Samsung mass producing HBM memory in 2016

[AnandThenMan]

So, so far, there isn't a need to educate yourself, and no need for citations now. If they are asked for, Abwx, that generally means they are wanted and needed.

Everyone and his dog knows AMD engineered HBM and holds several patents for the memory. A 0.2 second Google search turned up this.

http://www.google.com/patents/US20140089609
http://www.google.com/patents/US8922243
http://www.google.com/patents/US20140181387
http://www.google.com/patents/WO2014025676A1

 

[tential]

There's a lot of silly speculation here, but lets put our common sense hat on. AMD funded the development of HBM. AMD is still a billion dollar corporation that is probably smarter as a whole with their fleet of lawyers smarter than any poster here. They did the earlier "Heavy lifting" for Hynix. It would be incredibly incompetent of them if there is nothing in the contract of Hynix that give them a competitive advantage.

Because never in history has a multi billion dollar company made a bad move. NEVER!

Edit: [citation still coming]

 

[Abwx]

Everyone and his dog knows AMD engineered HBM and holds several patents for the memory. A 0.2 second Google search turned up this.

http://www.google.com/patents/US20140089609
http://www.google.com/patents/US8922243
http://www.google.com/patents/US20140181387
http://www.google.com/patents/WO2014025676A1

Good find and the dates correlates with Nvidia statements in march 2013 that they ll use stacked RAM in 2014, that was just a preventive move in case AMD/Hynix succeded earlier...

http://www.hardware.fr/news/12988/gtc-gpu-maxwell-puis-volta-dram-stacking.html

Lol at the pic of their HBM card....

 

[Azix]

Because never in history has a multi billion dollar company made a bad move. NEVER!

Edit: [citation still coming]

shouldnt you be hoping AMD gets something from this? I mean we can at least give AMD this little bit? They did make it right? So why can't we just accept they may make some profit or gain benefit from it?

If nvidia ever innovates like this I am sure nobody would deny them all the potential benefits from it. If someone said they were shutting out AMD from using it people would say AMD is doomed etc. If it was said that nvidia would get money from other companies that used it people would say nvidia's going to be swimming in the dough. They'd even be at the nvidia alter daily praising them for producing such VRAM tech.

But since its AMD... despite all they've done for us, they still suck and we can expect the worst...

looking forward to HBM APUs, GPUs, CPUs etc

 

[AnandThenMan]

shouldnt you be hoping AMD gets something from this?

You'd think. I've lost count how many times certain individuals have posted that Nvidia is not a charity and their hard work and money should not be expected to benefit AMD. So the reverse must be true.

 

[tential]

shouldnt you be hoping AMD gets something from this? I mean we can at least give AMD this little bit? They did make it right? So why can't we just accept they may make some profit or gain benefit from it?

If nvidia ever innovates like this I am sure nobody would deny them all the potential benefits from it. If someone said they were shutting out AMD from using it people would say AMD is doomed etc. If it was said that nvidia would get money from other companies that used it people would say nvidia's going to be swimming in the dough. They'd even be at the nvidia alter daily praising them for producing such VRAM tech.

But since its AMD... despite all they've done for us, they still suck and we can expect the worst...

looking forward to HBM APUs, GPUs, CPUs etc

What evidence is there that there is some competitive contract with Hynix. Samsung is going into MASS production of HBM memory in 2016. It doesn't matter if Hynix has HBM, nvidia can get it from Samsung.

I don't hope for anything, I look at the actual situation at hand which is that Hynix isn't the only player in the game. AMD invested heavily in HBM, made it an open standard, and now Nvidia will reap the benefits of AMD's hardwork.

There is no HOPE involved, it's how the situation played out...

Stop hoping for things and simply look at the reality of the situation...

You can't develop something, give it away for free, then get upset about it right afterwards....

 

[AnandThenMan]

You completely dodged the question.

 

[thesmokingman]

This guy doesn't think so.

If you look closely you can see the woodscrews.

 

[thesmokingman]

Good find and the dates correlates with Nvidia statements in march 2013 that they ll use stacked RAM in 2014, that was just a preventive move in case AMD/Hynix succeded earlier...

http://www.hardware.fr/news/12988/gtc-gpu-maxwell-puis-volta-dram-stacking.html

Lol at the pic of their HBM card....

Nvidia partnered with Intel/Micron to develop HMC. Since HBM became the standard, the traction for HMC fell out and now all the players are moving to HBM. He's probably holding a woodscrew sample of their idea of an HMC board. The irony is that Intel is on board with HBM too.

