Slashdot Mirror
Nvidia Claims Intel's Larrabee Is "a GPU From 2006"
Barence sends this excerpt from PC Pro:
"Nvidia has delivered a scathing criticism of Intel's Larrabee, dismissing the multi-core CPU/GPU as wishful thinking — while admitting it needs to catch up with AMD's current Radeon graphics cards. 'Intel is not a stupid company,' conceded John Mottram, chief architect for the company's GT200 core. 'They've put a lot of people behind this, so clearly they believe it's viable. But the products on our roadmap are competitive to this thing as they've painted it. And the reality is going to fall short of the optimistic way they've painted it. As [blogger and CPU architect] Peter Glaskowsky said, the "large" Larrabee in 2010 will have roughly the same performance as a 2006 GPU from Nvidia or ATI.' Speaking ahead of the opening of the annual NVISION expo on Monday, he also admitted Nvidia 'underestimated ATI with respect to their product.'"
"OH MY GOD! CPU AND GPU ON ONE DIE IS STOOOOOOOOPIIIIIDDDDDEDEDDDD!!!1111oneoneone"
How stupid is it really? So what if the average consumer actually knows very little about their PC. That doesn't necessarily mean it won't be put into a person's PC.
If they were really forward thinking, they could see it as an effort to bridge the gap between low-end PC's and high-end PC's. Now maybe, at some point in the future, people can do gaming a little better on those PC's.
Instead of games being nigh unplayable, are now running slightly more smoothly. With advance in this design, it could really work out better.
Sure, for the time being, I don't doubt that the obvious choice would be to have a discrete component solution for gaming. However, there might be a point where that isn't in the gamers best interests anymore. I'm not a soothsayer, I don't know.
Still, I can't only help but imagine how Intel's and AMD's ideas can only help everyone as a whole.
Lots of people here and analysts have written off AMD. I think AMD is in a great position if they can survive their short term debt problems which is looking increasingly likely.
Consider the following:
AMD is in a great position like no other company to capitalize on the coming CPU / GPU convergence. Everyone jeered when AMD bought ATI but it is looking to be a great strategic move if they can execute on their strategy.
AMD has the best mix of technology, they just have to put it to good use.
G. Washington on Government "it is force. Like fire, it is a dangerous servant and a fearful master."
From the SIGGRAPH paper they need something like 25 cores to run GoW at 60Hz. That's 1Ghz cores for comparison though. LRB will probably run at something like 3Ghz, meaning you only need like 8-9 cores to run GoW at 60, and with benchmarks stretching up to 48 cores you can see that this has the potential of being very fast indeed.
More importantly, the LRB has much better utilization since there aren't any fixed function divisions in the hardware. E.g. most of the time you're not using the blend units. So why have all that hardware for doing floating point maths in the blending units when 99% of the time you're not actually using it? On LRB everything is utilized all the time. Blending, interpolation, stencil/alpha testing etc. is all done using the same functionality, meaning that when you turn something off (like blending) you get better performance rather than just leaving parts of your chip idle.
I'd also like to point out that having a software pipeline means faster iteration, meaning that they have a huge opportunity to simply out-optimize nvidida and amd, even for the D3D/OGL pipelines.
Furthermore, imagine intel suppyling half a dozen "profiles" for their pipeline where they optimize for various scenarios (e.g. deferred rendering, shadow volume heavy rendering, etc. etc.). The user can then try each with their games and run each game with a slightly different profile. More importantly, however, is that new games could just spend 30 minutes figuring out which profile suits them best, set a flag in the registry somewhere, and automatically get a big boost on LRB cards. That's a tiny amount of work to get LRB-specific performance wins.
The next step in LRB-specific optimizations is to allow developers to essentially set up a LRB-config file for their title with lots of variables and tuning (remember that LRB uses a JIT compiled inner-loop that combines the setup, tests, pixel shader etc.). This would again be a very simple thing to do (and intel would probably do it for you if your title is high profile enough), and could potentially give you a massive win.
