We have 14nm Vega until the mid-2019 arrival of Navi on 7nm - How about a "Gigahertz Edition" redo?

So it has been kinda quiet on the Navi front until I saw this https://fudzilla.com/news/graphics/46526-big-navi-20-is-2020-or-later

So okay I'm guessing no big deal but what got me was the description of Navi:
Navi 10 is the Radeon RX 580 replacement that will pack much better performance at the same price range. This GPU won’t do that badly, but Nvidia always had the performance/mainstream covered with the GTX 960 or most recently GTX 1060 parts. Most likely, the Turing Geforce will also come with a mainstream performance part but just not at first.

So honestly what is up with that, first it was at GTX 1080 performance now it is just a replacement for the RX 580?
There are some questions surrounding what Fudzilla wrote I mean they do get things wrong but what is it with the change of direction from AMD?
Trying a chip that is half the size to cope with certain dynamics makes sense but the other part where you need to get work done on Navi (the intended version) still would mean it is not Navi 10 times 2 or does that not make sense?

And it seems were not the only ones that spotted this:
Bear in mind that the AMD CEO chose her words carefully and did not confirm that there will be a 7nm Vega gaming part, just that we will eventually see a gaming GPU on 7nm.
 
So it has been kinda quiet on the Navi front until I saw this https://fudzilla.com/news/graphics/46526-big-navi-20-is-2020-or-later

So okay I'm guessing no big deal but what got me was the description of Navi:


So honestly what is up with that, first it was at GTX 1080 performance now it is just a replacement for the RX 580?
There are some questions surrounding what Fudzilla wrote I mean they do get things wrong but what is it with the change of direction from AMD?
Trying a chip that is half the size to cope with certain dynamics makes sense but the other part where you need to get work done on Navi (the intended version) still would mean it is not Navi 10 times 2 or does that not make sense?

And it seems were not the only ones that spotted this:

I will sum it up for you, the press doesn't have a clue what AMD is going to do or how the next GPU will perform. Lisa runs a pretty tight ship so the leaks they used to get likely dried up and no one has solid info just rumors they are posting as fact. So anything about Navi I would take with a massive grain of salt, plus Vega at 7nm is likely your next gaming gpu anyway.
 
I will sum it up for you, the press doesn't have a clue what AMD is going to do or how the next GPU will perform. Lisa runs a pretty tight ship so the leaks they used to get likely dried up and no one has solid info just rumors they are posting as fact. So anything about Navi I would take with a massive grain of salt, plus Vega at 7nm is likely your next gaming gpu anyway.

There is no information about anything regarding gaming products from AMD.
This video is timestamped https://hardforum.com/threads/we-ha...z-edition-redo.1952587/page-5#post-1043667384

Nothing concrete no date no gpu designated.
 
Exclusive: The AMD Inside Story, Navi GPU Roadmap And The Cost Of Zen To Gamers

In 2016, AMD unveiled its first roadmap that officially contained the Navi GPU. It was scheduled to come soon after 7nm Vega and was supposed to be the next-generation GPU and land sometime in 2018. AMD held its Computex 2018 recently, to great success, but the one thing that bugged me was the lack of any new graphics cards for gamers.


Navi was also implicitly pushed back, a year at the very least, and the roadmap changed to something more tentative. While in Taiwan for Computex 2018, I had the opportunity to talk to sources intimately familiar with the entire situation and discovered there was a very interesting story to be told – one which made everything fit in place perfectly.

AMD-GPU-Roadmap-Polaris-Vega-Navi-1030x579.jpg

Navi was originally scheduled for release in 2018.

The first thing I will point out before I go onto the juicy details is that it is essential to understand AMD’s contextual backdrop – both in terms of talent and finances. The company has a market capitalization $15.25 billion and has struggled to turn a profit. In comparison, competitors like NVIDIA and Intel are giants with market capitalizations of $158.2 billion and $254.1 billion respectively and net income in the billions of dollars as well. The same goes for talent as well, it costs money and AMD has a relatively smaller pool of (very) talented engineers that can work on a given project at one time as compared to its much bigger rivals.

Lisa’s dilemma: A CPU comeback with semi-custom centric roadmaps or maintain expensive leadership in graphics for gamers

Pundits that have been following AMD’s progress will almost unanimously agree on one thing – AMD is a company that is cash-starved. With a finite flow of resources, the company has to be very careful of how it allocates the precious pool of R&D and how it does so – usually dictates its performance for the next couple of years.

This is also where our story begins. Kyle Bennet of HardOCP first reported a rift between the now-Radeon Technologies Group department and the company’s CEO Lisa Su quite some time ago. The issue was simple, Raja Koduri (the RTG boss) wanted more autonomy and there were rumors that they wanted to spin off the graphics department completely. Well, we now have the full story in-hand and the issue went much deeper.

It turns out that Lisa Su was focused primarily on bringing back AMD’s CPU side of things, and establishing a strong semi-custom GPU side. Maintaining leadership in the descrete graphics market (gamers) is a costly business and with the finite amount of resources the company had, something had to give.

Lisa packaged the graphics department neatly into Radeon Technologies Group and gave control of that to Raja Koduri, but at the same time devoted 2/3rds of the talent on-hand for RTG to develop the next semi-custom solution – which was Navi for Sony. The P&L of RTG was also not handed over to the group head and that meant they were effectively left with 1/3rd of the engineering talent devoted to making a graphics card for gamers and almost no control over their own finances.

