Raevenlordwhich is the world's first HBM2-powered add-in-card.

I might be missing something:

2/6/2017, 3:12 PM
Nvidia Quadro GP100: Big Pascal, HBM2, and NVLink comes to workstations
arstechnica.com/gadgets/2017/02/nvidia-quadro-gp100-price-details/

PowerPCWhich doesn't mean Nvidia doesn't have them. AMD just always chooses to show off what they have before they can actually deliver it in any reasonable form or quantity.

The "always" is clearly not warranted, given Ryzen launch.

oxidizedEventually people will realize how stupid it is to support something or someone, just because they're the underdogs

Will that happen when non Ti card will cost mere 999$ or after that?
I mean, the realization part.

NokironIt will be slower than that, more along the lines of a lower clocked Titan X Pascal. There are no GP100-chips with 3840 CUDA-cores, they are all at 3584.

Well I'm quite sure that nvidia has some gp100 chips with all cores enabled. But yes you are right there's no such a product released with full blown gp100.

ssdproHow did this thread go so far off down the "no, I swear AMD was actually first" path? The whole point is NVIDIA beat AMD to market. It is one thing to have a concept and show a single sample, it is another to turn it into a functioning product for sale.

For the record, AMD stock is still down 7.5% in the last week alone. Better hope those April sales numbers aren't as bad as March.

I'm quite skeptic about that it's really hbm2 what is keeping Vega back. Or is there some kind of agreement with sk hynix not to use samsung's hbm2s?

RejZoRHow about you stop your wild horses and start actually reading the posts mkay?

You do realize your whole argument is based on the assumption that since Nvidia hasn't publicly shown a card, the card must not exist, don't you?

bugYou do realize your whole argument is based on the assumption that since Nvidia hasn't publicly shown a card, the card must not exist, don't you?

Working HBM2 cards doing more important things than just running Doom too, the butthurt is real.

I don't really get why AMD is in the title of an nVidia announcement. Surely that's going to get the kids stirring.

horsemama1956I don't really get why AMD is in the title of an nVidia announcement. Surely that's going to get the kids stirring.

I do agree, it was always going to get people frothing at the mouth with rage, seems to have worked.

FluffmeisterI do agree, it was always going to get people frothing at the mouth with rage, seems to have worked.

But how else will they get the clicks like wccftech?

bugYou do realize your whole argument is based on the assumption that since Nvidia hasn't publicly shown a card, the card must not exist, don't you?

Well nothing is official until the Leather Jacket walks out on stage.

I dunno if you can really count putting it on an industrial compute card as beating AMD to putting it on a GPU...

RejZoRBusiness segment maybe, but not for consumers. Where AMD still holds the first for HBM and also for HBM2. Because RX Vega cards already exist, you still can't actually buy them yes, but they exist far more than anything NVIDIA might have. We've acually seen real, operating Vega cards.

Again, for all those with problems understanding rather barbaric simple English... Simply stating facts is now being a fanboy. Please find my sides somewhere around Kuiper's belt... (ignore the silly typos).

Business, yes, NVIDIA wins there with HBM2. For consumer, so far AMD has the HBM 1 and for now HBM2 crown as well, because they've shown more of the actual hardware than NVIDIA. Deal with it.

UbersonicI dunno if you can really count putting it on an industrial compute card as beating AMD to putting it on a GPU...

If availability is like the old tesla, then it's still 8 months away lol. Nvidia paper launches get old quick (at least they basically stopped that the last couple years for consumer).

UbersonicI dunno if you can really count putting it on an industrial compute card as beating AMD to putting it on a GPU...

So now the argument is the GP100 isn't a GPU? Come on guys, this is getting silly.

And you can buy Quadro equivalents already too.

Still can't buy Vega.

medi01I might be missing something:

2/6/2017, 3:12 PM
Nvidia Quadro GP100: Big Pascal, HBM2, and NVLink comes to workstations
arstechnica.com/gadgets/2017/02/nvidia-quadro-gp100-price-details/

And it was tested back in february too with VRay 3 (GPU render engine):
labs.chaosgroup.com/index.php/rendering-rd/v-ray-gpu-benchmarks-on-top-of-the-line-nvidia-gpus/

Looks like HBM2 makes a substantial difference.

Might be the 1st but absolutely no good to most people, well done nVidia HAH.

robalWhere is HBM2 equipped Titan then...

Why ? would you be willing to drop so much money on it ?, if so good for you.

Title of article: NVIDIA Beats AMD to Market On HBM2 - Announces Tesla P100

Can we just stop arguing about who was first, the answer is actually the title of the article. And regarding that ridiculous argument, does it even matter who is "first"? It is about who does it well at a good price. We all know nvidia will do it better but amd will offer lower performance and a better value. Can't that just make everyone happy? AMD is here to provide a product and keep competition in check. AMD is always a little behind but we need AMD.

medi01Will that happen when non Ti card will cost mere 999$ or after that?
I mean, the realization part.

