5800U was an overambitious and overhyped part that did not follow the DX9 spec to the letter. It tried to use new, hot from the factory (pun intended) DDR2. The result is a die-shrink, massive clocked Ti4x00 with psudo DX9 support and dumb driver tricks so their penismark scores would match their ATI counterparts. Nvidia eventually recovered from this mishap with the NV40.

Nope, I've seen more than a few pics showing 16x AA. (A recent [unexceptional] FX:U review, within the past week IIRC, showed a 16x nV pic next to a 6x ATi pic, both of 3DM03 GT1, and ATi's looked better--likely because of gamma correction, as an ATi driver dev pointed out to me.)

It's also interesting/disturbing to note that nV's AA actually _removes_ some clouds.

Here we go: http://www.vr-zone.com/reviews/NVIDIA/FX5800U/page4.htm

Obviously, it's tough to tell from such tiny shots, but the wings of the foreground plane look smoother in the ATi pic, probably due to gamma-correction.

Damage, your review was, as usual, a pleasure to read. I particularly liked the extensive screenshot comparisons. (The Serious Sam numbers are very interesting, and I wonder if that game is very dependent on vertex shaders, as the Radeon 9000 Pro, with its shader borrowed from R300, seems to perform much better than the 8500 on SS. Or perhaps the 9000 is an anomaly, shader performance isn't that important, and SS just likes a 500MHz 4x2 card better than a 380MHz 8x1, which is very reasonable.) I have a few questions, though, particularly since nVidia so greatly stressed the "Cinematic" aspect of their new architecture:

I don't think the FX is using FP16 in 3DM03, I think they're using INT. B3D had a recent thread where an FX user posted test numbers, and there was no difference between FP16 and FP32, whereas using INT (12-bit) resulted in a 3-4x boost.

I guess you checked out the MIP-maps in Q3 very well, as evident by your screenshots, but did you verify equal LOD? I'm still troubled by mboeller's post here: http://www.beyond3d.com/forum/viewtopic.php?t=5074&postdays=0&posto... Pity I can't read German, so I can't fully understand what the author is writing, but the pictures seem clear. nV seems to have lowered the quality of the LOD (blurrier textures), thus boosting their framerate. Something seems fishy, but I don't know if it's the site or the drivers in question.

I think you should have noted that nVidia switched their AF terminology from App/Bal/Aggr in the 42.xx's to App/Qual/Perf in the 43.45, specifically to invite comparisons to ATi's Qual/Perf. You note that ATi's Qual uses trilinear filtering, and you note that nV's "Qual" doesn't have MIP-map transitions as smooth as tri, but you don't seem to state clearly that nV isn't performing tri when it uses Bal/"Qual"--it's using a mix of bi and tri (meaning, only rough transitions at the intersection of MIP-map boundaries, not smooth transitions across the whole MIP-map as with tri). True, there are other trade-offs with ATi's AF, in that it's not full-sample at all angles, which may be important with flight-sims; but for the majority of FPS's, ATi should offer superior sampling on most surfaces. It's a toss-up, I think, but the bi vs. tri issue is important. 3DVelocity's review also showed how nV's AF is pretty terrible in certain racing sims, so there may be more problems on non-standard benchmark games.

While we're on the topic of IQ, I think you were remiss not to delve deeper into the differences between nV's and ATi's AA. ATi's is clearly superior because it uses a rotated-grid and employs gamma correction, whereas nV's "IntelliSample" (sounds like a sea of computing units, to me :P ) uses ordered-grid for their standard modes (read: the ones users will unknowingly compare directly to ATi's) and no gamma correction at all. You really should have used nV's 4xS, which is rotated-grid, to compare to ATi's 4x.

Anyway, those are clearly more in-depth, investigative issues, and ones I hope you look into once the rumored upcoming WHQL Det 50's are released in a few weeks. Wring all you can out of that $600 museum piece! ;)

(Lump me in the category of ppl who nod at TR's reviews.)

/me just simply shakes his head at tech-report...

As AG15 said, from what Beyond3D have shown, ONLY the application setting uses trilinear filtering, and is one of the reasons why the GFX looks half decent in this review.

This is AG #15 (who is not AG #27)

All the reader can tell is that there is some mip map blending going on. While that's prettier than no blending when you have colored mip map levels on, the question is whether that matters for solving the problem of mip map boundaries in motion. However, in your own comments, you've already said it does not. It is good to note that, but that was one sentence, non-highlighted, among many pictures...you then proceeded to silently compare what you know is not trilinear with what you know is, when directly comparable trilinear is available to you.

