Sunday, September 29th 2019

AMD "Navi 14" and "Navi 12" GPUs Detailed Some More

The third known implementation of AMD's "Navi" generation of GPUs with RDNA architecture is codenamed "Navi 14." This 7 nm chip is expected to be a cut-down, mainstream chip designed to compete with a spectrum of NVIDIA GeForce GTX 16-series SKUs, according to a 3DCenter.org report. The same report sheds more light on the larger "Navi 12" GPU that could power faster SKUs competing with the likes of the GeForce RTX 2080 and RTX 2080 Super. The two follow the July launch of the architecture debut with "Navi 10." There doesn't appear to be any guiding logic behind the numerical portion of the GPU codename. When launched, the pecking order of the three Navi GPUs will be "Navi 12," followed by "Navi 10," and "Navi 14."

"Navi 14" is expected to be the smallest of the three, with an estimated 170 mm² die-area, about 24 RDNA compute units (1,536 stream processors), and expected to feature a 128-bit wide GDDR6 memory interface. It will be interesting to see how AMD carves out an SKU that can compete with the GTX 1660 Ti, which has 6 GB of 192-bit GDDR6 memory. The company would have to wait for 16 Gbit (2 GB) GDDR6 memory chips, or piggy-back eight 8 Gbit chips to achieve 8 GB, or risk falling short of recommended system requirements of several games at 1080p, if it packs just 4 GB of memory.
The 350-400 mm² "Navi 12" is a whole different beast, with an estimated 64 compute units (4,096 stream processors). The big news in the 3DCenter.org report concerns its memory interface. AMD will stick to 256-bit GDDR6 memory with the "Navi 12," and probably dial up memory clocks compared to the 14 Gbps speed the "Navi 10" uses. This design choice is influenced by NVIDIA's decision to stick to 256-bit bus width with its "TU104" silicon. AMD appears to have had enough of expensive memory solutions such as HBM2, at least in this market segment. Source: 3DCenter.org
Add your own comment

38 Comments on AMD "Navi 14" and "Navi 12" GPUs Detailed Some More

#1
lynx29
wish Navi 12 had a timeline of release... I am waiting on it... and hopinh AMD gets the drivers more sorted in the mean time
Posted on Reply
#2
Divide Overflow
The performance GPU segment is in dire need of some competition.
Posted on Reply
#3
Kanan
Big Navi will be certainly memory bandwidth starved should they go this way, that's why they won't. These rumours are probably in some parts wrong. 384 bit makes much more sense, as even the current Navi GPUs are memory bandwidth starved. 512 Gb/s won't cut it either. Nvidia isn't comparable to this, as Big Navi strives to compete with the 2080 Ti or even be faster, which again, has a 384 bit bus. The 2080 non Ti got away with only 256 Bit bus because it leveraged the increased speed of GDDR6 compared to G5X and 384 bit, which the similarly fast 1080 Ti had back then. Big Navi will be much faster and this needs much more memory bandwidth than both GPUs, more in line with what the 2080 Ti has.
Posted on Reply
#4
ZoneDymo
kinda sad to see HBM not becoming the norm.
I would think that today the HBM memory used in the Fury X cards would be cheap(er) so they could slap that on everything but guess not.
Posted on Reply
#5
FordGT90Concept
"I go fast!1!11!1!"
Arcturus will probably have HBM. Navi is designed for gaming and gaming alone. Gaming doesn't benefit much from HBM.

HBM1...maximum density was 1 GiB per chip. 4 GiB ain't enough for anything these days (like 1280x720 res is all and not even in all newer games).
Posted on Reply
#6
Khonjel
ZoneDymo
kinda sad to see HBM not becoming the norm.
I would think that today the HBM memory used in the Fury X cards would be cheap(er) so they could slap that on everything but guess not.
Is it easier to cool GPU-HBM stack? I thought it would be but many GPU brands struggled with their coolers iirc.

