NVIDIA to License Kepler and Future GPU IP to 3rd Parties
by Anand Lal Shimpi on June 18, 2013 9:16 PM EST
Earlier today NVIDIA announced that it would begin licensing its Kepler GPU architecture to 3rd parties. This is a sensible next step for NVIDIA, but an unprecedented one among the two remaining discrete PC GPU suppliers.
Note that what NVIDIA is announcing today is contrary to AMD’s semi-custom approach to SoC production. AMD is offering to build (semi) custom tailored silicon to customer needs, while NVIDIA is taking a more ARM-like approach and offering its GPU IP to 3rd parties for integration on their own. In other words, NVIDIA is looking to compete with ARM and Imagination Technologies rather than AMD or Qualcomm.
In addition to its GPU architecture, NVIDIA is now also open to licensing its visual computing patents to 3rd parties. The visual computing patent portfolio includes all of NVIDIA’s 5500 patents in the area, as well as CUDA.
NVIDIA views its IP licensing business as additive rather than in lieu of its current GPU and SoC businesses. Time will tell whether or not this ends up being the case, but it’s quite obvious that at NVIDIA’s current size it wouldn’t be able to go after all GPU markets on its own - enabling others to do so makes a lot of sense from that perspective.
It Doesn’t End with Kepler: Future NVIDIA GPUs to Be Licensed
I asked NVIDIA about future GPU architectures beyond Kepler, and the answer was pretty awesome: future GPU architectures will be available to licensees at the time of tape out by NVIDIA. Licensees can choose whether or not to adopt an architecture right away or wait for any potential revisions, similar to what ARM does with its cores (e.g. Tegra 4i uses a later revision of the Cortex A9 core). This move has huge implications. Theoretically a licensee could bring an NVIDIA GPU to market before NVIDIA itself, although that does seem pretty unlikely. What we could see however is a licensee introduce a GPU configuration that NVIDIA had no intentions of bringing to market.
The model makes a lot of sense and expands NVIDIA’s role in the computing world beyond its life in PCs. In the PC space, NVIDIA built discrete GPUs that system integrators (and end users) put in their machines. In the post-discrete world where SoCs rule the landscape, NVIDIA believes it can be just as relevant by doing the same. The difference here is instead of NVIDIA building cards out of its GPUs and selling them, the SoC manufacturer would be responsible for all integration. It’s the same playbook, just modified to deal with the new world around it.
Targets for Integration
NVIDIA is quick to point out that Kepler is its first mobile to high-end GPU architecture. Capable of scaling from smartphones (Logan/Tegra 5 next year) to supercomputers (Titan), Kepler is inherently very flexible and makes a lot of sense as NVIDIA’s first target for its IP licensing program.
Although mobile is an obvious fit for Kepler licensing, NVIDIA hopes its GPUs will be used in new markets as well. NVIDIA’s refrain sounds quite similar to AMD’s. Neither knows where the next big market will be, but both want to be prepared for it when the time comes. It won’t be too long before smartphones and tablets reach their own Ultrabook moments when performance becomes good enough for the majority of the market and attention shifts elsewhere. When that happens, NVIDIA (and AMD, and others) believe that opportunities for continued growth will appear in new markets (e.g. TVs, wearables, other connected compute devices).
The Compute Connection
Although it’s clear that the greatest point of interest with today’s announcement revolves around getting NVIDIA’s GPU designs and graphics IP into new products, at a high level perspective NVIDIA has made it clear they’re licensing their visual computing technology, and that this isn’t just a play for graphics. As part of keeping themselves open to new markets, NVIDIA has told us that they’re essentially willing to do whatever makes financial sense as far as licensing goes, with both compute and graphics on the table. So at the same time as licensing out their graphics technology, NVIDIA has also opened the door to licensing out CUDA and their other GPU compute innovations if the price is right.
This can lead to several possibilities, ultimately relying on who’s interested and what market they represent. At a most basic level, licensing an NVIDIA GPU will get the buyer CUDA – binary compatibility and all – thanks to the fact that this would be the same hardware CUDA already runs on. However in the new “anything is possible” licensing system of NVIDIA, CUDA could also be licensed out separately. Device makers who simply want to add CUDA support to their devices, either to take advantage of some of the runtime’s unique functionality or merely to enable easier porting from existing NVIDIA systems, can now license the necessary CUDA IP from NVIDIA. The GPU computing market is still very young with a number of competing technologies, but thus far based on actual usage CUDA has proven to be a front runner compared to more widely supported (and open) environments such as OpenCL, so while NVIDIA is still trying to bring further users onto CUDA, they also have a CUDA user base they can leverage today.
