around 22-24 billion xstors.
 

Midwayman

Diamond Member
Jan 28, 2000
5,723
325
126
This is what Sony said:

The information provided by Bloomberg is false
We have not changed the production number for PlayStation 5

How is that not refuting the rumor of production issues?

They only confirmed they still plan on making 15 million this fiscal year. Not-
  • Where they are according to plan
  • If there have been production issues
  • How they intend to make up the shortfall if it exists
Just there are many ways that statement could be true, but still hiding info. What companies don't say is often as important as what they do. Still I may just be reading too much into it.
 

A///

Diamond Member
Feb 24, 2017
4,351
3,158
136
I know man. I just wrote the check for $3,600 so I could have product now - not in mid November. It was worth it.

Plus that container has a duplicate of what I just had flown over, so I was able to actually get more stock total by mid November too.

Opportunity costs everywhere.
If you don't mind me asking, are you a small biz retailer?
 

Hitman928

Diamond Member
Apr 15, 2012
6,186
10,693
136
They only confirmed they still plan on making 15 million this fiscal year. Not-
  • Where they are according to plan
  • If there have been production issues
  • How they intend to make up the shortfall if it exists
Just there are many ways that statement could be true, but still hiding info. What companies don't say is often as important as what they do. Still I may just be reading too much into it.

As far as I am aware, Sony has not given any production numbers for PS5, the 15 million units number came strictly form this rumor. Let's break it down.

What the rumor claimed:
After more than doubling their initial production number to 15M units, as they started to try to produce PS5's in volume, they discovered that as many as half of the SOCs couldn't meet spec or were defective and so they had to then reduce the 15M units down to 11M units by the end of March 2021.

What Sony said:
This rumor is false and we have not changed production numbers for the PS5 after starting volume production.

So where in that is the wiggle room to say Sony is hiding this big production problem secret? The way I see it, either the rumor was fake or Sony is flat out lying. You can choose the believe the latter but given the absurd claims of the rumor, I'm inclined to believe Sony.
 
  • Like
Reactions: Martimus

kurosaki

Senior member
Feb 7, 2019
258
250
86
View attachment 29903
The front fins are tied into the vapour chamber, but the stack height is much smaller than the rear fan. Even if the airflow wasn't obstructed by the PCB, you would need greater airflow to provide the same cooling through the front fin array, which means more RPM and thus more noise. The airflow is obstructed by the PCB and the shroud though, and has to take a hard 90 and travel in that thin stack between the fan and the board, along all the high z-height components, and the up and around the HDMI ports and out the back. If you tried to provide equal cooling, the exhaust air will be a loud, high velocity turbulent mess and the fan will be spinning like a banshee trying to force it all through while the back fan spins slow and easy. The best compromise for low acoustics would be to have both fans run in a way that produces the same amount of noise, as long as thermal constraints on all the subsystems are met.

In the case of an axial fan, the air is always obstructed by the PCB, and has to take a "90 degree turn", the same applies to AMD's "new" cooler. The only thing we have to focus on is how much total heat is going out either way, not the amount of air in CFM. If the CFM in the back fan is half of the front, it may still carry the same amount of heat energy due to absorbing more heat under time of contact with the fins. They would not have put a fan there if the amount of heat dissipated was miniscule. Of course this would be optimal in a positive pressure case, and of course a negative pressure case could have a very negative impact on this type of setup. As I see it, the more heat you could push out as fast as possible, the better. There is nothing positive recirculating hot air inside the case. Nvidias half'n half aproach still makes a ton of sense.
 

coercitiv

Diamond Member
Jan 24, 2014
6,677
14,272
136
Of course this would be optimal in a positive pressure case, and of course a negative pressure case could have a very negative impact on this type of setup. As I see it, the more heat you could push out as fast as possible, the better.
Again with this. Air pressure inside the case doesn't matter in this scenario, whatever air is pushed outside through the back vents does so due to pressure from the video card fan.

Nvidias half'n half aproach still makes a ton of sense.
Nvidia's approach does make a lot of sense, but not for the reasons you invoke. Air going out through the back of the case is only a fraction of the air that cools the card. It's a good idea to let air go out that route, but this does not significantly change the amount of heat that the video card dumps inside the case.

The biggest strength of this cooler design still relies on the unobstructed second fan, which prevents air temperature rising in the lower part of the case, since most of the card heat is immediately pushed up.
 

kurosaki

Senior member
Feb 7, 2019
258
250
86
Again with this. Air pressure inside the case doesn't matter in this scenario, whatever air is pushed outside through the back vents does so due to pressure from the video card fan.


Nvidia's approach does make a lot of sense, but not for the reasons you invoke. Air going out through the back of the case is only a fraction of the air that cools the card. It's a good idea to let air go out that route, but this does not significantly change the amount of heat that the video card dumps inside the case.

But of course the pressure level inside the case is going to inflict the performance of the GPU trying to push air out the back. If you have a couple of large exhaust fans in the case, but skipped the intake fans completely, which I have had in the past due to a low noise build, the computer is going to try to suck air from whatever hole there is (Dust in USB-ports etc). The GPU is not going to perform optimal as if you had 4x 14cm fans on the intake, and one or two 12cm exhaust fans "Positive pressure". In that case, we would help the Gpu push air outside, not risking to suck any of it into the case again.

The biggest strength of this cooler design still relies on the unobstructed second fan, which prevents air temperature rising in the lower part of the case, since most of the card heat is immediately pushed up.