Cmon, what you're saying is basically: "I better buy hardware from the underdog, even if they're worse in every way, just to fight a possible future monopoly" seriously man, i mean that's not the case with AMD now, not at all, but there's people thinking this way and it's the same people who bought old bulldozer and similar, which were a total fail, just to avoid a possible monopoly, nah.

oxidized<new portion of "alternative logic">

So, at what price point of non-Ti card will those silly underdog supporters realize how bad supporting underdog is, will it be at 999$ or 1299$? Don't tell me it would be 1499.

medi01So, at what price point of non-Ti card will those silly underdog supporters realize how bad supporting underdog is, will it be at 999$ or 1299$? Don't tell me it would be 1499.

Mine is alternative logic, and you're basically saying,"i don't give a shit how bad something is, i buy it as long as i support the underdogs", i mean, for real?

But well, keep talking about numbers please.

oxidizedyou're basically saying

Stop putting words in my mouth, oh alternative one.

Question that I asked was rather simple, although indeed rhetorical.

You don't need to bend over to support the underdog, it's the other way round.

medi01You don't need to bend over to support the underdog, it's the other way round.

It's the other way around? What way is, "the other way around"? Buying what's better for more money?

yawning while scratching Al Bundy style.

ssdproTitle of article: NVIDIA Beats AMD to Market On HBM2 - Announces Tesla P100

Can we just stop arguing about who was first, the answer is actually the title of the article. And regarding that ridiculous argument, does it even matter who is "first"? It is about who does it well at a good price. We all know nvidia will do it better but amd will offer lower performance and a better value. Can't that just make everyone happy? AMD is here to provide a product and keep competition in check. AMD is always a little behind but we need AMD.

It's all about the clicks, man.

Not one person here is capable of seeing the oxymoron in the title? AMD beat NVIDIA to HBM and HBM2 by Pioneering it. NVIDIA a company ten times larger than AMD feels the need to steal someone else's technology and then using their massive amounts of money to bring it to market first, even though the P100 news is a year old and was fully expected by now? Really, that's where the credit is given? And now Intel, also a MUCH larger company is asking AMD to help them with their iGPU's, lmao. And Microsoft, a company worth almost $200 billion can't even develop their own console hardware without AMD? Hmm, why don't Microsoft go to NVIDIA for console hardware? Hmm I wonder... You do not hire the Lazy and expect things to happen.

NVIDIA is like the thief that breaks into someone's vault and steals all the gold, then turns around and that thief gives that same gold to charity, and then the credit is given to the thief? Really? Every last one of you should be ashamed of yourselves for not having the moral fortitude and decency to know where the credit should be given for HBM2 and most major gaming developments in the first place. I guess with everyone's skewed morality here credit for HBM2's very existence should also be given to NVIDIA just because "Hey they used it first"? Maybe we should also thank NVIDIA for Vulkan's existence as well? Oh and thank NVIDIA for the Xbox, the Play Station and the Nintendo Wii. Oh and don't forget games ported from AMD based consoles to the PC, thank you NVIDIA for that too. I guess we should all thank NVIDIA for GDDR5X as well, I think they used it first too.

If NVIDIA was all that great of a tech developing company, then why don't they develop their own Graphics memory standards? Huh? Explain that to me. What major technology, either hardware or software that we can thank NVIDIA for once Vega releases? What on Vega will be directly developed by NVIDIA? Anything worth mentioning at all? What tech will be on the next Xbox that we can thank NVIDIA for?

Does anyone here have the decency to give credit for HBM2 where it is actually due? I'm not a fan of either company but I at least have eyes and can see where the majority of gaming breakthroughs, technologies and developments are coming from in the first place. Oh wait SLI perhaps? Err, still nope NVIDIA got that from buying out 3dfx, while AMD developed Crossfire 100% from the ground up themselves.

I like NVIDIA a LOT but they need to start developing major world changing tech of their own once in a while (like they used to in the early days of GeForce), like HBM and Vulkan, both of which are changing the gaming landscape with no help in sight from NVIDIA.

amd did announce a vega instinct card in december but they didnt disclose the memory ;P

SkOrPnAMD beat NVIDIA to HBM and HBM2 by Pioneering it. NVIDIA a company ten times larger than AMD feels the need to steal someone else's technology and then using their massive amounts of money to bring it to market first, even though the P100 news is a year old and was fully expected by now?

AMD being as generous as they are, didn't keep it to themselves and it has since become a JEDEC standard for all to manufacture and use (you can't steal an open standard - proprietary implementations excluded ). It's a smart move by AMD because widespread adoption of the technology increases volume and an increase in volume generally leads to cheaper prices for all. For the consumer, this means more SKUs which implement HBM in the future. Leaving Nvidia out of this equation, means missing out and a large chunk of the market, thus slowing adoption. That's one of the great things about AMD - they understand that being a smaller player means they have to get creative.