POLL: nVidia's Silence on GT300

[bryanW1995]

Originally posted by: akugami

Originally posted by: Keysplayr
Can you guys define, "late to the party" for me please? I can understand if Nvidia announced a GT300 launch in June, July or August and it's still not here yet. But there have been no such announcements by them at all. You are only considering GT300 late because ATI is launching (pre-launching) R8xx soon. And last time I checked, there is no rule saying both companies have to launch at the same time, and if one does, and the other doesn't, the other is late.

The only thing you can accurately construde from current events is, ATI is launching R8xx before Nvidia is launching GT300. This doesn't make GT300 late. When we get an official launch date for GT300, and that time comes and goes, THEN you can call GT300 late.

I'd call it (and this can apply to product lines from either ATI or nVidia) late if it is released well over a month later than whatever product it is competing against. For instance, if the GT300 was released 6-8 weeks after the Radeon 5xx0 series then I'd call it late.

A 4 week window of opportunity is great for ATI but I don't think it will make a significant dent unless ATI's new GPU's are better than nVidia's new GPU's. However, a 6-8 window (or more), would be pretty substantial. Keep in mind I'm not in any way shape or form saying the Gt300 will be that late. All of us really have no clue. Just illustrating an example. Another is how the X1800 was expected to release before whatever nVidia's new GPU was at the time. Because of bugs, the X1800 was released well after it's competing GPU. The X1800 wasn't a bad GPU but being late certainly did hurt ATI.

One of the reasons (I think) AMD is able to release R8xx so quickly, is that R8xx (I think) is basically 2 R770's in one chip. Anyone who has seen the schematic photo for Cypress:

Cypress Architecture Schematic

You can see that there isn't one big core. It looks to me like they took 2 40nm 4770's (with the exception of 800sp instead of 640) and "glued" them.
"Glued" being a crude description, I'm sure there is more elegance to the design than that.

Anyway, A 4770 had a 128-bit memory interface. You can see each "core" in the schematice has 2 64-bit registers for the 256-bit total between both "cores". Also explains the doubling of everything. 800>1600 sps, 16 to 32 ROPs, 40 to 80 TMU's. This could also have been a contributing factor to the 4770 shortage for a while. Dedicating most of it's 40nm cores for Cypress, but I don't have any data to back this up. Grain of salt.

I understand what you're saying but I don't think it will be that big of an issue if they actually did so. While it's not the most elegant or efficient solution it can be made to work. Intel essentially did the same thing with the Pentium D by slapping two P4's together. This staved off AMD's advance long enough for them to come up with a "true" dual core CPU. With the massive parallelism of GPU's I think "duct taping" two older (though updated) GPU cores might not be as bad as it sounds. There will be a performance hit for overhead but it should provide updated performance. Bottom line is performance, not elegance.

Also, I don't think we can make a claim that the GT300 is "new" while the Radeon 5xx0 series is "derivative" until we see more of the GT300 and Radeon 5xx0 and what each does differently or better than it's respective predecessor from a hardware standpoint. All of that will likely be dissected by January '10 but for now, we simply can't say. Too little information.

funny how amd's old argument against intel's q6600 is now being used against them...

"but, but, q6600 is just two e6600's slapped together with duct tape, glue, and paper clips" - amd fanboi

"it's also about 17 bajillion times faster than your piece of shit monolithic quad core that is later than hell and has to be slowed down 10% via a bios update to even work" - pat gelsinger

"um, but ours looks cooler in a diagram" - amd fanboi

 

[Obsoleet]

I think MrK6 is spot on. And Nvidia can compete on price.. until Windows 7 launch day. Even with no DX11 games, Win7 is a big deal (much bigger than any previous Windows release) and people will want DX11 hardware support on a card that runs cooler, is the same price or cheaper than NV's large dual card solutions, and has no SLI driver issues to get to that performance.

If and when Nvidia catches up to the 5870, ATI will have multiple Crossfire solutions ready (single card, dual slot pcb and dual pcie) to take the crown again. ATI can undercut NV pricing as their process, and design, is more mature.

This is all assuming best case scenario happens for Nvidia from today onward- their card isn't too late to market, they have exceptional drivers for their new architecture ready, and it's not poorly engineered (it could be another NV30). Barring all those very possible factors from happening, ATI still has the firepower to outgun and undercut them.


What will be resorted to is what has already has been by Nvidia, marketing proprietary solutions like 3d vision full tilt, using their niches to downplay slower, more expensive, outdated designs. Since 3d pc gaming began, no one has succeeded with proprietary solutions besides 3dfx and that was temporary. Without Microsoft, forget it. NV's proprietary solutions are dead already and not worth discussing at all.

