Nvidia Announces Pascal-Based Tesla P100 GPU With HBM2

[marvin83]

It does matter if it is a single GPU vs dual because what is to stop nVidia from launching a dual Pascal part with this performance?

TDP, obviously. 300W vs 300W. AMD wins in single precision, loses in double precision.

You really seem to be raging against nVidia and seem to know that HBM 2 wont be available until later. Not sure why. You should hope nVidia keeps challenging AMD because if they don't then AMD will become just like nVidia in pricing, it has happened before and it will happen again.

Why would I hope for the monopoly to win? Have you looked at Quaddro prices!? It isn't even a contest between price/performance ratio of AMD vs Nvidia's professional cards, but Quaddro continues to sell because that is what people bought the last time they bought a card and don't care to compare.

https://news.samsung.com/global/samsung-begins-mass-producing-worlds-fastest-dram-based-on-newest-high-bandwidth-memory-hbm-interface

Mass production =/= mass customer availability

Samsung began mass production of HMB2 in the beginning of this year. Unless you know something we do not, and please if you do post your sources, I don't think nVidia would be paper launching a product a year out nor that they would say businesses would be able to actually buy the product in June.

Guess we can only wait and see.

If Nvidia isn't paper launching, then show me were a business can buy one? How much does it cost? If the intended market cannot purchase the item, it is, by definition, a paper launch. Nvidia said in the presser, Q1 2017 (aka March).

If you need sources, try ANY tech news site...

So you know what the TDP of a dual Pascal GPU would be? You have information that is not out yet?

I didn't say win. I said challenge. Big difference. I wouldn't consider nVidia a monopoly either. AMD has had some meh GPUs up until the Fury line. Or do you think the R9 290x launch was the best ever? It wasn't. Most people with a HD 7970GHz stayed with that because at launch the R9 290X was not worth it, especially not until the aftermarket cooling launched and fixed the horrible throttling issues Hawaii XT had.

Mass Production means mass volume meaning customer availability is not far off. SK Hynix is a bit behind Samsung with 4GB HBM2 chips not in mass production until at least Q3 2016.

As for when, they can't buy it yet but per the other article on Toms data centers will be able to buy the systems with this GPU in June. Most products are "paper launched" to start then they become available.

Either way this is the Tesla part, which is how nVidia always starts their new GPUs in the data center market then they trickle down to workstation and consumer.

Besides no one would pay for a Tesla for gaming. Not worth the cost.

Oh and both are very costly. The FirePro 9100 is, when not on sale, normally $4000. The Quadro equivalent, the K6000, is also around $4000 normally. Of course on both sides it depends on what you do because in some cases AMD is better in others nVidia is better.

It does matter if it is a single GPU vs dual because what is to stop nVidia from launching a dual Pascal part with this performance?

TDP, obviously. 300W vs 300W. AMD wins in single precision, loses in double precision.

You really seem to be raging against nVidia and seem to know that HBM 2 wont be available until later. Not sure why. You should hope nVidia keeps challenging AMD because if they don't then AMD will become just like nVidia in pricing, it has happened before and it will happen again.

Why would I hope for the monopoly to win? Have you looked at Quaddro prices!? It isn't even a contest between price/performance ratio of AMD vs Nvidia's professional cards, but Quaddro continues to sell because that is what people bought the last time they bought a card and don't care to compare.

https://news.samsung.com/global/samsung-begins-mass-producing-worlds-fastest-dram-based-on-newest-high-bandwidth-memory-hbm-interface

Mass production =/= mass customer availability

Samsung began mass production of HMB2 in the beginning of this year. Unless you know something we do not, and please if you do post your sources, I don't think nVidia would be paper launching a product a year out nor that they would say businesses would be able to actually buy the product in June.

Guess we can only wait and see.

If Nvidia isn't paper launching, then show me were a business can buy one? How much does it cost? If the intended market cannot purchase the item, it is, by definition, a paper launch. Nvidia said in the presser, Q1 2017 (aka March).

If you need sources, try ANY tech news site...