I don't think there is a difficulty in equivalent comparison: trilinear with no aniso is directly comparable with the 9700 in "Quality" and the GF FX in "Application". Your non aniso benchmark results are completely misleading.

As for your aniso tests, you have a point, but let me propose that 9700 in 16x(a)P versus GF FX in 8x(n)Q seems a more suitable comparison...both are better than 8x bilinear (and you could make observations about how much better, in what way, and in what circumstances). As you say, the angle issue is a factor, but trilinear versus a bilinear blending that doesn't remove mip map boundary issues seems worse. It is because the Balanced method does not appear to do a good job of removing mip map boundaries (but does do a good job of removing performance hit, is used even when not using aniso filtering and trilinear is asked for, and happens to look pretty in colored mip map screen shots) that I don't think it should be compared to trilinear..it looks like a reviewer focused benchmark booster. What, you want ATI to be prompted to specify "Performance" as default because reviewers don't take the time to analyze these things? You just benched in default despite your observations...atleast put some big bold letters pointing out that the benchmark results have this issue.

Already people think the GF FX is leading widely in Quake III scores, for example, due to some mysterious driver excellence. That leads to false expectations of the product and improvements to come in other games, etc., when it is just that the simple demands of the game allow not using trilinear to offer significant performance gains.

BTW, Beyond3D did have big bold letters for the issue, and in their 5600 review from today, used Application for the non aniso tests.

Also BTW, if I'd disagreed with the people who said it was a good review (other than this glaring and extremely common problem), I'd have mentioned it.

BTW 3, substitute 9700 with 9800 as appropriate. :P

Off to AG land for another 6 hours I guess.

I think #11 is right about the image quality tests in 3DMark03. The 43.00 drivers show frame 1799 and all the others are frame 1779, according to the 3DMark03 table at the bottom of each screen. After alt+tabbing between these it's obvious that it's not the same frame. Or am I missing something here?

Anyways, good review.

So now ATI has the big name for decent drivers and Nvidia doesn't? this is all one big mess. (wow.... ATI has come far)

I'm just sitting back and relaxing I don't want to buy a video card right now - nothing will REALLY push current cards......

I mean things suddenly clicked with me reading that review..... it's like.... I've just seen the light..
(explanation below)

I have NEVER been a fan of AA or AF - I don't think it add's that much to the experience... but if I could get it for "free" I'd take it

and HELL according to the review anything faster than a ti4600 (a R9700 non pro for like just over 200$) seems to be able to run my choice resolution of 1024x768 AND with all the AA and AF I can throw at it and still get over 60fps average in most of those benchmarks!

As long as I've got 1024x768, high detail and 32bit - I'm happy,.... but AA and AF for free AND on an "old" 6+ month card AND 60-100fps with the R9700 non pro.. I'm like wow......
yes, I realise the review didn't review the r9700 non pro, however I just subtracted about 15% from the R9700pro scores

Definately cool stuff.... good time to be in the market for a video card.... :)

Wow, downhill spiral. Did you really take my comments with so much hostility that you felt such hostility in return was in order? Which comments among the "you have a point" and "BTW, if I'd disagreed with the people who said it was a good review (other than this glaring and extremely common problem), I'd have mentioned it" gave you the impression of personal attack?

I tried to use bold to emphasize, though you seem to take it as an offense. I'm sorry, I wasn't aware it would appear so thick and bright as to appear to be shouting.
Your taking the opportunity to make a mocking commentary was disappointing.

I was offering criticism where I felt it was warranted.

I had thought you analyzed the mip map boundaries in motion. If not, the observations that state Balanced/Quality mode mip map issues remain informal observations (like this: http://www.beyond3d.com/forum/viewtopic.php?t=4772 ), whereas I thought a review had finally discussed and contrasted the subject in detail. My mistake.

Some further comments:

I am already aware that mip map boundaries are hard to see in screenshots.

Beyond3D does indeed say that the nv30 only does Trilinear with Application mode. They discuss their nv30 article findings and the actions they are taking for their recent review here:
http://www.beyond3d.com/previews/nvidia/nv31/index.php?p=4

This issue wasn't one of being "harder on the GF FX", but of misrepresentation. Since most sites do exactly what you have done, benchmark the defaults as provided by the drivers for comparison as if they are equivalent because they are the defaults, or for being labelled the same, it does seem to me to be a consistent and significant issue. It also seems to me an issue directly intended by nVidia by offering Trilinear only in "Application" mode, and renaming Balanced and Aggressive as they intend them to be benchmarked against the 9700's settings.
Therefore, I do view them "getting away" with that nearly universally as significant. I understand that you disagree, but I do not think my opinion warrants disparagment, nor do I think I'm magnifying something insignificant to a "monumental" degree as it is giving a tangible increase to GF FX benchmark figures, and it does lend itself to expectations of performance being "fixed" to match the higher results for other applications.

