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.'"
Good, learn from that and don't make that same mistake again!
Larrabee [...] will have roughly the same performance as a 2006 GPU from Nvidia or ATI.'
DOH!
Belief is the currency of delusion.
No wonder it's so slow. He keeps making reference to how it paints things. Can't move on to another frame until the previous one has dried.
So why is NVIDIA on the defensive?
Intel is aiming at number crunchers (note that their chip uses doubles, not floats). They don't want NVIDIA to steal that market with CUDA.
When Intel says "graphics", they mean movie studios, etc.
If Larrabee eventually turns into a competitor for NVIDIA, all well and good, but that's not their goal at the moment.
No sig today...
At least Intel documents their hardware. Fuck NVIDIA and their stupid proprietary hardware!
Glass
"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.
A recent journal article on ArsTechnica points to an Intel blog on Larrabee: http://arstechnica.com/journals/hardware.ars/2008/05/01/larrabee-engineer-on-personal-blog-larrabee-is-all-about-rasterization Curious.
Putting syrup in coffee is some form of blasphemy.
Ten years ago you would see Nvidia GPUs in everything from low- to high-end. Today, not so much - Intel dominates the low-end spectrum, with ATI hanging onto a somewhat insignificant market share. The Larrabee is Intel moving upmarket. Sure, it might not perform as well the latest Nvidia or ATI high-end GPU but it might be enough in terms of performance or have other benefits (better OSS support) to win some of Nvidia's current market share over. Considering it's supposedly the Pentium architecture recycled, it's also reasonable to assume the design will be relatively cost-effective and allow Intel to sell at very competitive prices while still maintaining healthy profit margins.
It's a classic case of disruption. Intel enters and Nvidia is happy to leave because there's a segment above that's much more attractive to pursue. Continue along the same lines until there's nowhere for Nvidia to run, at which point the game ends - circle of disruption complete. See also Silicon Graphics, Nvidia's predecessor in many ways.
...and ATI/AMD easily bests nVidia. Somehow, I'm not surprised.
~ C.
Because the drivers are open source and work out the box on every modern Linux distro.
I like my compiz eye-candy and Intel delivers more than enough performance for it.
If, in the future, the trend evolves that all gpu's are integrated.
Intel, nvidia, AMD and ATI...
Who is the odd one out there?
I record my sleeptalking
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."
Company says competitor's product sucks! News at 11.
of a Geforce 8 series(which came out in 2006)???
EXCELLENT!
Thanks AMD for suggesting intel, Im gonna save lots of money on my next motherboard by not needing an nvidia graphics card!
but the extra programability larrabee have as its just a bunch of cpus with some gpu instructions,this wont allow some kind of workarounds,optimizations and diferent raster techniques that make it overcomes the raw power barrier?
to not mention the ressurection of some techniques that never catched on in fixed triangle rendering hardwares like nurbs,voxels and etc?
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.
Regardless of Larrabee being crap performance when it's released in 2010, this is a step in the right direction even if Intel doesn't know how to make very good graphics cards. In time, I'm sure, there won't be a difference between CPU/GPU, and all the memory will be shared (for the majority of systems). We'll be looking back saying "wow, why would anyone want that extra memory from the graphics card just sitting there while my system has maxed it's main physical memory?". If Intel drops into the graphics market, with AMD already there and NVIDIA to soon follow (if the rumours are correct), it really looks like an interesting future. Good luck boys!
With VIA going and nVidia rumored to stop developing chipsets (at least it won't make it any easier for AMD/ATI even if they continue), AMD is missing someone to develop and manufacture good motherboard chipsets.
Twinstiq, game news
Artists need faster render times more than they faster on-screen interaction. Larrabee would be a good mixture for them.
No sig today...
"[....] the "large" Larrabee in 2010 will have roughly the same performance as a 2006 GPU from Nvidia or ATI."
As a KDE 4 user, I thought it was the 2008 Nvidia GPUs that had the same performance as the Intel Pentium III Tualatins from 2002.
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.