I agree, the air going out in the back is going to be relatively low in volume, but hotter than the air from the front fan. The front fan is going to be able to push a higher volume at a given time, and therefor not pick up as much heat per volume. so the inside fan is going to produce air which is a couple of degrees hotter, but in lager amount, and the back fan is going to push out a smaller volume than the front, but that air probably have absorbed more heat under time of fin contact and is going to be several degrees hotter.

If no reviewer is going to FLIR the shit out of this cooler, i'm willing to sacrifice myself! :D
 
Last edited:
  • Like
Reactions: lightmanek

coercitiv

Diamond Member
Jan 24, 2014
6,677
14,272
136
The front fan is going to be able to push a higher volume at a given time, and therefor not pick up as much heat per volume. so the inside fan is going to produce air which is a couple of degrees hotter, but in lager amount, and the back fan is going to push out a smaller volume than the front, but that air probably have absorbed more heat under time of fin contact and is going to be several degrees hotter.
That is just poor understanding of physics. Amount of heat absorbed by air molecules per unit of time scales linearly with temperature delta between air and heatsink surface. You do not remove the same amount of heat by running air slower through a heatsink just because air has time to get hotter. Running air slower through a heatsink is subject to massive diminishing returns, that is unless the heatsink is doing a very poor job at transferring heat.

If you have a couple of large exhaust fans in the case, but skipped the intake fans completely, which I have had in the past due to a low noise build, the computer is going to try to suck air from whatever hole there is (Dust in USB-ports etc). The GPU is not going to perform optimal as if you had 4x 14cm fans on the intake, and one or two 12cm exhaust fans "Positive pressure".
The video card fan locally creates far more pressure that negates the dynamics of the case for the purpose of pushing air out the back. Moreover, a negative pressure case with fans pushing air out the top and air being allowed to come in through the bottom would actually be quite beneficial for the Nvidia cooler.
 

Dribble

Platinum Member
Aug 9, 2005
2,076
611
136
Just wanted to say I can't believe J2C was such a child that he decided to leak sensitive images because he was annoyed by a red line.

Bloody hell man. Bloody hell.
He did make it obvious that AMD have basically taken an Nvidia 2xxx founders edition cooler, stuck Radeon over the Nvidia logo and given it the "gamer" look (i.e. all those stealth fighter angles and etched lines also found in "gamer" laptops and monitors).

(nicked from DannyD @ guru3d)
1600252000435.png
 
Last edited:

Karnak

Senior member
Jan 5, 2017
399
767
136
He did make it obvious that AMD have basically taken an Nvidia 2xxx founders edition cooler, stuck Radeon over the Nvidia logo and given it the "gamer" look (i.e. all those stealth fighter angles and etched lines also found in "gamer" laptops and monitors).
He didn't care about Turing's FE in that regard so...

d974-01-0.jpg
 

kurosaki

Senior member
Feb 7, 2019
258
250
86
at absorbed by air molecules per unit of time scales linearly with temperature delta between air and heatsink surface. You do not remove the same amount of heat by running air slower through a heatsink just because air has time to get hotter.



Running air slower through a heatsink is subject to massive diminishing returns, that is unless the heatsink is doing a very poor job at transferring heat.

*The "front" fan is acting almost in the same way a fan for a rad or CPU tower would do. Pushing air through 1-3 cm fins at a rather high pace with quite little obstruction besides the fins. The "Back fan" is acting as a regular GPU-fan that has to push the air out at an angle that in itself causes a pressure loss. The air is as you said, going to be warmer, does that mean diminishing returns? Of course not. You put it out yourself. The dissipation of heat is a linear function of the delta. as long as the delta is kept reasonably high, the cooling function is going to be good, does that mean it's going to be as effective as the one pushing air straight through the fins? No. But we cant have a PCB-less card now, can we?

Again, Nvidia wouldn't have put a fan on the back for diminishing returns *

🤦‍♂️ I'll just have to buy a 30xx to prove a point now, dont I?
 
Last edited:

GodisanAtheist

Diamond Member
Nov 16, 2006
7,166
7,666
136
He didn't care about Turing's FE in that regard so...

d974-01-0.jpg

- I had the old XFX 7950 Ghost that followed this design and it was by far the nicest looking card I've ever owned.

A shame companies like XFX and Evga have moved away from the clean understated look to the cluttered gamer jank look.

As far as RDNA2, I don't mind the shroud design, although it does look a bit like a poor man's founder's edition. Some renders if the 2 fan cooler (which was the original teaser shot of the shroud way back when) and it looks perfectly serviceable as well.
 

blckgrffn

Diamond Member
May 1, 2003
9,298
3,440
136
www.teamjuchems.com
- I had the old XFX 7950 Ghost that followed this design and it was by far the nicest looking card I've ever owned.

A shame companies like XFX and Evga have moved away from the clean understated look to the cluttered gamer jank look.

As far as RDNA2, I don't mind the shroud design, although it does look a bit like a poor man's founder's edition. Some renders if the 2 fan cooler (which was the original teaser shot of the shroud way back when) and it looks perfectly serviceable as well.

Honestly, I really like the clean look of my "stock" blower 5700xt with the slight bend to the shroud and the backlit RADEON text. It looks great in my case. I have all the text on my mobo set to match in Radeon Red and got my ARGB fans set to "please the 12 year old version of myself" mode because pandemic.