So you know what the TDP of a dual Pascal GPU would be? You have information that is not out yet?

I didn't say win. I said challenge. Big difference. I wouldn't consider nVidia a monopoly either. AMD has had some meh GPUs up until the Fury line. Or do you think the R9 290x launch was the best ever? It wasn't. Most people with a HD 7970GHz stayed with that because at launch the R9 290X was not worth it, especially not until the aftermarket cooling launched and fixed the horrible throttling issues Hawaii XT had.

Mass Production means mass volume meaning customer availability is not far off. SK Hynix is a bit behind Samsung with 4GB HBM2 chips not in mass production until at least Q3 2016.

As for when, they can't buy it yet but per the other article on Toms data centers will be able to buy the systems with this GPU in June. Most products are "paper launched" to start then they become available.

Either way this is the Tesla part, which is how nVidia always starts their new GPUs in the data center market then they trickle down to workstation and consumer.

Besides no one would pay for a Tesla for gaming. Not worth the cost.

Oh and both are very costly. The FirePro 9100 is, when not on sale, normally $4000. The Quadro equivalent, the K6000, is also around $4000 normally. Of course on both sides it depends on what you do because in some cases AMD is better in others nVidia is better.

It does matter if it is a single GPU vs dual because what is to stop nVidia from launching a dual Pascal part with this performance?

TDP, obviously. 300W vs 300W. AMD wins in single precision, loses in double precision.

You really seem to be raging against nVidia and seem to know that HBM 2 wont be available until later. Not sure why. You should hope nVidia keeps challenging AMD because if they don't then AMD will become just like nVidia in pricing, it has happened before and it will happen again.

Why would I hope for the monopoly to win? Have you looked at Quaddro prices!? It isn't even a contest between price/performance ratio of AMD vs Nvidia's professional cards, but Quaddro continues to sell because that is what people bought the last time they bought a card and don't care to compare.

https://news.samsung.com/global/samsung-begins-mass-producing-worlds-fastest-dram-based-on-newest-high-bandwidth-memory-hbm-interface

Mass production =/= mass customer availability

Samsung began mass production of HMB2 in the beginning of this year. Unless you know something we do not, and please if you do post your sources, I don't think nVidia would be paper launching a product a year out nor that they would say businesses would be able to actually buy the product in June.

Guess we can only wait and see.

If Nvidia isn't paper launching, then show me were a business can buy one? How much does it cost? If the intended market cannot purchase the item, it is, by definition, a paper launch. Nvidia said in the presser, Q1 2017 (aka March).

If you need sources, try ANY tech news site...

So you know what the TDP of a dual Pascal GPU would be? You have information that is not out yet?

I didn't say win. I said challenge. Big difference. I wouldn't consider nVidia a monopoly either. AMD has had some meh GPUs up until the Fury line. Or do you think the R9 290x launch was the best ever? It wasn't. Most people with a HD 7970GHz stayed with that because at launch the R9 290X was not worth it, especially not until the aftermarket cooling launched and fixed the horrible throttling issues Hawaii XT had.

Mass Production means mass volume meaning customer availability is not far off. SK Hynix is a bit behind Samsung with 4GB HBM2 chips not in mass production until at least Q3 2016.

As for when, they can't buy it yet but per the other article on Toms data centers will be able to buy the systems with this GPU in June. Most products are "paper launched" to start then they become available.

Either way this is the Tesla part, which is how nVidia always starts their new GPUs in the data center market then they trickle down to workstation and consumer.

Besides no one would pay for a Tesla for gaming. Not worth the cost.

Oh and both are very costly. The FirePro 9100 is, when not on sale, normally $4000. The Quadro equivalent, the K6000, is also around $4000 normally. Of course on both sides it depends on what you do because in some cases AMD is better in others nVidia is better.

At the end of the day, this is all win for AMD as they own HDM (co-own with Hynix, really). So, no matter who decides to use HBM (nVidia, Intel, AMD, Samsung), AMD is still making money off that patent.

Go underdog AMD!