The result of this choice was that AMD was spectacularly succesfull at its x86 comeback and also locked in Apple and another client on the semi custom side – the cost, however, was something that gamers paid. Luckily for AMD, this is around the same time that the cryptocurrency market started booming and it came into a windfall as Vega turned out to be great mining GPU and started to sell like hot cakes.

AMD built Vega for Apple and it is building Navi for the Sony PS5 – which is expected to launch in 2020

The reason why Lisa did that was simple: semi-custom applications is a lucrative business. The margins are low, but the volume is high and the net income is consistent. Catering to gamers was not part of the win-condition; making AMD a viable, financially robust company was. Here is a fun fact: Vega was designed primarily for Apple and Navi is being designed for Sony – the PS5 to be precise.

This meant that the graphics department had to be tied directly to the roadmap that these semi-custom applications followed. Since Sony needed the Navi GPU to be ready by the time the PS5 would launch (expectedly around 2020) that is the deadline they needed to work on. Similarly, for Vega, Apple’s timeline is what actually dictated the release of the GPU and not the other way around. AMD’s Radeon graphics cards were intricately tied to the industry’s semi-custom roadmaps by design and that is something that a lot of people disagreed with. This is also what, I suspect, precipitated the departure of key executives including the RTG boss, Raja Koduri.

She also had a different kind of vision for the graphics department – the professional side of things as a star player. The gaming market has lower margins and a higher cost of leadership. Not only do you need to have performance leaps after every year or so, you need to achieve economies of scale to bring them down to a lower enough cost for gamers to be able to afford them – and that can only happen if your yields are completely in-line. 7nm is the bleeding edge of process technology, it is roughly equivalent to Intel’s 10nm process and it goes without saying that yields are less than ideal on this node.

The world’s first 7nm GPU demo that AMD showcased at Computex last week was always meant for the professional GPU market and not for gamers. This is the market that can afford a much higher cost for the same SKU and allows the company to make do with low yields. But Lisa Su also said that “7nm GPUs are coming to gamers” so we should see 7nm Vega sometime next year right? As it turns out, that isn’t what she meant.

AMD-2018-Navi-and-nextgen-roadmap-1480x398.jpg


Roadmap: AMD’s Navi 10 will arrive in late 2019 and will be the first non-GCN GPU, no Vega 7nm for gamers

Probably one of the biggest revelations in my chats was that Vega will not be arriving for gamers – ever. As I mentioned earlier, AMD is building Navi for Sony and it is their deadlines that matter to Lisa right now, nothing else. This is also why the company changed its “official roadmap” to a very tentative structure – a far cry from the concrete and quantitative ones it used to use before. Also keep in mind that all roadmaps are for Radeon and since the Instinct lineup is part of the Radeon brand, you cannot differentiate the gaming side from the professional side anymore.

Here is the crux of what I learned:

  • Vega 7nm will not be coming to gamers.
  • Navi 10 will be the first Navi part to arrive and will be landing sometime in 2H 2019 or early 2020, depending on a couple of factors. The performance level of this part will be equivalent to Vega and it will be a small GPU based on 7nm.
  • Navi 14 will follow Navi 10 soon after.
  • Navi 20 is going to be the true high-end GPU built on the 7nm node and as things stand right now, you are tentatively looking at it landing sometime around 2021.
  • Navi will also be the first architecture to transition away from GCN (and along with it, the 4096 SP / 64 CU limit that is inherent to the uArch implementation.)
  • ‘Next-Gen’ architecture is the uArch formerly codenamed KUMA internally before AMD decided it didn’t like that name too much (oops) and will be based on the same brand new major architecture that AMD rolls out with Navi.
Remember when Lisa said that ‘7nm GPUs will be arriving for gamers’? Well, notice she never said 7nm Vega will be arriving for gamers – the GPU in question was Navi. Navi 10 to be more specific, and from what I know, this will not be a high-end part. It looks like NVIDIA won’t be facing any competition on the gaming side of things from Radeon even in 2019.

Navi 14 will be the immediate successor to Navi 10 and not much was revealed about this part except that it will come after 10.

Navi 20 is the GPU that you are waiting for and will be a true high-end gaming GPU manufactured on the 7nm process by AMD. The downside? it won’t be coming anytime soon. In fact, our source stated it could take as long as 2021 before it sees the light of day.

by WCCFtech
 
Exclusive: The AMD Inside Story, Navi GPU Roadmap And The Cost Of Zen To Gamers

In 2016, AMD unveiled its first roadmap that officially contained the Navi GPU. It was scheduled to come soon after 7nm Vega and was supposed to be the next-generation GPU and land sometime in 2018. AMD held its Computex 2018 recently, to great success, but the one thing that bugged me was the lack of any new graphics cards for gamers.


Navi was also implicitly pushed back, a year at the very least, and the roadmap changed to something more tentative. While in Taiwan for Computex 2018, I had the opportunity to talk to sources intimately familiar with the entire situation and discovered there was a very interesting story to be told – one which made everything fit in place perfectly.

View attachment 80813

Navi was originally scheduled for release in 2018.

The first thing I will point out before I go onto the juicy details is that it is essential to understand AMD’s contextual backdrop – both in terms of talent and finances. The company has a market capitalization $15.25 billion and has struggled to turn a profit. In comparison, competitors like NVIDIA and Intel are giants with market capitalizations of $158.2 billion and $254.1 billion respectively and net income in the billions of dollars as well. The same goes for talent as well, it costs money and AMD has a relatively smaller pool of (very) talented engineers that can work on a given project at one time as compared to its much bigger rivals.