If NV defeats all my predictions, which would be amazing, Intel is still more than likely going to swoop in to finish them off with Larrabee. A dual benefit to Intel, because they have no need for Nvidia, but all the need in the world to not kill off AMD.

 

[Barfo]

Originally posted by: Obsoleet
If NV defeats all my predictions, which would be amazing, Intel is still more than likely going to swoop in to finish them off with Larrabee. A dual benefit to Intel, because they have no need for Nvidia, but all the need in the world to not kill off AMD.

You speak as if this generation will determine whether or not Nvidia stays on business or not. Even if they release another NV30 (which I think they won't) they're far from finished, me thinks.

 

[taltamir]

nvidia released products at a certain MSRP.
AMD LATER released similar product at half the MSRP.
nVidia adjusted prices... yet for some reason some people have decided that this means they are incapable to compete or catch up. what gives? When it comes time to buy, so far nvidia products seem to more often than not be the better deal.

 

[Barfo]

Originally posted by: taltamir
nvidia released products at a certain MSRP.
AMD LATER released similar product at half the MSRP.
nVidia adjusted prices... yet for some reason some people have decided that this means they are incapable to compete or catch up. what gives? When it comes time to buy, so far nvidia products seem to more often than not be the better deal.

I was under the impression ATI is still the best value under most scenarios, even with Nvidia price cuts.

 

[taltamir]

Originally posted by: Barfo

Originally posted by: taltamir
nvidia released products at a certain MSRP.
AMD LATER released similar product at half the MSRP.
nVidia adjusted prices... yet for some reason some people have decided that this means they are incapable to compete or catch up. what gives? When it comes time to buy, so far nvidia products seem to more often than not be the better deal.

I was under the impression ATI is still the best value under most scenarios, even with Nvidia price cuts.

If you look at MSRP; or maybe just at newegg as if no other etailers exist.
Most etailers don't sell at msrp. selling below or above it.

 

[alyarb]

that's true, but the 4850 has the 9800 GT beat in value, the 4870 1gb has the GTX 260/216 beat in value, and the 4890 has the GTX 275 beat in value as well. unless i'm missing something.

 

[taltamir]

Originally posted by: alyarb
that's true, but the 4850 has the 9800 GT beat in value, the 4870 1gb has the GTX 260/216 beat in value, and the 4890 has the GTX 275 beat in value as well. unless i'm missing something.

the 4850 does indeed beat 9800GT in PERFORMANCE. The others, not so much. different games play better on each. And the difference is negligible anyways.

But they do not beat them in VALUE if you accept what I said to be true. Only if the MSRP is king do they beat the nvidia cards in value. aka. Who is the better VALUE purchase depends on the actual price, which differs.

 

[alyarb]

MSRP or not, i can't find any G200 cards priced below $150/160 which is where the RV770s are.

 

[happy medium]

A 8800gtx has the 4850 beat in value because it's 3/4 years old and is almost as fast, so who needed a 4850. The 9800gt is also 3/4 years old and everybody and there mother had/has a 8800/9800gt. Just because a company can finally catch up to anothers technology 2/3 years later and beat there prices dosen't mean that they are a better value. It shows they have to lower there prices to gain a little market share because of prior poor slow uncompetative products (2900xt/pro,3850,3870). Nvidia charges higher prices cause they can and make money doing it. Why? because there launched products are always faster and become popular. 4870 1gb and the gtx260 are very competative price wise. What's the difference 5$? The 4890 was just released 5 months ago? Everyone already had a gtx280/285, 4870 1gb, so who really needed it? The speed of the 4890 was released 2 years ago with the gtx280. So after 2 years they made a card cheaper and as fast.
I'm no fanboy but AMD hasn't exactly been doing well latley. They seem to be followers more then innovators. Don't get me wrong, I hope they make good products so I don't have to spend 400$ on a gtx360.

 

[alcoholbob]

Win by caps lock.

 

[dguy6789]

You could apply the same argument to the GTX 295. It took forever to come out, was way more expensive(than the 4870x2) and was faster by a tiny amount at most(was slower in plenty of tests too, just not the majority), yet people considered it a "win". Next is that the 4850x2(which very conveniently gets left out of discussions) was always as fast or faster and cheaper everywhere than the GTX280 and GTX285. 4870 was always cheaper than the GTX 260 at almost every store, not just Newegg. 4890 was also cheaper than the GTX275 at every store. Who cares if it took the 4850 however long to surpass the 8800GTX? That time alone is not a problem since the price did it justice. When the 4850 came out, it was faster than everything Nvidia had at the same price or lower. There's no bias, these are just simple facts.

There can't be anyone who has been an enthusiast following the GT200 and RV770 product lines without bias that wouldn't say the RV770 based products have consistently been the better value if you look at price vs performance. I don't see how it's even a debate. I fully expect people to reply to this and say "but but the GTX 295 is teh fastest so the whole RV770 line is a failure!!111" even though I already covered that.