Whether it is GPU or CPU or GPGPU, they're all missing the mark, IMO. Those chips are a pain in the ass to program and they are not universal. Mixing MIMD parallelism with SIMD parallelism is a match made in hell. Multithreading is seriously flawed. Intel knows that. That's why they're so busy working on domain-specific dev tools to keep the programmer insulated from all the nastiness. It's not going to work because there is no flexibility. The industry is in dire need of a seismic paradigm shift and the longer it waits, the more painful it's going to be down the road. To find out how to solve the parallel programming crisis, read Transforming the TILE64 into a Kick-Ass Parallel Machine.
So intel will only be about 4 years behind current in their graphics system when it comes out.
In that case, it's probably the biggest leap they'll have ever made.
Funny, I see it the other way round:
Trying something innovative has become rare, most executives prefer to go for the next iteration of "$ProvenProduct". What you call a wild goose chase, I call a refreshing attempt to do something new and better. Of course there is a risk of failure, but Intel can afford taking some risks.
C - the footgun of programming languages
The major difference between Lafabee and contemporary GPUs is that Larabee is really fully programmable. It even supports multitasking and protection (it has paging system). It does not force programmer to use strictly data-parallel algorithms and does not make multipass algorithms so expensive (starting a task on Stream SDK is very costly - around 30ms or so, involvig X server and other unnecessary components on my Ubuntu box). Many algorithms (bitonic sort for example) are a joke on NV/ATI just because of a huge cost of starting subsequent stages of computation.
The only hope for NVidia and ATI in GPGPU area is making their devices more flexible and less pinned to traditional graphics processing, making them fully open and less dependent on X and proprietary drivers/extensions. I'm looking forward for fully open and programmable offerings from all three vendors, not for silly comments thrown at competitors.
FTA:
Funny how in the 9500pro's release there was such a focus on not using raw video horsepower to draw frames, but use occlusion and other things to save time/memory/bandwidth and increase speed in rendering.
Versus the Gforce line of depending on raw horsepower and drawing everthing in a scene.
Brute force or thinking ahead?
I have to admit, I like the idea that Kneo24 had upthread: Make a game's speed depend more on the grfx card, not just the system CPU (+card) but CPU on the vid card.
Interesting idea that would make upgrades more appealing.
Have you read the moderator guidelines? Well, have you, PUNK? (and I want a Karma: Gnarly option)
And when you move up to 790gx with side port ram then AMD systems gets even faster with out useing system ram. Also intel poor drivers are unlikely to make any INTEL GPU good.
I actually posted that response, and Paul Glaskowsky is definitely not clueless. The article they're referring to, however, is pretty bad.
The nVidia drivers are binary only, so they are not available in the standard source repositories and are not compiled and included by default in most opensource distribution.
Ubuntu has made the necessary arrangement and provides, out-of-the-box a tool that can automatically download and install binary drivers from within the usual setup tool.
It think that's why the parent poster may refer to.
That means that, instead of having to manually download a package and execute it (from the command line) - which isn't complicated but require some interaction with the computer - installing a binary driver under Ubuntu simply means clicking the button "yes" on a dialog asking "the following hardware requires non-free proprietary driver, would you like to install them".
It's made trivial enough so computer non-litterate users can still do it easily - well, almost. The users still need to think that maybe they should get some software to make the graphics work better.
Behind the scene, cliquing "yes" automatically add the non-free drivers repository to apt-get and selects the necessary package for installation.
The results are similar (although differently implemented) to opensuse's one-click install (where you click on a link in a web page to a file with name ending in ".ymp") and the corresponding repositories are added to YaST and packages selected for installation.
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
So you're claiming perceptions can never change, so Intel should just give up? More competition in this arena can only be good for us.
AMD is missing someone to develop and manufacture good motherboard chipsets.
Haven't been following the news recently ?!?
ATI/AMD latest serie of chipsets (the 790) is quite good. That's the reason why VIA announced dropping that market in the first place.
The only problem is that currently, nVidia's SLI is a proprietary technology requiring licensing. So that's why a lot of player still buy nvidia's chipsets and avoid ATI's - not that these are bad, on the contrary, but they only lack the license required for SLI.
This SLI problem is also explaining why nVidia may have to consider stopping producing intel chipset : They never licensed their SLI technology to Intel to have SLI-compatible Intel-made chipsets. (Either forcing gamers to use nVidia chipsets or requiring convoluted hacks with SLI chipsets acting as bridges between the main northbridge and the GPUs as in Skulltrail).