Lisa’s dilemma: A CPU comeback with semi-custom centric roadmaps or maintain expensive leadership in graphics for gamers

Pundits that have been following AMD’s progress will almost unanimously agree on one thing – AMD is a company that is cash-starved. With a finite flow of resources, the company has to be very careful of how it allocates the precious pool of R&D and how it does so – usually dictates its performance for the next couple of years.

This is also where our story begins. Kyle Bennet of HardOCP first reported a rift between the now-Radeon Technologies Group department and the company’s CEO Lisa Su quite some time ago. The issue was simple, Raja Koduri (the RTG boss) wanted more autonomy and there were rumors that they wanted to spin off the graphics department completely. Well, we now have the full story in-hand and the issue went much deeper.

It turns out that Lisa Su was focused primarily on bringing back AMD’s CPU side of things, and establishing a strong semi-custom GPU side. Maintaining leadership in the descrete graphics market (gamers) is a costly business and with the finite amount of resources the company had, something had to give.

Lisa packaged the graphics department neatly into Radeon Technologies Group and gave control of that to Raja Koduri, but at the same time devoted 2/3rds of the talent on-hand for RTG to develop the next semi-custom solution – which was Navi for Sony. The P&L of RTG was also not handed over to the group head and that meant they were effectively left with 1/3rd of the engineering talent devoted to making a graphics card for gamers and almost no control over their own finances.

The result of this choice was that AMD was spectacularly succesfull at its x86 comeback and also locked in Apple and another client on the semi custom side – the cost, however, was something that gamers paid. Luckily for AMD, this is around the same time that the cryptocurrency market started booming and it came into a windfall as Vega turned out to be great mining GPU and started to sell like hot cakes.

AMD built Vega for Apple and it is building Navi for the Sony PS5 – which is expected to launch in 2020

The reason why Lisa did that was simple: semi-custom applications is a lucrative business. The margins are low, but the volume is high and the net income is consistent. Catering to gamers was not part of the win-condition; making AMD a viable, financially robust company was. Here is a fun fact: Vega was designed primarily for Apple and Navi is being designed for Sony – the PS5 to be precise.

This meant that the graphics department had to be tied directly to the roadmap that these semi-custom applications followed. Since Sony needed the Navi GPU to be ready by the time the PS5 would launch (expectedly around 2020) that is the deadline they needed to work on. Similarly, for Vega, Apple’s timeline is what actually dictated the release of the GPU and not the other way around. AMD’s Radeon graphics cards were intricately tied to the industry’s semi-custom roadmaps by design and that is something that a lot of people disagreed with. This is also what, I suspect, precipitated the departure of key executives including the RTG boss, Raja Koduri.

She also had a different kind of vision for the graphics department – the professional side of things as a star player. The gaming market has lower margins and a higher cost of leadership. Not only do you need to have performance leaps after every year or so, you need to achieve economies of scale to bring them down to a lower enough cost for gamers to be able to afford them – and that can only happen if your yields are completely in-line. 7nm is the bleeding edge of process technology, it is roughly equivalent to Intel’s 10nm process and it goes without saying that yields are less than ideal on this node.

The world’s first 7nm GPU demo that AMD showcased at Computex last week was always meant for the professional GPU market and not for gamers. This is the market that can afford a much higher cost for the same SKU and allows the company to make do with low yields. But Lisa Su also said that “7nm GPUs are coming to gamers” so we should see 7nm Vega sometime next year right? As it turns out, that isn’t what she meant.

View attachment 80814

Roadmap: AMD’s Navi 10 will arrive in late 2019 and will be the first non-GCN GPU, no Vega 7nm for gamers

Probably one of the biggest revelations in my chats was that Vega will not be arriving for gamers – ever. As I mentioned earlier, AMD is building Navi for Sony and it is their deadlines that matter to Lisa right now, nothing else. This is also why the company changed its “official roadmap” to a very tentative structure – a far cry from the concrete and quantitative ones it used to use before. Also keep in mind that all roadmaps are for Radeon and since the Instinct lineup is part of the Radeon brand, you cannot differentiate the gaming side from the professional side anymore.

Here is the crux of what I learned:




    • Vega 7nm will not be coming to gamers.
    • Navi 10 will be the first Navi part to arrive and will be landing sometime in 2H 2019 or early 2020, depending on a couple of factors. The performance level of this part will be equivalent to Vega and it will be a small GPU based on 7nm.
    • Navi 14 will follow Navi 10 soon after.
    • Navi 20 is going to be the true high-end GPU built on the 7nm node and as things stand right now, you are tentatively looking at it landing sometime around 2021.
    • Navi will also be the first architecture to transition away from GCN (and along with it, the 4096 SP / 64 CU limit that is inherent to the uArch implementation.)
    • ‘Next-Gen’ architecture is the uArch formerly codenamed KUMA internally before AMD decided it didn’t like that name too much (oops) and will be based on the same brand new major architecture that AMD rolls out with Navi.
Remember when Lisa said that ‘7nm GPUs will be arriving for gamers’? Well, notice she never said 7nm Vega will be arriving for gamers – the GPU in question was Navi. Navi 10 to be more specific, and from what I know, this will not be a high-end part. It looks like NVIDIA won’t be facing any competition on the gaming side of things from Radeon even in 2019.