And then of course the next step after that is LRB-specific code. I.e. you write stuff outside D3D/OGL to leverage the LRB specifically. This probably won't happen for many games, but you only need to convince Tim Sweeney and Carmack to do it, and then most of the high profile games will benefit automatically (through licensing). My guess is that you don't need to do much convincing. I'm a graphcis programmer myself and I'm gagging to get my hands on one of these chips! If/when we do I'll be at work on weekends and holidays coding up cool tech for it. I'd be surprised if Sweeney/Carmack aren't the same.
I think LRB can be plenty competitive with nvidia and amd using the standard pipelines, and there's a very appealing low-fricion path for developers to take to leverage the LRB specifically with varying degrees of effort.
Sorry, but I did exactly that, and got bitten recently: NVidia's drivers for old graphics cards lag behind more and more. I can no longer update one of my systems because the ABI version for their GLX doesn't get updated.
The fix would be trivial (just recompile the current version), but Nvidia clearly would rather sell me a new card.
With all OpenGL extensions supported working properly, to latest and greatest from NVIDIA where I can never be sure which extension work on which driver with which card.
Yes. I know about ATI releasing the specs, which is why I said it might have gotten better now, though I guess it's going to be some time before we see anything happen (but it probably will)
"DRM is like the Ford Pinto: it's a smooth ride, right up the point at which it explodes and ruins your day."-C.Doctorow
I wouldn't call it that.
I'd call it a knee-jerk reaction to a non-issue.
Nvidia are getting very scared now that ATi are beating them senseless. I run both ATi and Nvidia, so don't go down the "you're just a fanboy" angle either.
I've seen chip makers come and go, this is just another attempt by Nvidia to try and sure up support for their product, but this time they can't turn to ATi and say "look how crap their chips are" - they have to do it to Intel who are aiming the chips at corporate markets.
To be honest, the best bang for buck at the lower end of the market for 2D seems to be the Intel chips. One thing that does tend to surprise people is the complete lack of performance that the Nvidia chipsets have when not in 3D. ATi don't seem to have these problems having built around a solid base of 2D graphics engines in the 90's (Rage/RageII is at least one reason why people went with Macs back then). Nvidia is really feeling the pinch with ATi taking up the higher end of the market (pro-gear/high end HD) and intel suring up the lower end (GMA, etc). Nvidia pretty much are stuck with consumers buying their middle of the line gear (8600/9600).
When you aim high you tend to hurt real when you fall from grace, the whole 8800 to 9800 leap was abysmal at best unlike their main competitor who really pulled their finger out to release the 3xxx & 4xxx series.
All in all this seems like a bit of pork barrelling on Nvidia's part to detract from the complete lack of performance in their $1000 video card range. If anything this type of bullshit will be rewarded with a massive consumer (yes, geek and gamer) backlash.
I know my products, I know their limitations - I don't need some exec talking crap to tell me, and base level consumers will never read it.
Intel has made some bad mis-steps in the past, and one of them was failing to design their processors around the strengths and weakness' of their memory architecture. Rambus is a prime example. It was a superior solution for the wrong problem, and Intel failed to design their processors to take advantage of the memory's strengths, and it looks like they are doing it again. The limiting factor in CPU / GPU performance isn't how many instructions you can pound into any given second, its how much total memory can you get at, in that time frame. It does you no good to be able to process 16 billion pixels / second, when you can only get the data for 4 billion per second from your memories. Better to build a system that can get 6 Billion per second from the memory, and can process only 6 billion per second. That is the fundamental problem that Nvidia seems to understand, and Intel doesn't.
-=Geoskd
I wish I had a good sig, but all the good ones are copyrighted
2d performance is more than just how fast you can refresh a framebuffer from memory. Check out x11perf -aa10, which tests drawing 10pt anti-aliased fonts. My radeon 9250 with open source drivers gets about a 2x better score than my brand new 4850 with fglrx. The difference is that ati/amd (and nvidia as well) don't spend nearly as much time optimizing these parts of the driver(considered "2d" but they really use the 3d engine) while you need hardware acceleration and driver support to do it at a good speed(which the open source r200 driver does, even faster than pure software on my not too sluggish phenom 9950).
thisnukes4u.net