And Intel is now retaliating by refusing nVidia access to QuickPath Interconnect.
So either nVidia will have to drop the Intel chipset market (and only produce SLI-bridge like in the Skulltrail hack).
Or nVidia will have to give possibility to license SLI, and thus lose an interesting market that they had managed to lock.
Hence the rumors you mention.
Nonetheless they aren't going to stop producing chipsets for AMD (still popular among gamer) nor for VIA (they have even announced new chipset able to play DX10 games and Vista in all its aero glory on VIA Isaiah ITX platforms)
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
As I've used this particular system only linux for about 7 years with various distro's, I am well aware of the configuration issues. This bug has been filed months ago.
The Current workaround: don't update X11 until Nvidia updates their proprietary GLX library for the legacy drivers. This nicely illustrates the problem with closed source drivers.
There will come a time -not chosen by you, but by the manufacturer- when the hardware you bought will stop functioning correctly.
Didn't the 8800 series come out at the end of 2006? The first gen 8800GTS 640MB and the 8800GTX 768MB those are still powerful video cards by today's standards.... so if Larrabee is "a GPU from 2006" then isn't that a compliment to Intel?
But the chips tell a different story.
Larrabee will be a low end gamers device but a high end number cruncher.
No sig today...
There's a lot more than you think.
No sig today...
As Moore's law makes silicon cheaper, what are you going to do with it? more cache, more cores... why not a GPU? Concurrent software to utilize multi-cores is not yet mainstream (maybe never), so that leaves cache and GPU.
In a way, the existence of separate GPUs is just a sign that the CPU wasn't powerful enough to deliver the graphics the market wanted (and would pay for). When CPU's are powerful enough (clock speed or multi-core), they'll subsume the GPU, as they did maths co-processors and cache. ie. The silicon would be partitioned into CPU, GPU and cache - but it would all be on the one chip (called the "CPU" no doubt).
Intel already owns a fair bit of the integrated graphics market. They have great access to channels. Even if this is only half as good as a separate GPU, they will increase market share. I can't see what could stop them... except maybe a patented technology that can't be worked around. Some manufacturers of separate GPU's will survive in specialized niches. Some.
Here is one area in which NVIDIA clearly has the upper hand over Intel. They apparently have figured out how to perform incremental functions in a non-linear fashion!
...
Great. Just 13 years after finally proving Fermat's Last Theorem, NVIDIA throws a new challenge at the Mathematicians! Now they'll never get any real work done
Guns don't kill people; Physics kills people! - John Lithgow as Dick Solomon on Third Rock From The Sun
AMD's forthcoming Fusion platform ... will combine a GPU and a CPU on one die.
"Joining both components on the same die doesn't buy you that much," he commented. "It's not like there's a real bottleneck there. And every square millimeter you add to the die is a very expensive millimeter. It's an incremental expense, not a linear function. It's cheaper to separate them."
I think a CPU/GPU in one will be attractive to the low-end of the market (between integrated graphics and GPU). As silicon gets cheaper, this approach will creep upmarket til it dominates.
Hmm... Well, good, or not so good, I suppose that cheap x16 integrated 2006 graphics would beat the pants off of non-integrated 2009 tech.
In any case, the real exciting thing to me is that Intel has a track record of support for open 3D drivers on Linux.
http://en.wikipedia.org/wiki/Graphics_hardware_and_FOSS
If Intel continues this practice with Larabee -- it's an easy, clear win for me. Larabee gets my support _just_ for open drivers.
We may have different opinions on Larrabee's technical characteristics, but I'm glad this didn't instantly become a big personal conflict.
. png
Well, hell, that's most of the market.
Knocking someone else's product when you have problems of your own with your newer products.
Or maybe I'm just bitter since I own a laptop with one of those chips and after a month seem to be having issues.
I use to be a big nVidia guy, but those days are nearing their end.
No sig for you!!
Although I appreciate the attention from NVIDIA and Slashdot, I can't support that alleged quote from my blog (http://speedsnfeeds.com).