Navi 14 will be the immediate successor to Navi 10 and not much was revealed about this part except that it will come after 10.

Navi 20 is the GPU that you are waiting for and will be a true high-end gaming GPU manufactured on the 7nm process by AMD. The downside? it won’t be coming anytime soon. In fact, our source stated it could take as long as 2021 before it sees the light of day.

by WCCFtech


The amount of salt needed to take this post in would put me into Hypovolemic shock
 
Exclusive: The AMD Inside Story, Navi GPU Roadmap And The Cost Of Zen To Gamers

In 2016, AMD unveiled its first roadmap that officially contained the Navi GPU. It was scheduled to come soon after 7nm Vega and was supposed to be the next-generation GPU and land sometime in 2018. AMD held its Computex 2018 recently, to great success, but the one thing that bugged me was the lack of any new graphics cards for gamers.


Navi was also implicitly pushed back, a year at the very least, and the roadmap changed to something more tentative. While in Taiwan for Computex 2018, I had the opportunity to talk to sources intimately familiar with the entire situation and discovered there was a very interesting story to be told – one which made everything fit in place perfectly.

View attachment 80813

Navi was originally scheduled for release in 2018.

The first thing I will point out before I go onto the juicy details is that it is essential to understand AMD’s contextual backdrop – both in terms of talent and finances. The company has a market capitalization $15.25 billion and has struggled to turn a profit. In comparison, competitors like NVIDIA and Intel are giants with market capitalizations of $158.2 billion and $254.1 billion respectively and net income in the billions of dollars as well. The same goes for talent as well, it costs money and AMD has a relatively smaller pool of (very) talented engineers that can work on a given project at one time as compared to its much bigger rivals.

Lisa’s dilemma: A CPU comeback with semi-custom centric roadmaps or maintain expensive leadership in graphics for gamers

Pundits that have been following AMD’s progress will almost unanimously agree on one thing – AMD is a company that is cash-starved. With a finite flow of resources, the company has to be very careful of how it allocates the precious pool of R&D and how it does so – usually dictates its performance for the next couple of years.

This is also where our story begins. Kyle Bennet of HardOCP first reported a rift between the now-Radeon Technologies Group department and the company’s CEO Lisa Su quite some time ago. The issue was simple, Raja Koduri (the RTG boss) wanted more autonomy and there were rumors that they wanted to spin off the graphics department completely. Well, we now have the full story in-hand and the issue went much deeper.

It turns out that Lisa Su was focused primarily on bringing back AMD’s CPU side of things, and establishing a strong semi-custom GPU side. Maintaining leadership in the descrete graphics market (gamers) is a costly business and with the finite amount of resources the company had, something had to give.

Lisa packaged the graphics department neatly into Radeon Technologies Group and gave control of that to Raja Koduri, but at the same time devoted 2/3rds of the talent on-hand for RTG to develop the next semi-custom solution – which was Navi for Sony. The P&L of RTG was also not handed over to the group head and that meant they were effectively left with 1/3rd of the engineering talent devoted to making a graphics card for gamers and almost no control over their own finances.

The result of this choice was that AMD was spectacularly succesfull at its x86 comeback and also locked in Apple and another client on the semi custom side – the cost, however, was something that gamers paid. Luckily for AMD, this is around the same time that the cryptocurrency market started booming and it came into a windfall as Vega turned out to be great mining GPU and started to sell like hot cakes.

AMD built Vega for Apple and it is building Navi for the Sony PS5 – which is expected to launch in 2020

The reason why Lisa did that was simple: semi-custom applications is a lucrative business. The margins are low, but the volume is high and the net income is consistent. Catering to gamers was not part of the win-condition; making AMD a viable, financially robust company was. Here is a fun fact: Vega was designed primarily for Apple and Navi is being designed for Sony – the PS5 to be precise.

This meant that the graphics department had to be tied directly to the roadmap that these semi-custom applications followed. Since Sony needed the Navi GPU to be ready by the time the PS5 would launch (expectedly around 2020) that is the deadline they needed to work on. Similarly, for Vega, Apple’s timeline is what actually dictated the release of the GPU and not the other way around. AMD’s Radeon graphics cards were intricately tied to the industry’s semi-custom roadmaps by design and that is something that a lot of people disagreed with. This is also what, I suspect, precipitated the departure of key executives including the RTG boss, Raja Koduri.

She also had a different kind of vision for the graphics department – the professional side of things as a star player. The gaming market has lower margins and a higher cost of leadership. Not only do you need to have performance leaps after every year or so, you need to achieve economies of scale to bring them down to a lower enough cost for gamers to be able to afford them – and that can only happen if your yields are completely in-line. 7nm is the bleeding edge of process technology, it is roughly equivalent to Intel’s 10nm process and it goes without saying that yields are less than ideal on this node.

The world’s first 7nm GPU demo that AMD showcased at Computex last week was always meant for the professional GPU market and not for gamers. This is the market that can afford a much higher cost for the same SKU and allows the company to make do with low yields. But Lisa Su also said that “7nm GPUs are coming to gamers” so we should see 7nm Vega sometime next year right? As it turns out, that isn’t what she meant.