 

[positivedoppler]

[citation needed]

It's all over the internet, but let me google that for you.
http://techreport.com/review/28294/amd-high-bandwidth-memory-explained

Somebody even found AMD's patent.
http://www.overclock.net/t/1556356/various-amd-hbm-presentation-and-slides/60

 

[tential]

You completely dodged the question.

Do you have a card with HBM?
After all that AMD has done for us developing this technology, shouldn't you at least get a card with HBM? Or else, we won't have HBM cards in the future if you don't support AMD right?

 

[Abwx]

Nvidia partnered with Intel/Micron to develop HMC. Since HBM became the standard, the traction for HMC fell out and now all the players are moving to HBM. He's probably holding a woodscrew sample of their idea of an HMC board. The irony is that Intel is on board with HBM too.

That s not HMC since they stated that vias and TSVs would be used, it was added in the comment section by the HFR journalist who added that the pic was irrelevant.

Another one that i did find at SA :

but this is not to be confused with the High Bandwidth Memory that Nvidia, AMD, and Hynix are creating.

http://semiaccurate.com/forums/showpost.php?p=242282&postcount=1128

A big lol if it wasnt a shameless attitude with Nvidia quoted first in a project where they did absolutely nothing, that s litteraly usurpating credits and using shill sites to spread lies...

 

[thesmokingman]

That s not HMC since they stated that vias and TSVs would be used, it was added in the comment section by the HFR journalist who added that the pic was irrelevant.

Another one that i did find at SA :

http://semiaccurate.com/forums/showpost.php?p=242282&postcount=1128

A big lol if it wasnt a shameless attitude with Nvidia quoted first in a project where they did absolutely nothing, that s litteraly usurpating credits and using shill sites to spread lies...

HMC iirc was a venture between Intel/Micron. Intel however is developing a derivative of HMC for their own use. Intel and Micron chose not to wait for JEDEC to weigh in on it and went their own way. That was the process that Nvidia was banking on till HBM got the nod. AMD's venture with Hynix paid off and here we are today. However, Intel is also on board with HBM and as far as I've read and are looking to incorporate HBM as well. There are a few articles comparing HMC to HBM. Both are high bandwidth and high cost, but HBM is still a bit cheaper to produce and less complicated iirc. Anyways I we're saying the same thing in essence.

 

[Keysplayr]

Much simpler manufacturing processes than this are patented, what you fail to understand is that it s the methodology that is patented.

Of course you can dispute this patent in courts, but you ll have to prove that there was functional prior art, and there s no prior art that is functional, otherwise one could patent anything that has a potential to be manufactured without even proving that it can be manufactured, that is, to patent a possibility...

Now, do you think that it s a guess less educated than what you posted..?.

A million percent, yes. Because that is all it is. A guess without really knowing anything at all.

 

[Keysplayr]

Everyone and his dog knows AMD engineered HBM and holds several patents for the memory. A 0.2 second Google search turned up this.

http://www.google.com/patents/US20140089609
http://www.google.com/patents/US8922243
http://www.google.com/patents/US20140181387
http://www.google.com/patents/WO2014025676A1

And all this translates as what, in your mind?

 

[Keysplayr]

What evidence is there that there is some competitive contract with Hynix. Samsung is going into MASS production of HBM memory in 2016. It doesn't matter if Hynix has HBM, nvidia can get it from Samsung.

I don't hope for anything, I look at the actual situation at hand which is that Hynix isn't the only player in the game. AMD invested heavily in HBM, made it an open standard, and now Nvidia will reap the benefits of AMD's hardwork.

There is no HOPE involved, it's how the situation played out...

Stop hoping for things and simply look at the reality of the situation...

You can't develop something, give it away for free, then get upset about it right afterwards....

^bold. This is really the entire "problem" we've come across in here. Because AMD does so poorly, people are hoping that they can get one over on the one that is doing so well, as in Nvidia. Underdog support is all well and good, but there does come a time where the dog has to be put down because it can't stand up anymore and can't eat.

 

[DeathReborn]

Well since you apparently have all the answers, what's it going to be?
Is it going to be Nvidia using HBM for Pascal limited to 4GB?

Or wait to release Pascal at the time HBM2 is available at the end of 2016 according to folks in here?

Or stick with GDDR5?

Well, to the first option I say Har dee har harrrrrr! I don't know of any company that would shoot themselves in the fo......

Second option? I seriously doubt it.

Third, if need be.