 

[thilanliyan]

Originally posted by: taltamir
When it comes time to buy, so far nvidia products seem to more often than not be the better deal.

Not here in Canada at least. At the time I was buying, the 4870 was the better deal price wise. Even now, a 4890 is usually cheaper than the GTX275 which arguably beats it and competes with the GTX285 in some cases.

 

[crisium]

I see consistently that the 4890 is cheaper than the 275, the 4870 than the 260, 4850 than the 250... how is Nvidia the better deal?

 

[alyarb]

somehow being first to market is relevant to buyers in 2009 even when the tech is 3 years old.

 

[taltamir]

Originally posted by: thilan29

Originally posted by: taltamir
When it comes time to buy, so far nvidia products seem to more often than not be the better deal.

Not here in Canada at least. At the time I was buying, the 4870 was the better deal price wise. Even now, a 4890 is usually cheaper than the GTX275 which arguably beats it and competes with the GTX285 in some cases.

true, in most markets outside the USA nvidia is grossly overpriced compared to AMD

 

[SlowSpyder]

Originally posted by: Crisium
I see consistently that the 4890 is cheaper than the 275, the 4870 than the 260, 4850 than the 250... how is Nvidia the better deal?

Not all that long ago there was a deal where the 4890 was on sale for under $150 (AR, Bing cashback). Obviously that's not the everyday price, but I barely see the GTX260 216 get that low when it's on sale.

 

[SlowSpyder]

Originally posted by: Keysplayr

Originally posted by: HurleyBird
Silence can be a good or a bad thing. In the case of G80, it was a very good thing, in terms of G200 40nm derivatives, it wasn't such a good thing. Probably more often a good thing than not.

In terms of graphics though, being significantly late to the party with a new architecture has never been a good thing, has it?

I think G300 will probably be launched in late Q4 at the earliest, and maybe sometime in Q2 if it becomes another GeforceFX or R600 fiasco.

In terms of performance, 10-20% faster than HD 5870 is probably a good starting point, but since it is a significantly new design it could really be anywhere from -25% to +50%. There's really just too much unknown right now.

Can you guys define, "late to the party" for me please? I can understand if Nvidia announced a GT300 launch in June, July or August and it's still not here yet. But there have been no such announcements by them at all. You are only considering GT300 late because ATI is launching (pre-launching) R8xx soon. And last time I checked, there is no rule saying both companies have to launch at the same time, and if one does, and the other doesn't, the other is late.

The only thing you can accurately construde from current events is, ATI is launching R8xx before Nvidia is launching GT300. This doesn't make GT300 late. When we get an official launch date for GT300, and that time comes and goes, THEN you can call GT300 late.

One of the reasons (I think) AMD is able to release R8xx so quickly, is that R8xx (I think) is basically 2 R770's in one chip. Anyone who has seen the schematic photo for Cypress:

Cypress Architecture Schematic

You can see that there isn't one big core. It looks to me like they took 2 40nm 4770's (with the exception of 800sp instead of 640) and "glued" them.
"Glued" being a crude description, I'm sure there is more elegance to the design than that.

Anyway, A 4770 had a 128-bit memory interface. You can see each "core" in the schematice has 2 64-bit registers for the 256-bit total between both "cores". Also explains the doubling of everything. 800>1600 sps, 16 to 32 ROPs, 40 to 80 TMU's. This could also have been a contributing factor to the 4770 shortage for a while. Dedicating most of it's 40nm cores for Cypress, but I don't have any data to back this up. Grain of salt.

So, at first glance, and if this schematic pic is accurate (unknown), it would seem that is exactly what AMD has done. Joined 2 800sp 4770's together, with other enhancements such as DX11 compliance, improved power circuitry, Eyefinity hardware. Sure, it can be argued that this isn't the case, but that's sure what it looks like to me. It could turn out that this schematic is not truly representative of the actual x-ray shot of the die. Anyone have a link to an actual die shot?

I'm going to be open minded about this and consider all data, but that's all I see right now.

Conversely, Nvidia is releasing an entirely new architecture from the ground up according to leaks and rumors (we will have to see).
It isn't just a die shrink and doubling of GT200 tech AFAIK.

So, late to the party might just be a party Nvidia never meant to attend. They have their own schedule as AMD has theirs.