View attachment 80814

Roadmap: AMD’s Navi 10 will arrive in late 2019 and will be the first non-GCN GPU, no Vega 7nm for gamers

Probably one of the biggest revelations in my chats was that Vega will not be arriving for gamers – ever. As I mentioned earlier, AMD is building Navi for Sony and it is their deadlines that matter to Lisa right now, nothing else. This is also why the company changed its “official roadmap” to a very tentative structure – a far cry from the concrete and quantitative ones it used to use before. Also keep in mind that all roadmaps are for Radeon and since the Instinct lineup is part of the Radeon brand, you cannot differentiate the gaming side from the professional side anymore.

Here is the crux of what I learned:




    • Vega 7nm will not be coming to gamers.
    • Navi 10 will be the first Navi part to arrive and will be landing sometime in 2H 2019 or early 2020, depending on a couple of factors. The performance level of this part will be equivalent to Vega and it will be a small GPU based on 7nm.
    • Navi 14 will follow Navi 10 soon after.
    • Navi 20 is going to be the true high-end GPU built on the 7nm node and as things stand right now, you are tentatively looking at it landing sometime around 2021.
    • Navi will also be the first architecture to transition away from GCN (and along with it, the 4096 SP / 64 CU limit that is inherent to the uArch implementation.)
    • ‘Next-Gen’ architecture is the uArch formerly codenamed KUMA internally before AMD decided it didn’t like that name too much (oops) and will be based on the same brand new major architecture that AMD rolls out with Navi.
Remember when Lisa said that ‘7nm GPUs will be arriving for gamers’? Well, notice she never said 7nm Vega will be arriving for gamers – the GPU in question was Navi. Navi 10 to be more specific, and from what I know, this will not be a high-end part. It looks like NVIDIA won’t be facing any competition on the gaming side of things from Radeon even in 2019.

Navi 14 will be the immediate successor to Navi 10 and not much was revealed about this part except that it will come after 10.

Navi 20 is the GPU that you are waiting for and will be a true high-end gaming GPU manufactured on the 7nm process by AMD. The downside? it won’t be coming anytime soon. In fact, our source stated it could take as long as 2021 before it sees the light of day.

by WCCFtech


It's WCCFtech, hardly a reliable source and I am telling you AMD is being tight lipped about their gpu plans. Not only that but he is speculating yield problems cause of the Intel 10nm disaster... One just has nothing to do with the other. Looks like shotgun guessing with hopes he got some part of it right.
 
It's the part about having to wait until at least 2021 for a true high performance GPU that got me.
 
It's the part about having to wait until at least 2021 for a true high performance GPU that got me.

Got you how? There is no way AMD will not launch a 1080TI + 10~20% level card before 2021. I simply do not see that ever working. It might not be cheap, and it might not be super power efficient (as again I am saying we will see a die shrunk VEGA 10 with a decent clock speed bump instead of power savings thus giving us a 1080TI level card on Team Red) but there will be one late this year or by Q1 of next year.
 
It's the part about having to wait until at least 2021 for a true high performance GPU that got me.
Told you so :)
It will take time. I'm not to sure about the year but it is clear when you move people around their project and current projects have a time line for completion and starting to make something from scratch is time consuming.

When your current design Navi is made with a different design philosophy then the stuff you need to change if it is critical to what makes it work you can't change components and you can't trash the project either. That is why there are no consumer products announced.
Got you how? There is no way AMD will not launch a 1080TI + 10~20% level card before 2021. I simply do not see that ever working. It might not be cheap, and it might not be super power efficient (as again I am saying we will see a die shrunk VEGA 10 with a decent clock speed bump instead of power savings thus giving us a 1080TI level card on Team Red) but there will be one late this year or by Q1 of next year.
Can't see that happening really because of price and performance Vega did not get the 12nm treatment for a reason ....
 
Last edited:
Told you so :)
It will take time. I'm not to sure about the year but it is clear when you move people around their project and current projects have a time line for completion and starting to make something from scratch is time consuming.

When your current design Navi is made with a different design philosophy then the stuff you need to change if it is critical to what makes it work you can't change components and you can't trash the project either. That is why there is no consumer products announced.
Can't see that happening really because of price and performance Vega did not get the 12nm treatment for a reason ....

Yes you did. Its just a bit of a shame. If mGPU had descent developer support, I'd probably just grab a couple of Vega 64's and be done with it. Now, I'm not sure what to do.
 
Got you how? There is no way AMD will not launch a 1080TI + 10~20% level card before 2021. I simply do not see that ever working. It might not be cheap, and it might not be super power efficient (as again I am saying we will see a die shrunk VEGA 10 with a decent clock speed bump instead of power savings thus giving us a 1080TI level card on Team Red) but there will be one late this year or by Q1 of next year.
They probably could do that with a die shrunk vega, aka Vega 7nm, they're already at ~1080 speed with Vega 14nm, just it needs clocks in the upper 1GHz range.
But they won't because it would be a one trick pony and only a few % of the gaming market would bother (remember Ti is a few % of market max). There is no financial reason for AMD to do this right now while they are just starting to turn things around... and are selling Zen like hotcakes and vega to apple and the mining crowd, plus lots of custom stuff.

Hence long waits for all us gamers.
If anyone has a V64 for sale for $400, Pm me lol.
 
Last edited:
Yes you did. Its just a bit of a shame. If mGPU had descent developer support, I'd probably just grab a couple of Vega 64's and be done with it. Now, I'm not sure what to do.