Then there is also the option that Pascal will release on schedule with HBM2 properly in place long before the end of 2016.

http://www.fudzilla.com/news/graphics/38555-samsung-to-make-hbm-2-memory-in-2016

http://linustechtips.com/main/topic...sung-is-in-and-beat-hynixs-initial-offerings/

http://wccftech.com/samsung-enters-hbm-market-1h-2016-hpc-gpu-ready-hbm-15-tbs-bandwidth-48-gb-vram/

Not much stopping them releasing a 1060 (or whatever they'll call their next gen) with 4GB HBM1 for $250-350 @980+ performance. It would get pascal out the door and a staggered release is nothing new to Nvidia, market cannibalisation aside...

 

[Keysplayr]

Not much stopping them releasing a 1060 (or whatever they'll call their next gen) with 4GB HBM1 for $250-350 @980+ performance. It would get pascal out the door and a staggered release is nothing new to Nvidia, market cannibalisation aside...

That is true. Nothing wrong with the lower end or mid range with 4GB HBM1. But this depends entirely on how far off HBM2 production REALLY is.

 

[ShintaiDK]

HBM/Interposer cost also decides how low it will go. I doubt we see full lineups anytime soon. I wouldnt be surprised if even with HBM2, it was still for 300$+ cards only.

 

[tential]

^bold. This is really the entire "problem" we've come across in here. Because AMD does so poorly, people are hoping that they can get one over on the one that is doing so well, as in Nvidia. Underdog support is all well and good, but there does come a time where the dog has to be put down because it can't stand up anymore and can't eat.

What really gets me is that all of these people who are praising hbm, saying it's amazing and that we need to buy amd products because of hbm. That we should hope amd has some type of exclusivity with hynix despite it clearly shown that amd will be a small part of hbm production.

None of them have an hbm product but they are specifically talking about how amazing hbm is and how we need to support amd since they were the first to make it.

If hbm is so amazing why don't any if them have it.....

 

[Keysplayr]

What really gets me is that all of these people who are praising hbm, saying it's amazing and that we need to buy amd products because of hbm. That we should hope amd has some type of exclusivity with hynix despite it clearly shown that amd will be a small part of hbm production.

None of them have an hbm product but they are specifically talking about how amazing hbm is and how we need to support amd since they were the first to make it.

If hbm is so amazing why don't any if them have it.....

None of them? I think that is unlikely. You mean in this thread? I dunno.

 

[Ma_Deuce]

What evidence is there that there is some competitive contract with Hynix. Samsung is going into MASS production of HBM memory in 2016. It doesn't matter if Hynix has HBM, nvidia can get it from Samsung.

I would be more surprised to see evidence of business contracts than not. It's not like these companies go out of their way to advertise things like that. It happens, but it's far from the norm IMO.

Depending on the applications and interests from the bigger fish, I could see Nvidia getting squeezed out. AMD too if they don't have some kind of deal.

 

[Abwx]

A million percent, yes. Because that is all it is. A guess without really knowing anything at all.

Because you know something about it..?..

Tell us, we are all ears...

^bold. This is really the entire "problem" we've come across in here. Because AMD does so poorly, people are hoping that they can get one over on the one that is doing so well, as in Nvidia. Underdog support is all well and good, but there does come a time where the dog has to be put down because it can't stand up anymore and can't eat.

So i guess that Nvidia does even more poorly since they are constantly copying what their competitor do first, they may make more money but technologicaly they are not up to AMD...

How happen that the so called underdog is the most innovative.?.

 

[Ma_Deuce]

Why restrict HBM to dGPU only? HBM can be used in every other segment I would imagine. Mobile. Professional. Commercial/Compute. Super computing. Automotive.
Anyway, if we must restrict HBM to dGPU, then what I said refers to Nvidia having massively more potential order volume than AMD. Nearing 80% and climbing? So, the client where the MOST money to be made from HBM sales in the dGPU market between AMD and Nvidia, is Nvidia. Hynix would have been incredibly stupid to paint themselves into a corner by not giving Nvidia at least EQUAL dibs on memory. But wonders never cease.

You mention all of the other markets that HBM could be useful for, but then quote Nvidia of having 80% more potential order volume. Is that 80% you are throwing out just the small discrete gpu market or is it taking into consideration other markets as well?

If Hynix is selling all they can make now and getting contracts in place to ramp up production and sell all the future units they can make, they aren't painting themselves into anything by excluding Nvidia. (If they are, all it is is speculation from both sides that I can tell).

 

[tential]

I would be more surprised to see evidence of business contracts than not. It's not like these companies go out of their way to advertise things like that. It happens, but it's far from the norm IMO.

Depending on the applications and interests from the bigger fish, I could see Nvidia getting squeezed out. AMD too if they don't have some kind of deal.

I do not know about other major players to comment on this, but that would be amusing if neither company could get a volume product out in 2016 due to production being purchased by other companies. Would make us all wrong lol.