One advantage I can see is that brands like XFX and MSI won't be able to cheapen out on VRAM cooling.

Kanan
Big Navi will be certainly memory bandwidth starved should they go this way, that's why they won't. These rumours are probably in some parts wrong. 384 bit makes much more sense, as even the current Navi GPUs are memory bandwidth starved. 512 Gb/s won't cut it either. Nvidia isn't comparable to this, as Big Navi strives to compete with the 2080 Ti or even be faster, which again, has a 384 bit bus.
Has anyone confirmed this? That VRAM OC actually increases decent performance?
I know GPU oc does very little anymore but does vram oc quantifiably increase performance to say with confidence that current cards are bandwidth starved.
And iirc Nvidia (and later AMD I think) now does some kind of memory compression so not be bandwidth starved.
Posted on Reply
#7
Manoa
another tard card, from 250 to 350mm waw I am falling from my chair and they whant 700$ for it...yhe right whay not 7000$
Posted on Reply
#8
PrEzi
It seems no-one is watching Moore's Law is Dead ? Pity.
Recommended for ya all:
Posted on Reply
#9
springs113
Not to off putting but Im curious about all the 7nm and navi issues. I have yet to experience any issue with my x570/3700x/5700xt combo. No driver issues, core boosting issues of the sort. While I may be the minority, I feel that a lot of issues are blown out of proportion and to some extent people lying. Amds drivers have been solid for me for quite sometime now. Ive been fortunate with nvidia as well. All in all im just looking for healthy competition on all fronts.
Posted on Reply
#10
AlB80
Samsung high density GDDR6 chips are in mass production. 16GB via 256 bit is real.
Posted on Reply
#11
nguyen
the only people stupid enough to believe in AMD rumor are the fanatics, remember "Poor Volta" PR ? AMD will at most release a 300W GPU that is competitive with 2080 Super, any higher wattage GPU are guaranteed PR nightmare.
Posted on Reply
#12
kings
It's not AMD's fault that some people can't contain themselves and just talk nonsense to get views!

We should filter things better and not believe everything youtubers say or appear on the internet.

I thought people had learned after the Zen 2 rumors fiasco, but apparently not!
Posted on Reply
#13
Darmok N Jalad
ZoneDymo
kinda sad to see HBM not becoming the norm.
I would think that today the HBM memory used in the Fury X cards would be cheap(er) so they could slap that on everything but guess not.
Maybe it’s just not economical right now. I think AMD started with the 5700 series just to replace the expensive Vega 56 and 64. The 5700 series is likely much cheaper to produce, improving mid-range margins. They also couldn’t go lower until Polaris supplies start drying up.
Posted on Reply
#14
TheinsanegamerN
springs113
Not to off putting but Im curious about all the 7nm and navi issues. I have yet to experience any issue with my x570/3700x/5700xt combo. No driver issues, core boosting issues of the sort. While I may be the minority, I feel that a lot of issues are blown out of proportion and to some extent people lying. Amds drivers have been solid for me for quite sometime now. Ive been fortunate with nvidia as well. All in all im just looking for healthy competition on all fronts.
If all you want is "healthy competitioon" then why are you trying to excuse AMD's poor drivers for Navi's launch on "it must be trolls/liars/overblown" and push your annecdotal experience as fact? That kind of blind fanboyism will only hold healthy cometition back, not push it forward.

Many reviewers and users have had problems with Navi's drivers since launch. Many people still dont have working freesync, or blackscreen crash issues. This is reminiscint of AMD's driver problems back in the late 2000s, you know, the ones that persisted over the course of months? Those driver ssues are why fermi sold so well despite being hot garbage, AMD was just too unstable/unpredictable.