Multigpu support sucks no matter which company you pick, I would stay away from that. I would expect a refresh in 2019 for the gaming side and I expect it likely to be the 7nm version of Vega despite the drivel WCCFtech put out. Now I could be wrong but it would be super easy to do since it's just a node shrink and if yields are good then I see no reason why AMD would not release it. If anything Lisa Su would like Nvidia to underestimate what they can actually bring to the table. I expect AMD has gone to a pro first launch then improve yield of the process and then launch the gaming side. I dont think the 1180 will be turning heads when it finally launches so I think AMD is taking a wait and see approach since they are selling every gpu they make now easily.
 
They probably could do that with a die shrunk vega, aka Vega 7nm, they're already at ~1080 speed with Vega 14nm, just it needs clocks in the upper 1GHz range.
But they won't because it would be a one trick pony and only a few % of the gaming market would bother (remember Ti is a few % of market max). There is no financial reason for AMD to do this right now while they are just starting to turn things around... and are selling Zen like hotcakes and vega to the mining crowd.

Hence long waits for all.

I'd have to see how many wafer starts AMD has under contract to be sure, but I suppose there is the chance that they predict they will have every die fabbed sold thanks to the gaming/crypto market so they will just ride it out and continue banking the profits.

Vega is a much better Arch then many here give it cresit for. You can underclock and under volt it and have slightly better Fury X performance while sipping a tiny bit of power. That gives you 1080P max performance and decent FreeSync'd 1440p.

If you want max FreeSync performance, then a VEGA 56 flashed with a 65 bios and a GPU block are what you need. With sustained core speeds north of 1700Mhz (which all of my 56s can do) and HBM @ 1100Mhz you have a 1070ti+ level GPU. 64S under water and HBM @ 1025/1050 gets you north of a highly clocked 1080.

I get for 4k (especially with no FS support) a 56/64 is a bit lean for modern games but there are a ton of older games you can smash at 4k.

I just love the fact that every one of my VEGAs has paid for itself a few times over and I continue to bank the profits they make now. I could sell my cards off tomorrow and make another 3500. That's a nice comforting thought ;)
 
  • Like
Reactions: N4CR
like this
My personal opinion, the GCN architecture has had its time, well over its time in fact. If it were me, I'd put Vega to bed, and focus completely on getting the next generation out asap, ahead of schedule. Make it grand, and wow gamer's once again with a competitive product. Trying to focus and put any time and money into Vega is like feeding a zombie, you're just shoving your resources into a dead thing. That is my personal opinion, no offense. Leave it to add-in-board partners to build some robust cards around Vega with some air-cooled and liquid-cooled cards, and leave it at that for 2018.


Pro Duo Vega...

I agree with you - though it's starting to seem like we might be lucky to see a 2019 new AMD gaming card (pro cards yes, gaming, not so much)...
 
I'd have to see how many wafer starts AMD has under contract to be sure, but I suppose there is the chance that they predict they will have every die fabbed sold thanks to the gaming/crypto market so they will just ride it out and continue banking the profits.

Vega is a much better Arch then many here give it cresit for. You can under clock and under volt it and have slightly better Fury X performance while sipping a tiny bit of power. That gives you 1080P max performance and decent FreeSync'd 1440p.

If you want max FreeSync performance, then a VEGA 56 flashed with a 65 bios and a GPU block are what you need. With sustained core speeds north of 1700Mhz (which all of my 56s can do) and HBM @ 1100Mhz you have a 1070ti+ level GPU. 64S under water and HBM @ 1025/1050 gets you north of a highly clocked 1080.

I get for 4k (especially with no FS support) a 56/64 is a bit lean for modern games but there are a ton of older games you can smash at 4k.

I just love the fact that every one of my VEGAs has paid for itself a few times over and I continue to bank the profits they make now. I could sell my cards off tomorrow and make another 3500. That's a nice comforting thought ;)

Agreed, it can also be efficient if need be, it's quite an unusual card. But a few people get bad undervolters so it's still a bit of luck of the draw.

Does the 64 not OC as [H]ard as the 56? Why is the 56 better?
I do want a freesync setup if business goes well and will be keeping my eye out for bargain V64s
 
Agreed, it can also be efficient if need be, it's quite an unusual card. But a few people get bad undervolters so it's still a bit of luck of the draw.

Does the 64 not OC as [H]ard as the 56? Why is the 56 better?
I do want a freesync setup if business goes well and will be keeping my eye out for bargain V64s


The 64s tend to not clock as high since it's the full 64 CU. I've only got one 64, but from what I have read 1025Mhz is a good HBM clock on them, with avg OC being closer to 975/1000Mhz.
 
But they won't because it would be a one trick pony...

Remember that reducing die size will make it cheaper, if they do nothing else to it- just reducing the size of the GPU and thus the interposer would do wonders for their BOM while potentially increasing production due to higher assembly yields (GPU + HBM on interposer).
 
Last edited:
what you fail to realize is now AMD is a blow torch, that takes a reactor to power and has less performance.
And don't foget that it cost just as much as the other crap cards that run cooler, use a lot less power and have high performance.

Yep amd fan boys have another winner

BUT DONT WORRY a good card is just around the corner. Give us 2, 3 years tops
 
what you fail to realize is now AMD is a blow torch, that takes a reactor to power and has less performance.
And don't foget that it cost just as much as the other crap cards that run cooler, use a lot less power and have high performance.