The most obvious avenue for any potential CUDA licensing would be HPC users looking for greater integration beyond today’s CPU + GPU setups we see in systems like Titan. However NVIDIA is also pursuing this with forthcoming SoCs like Logan and further products integrating their Denver CPU, so it’s not a market that’s being ignored by NVIDIA. On the other hand more novel uses of GPU compute in the embedded space, encompassing everything from TVs to automotive to traditional appliances, are areas that have been identified as potential growth avenues for GPU computing by NVIDIA and other GPU firms in the past, not all of which NVIDIA is directly serving right now. In all of these cases licensing can focus on CUDA, or even more broadly just licensing specific NVIDIA compute technologies that would be useful to include in these products; even obscure technologies like Kepler’s low-overhead soft-ECC implementation could potentially be of value as a licensed technology.
NVIDIA Can Now Go After Apple & Samsung Business
The cynic in all of us can point to NVIDIA’s struggles with getting Tegra 4 into devices and out the door as motivation behind wanting to license its GPU IP. Beating Qualcomm has proven to be very difficult. Even Intel has had a wonderfully difficult time of making its way into the mobile space. So is that what this licensing play is all about? To an extent, perhaps.
Had Tegra 4 been out and available, I think it’s safe to say that the SoC would likely have been used in at least some previous Tegra 3 design wins. Tegra 4i will hope to do the same for smartphones. I see no reason for these businesses to stop, but I think it’s quite obvious that there’s a huge gap between where the Tegra business is today and where Qualcomm is.
By licensing its GPU IP, NVIDIA opens itself up to additional customers (and revenue) that otherwise wouldn’t have considered it. I doubt Apple would ever use an off-the-shelf Tegra SoC, but NVIDIA can now compete for Apple SoC business alongside Imagination Technologies. Should Apple decide to one day drop Intel altogether and bring all of its CPU design in house, it now has a GPU vendor it can license cores or technologies from - just like it does with ARM. The exact same goes for Samsung.
Both Apple and Samsung have histories of licensing GPU IP from Imagination. NVIDIA now has a chance of going after that business.
The same could be said at the other end of the spectrum. The mobile SoC wars we saw unfold over the past few years are about to heat up in the server market. Where integration of high performance GPU architectures makes sense in servers, NVIDIA now has an offering to those that are interested.
GPUs Today, LTE Tomorrow?
NVIDIA isn’t officially announcing plans to license its Icera modem IP, but I’m told that’s the next logical step. NVIDIA is investing handsomely in Tegra 4i and its modem architectures, but similar to its GPU business - in order to address a much larger market, it will have to consider licensing that IP.
Final Words
Although unexpected from a timing perspective (we had no hint that NVIDIA was going to drop this on us today), NVIDIA’s move to license its GPU IP is very sensible. All growth markets where compute is concerned are moving forward with high levels of integration. For NVIDIA to not only remain relevant in the broader world but also grow with it, it must have a strategy in place for markets where integration is required.
Where those new markets are, and ultimately what this means for NVIDIA’s financials is beyond the scope of our analysis - it’s simply the right (only?) move.
Facebook
Twitter
RSS
58 Comments
View All Comments
Yorgos - Wednesday, June 19, 2013 - link
"the way it meant to be played"sense the irony.
testbug00 - Wednesday, June 19, 2013 - link
The problem is for a company to integrate the Silicon into their products would take a good 1.5-2 years... probably longer (for Kepler).It might pay off, but it seems to be a desperation move to me.... We will see :)
testbug00 - Wednesday, June 19, 2013 - link
LOL. What are you talking about.Hahahahaha.... Intel is going out of their way to stop licensing GPU cores (see from old Atom to new Atom).