AMD was getting a lot better, but that largely is due ot them pushing the same architecture for 7 years straight. They had plenty of time to iron the bugs out, now they are back to finding bugs and taking months to fix them. These drivers would undermine the launch of a hypothetical 5800/5900XT card. AMD should absolutely be held accountable for these problems, lest t hey think letting the community hang out to dry is acceptable (again).
Posted on Reply
#15
iO
Thats some vague speculation when Vega10 has the same "num_sdp_interfaces" value of 16, which then could point to a 2048 bit wide HBM2(e) interface. Also more plausible then suffocating a big GPU with just 256bit...
Posted on Reply
#16
moproblems99
TheinsanegamerN
If all you want is "healthy competitioon" then why are you trying to excuse AMD's poor drivers for Navi's launch on "it must be trolls/liars/overblown" and push your annecdotal experience as fact? That kind of blind fanboyism will only hold healthy cometition back, not push it forward.

Many reviewers and users have had problems with Navi's drivers since launch. Many people still dont have working freesync, or blackscreen crash issues. This is reminiscint of AMD's driver problems back in the late 2000s, you know, the ones that persisted over the course of months? Those driver ssues are why fermi sold so well despite being hot garbage, AMD was just too unstable/unpredictable.

AMD was getting a lot better, but that largely is due ot them pushing the same architecture for 7 years straight. They had plenty of time to iron the bugs out, now they are back to finding bugs and taking months to fix them. These drivers would undermine the launch of a hypothetical 5800/5900XT card. AMD should absolutely be held accountable for these problems, lest t hey think letting the community hang out to dry is acceptable (again).
I think you need to take a deep breath. There are plenty of people that have no problems and plenty of people that have varying levels of problems. Just like everything else. I had a crappy experience with my 980. Others did not.

Similarly, many people had problems with the 2080ti, was that blown out of proportion... likely. Welcome to the internet.
Posted on Reply
#17
medi01
btarunr
This design choice is influenced by NVIDIA's decision to stick to 256-bit bus width
What?
Posted on Reply
#18
efikkan
lynx29
wish Navi 12 had a timeline of release... I am waiting on it... and hopinh AMD gets the drivers more sorted in the mean time
The drivers should be ready, they are the same as other Navi based products, and are only slightly different from Vega drivers. The one positive side effect of their slow innovation is driver support, as GCN variants have very few driver differences between them.
The problems AMD tend to have have nothing to do with Navi itself.

Kanan
Big Navi will be certainly memory bandwidth starved should they go this way, that's why they won't. These rumours are probably in some parts wrong. 384 bit makes much more sense, as even the current Navi GPUs are memory bandwidth starved. 512 Gb/s won't cut it either.
These "rumors" are just speculation. Some may end up being true, some may not, but this is just random speculation from various forums etc. recycled as "news".
As you point out, there isn't a whole lot faster 256-bit memory available, more bandwidth will be required to compete in the high end.
And then there is heat. A bigger Navi will quickly consume in the ~300W range.

PrEzi
It seems no-one is watching Moore's Law is Dead ? Pity.
Wonderful, the guy who claims that AMD is supposedly "renaming" chip codenames to make "leaks" fit and AMD is potentially "holding big navi back".
No one should be watching that trash.
Posted on Reply
#19
Chrispy_
If you read the source article, you'll realise that this is 99.9% speculation.

Datamining a linux driver shows that Navi 12 has the same number of memory interfaces as the 5700-series. That is literally all they have. Everything else is pure speculation and guesswork, they even say that they're guessing when listing sources of the information.

Navi 14 is definitely a cheaper, smaller product aimed at the lower end of the market.
Navi 12 could be any number of things:
  • A revision of Navi 10 that makes improvements to clockspeeds, bugfixes, or adds additional compute functions for workstations and servers
  • A revision of Navi 10 that includes extra hardware for the PS5 and XBox Scarlet (raytracing or DRM? Who knows!)
  • A larger GPU than Navi 10 with more shaders but no extra VRAM interfaces.
That last option is what everyone wants it to be, but if the datamining concludes that it's still limited to 8GB of GDDR6 on a 256-bit bus, it's unlikely to be in the next performance class up and even if it does have, say, 3584 shaders - it's going to be hamstrung by memory bandwidth.