 

[TJ Hooker]

At the end of the day, this is all win for AMD as they own HDM (co-own with Hynix, really). So, no matter who decides to use HBM (nVidia, Intel, AMD, Samsung), AMD is still making money off that patent.

Go underdog AMD!

HBM is a JEDEC standard. AMD/Hynix may have some specific design/implementation that they protect via patent, trade secret, or whatever, but I think overall people are free to implement their own HBM without owing anything to AMD/Hynix.

http://wccftech.com/amd-squashes-rumors-hbm-ip-licensing-fees-memory-standard-free/

 

[marvin83]

At the end of the day, this is all win for AMD as they own HDM (co-own with Hynix, really). So, no matter who decides to use HBM (nVidia, Intel, AMD, Samsung), AMD is still making money off that patent.

Go underdog AMD!

HBM is a JEDEC standard. AMD/Hynix may have some specific design/implementation that they protect via patent, trade secret, or whatever, but I think overall people are free to implement their own HBM without owing anything to AMD/Hynix.

http://wccftech.com/amd-squashes-rumors-hbm-ip-licensing-fees-memory-standard-free/

Actually, we're both technically wrong.

AMD is voluntarily taking no royalties for the usage of HBM/HBM2/etc. It's basically akin to their policy on FreeSync (the free GSync free alternative).

However, just because it's a JEDEC standard, doesn't mean they can't take royalties for it. AMD did most of the heavy lifting for the HBM standard.

 

[TJ Hooker]

At the end of the day, this is all win for AMD as they own HDM (co-own with Hynix, really). So, no matter who decides to use HBM (nVidia, Intel, AMD, Samsung), AMD is still making money off that patent.

Go underdog AMD!

HBM is a JEDEC standard. AMD/Hynix may have some specific design/implementation that they protect via patent, trade secret, or whatever, but I think overall people are free to implement their own HBM without owing anything to AMD/Hynix.

http://wccftech.com/amd-squashes-rumors-hbm-ip-licensing-fees-memory-standard-free/

Actually, we're both technically wrong.

AMD is voluntarily taking no royalties for the usage of HBM/HBM2/etc. It's basically akin to their policy on FreeSync (the free GSync free alternative).

However, just because it's a JEDEC standard, doesn't mean they can't take royalties for it. AMD did most of the heavy lifting for the HBM standard.

Quote from that article: "the IP is part of the JEDEC’s JESD235 standard and is allowed to be implemented without compensation (or under reasonable terms). Furthermore, Nvidia and AMD have a very diverse cross-licensing agreement which wouldn’t have allowed royalty demands in the first place."

Like I said before, AMD may own some IP related to their own implementation, i.e. the interposer they used. You're right that they could charge licensing fees for that, which they are choosing not to. However, they cannot charge licensing fees for HBM use in general, and I don't think there would be anything stopping someone from developing their own interposer solution. Although that is obviously unnecessary due to AMDs open stance.

 

[marvin83]

At the end of the day, this is all win for AMD as they own HDM (co-own with Hynix, really). So, no matter who decides to use HBM (nVidia, Intel, AMD, Samsung), AMD is still making money off that patent.

Go underdog AMD!

HBM is a JEDEC standard. AMD/Hynix may have some specific design/implementation that they protect via patent, trade secret, or whatever, but I think overall people are free to implement their own HBM without owing anything to AMD/Hynix.

http://wccftech.com/amd-squashes-rumors-hbm-ip-licensing-fees-memory-standard-free/

Actually, we're both technically wrong.

AMD is voluntarily taking no royalties for the usage of HBM/HBM2/etc. It's basically akin to their policy on FreeSync (the free GSync free alternative).

However, just because it's a JEDEC standard, doesn't mean they can't take royalties for it. AMD did most of the heavy lifting for the HBM standard.

Quote from that article: "the IP is part of the JEDEC’s JESD235 standard and is allowed to be implemented without compensation (or under reasonable terms). Furthermore, Nvidia and AMD have a very diverse cross-licensing agreement which wouldn’t have allowed royalty demands in the first place."

