VRWORLD - 14NM AMD GREENLAND TAPES OUT: ATTACK ON NVIDIA PASCAL, INTEL XEON PHISource of that information?
Sacrifice other opportunities? Since when is securing a contract with one of the most profitable companies around get turned into having to sacrifice? Why would you turn down good known money instead of going with 3rd party sellers?
AMD is more desperate for more business, there is no doubt about that. But that can also work in their favor.All i know is this is going to be great for AMD, it's a win
I guess my last post was misunderstood and quite frankly, not in the mood to elaborate much. All i meant is that Nvidia has more leverage in a negotiation room due to it's market position, that's a fact.
That might not please some people here but it is the reality. I have a soft spot for AMD and many here know this, so i cannot be called a Nvidia fanboy ()
AMD is more desperate for more business, there is no doubt about that. But that can also work in their favor.
I am just going by what AMD themselves said, and they saidYou're not going to get any better sources than that, even if it was 100%. Also I can't remember when, I remember Lisa Su refering to 14nm and saying the fabs have done an excellent job with it, "fabs" plural.
I think there is a solid indication they are going that route, but it's not 100%..
If indeed they had another fab player (Samsung), then they would have stated that here (and not use the word all), it is their outlook in their financials, so, it doesn't add up at this point that AMD is doing anything with Samsung's fabs, unless it occurred AFTER 04/21/16. I suppose another option is for GloFlo to ask for Samsung's help, and that could be possible, and wouldn't be mentioned here, but, that is a very long shot, since it would require for them to get AMD's permission to do such a thing.AMD relies on GLOBALFOUNDRIES Inc. (GF) to manufacture all of its microprocessor and APU products and a certain portion of its GPU products, with limited exceptions. If GF is not able to satisfy AMD's manufacturing requirements, its business could be adversely impacted; AMD relies on third parties to manufacture its products, and if they are unable to do so on a timely basis in sufficient quantities and using competitive technologies, AMD's business could be materially adversely affected; failure to achieve expected manufacturing yields for AMD's products could negatively impact its financial results; the success of AMD's business is dependent upon its ability to introduce products on a timely basis with features and performance levels that provide value to its customers while supporting and coinciding with significant industry transitions;
Engineering samples != final tape out (rarely does).VRWORLD - 14NM AMD GREENLAND TAPES OUT: ATTACK ON NVIDIA PASCAL, INTEL XEON PHI
It wasn't a Greenland, but Polaris.
From AMD Reports 2015 Fourth Quarter and Annual Results.AMD previewed its revolutionary 14nm FinFET Polaris GPU Architecture, highlighting significant architectural improvements including High Dynamic Range (HDR) monitor support and a 2x performance-per-watt improvement over the prior generation. The GPUs deliver a remarkable generational jump in power efficiency, and are designed for fluid frame rates in graphics, gaming, VR, and multimedia applications on small form-factor thin and light computer designs.
Yeah I've been really impressed with her so far, she doesn't seem to be the type to overhype. Her closing speech at the end of the Computex was pretty nice as well.Fully agree... Lisa sure seems to be making progress lately. She's leading a pretty frugal operation and not looking back.
GloFo and Samsung share the same process, nothing stops AMD from knocking on Korean's door.I am just going by what AMD themselves said, and they said
If indeed they had another fab player (Samsung), then they would have stated that here (and not use the word all), it is their outlook in their financials, so, it doesn't add up at this point that AMD is doing anything with Samsung's fabs, unless it occurred AFTER 04/21/16. I suppose another option is for GloFlo to ask for Samsung's help, and that could be possible, and wouldn't be mentioned here, but, that is a very long shot, since it would require for them to get AMD's permission to do such a thing.
What all this basically means is, they have all their marbles in one basket with GloFlo. If GloFlo can't meet AMD's order, they will have serious repercussions as stated above.
Engineering samples != final tape out (rarely does).
From AMD Reports 2015 Fourth Quarter and Annual Results.
They would have said it has entered volume production if indeed it would have, but they didn't, so it didn't happen, and again, it wasn't listed in their financials.
It isn't like they can lie about these things to the SEC, if it would have been done, they would have said it.
It also costs lots and lots of $$$ for the orders, and if they put all their $$$ on the GloFlo contract, then, it is hard to get more revenue out of the air.
The perfect example of this is the game console wins. Every AMD naysayer laughed and actually boasted that it was too low a margin product for Nvidia to even consider.AMD is more desperate for more business, there is no doubt about that. But that can also work in their favor.
OK, so what about this? Middle of June 2015
The perfect example of this is the game console wins. Every AMD naysayer laughed and actually boasted that it was too low a margin product for Nvidia to even consider.
Look at the continuing fallout from that piece of hubris.
Well, if they withhold "full Tonga" from me again, I won't be happy.
I guess we have to wait and see if we seem to be missing a gpu from AMD?
You mean NVIDIA dominating even more and making a lot more money than AMD since they won the console business?
Why is this such a big deal to everyone?
Why is this such a big deal to everyone? Full tonga was what? 5-10% faster?
Could any human being sit down at two computers one with cutdown tonga and one with full blown masterrace Tonga and actually feel a difference? They are the exact same performance class, if you can't even notice the difference then what is the huge concern?
I am just going by what AMD themselves said, and they said
AMD relies on GLOBALFOUNDRIES Inc. (GF) to manufacture all of its microprocessor and APU products and a certain portion of its GPU products, with limited exceptions.
If a newer $1000 GPU is loosing to an older $550 hd7970 is dominating, than I agree with you, not neceserily with your definition of dominating.
Shame amd and nv are not competing directly. Prices would be better.
Also make no mistake, Nvidia wanted that business as much as AMD. Margins didn't miraculously get worse from the previous generations when Nvidia was supplying GPUs for consoles.The perfect example of this is the game console wins. Every AMD naysayer laughed and actually boasted that it was too low a margin product for Nvidia to even consider.
Look at the continuing fallout from that piece of hubris.
As I said in that post, they could well have done it, AFTER 04/21/16, but, there is no way for us to know until the next quarter is out.GloFo and Samsung share the same process, nothing stops AMD from knocking on Korean's door.
I don't disagree that they didn't have engineering samples out at this time last year, I just don't agree that they have been in production since then.OK, so what about this? Middle of June 2015
KitGuru - AMD : We have taped out our first FinFET products
Anyway, we will see at the end of this month
The foundation of our growth strategy is building great products with solid execution. During the first quarter of 2016, we continued to execute our product roadmap and delivered new products. In February 2016, we demonstrated our upcoming 2016 Polaris GPU architecture featuring AMDs 4 th generation Graphics Core Next architecture, which was sampled to OEMs in the first quarter of 2016. We launched the AMD A10-7860K APU designed to help enable smooth play of online games and AMD Athlon X4 845 desktop processor, which features our Excavator x86 architecture. We announced our 3 rd generation AMD embedded G-Series SoCs and Embedded G-Series LX SoCs designed to expand developers ability to scale x86 platforms. We continued to expand our leadership position in Virtual Reality (VR) by introducing AMD Radeon Pro Duo, a platform aimed at most all aspects of VR content creation.
Based on what? Metal uses OpenCL for compute pipeline exactly in the same way as Vulkan will use OpenCL 2.0/2.1 for compute pipeline rendering in games.
Most people who claim that OpenCL is dying or will be phased out by graphics API pretty much do not know what they are talking about. It might happen, but not in close future. And by that I mean upcoming 5-10 years.
Yeah, Metal is just another explicit API and it best suits GCN (and a 9th Gen of Intel iGPUs) with its bindless resources uarch