TheJian - Sunday, June 23, 2013 - link
"Had Tegra 4 been out and available, I think it’s safe to say that the SoC would likely have been used in at least some previous Tegra 3 design wins."This has to be one of the most ridiculous statements I've seen you from anand. If S800 was out and available I'm guessing it would be used in some S600 design wins. I can say this every year for EVERY product ever produced. If Intel's broadwell was out now, I'm sure it would be selling in haswell models instead of haswell. Do we see how dumb this is?
"The cynic in all of us can point to NVIDIA’s struggles with getting Tegra 4 into devices and out the door as motivation behind wanting to license its GPU IP. "
What struggles? The first device they are selling to is THEMSELVES. And it isn't out yet...LOL.
http://venturebeat.com/2013/06/03/toshiba-launches...
2 toshibas with T4 (and a 3rd with a T3)
Vizio has a T4 (and T3) coming also that they showed at CES
Also the Asus Transformer Pad Infinity, HP SlateBook x2 both T4, not to mention Mad Catz MOJO (they are SEEKING deal T4 they said).
BungBungame's Kalos tablet uses T4 also
Couple those with Ouya, gamepop, wikipad etc and I think tegra has a pretty good year lined up even before the T4i. Hp, Toshiba and Asus all showing tegra support. Who's left besides Samsung/LG/Apple (who does their own stuff-but now may go NV next year with a T5 or kepler gpu at least? Who knows)? I guess you guys missed computex? All 3 tablets (all but Kalos) with T4 were on display there 3 weeks ago. Is this the AMD love showing again? No mention of a T4 device or did I miss it in your computex coverage? How about their award, top in handhelds (so no Vita or 3DS victories or anyone else...LOL)?:
"NVIDIA today received its fifth consecutive Best Choice Award at Computex, as the SHIELD open-platform gaming device won the top Golden Award in the smart handheld category, as well as a special Media’s Choice Award, voted on by editorial staff of local publications."
And the Media Choice award too...LOL But this T4 thing has trouble. You guys were all over Computex and NV doesn't even get a mention...The president of Taiwan handed it to them...LOL. I hope you guys know alexa will be showing you further down this year...How long will you guys keep hiding NV products, hiding any articles about NV making record quarter after quarter, make excuses for lack of FCAT results, and BS the public about AMD cpus (an A8-5600 for all single gpus is good in your 1440p articles?...ROFL)? Does AMD really pay enough to have you have your alexa traffic off by a good 1/2 in the last 9 months? Sheesh. Wasn't shield a centerpiece at Google I/O? :) Just Glass, GS4 and Shield right? Missed that too? I can't believe you guys covered all Intel stuff at computex but not mention any of the 3 tablets from Nvidia on display at computex (but had time to SPOT THE KABINI...LOL). Whatever. More NV hate from Anandtech. Even the GPU's got an award at computex, nothing about that either from anandtech. It's comic you guys have the only 780M laptop with cpu throttling issues so GTX 780m can't shine...LOL.
"Except, either due to our particular MSI GT70 sample being a lemon and having CPU throttling issues (or it may be a design problem that affects all of MSI’s current GTX 780M notebooks—we’re not entirely sure), the 7970M really isn’t that far off the GTX 780M performance."
From the top article at anandtech on the 7970 enduro junk (yeah, enduro runs like junk).
http://www.laptopmag.com/reviews/laptops/msi-gt70-...
You're the only one with a crappy Lemon laptop running 780m. Exact model kicking some butt. You're the only ones with problems with FCAT, the data is just too large, drivers caused invalid data blah blah blah. Anything to wait until AMD fixes their prototype drivers :) Still no part2 of Ryans FCAT articles etc etc...
T4i announcements can't be far away, and that reaches a whole other market via $100-$400 phones (aimed at $100-200), but until then it is basically modem-less and thus, basically PHONE-LESS. I've said it before and I'll say it again, you can't really announce product launches without knowing exactly HOW MANY can NV allocate to you? I don't suspect anyone will know that until NV sees how well Shield sells in the first month (hence the July ship date for T4 to everyone else which gives them a month of sales to test with). If shield sells 10mil (joke of course) why would I even allocate a single chip to a tablet? I'll sell 10mil shields and tell you tough luck buddy, we make more on shield than a soc until shields are stuck on shelves :) Well DUH...