On a parting note, I did not say you thought you were flawless...if I thought you'd believed that, why would I have posted? I am glad that aside from the verbal sparring you did take my input on board, and I just wish criticism of this issue could have been taken other than personally.

In all seriousness, that was the best of the Geforce FX reviews that I have read. You think you got enough shots of Dawn on the front page? =)

"Other NVIDIA partners have cooked up alternative cooler designs for the FX 5800 Ultra, but most cards will probably be similar to this one"
Well i have a Leadteak 5800 Ultra, and it's cooler solution is not the same,
no annoying sound on my card, and only takes one pci slot.

Excellent review. Worth the wait.
Best line it? None, its in the comments. (#46 to be exact).

I never claimed to be the pope of graphics reviews.

Even as a Catholic, I found that quite funny.

So basically Damage spent $560 some odd dollars on a vid card everyone knew was too little, too late.

Damn shame that Nvidia screwed up with the NV30. But I just hope ATI and Nvidia and Matrox and BitBoys Oy will continue to push the designs harder and faster so it benifits you, me, and my left big toe. And damnit... they better start getting cheaper. I refuse to buy a vid card that's $400+ that's loud and annoying. At that price they better include some midget to get in my computer and blow on the card to keep it cool.

I can see what the point of nvidia's performance AF mode is. As you can see in the screenies the LOD is not any better with 8xAF on than with no AF and better filtering. I have a Radeon 8500 and I know that many games don't look too good without trilinear filtering with the AF.

Looks like Damage could use a pair of these:
http://www.bose.com/noise_reduction/personal/qc_headset/index.html

(They actually work; I was able to try a pair in our noisy computer room this weekend.)

1) I've heard rumor that the retail Dustbuster is slightly quieter than pre-release Dustbusters. Any idea if that's true?

2) Comanche still doesn't seem like a very useful benchmark to me

3) Interesting, Damage's writeup made the FX look better than others I've seen. My guess is because most of the game tests were only at 4x AA instead of 8x like other sites have used. Not saying that's good or bad, it's just a new take on things. :)

4) Damage, wanna try removing the Dustbuster, and time how long it takes the FX to melt itself? That would be pretty cool.

ER

From page 5 of the article:
" NV30's pixel shaders can execute shader programs with as many as 1024 instructions in a single rendering pass with dynamic branching and looping.y]

The NV30 has no such dynamic branching and looping inside the pixel shader. IIRC, it can do at most static looping and has no branching capabilities at all except to render all possibilities and pick the correct one. Dynamic branching and looping is a major feature of upcoming PS3.0 hardware such as R400 and NV4x.

IMO - The GFFx 5800 Ultra would not have stood a chances against the R97Pro if it was clock for clock.

Nice review. I know Quake III is an old game, but I must say that I'm impressed with the GFFX's performance on it. Overall though, I prefer the Radeon 9800 Pro by a long way.

Umm....Scott, did you mix up the pic's comparing the image quality of the 43.00 and 43.45's because the one labeled as being from the 43.00's look a lot worse to me than the one from the 43.45's with some nasty artifacts underneath the butterfly. Are you saying nVidia improved their driver image quality with the newer drivers? I'm confused.

Haha... Nice Steel.

Good review.

From the conclusion:
""This would have been a great product had it arrived six months earlier at this same clock speed with lower heat levels, a more reasonable cooler, and lower prices. "
lol. if...if...if....ifff

'And if a frog had wings, he wouldn't bump his ass a'hoppin.....or my name aint Nathan Arizona!!'

One good thing (IMO) in the design of this card is the choice of using thermal management control. (Probably) Nvidia was forced to do this and is a shame that both Nvidia and Ati do not use this on a regular basis, at least on their high-end cards. And take into account that they already have the technology from their mobile parts.

Jean

You think you got enough shots of Dawn on the front page?

Hmm... the third one seems to suffer from some really bad rendering artifacts though. Texture compression issues, maybe? :D

Would have been nice if any useful number had ever hit retail.

Oh well, NV swears NV35 will be out soon, and will be the 9700 killer NV30 was going to be.

What would a 97/9800 do if it were overclocked to match the 500 MHz of the 5800? Yea, I know it's like comparing XP's to P4's, but we do that anyway.

My Sapphire 9700 just seems like a better and better buy...