Yep amd fan boys have another winner

BUT DONT WORRY a good card is just around the corner. Give us 2, 3 years tops
If only it was that simple. You do need to understand that AMD has "no money" . So explain it to yourself how much can you do with no money, you look and condemn what AMD does and blame fan boys in reality fan boys have nothing to do with the whole situation.

As long as you want to paint a picture with only the competition in mind then see how well that works when they have no money and you can judge them on their performance until then your indignation about AMD is just based on bias.
 
no my indignation is based on last year when the so called great card came out is just more old shit with a high price tag.

If they bring out something that is worth what they are charging I will buy one that day.

as far as an uninformed statement of no money.

revenue for the fourth quarter of 2017 of $1.48 billion , operating income of $82 million and net income of $61 million

they did even better in 2018 first quarter $1.65B
but their overhead went thru the roof.

No money or no leadership
 
as far as an uninformed statement of no money.

revenue for the fourth quarter of 2017 of $1.48 billion , operating income of $82 million and net income of $61 million

they did even better in 2018 first quarter $1.65B
but their overhead went thru the roof.
Those numbers are meaningless without their competitor's revenue and R&D expenditures for comparison. Just because AMD is finally profitable doesn't erase the years of missed opportunities when they couldn't hire the best talent, couldn't get the best contracts with OEMs, and so on. The way you talk it's almost as if you think AMD was just being lazy or something otherwise they couldn't possibly be behind NVidia.
 
no my indignation is based on last year when the so called great card came out is just more old shit with a high price tag.
If they bring out something that is worth what they are charging I will buy one that day.
as far as an uninformed statement of no money.
revenue for the fourth quarter of 2017 of $1.48 billion , operating income of $82 million and net income of $61 million
they did even better in 2018 first quarter $1.65B
but their overhead went thru the roof.
No money or no leadership
It takes about 3 years to make a GPU.
 
3 years to make a GPU...no it takes 3 years from inception to product.
For over 2 years they talked shit about their great new gpu. then last year they came out with crap.
Even said it wasn't what they wanted.
If it wasn't what you wanted why would it be something anyone else wanted ?????????
thats my point, they know they are all talk and not much action.
so how many 3 years do they need to do anything worth looking at?
 
3 years to make a GPU...no it takes 3 years from inception to product.
For over 2 years they talked shit about their great new gpu. then last year they came out with crap.
Even said it wasn't what they wanted.
If it wasn't what you wanted why would it be something anyone else wanted ?????????
thats my point, they know they are all talk and not much action.
so how many 3 years do they need to do anything worth looking at?

They did not talk shit they overplayed the features that were on Vega in the end that did not amount to much performance but were for developers and that was a rather silly mistake on RTG part in promoting Vega. Don't forget that people whom did those interviews never asked relevant questions hence many thought Vega was really special.....
I still own a R9 290X and that one still been great and at the time it beat Nvidia hands down.

You started posting financial numbers so you can figure out the part where they are making something worthwhile, if you cared to read the whole thread you find answer to that.
 
So we had the debate about how things scale or not but this is funny when someone like wccftech posts this:



I mean he gets it :) not that that is a miracle but how come no one at AMD did?
 
they overplayed the features that were on Vega in the end that did not amount to much performance but were for developers and that was a rather silly mistake on RTG part

Honestly this has been an issue with ATI (and now AMD RTG) from the beginning; they put in features that are either not standardized, or not mainstream such to the point that they require significant developer support- support that they don't have a program to really provide developers assistance with.

So useful or not, such features stay largely ignored by developers and are generally relegated to being PR bullet points, at least for the debut products with such features.
 
Quoting out their operating expenses and earnings need to also take in account how much of that is CPU and the fighting on the dual front. The little money they are finally earning has to work on R&D for both AMD and RTG and going against a huge nvidia and huge intel is not going to help things
 
I found 2 posts from Seronx on Navi , not sure how valid these are but does seem to point towards a different approach to the gpu then what we have seen under GCN.
https://semiaccurate.com/forums/sho...nm-Information&p=302010&viewfull=1#post302010

Most recent speculation for Navi.
- >40% IPC increase
- >50% Frequency increase
- Tiny Super-SIMD unit => Two Core ALU arrays connected to one Side ALU array. 2 ADDs/MULs/MACs + 1 Convert/Mov/Transcendentals
- Tiny CU => 2 Super-SIMD CUs replace 4 Normal SIMD CUs.
- 32 Tiny Super-CUs = 64 Normal-CUs
- 30% area reduction from Normal CU + 7nm area reduction
- >40% frequency boost from 7nm.
~ 128 * 32 * 2 * 1.73 GHz => ~14.2 TFLOPs
~ 256 TMUs for 16 CU Arrays, 1 TATD has 16 TMUs, 2 CUs share 1 TATD => 16 TATDs = 256 TMUs
~ If ROPs follow TMUs, then 4 * 16 => 64 ROPs
~ GDDR6 384-bit -> 672 gigabytes per second to 768 gigabytes w/ 12 GB => Essentially 3x 4 GB HBM2.
Next-gen 7nm+
Will bring the the big guns with BIG SUPER-CU.
Essentially the above but...
~128 * 64 * 2 * <1.7 => <27 TFLOPs
~ Two TATDs per CU array; 4 CUs share two TATDs => 512 TMUs.
~ Two RBEs per CU array => 128 ROPs
~ 2x HBM3 => ~1024 GB/s (I have seen numbers go up as high as 1364 GB/s)

Both edge more than double previous gen. (Polaris -> Navi and Vega -> Next-gen) // Next-gen is most likely a new architecture name rather than it being stars. Not it being an actual new architecture, or its name is a star but isn't named yet.