First, what's being described as a quote is actually just John Montrym's summary from my original post, which is here:
http://news.cnet.com/8301-13512_3-10006184-23.html
What I actually described as equating to "the performance of a 2006-vintage... graphics chip" was a performance standard defined by Intel itself-- running the game F.E.A.R. at 60 fps in 1,600 x 1,200-pixel resolution with four-sample antialiasing.
Intel used this figure for some comparisons of rendering performance. If Larrabee ran at 1 GHz, for example, Intel's figures show that it would take somewhere from 7 to 25 Larrabee cores to reach that 60 Hz frame rate.
Larrabee will probably run much faster than that, at least on desktop variants.
Well... rather than writing the whole response here, I think I'd rather write it up for my blog and publish it there. Please surf on over and check it out:
http://news.cnet.com/8301-13512_3-10024280-23.html
Comments are welcome here or there.
. png
JUST IN!!! Nvidia claims to have found a yetti in one of their product labs. I mean come on making claims on a product that hasn't released and wont release for at least a year is just speculation and hype.
The funny thing is that AMD had pretty good chipsets several years ago. Around the year 2000 or so, their demonstration boards with the "Irongate" Chipset ruled. But they chose not to manufacture those in serious numbers and left the field to VIA and NVidia. Seems they reconsidered that attitude.
Otherwise, I think their strategy with regard to graphics stuff is pretty smart. As I posted elsewhere in this thread, "Fusion" seems a viable way to get a bit more performance/$ out of integrated graphics. And the Open Source drivers should bring them a good position in the Linux market.
C - the footgun of programming languages
They don't really have any choice. Scientific visualisation, photorealistic ray-tracing, and supercomputing are both high-profit margin fields for vendors. Intel has to maintain a presence otherwise Nvidia and ATI will just take all their marketshare.
From Intel's viewpoint, GPU's are rapidly becoming like CPU's with multiple floating-point units, so they have to move towards that point in the hope of getting there before Nvidia and ATI.
Vintage computer adverts: http://www.vintageadbrowser.com/computers-and-software-ads
I don't see why people on Slashdot get so worked up about Larrabee in the negative way.
Yes it's for gaming (Why else is Abrash listed as an author on the Larrabee paper?). Yes it's for high end systems. Yes they are aiming to win (as they've put it).
Personally, I believe Larrabee will be a huge success, but even if it isn't- look at it from the research side of things. We read every day of interesting and different technologies that are basically proof of concept and never make it to market. Intel is taking a radically different approach to graphics and putting it to market. Who wouldn't be excited?
Even if Larrabee fails- it is still a great step forward for graphics processing and multi-core systems.
Don't hate Intel just because they believe in Larrabee and you don't. Or because you love your nVidia card. Give them the props they deserve for being so innovative.
I've always found the biggest issues with Intel was due to deficiencies in the hardware, not the drivers. Drivers tended to install fairly easily, or be OS-native (even Linux support was great), however in terms of inherent functionality the hardware was at most near the middle lines.
ATI on the other hand, was well known for shit-tastic drivers until AMD stepped in more recently.
I never went with 3DFX. I had a *thinks* matrox thingie - the m3d or summat. Had the PowerVR chip in it.. then I think it was a Riva TNT.. and then.. I think I went onto an intel chip from that i710 or something..
I think my previous card crapped out and I needed a cheap replacement, so got a hideously cheap OEM version of it - and then found it was faster than the more expensive card I had before..
Anyway, not sure about the order of the cards, but the point I wish to make is at one time intel did make a decent discrete graphics card - before they decided to leave the market to nVidia and ATI.
They did it once before and no reason to think they can't do it again.
For something that was back in the early K8 days, it seems like 99% of the boards on the market today for AMD CPUs have nvidia/via chipsets.
And since Phenom and AM2+ socket appeared, 99% of the boards on the market for these use nvidia/ati chipset.
The few VIA based motherboards you can see usually are based on derivative of the KT800 chipset that was already available back in the early K8 days (as the memory controller in on the CPU and the chipset only communicates using HyperTransport - one can pretty much mix'n'mach most chipset almost regardless of the processor generation).