It's good to be optimistic, but in this case there is very little information to go on, and that little information indicates that it's not actually a larger GPU than Navi 10.

springs113
Not to off putting but Im curious about all the 7nm and navi issues. I have yet to experience any issue with my x570/3700x/5700xt combo. No driver issues, core boosting issues of the sort. While I may be the minority, I feel that a lot of issues are blown out of proportion and to some extent people lying. Amds drivers have been solid for me for quite sometime now. Ive been fortunate with nvidia as well. All in all im just looking for healthy competition on all fronts.
I was late to the Navi game, still doing boring compatibility and performance testing on (now returned to Nvidia) Titan RTX and Quadro RTX cards.
As such, the first Navi driver I experienced was 19.9.1 which seemed fine, and 19.9.2 came out a couple of days later and has been flawless in a whole bunch of compute/encode/gaming on W10 1903.
Tiny sample size, but it seems better than Vega's early drivers to me at least.
Posted on Reply
#20
medi01
Manoa
from 250 to 350mm waw
At the moment 250mm card is:

14% behind 2080 (545 mm² )
21% behind 2080s (>545 mm²)
39% behind 2080Ti (754 mm²)



350mm2 would mean 40% bigger die area, 400mm would mean +60%.
Scaling wouldn't be perfect, but it should comfortably land AMD in "well beyond 2080/2080s" performance area, and in "not intentionally crippled by green" games possibly spanking 2080Ti.


Chrispy_
A revision of Navi 10 that includes extra hardware for the PS5 and XBox Scarlet (raytracing or DRM? Who knows!)
Why would that thing need a Linux driver?
Posted on Reply
#21
f22a4bandit
springs113
Not to off putting but Im curious about all the 7nm and navi issues. I have yet to experience any issue with my x570/3700x/5700xt combo. No driver issues, core boosting issues of the sort. While I may be the minority, I feel that a lot of issues are blown out of proportion and to some extent people lying. Amds drivers have been solid for me for quite sometime now. Ive been fortunate with nvidia as well. All in all im just looking for healthy competition on all fronts.
You're lucky to have not experienced any issues. My friend experienced crashes and blue screens with his 5700 XT and needed to roll drivers back to 19.7.2 to get it stable. I myself haven't had anything but bad luck with my 5700 XT - crashing any game to desktop that's more demanding than Rimworld. And yes, I've updated BIOS to latest, done DDU uninstalls, turned off hardware acceleration and nearly every other fix in the book to no avail.
Posted on Reply
#22
lexluthermiester
lynx29
wish Navi 12 had a timeline of release... I am waiting on it... and hopinh AMD gets the drivers more sorted in the mean time
Alot of people are. The RX5600's are particularly interesting at the price range implied.

The 5800's look good and will be interesting to benchmark.
Posted on Reply
#23
Chrispy_
medi01
Why would that thing need a Linux driver?
Devkits, maybe? Linux drivers take the kitchen-sink approach when it comes to support because the potential ecosystem has infinite permutations.
The short answer is "I don't know" much like everyone outside of AMD at this point. 99.9% speculation with no hard evidence to support a larger chip other than the echo chamber of hopes ;)
Posted on Reply
#24
Manoa
doesn't mater, even if it the true it still a tard card :x
Posted on Reply
#25
Xaled
springs113
Not to off putting but Im curious about all the 7nm and navi issues. I have yet to experience any issue with my x570/3700x/5700xt combo. No driver issues, core boosting issues of the sort. While I may be the minority, I feel that a lot of issues are blown out of proportion and to some extent people lying. Amds drivers have been solid for me for quite sometime now. Ive been fortunate with nvidia as well. All in all im just looking for healthy competition on all fronts.
Just don't listen to lynex29. I really doubt that he owns an AMD product. He is probably just one of those nvidia/intel guys that hijack almost every news post about AMD.
Posted on Reply
Add your own comment