Like I said before, AMD may own some IP related to their own implementation, i.e. the interposer they used. You're right that they could charge licensing fees for that, which they are choosing not to. However, they cannot charge licensing fees for HBM use in general, and I don't think there would be anything stopping someone from developing their own interposer solution. Although that is obviously unnecessary due to AMDs open stance.

Either way, AMD needs $$$ help, so they should've took at least a small cut for this.

However, I can't wait for the ZEN+ CPU's to come out and their first HBM2 card to come out... Patiently waiting.......................................

 

[jimmysmitty]

At the end of the day, this is all win for AMD as they own HDM (co-own with Hynix, really). So, no matter who decides to use HBM (nVidia, Intel, AMD, Samsung), AMD is still making money off that patent.

Go underdog AMD!

HBM is a JEDEC standard. AMD/Hynix may have some specific design/implementation that they protect via patent, trade secret, or whatever, but I think overall people are free to implement their own HBM without owing anything to AMD/Hynix.

http://wccftech.com/amd-squashes-rumors-hbm-ip-licensing-fees-memory-standard-free/

Actually, we're both technically wrong.

AMD is voluntarily taking no royalties for the usage of HBM/HBM2/etc. It's basically akin to their policy on FreeSync (the free GSync free alternative).

However, just because it's a JEDEC standard, doesn't mean they can't take royalties for it. AMD did most of the heavy lifting for the HBM standard.

Not only the JEDEC standardization but HBM is based on Samsungs Wide I/O memory technology.

 

[Coonah]

Hmm... looks like Polaris might take a chunk of the GPU market before nVidia get their act together with HBM2. I reckon early 2017 is pushing it.

 

[Matt_550]

LOL, that's rich. Samsung's HBM2 hit the production phase well before SK Hynix's did. The first Pascal cards with HBM2 should be out around August. AMD will be waiting till Vega, as Polaris will not incorporate HBM2, which will most likely hit the market late Q1 2017. AMD has to make some money off that new dual GPU money waste they came out with.

 

[Coonah]

LOL, that's rich. Samsung's HBM2 hit the production phase well before SK Hynix's did. The first Pascal cards with HBM2 should be out around August. AMD will be waiting till Vega, as Polaris will not incorporate HBM2, which will most likely hit the market late Q1 2017. AMD has to make some money off that new dual GPU money waste they came out with.

We'll see. Nvidia are pushing out Pascal early because AMD's Polaris release has been announce for Q4 this year.

 

[tsnor]

[/quotemsg] ...However, just because it's a JEDEC standard, doesn't mean they can't take royalties for it. AMD did most of the heavy lifting for the HBM standard.[/quote]

Just ask the trolls at Rambus

 

[Coonah]

...However, just because it's a JEDEC standard, doesn't mean they can't take royalties for it. AMD did most of the heavy lifting for the HBM standard.[/quote]

Just ask the trolls at Rambus[/quotemsg]

Yep... Intel have been hammered by AMD in court before, no reason Nvidia would want to go down that road to pinch their memory tech.
Nvidia have been going on about GDDR5x up until recently announcing HBM2. Sounds like a behind the scenes deal has been done to release the tech to JEDEC or under royalty in a deal with Samsung.
I don't think that Pascal or Polaris will see a great advantage at the moment with HBM1 vs HBM2. My tip is the bottleneck will come with the chips rather than the memory. You can see this in the Fury X vs 980ti benchmarks.... Both run at 100% GPU saage but the Fury uses half it's faster RAM @ 4k and the 980ti uses 3/4 it's slower RAM with fairly similar performance across the 2 cards. Neither is maxing out it's memory... Should be a good fight with the next gen GPU's

 

[InvalidError]

Nvidia have been going on about GDDR5x up until recently announcing HBM2. Sounds like a behind the scenes deal has been done to release the tech to JEDEC or under royalty in a deal with Samsung.

HBM2 has been a JEDEC standard since January 12th 2016 and Samsung announced intent to begin production on January 16th. No "behind the scene" deal there, Samsung simply waited until HBM2 officially became a standard before committing to it.