I'm always confused by ridiculous claims T4 is having trouble selling to devices...LOL. I'm kind of shocked Anand himself is doing this. Seriously? You can't be this dumb or ignorant. If a company like HP etc announced something then shield sold like hotcakes forcing a few million HP pre-orders (insert amount here, whatever) to be delayed for months until shield slowed down, there would be a ton of HP hate, and probably some NV hate. Nobody will risk this hate and SMART business would delay saying a word until allocations are known and product is shipping. You'd have to know this Anand. So why make these comments? Any proof of T4 being turned away by device makers? And I mean literally an OEM saying T4 sucks we're running away and have no plans because it's bad? I don't see any S800 announcements yet either...For the same reasons no doubt (hiding power use surely doesn't help). But do we think S800 isn't selling because of no announcements? No, that's SILLY. If a chip isn't even SHIPPING yet you can't announce squat.
http://blogs.nvidia.com/blog/2013/05/31/big-games-...
25+ tegra 4 optimized games, with arma and hawken (according to kotaku) being exclusives so far and also Dead Trigger 2 if memory serves. If they are telling the truth it's a pretty good launch for something they dev'd for 10mil...LOL. IF it's a bunch of lies, well it will deservedly bite them in the butt. Anyone want to place a bet as to whether they'll be out of stock in a week or less at $300? The list of features making 3DS and Vita (never mind GDC2013 showing only 2% making a 3DS game and 5% planning vita games vs. 60% for mobile at GDC 2013, 2500 devs don't lie) worthless now is long. Stonking soc, 720p, HD movies out to tv (playing anything android can), 4x or more main memory (vita has 512mb this has 2gb 3DS has less than both), 16GB included (and a slot free), the entire android library of apps/games, TV browsing, pc streaming, GPS (3G vita has this though right?) and on and on...At $350 it was a tougher sell, but at $300 I think they'll be gone in short order. I'm sure Kepler based T5 will be in it next year and a new one every year. I wouldn't stop as long as they made a $1 profit. Proliferate Tegra games, is the name of the game here and sell gpus to stream from. Slowly kill directx making windows pointless with google's android help (if I don't need office or directx games why do I need windows?). HTML5, OpenGL, WebGL, OpenCL etc FTW :) Kill DirectX now thanks.
IP lic note: I wouldn't want to be imagination right now. They're broke already. This will kill them slowly or fast. They're dead. They had to borrow 20mil for a measly mips 100mil purchase. Maybe Apple buys them? Otherwise, welcome to the list of defunct gpu makers. Since both AMD/NV did this to them already in the desktop market years ago, does this mean they killed them twice?...ROFL.
TheJian - Sunday, June 23, 2013 - link
http://www.notebookcheck.net/Toshiba-intros-the-Re...Two more Tegra devices, one with T4 other with T3. I don't think these are different from the previously mentioned Excite Write/Excite Pro lines with T4. So devices are growing as shown.
Krysto - Tuesday, June 25, 2013 - link
For a company that wants CUDA to be as popular as possible (more than OpenCL), and a company that likes to have exclusive games tied to its GPU technology, this strategy makes PERFECT SENSE.I doubt Apple will consider Kepler, but maybe Maxwell. I could definitely see Samsung trying it out, though. They've been pretty confused about what to use in their SoC's lately. Is it Mali? Is it PowerVR? Hell, just go with Qualcomm.
I'm also not sure if Samsung is already their client or not, but Nvidia definitely has a pretty big manufacturer lined up to get it. Maybe it's Huawei or someone like that. Nvidia wouldn't have announced this if they didn't already have customers. Would be pretty embarassing to announced it, and then have no one want it.
PINWIZARD - Wednesday, June 26, 2013 - link
I wouldn't be surprised to see both Samsung and Apple license. Gaming is a very profitable market that both have publicly expressed interest in exploiting. If done right Apple could capitalize on an all purpose console of their own in the next year or two. Nvidia did a veryshrewd maneuver in recognizing the sheer hate, & competitiveness S & A have with each other
by instilling the "what if" factor if one thinks the other might out-maneuver them by licensing. IP? They will have no choice but to license if they want to keep relevant in a very profitable and competitive gaming market that will keep advancing at a pace that Imagination, or any other in-house GPU attempts will not be enough,
Krysto - Tuesday, June 25, 2013 - link
I'm sure Nvidia will give it to them, as soon as Intel gives them license to build CPU's.