And he explains it further in this post:
https://semiaccurate.com/forums/sho...nm-Information&p=302021&viewfull=1#post302021
Basis: Super-SIMD 200 is an optimized SIMD for better performance per mm2 and watt. Super-SIMD includes vector execution unit. Each vector execution unit includes two sets of core ALUs and one set of side ALUs, each having N number of ALUs equal to the SIMD width.

Small Super-CU => In small compute unit, two super-SIMDs a[32 ALUs],b[32 ALUs] replace the four single issue SIMDs[4x16 ALUs]. In CU 500, the ALU to texture ratio can be consistent with known compute units. Instruction per cycle (IPC) per wave can be improved and a reduced wave can be required for 32 KB VGPRs. CU 500 can also realize lower cost versions of SQ and LDS.

So small CU:
64 ALUs to one TCP, TATD, small LDS, small Scheduler.

Big Super-CU => A super-SIMD based compute unit 400 with four super-SIMDs(4x32 ALUs), two TATDs, one instruction scheduler, and one LDS. Super-SIMD based compute unit can provide the same ALU to texture ratio found in a typical compute unit while allowing for better L1 performance.

128 ALUs to two TCPs, two TATDs, large LDS, large Scheduler.

Then, there is the mixed CUs;
T-ALUs which are the side ALUs(and connected to one set of core ALUs) can be varied.
128 ALUs are actually = 192 ALUs.
(16 ALUs of Core and 2 ALUs of Full) * 4 => At minimum: 80 ALUs or 64 FMA + 8 FMA + 8 T-ALUs.
Small mixed CU:
64 ALUs are actually => 96 ALUs
(16 Core ALUs + 2 ALUs of Full) * 2 => At minimum: 40 ALUs or 32 FMA + 4 FMA + 4 T-ALUs.

So, it is scalable in design. From SIMDs like Intel's EUs (2xSIMD4+1xT_SIMD4 *2 for smallest CUs) to bigger than current CUs (2x4xSIMD16 + 4xT_SIMD16 *4 for biggest CUs).

It will be interesting for the smaller CUs in FDSOI. It would allow AMD to get Radeon against Adreno, or Qualcomm licenses Radeon over Adreno.
 
Quoting out their operating expenses and earnings need to also take in account how much of that is CPU and the fighting on the dual front. The little money they are finally earning has to work on R&D for both AMD and RTG and going against a huge nvidia and huge intel is not going to help things

Also, having money and being huge does not guarantee that those companies will do well, either.
 
This video has a small segment on what is happening with AMD/RTG and the gpu it explains a little on what is the way AMD sees how to deliver us with their products.

It is timestamped but you can listen to the introduction the whole video is long winded but has some okay viewpoints on what is happening or about to happen.
 
Anandtech says 7nm Vega is coming this year:

AMD’s 7nm Vega GPU has been successfully taped out, and it is currently sampling among AMD’s customers with a commercial launch towards the end of this year.


I wish I could find out more about how it looks vs. the nVidia RTX cards.
 
Anandtech says 7nm Vega is coming this year:




I wish I could find out more about how it looks vs. the nVidia RTX cards.

If they have similar performance and are closer to what the 10 series cards' prices were on release it would be the first amd card I'd consider getting in a while.
 
If AMD changes there mind and makes a gaming version of the 7nm Vega, I would be interested. Otherwise it looks like Navi is still a while off.
 
If AMD changes there mind and makes a gaming version of the 7nm Vega, I would be interested. Otherwise it looks like Navi is still a while off.

The odd thing is now the story going around that the new version of Vega (7nm) is not just a scaled version of Vega 64/56.
The Vega time line is a little surprising if there is a gaming Vega 7nm coming out the same year as the Navi GPU for gaming?
 
Last edited:
I am not sure why so many hate on Vega? Is it as fast as a 1080ti? No. Does it use more power then an Nvidia gpu? Sure with the insane stock voltage. If you tweak a VEGA GPU then its pretty efficient though. I love the fact that my gpu will make me a millionaire if I make the proper guess with the right crypto blowing up. Right now I am banking ETN @ 30+ coins a day and am HODL on everything for a year or so.

AMD did a lot with VEGA, and having to use it as an "All in One" for both major compute and graphics has definitely hurt. AMD could have stripped VEGA down and probably milked another 2-350Mhz of core clock out of it, but they would have been completely giving up the high margin big data market they are trying to break into. I think VEGA is actually a step in the right direction, it just tried to do too much too fast.

AMD *CAN* complete, and I hope the refresh of VEGA will get them through the year and they continue to invest R&D into NAvi's replacement. If they can get HBM supply flowing, they will sell every single VEGA they can make.

they hate Vega because they couldn't get nvidia cards especially the 1080 and the 1080ti for cheap.
 
That whole argument sounds silly because of the R9 290X. Faster and cheaper yet .....

yet?
it was faster, it spanked The 780 and the 780ti I remember seeing watercooled MSI R9-290X annihilating ln2 780ti's, but people still bought nvidia anyway. AMD realised that NVIDIA has mindshare why bother with chasing the high performance crown when those who want it will buy NVIDIA anyway e.g this forum.
 
Back
Top