And these mainboards are targeted to the budget segment (usually feature only a couple of slots, and sometimes integrated graphics).
All the high-end boards are nvidia or ati based.
The ATI are specially popular in research because they provide 4 long PCIe slots (16x physical, usually 8x bandwith when all 4 in use), often in altening succession (one PCIe 16 each to slot) enabling scientist to put 4 dual-slot cards for GPGPU (CUDA or Brook)
I'm not really seeing a lot of boards on the market (especially carried in stores) that use the AMD chipset.
I don't know, maybe the few stores you checked either carry only old (pre-Phenom) motherboard or sell more nvidia-based because they are popular because of the SLI support.
But most on-line shop I use have both nvidia and ati based motherboards.
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
So, Vendor A says Vendor B's product is no good. When did market trash talk like this become Earth Shattering News warranting Slashdot's attention? If the referenced article had been by a non-Nvidia person, maybe this would be interesting. Maybe. But originating from Nvidia, then the article, and the resulting Slashdot commentary, is a total waste of time.
The ideas in "Kick-Ass Parallel Machine" are interesting - to some! Of course, we are still talking about "toy" processors / processing - to some! MIPS, micro-parallelism are great to some jobs, not all. Of course the enhancements in one part can later be applied to larger systems but it takes time and sometimes is not so easy. I also could argue that clock-less (no ticks) system would be more efficient, no wasted cycles, easy to optimize by load, whatever.
Agreed, multi-threading today is flawed, how about multi-tasking, much easier! And even doing vector processing, a very old technology in big systems, only solves some specific problems. Handy in small scale, todays systems don't get even near to what the huge vector processors did 20 yeras ago, but a beast to write a compiler for that. I fell in love of that when young - several thousand time performance (execution time) enhancement going from scalar mode to vector mode in one weather simulation program and only took one week to tune the program and the compiler right, pure luck!
And even otherwise - did my graduate work -70 based on US radar data processing - non-classified 128 path parallel processing to feed the computers, sorting, filtering etc. I'm sure the classified performance was much better even then. So - we need new ideas?
integrated video motherboard with a Athlon 64x2/4200 ... I think that's recent enough to be supported. Nothing after 169 will produce anything but blackscreen, and I can't even reinstall 169* because it doesn't work with Xen-enabled kernels. I've gotten NO help either from the forums or Nvidia... all I got from Nvidia was a request for diagnostic outputs from their script. Which I ran, sent to them, and never heard from them since. So I'm running vesa.
I am now looking for a AMD/ATI graphics card that actually works in Linux, preferably known to work with Debian. If anyone has one, please post.
Tech Public Policy stuff
Are you on medication?
If so, you may ask your doctor to change the dosage, if not, perhaps you should be.
This is a simple FC9 install
- The X11 update is standard
- The driver is supported through the legacy program, but not up to date with recent OS libraries.
- Bug was filed, a single on topic remark including a temporary workaround does not constitute flooding.
It is clear that you are well aware of that, or you wouldn't have ranted anonymously.
nvidia should concentrate on their main product, graphics cards, and better them, instead of bickering about another company's different product line, and trying to encroach into it. they got their ass whopped by ati's latest release, yet they are there just criticizing intel.
Read radical news here
i love all these comments suggesting ati/intel/nvidia are superior because ati/intel/nvidia has better Linux drivers/support. LOLOLOL! like anyone cares at these companies? they support linux because the linux 'community', while small, is quite loud when they feel spurned and could have influence on purchases by non-techie friends. Dell provides a linux option because it makes them look COOL to geeks. If they sell a few more laptops, great, but they could drop it tomorrow and not notice. It's about appearances...
oh and i love these comments when coupled with "i do my gaming on windows". that being the case, why care about linux performance?
don't get me wrong, i loves me some Ubuntu. However, I just don't think it's arrived. Not in the sense that it is an important factor in hardware design for mainstream tech companies. more of an afterthought...
Be fair to your 9250 and 4870. The 9250 has a dedicated 2D graphics stage, which (while neutered etc. etc.) has to compete with a software-defined and 3D-pipelined 2D display engine in the 4870. The silicon beats the software, as expected.
the driver department of ati really needs a revamp.
Read radical news here