"Late to the party." Well, Nvidia may not behind their own launch schedule, but I think it's safe to say if you are a GPU manufacturer, and your competitor was about to release a product that runs on a more advanced manufacturing tech which allows for them to create a product that has better performance at a lower price point then your current product line up, you'll want to get something out to answer them sooner than later. Not to mention that they'll have DX11 support which may be of some use in the near future, and definitely will be of use down the road, and your products can't run it at all, again I'd think you'd want to get something out the door to counter them. So while they very well could be right on schedule, or even ahead of schedule regarding their own goals, in the consumer space it appears they are going to be 'late to the party'. Though with that being said, I think as the GeForce 5800 taught Nvidia and the Radeon 2900XT taught AMD, still getting to the party with something worth getting there with may very well be more important than just trying to get there as quick as you can.

When we get an official launch date for GT300, and that time comes and goes, THEN you can call GT300 late.

Nvidia should just declare a launch date of June 3rd 2013 for the GT300. Then when they get it out in 2010 rave about how early they are with their product launch.

As far as the gluing two 4770's together while Nvidia is building a brand new architecture, while AMD's approach may not be very revolutionary, it may not be a bad approach either. Wasn't the GTX280 little more than 2 9800GTX's worth of 'stuff'? You could also look at it as AMD has been more forward thinking by supporting DX10.1 since the 38x0 cards, getting a 'feeler' 40nm part out much earlier than Nvidia, and building hardware tesselation into their cards for some generations now. That line of thinking might explain why they are able to get a part out sooner than Nvidia as well.

 

[MrK6]

Originally posted by: taltamir
nvidia released products at a certain MSRP.
AMD LATER released similar product at half the MSRP.
nVidia adjusted prices... yet for some reason some people have decided that this means they are incapable to compete or catch up. what gives? When it comes time to buy, so far nvidia products seem to more often than not be the better deal.

Well, companies generally release products at a price they believe will be most profitable (on a sale curve). When they have to sell below this price, it obviously cuts into their profits (sometimes so much that there are none). I wonder how much money NVIDIA was making (or losing) due to the price/performance blow it took from the 4xxx series.

My general analysis of the GTX vs. 4xxx series has always been NVIDIA came out with a fast, improved product, and marketed at a price they thought would maximize their profits. AMD came out with a product that was almost as fast and cost 1/2-2/3 of the price. NVIDIA had to cut prices to remain competitive. However, I'll bet the GTX series was much more expensive to produce than was the 4xxx series, and that price war really but the squeeze on NVIDIA.

I'd always thought AMD's marketing plan of focusing on the mid-range and high-end with a scalable chip was pretty sharp on their part. Rather than go all out for the "performance crown," they stuck to smaller chips with better yields, cheaper board designs, and offered competitive performance and great prices. My question is it looks like this is how AMD has lined itself up for this coming generation. NVIDIA seems to be creating another monolithic/mammoth GPU. Do they have confidence it will work this time or are they slow to learn? I mean, how deep are their pockets if they want to keep selling at lower than ideal prices?

 

[Obsoleet]

Originally posted by: Barfo

Originally posted by: Obsoleet
If NV defeats all my predictions, which would be amazing, Intel is still more than likely going to swoop in to finish them off with Larrabee. A dual benefit to Intel, because they have no need for Nvidia, but all the need in the world to not kill off AMD.

You speak as if this generation will determine whether or not Nvidia stays on business or not. Even if they release another NV30 (which I think they won't) they're far from finished, me thinks.

AMD won't put Nvidia out of business, they'll simply defeat them this coming GPU launch. After that, Intel will be the ones who put them out of the standalone GPU business with Larrabee. It doesn't have to be fast, just fast enough and get wide market saturation which Intel can provide.

 

[alyarb]

you can't be serious; larrabee is the least likely architecture to succeed in D3D and there is absolutely no performance data available to support this or that outcome.

 

[s44]

Fanboys will be fanboys.

 

[s44]

Originally posted by: MrK6
However, I'll bet the GTX series was much more expensive to produce than was the 4xxx series, and that price war really but the squeeze on NVIDIA.

There's really no evidence of this, only assumptions. ATI relied heavily on GDDR5 for their memory bandwidth, and the eventual price drop on that surely helped them, but that doesn't mean their designs were significantly cheaper near launch.

 

[alyarb]

the G200 GPU was more expensive to produce and remains more expensive to produce to this day. The cards themselves are also more expensive to produce because of the wide memory systems they offer. RV770 was a smaller die and yields were a good deal higher both at launch and today, i just can't remember exactly how much higher they were. I remember G200 on 65nm being below 40%, however. The 4870 pricing at launch was due in part to the stir it caused and it generated a spike in demand for GDDR5 when we were in a shortage. The world's supply of GDDR5 has caught up with demand and prices have subsided as a result. TSMC 55GP is more mature and prices have subsided as a result.

 

[Keysplayr]

Originally posted by: alyarb
the G200 GPU was more expensive to produce and remains more expensive to produce to this day. The cards themselves are also more expensive to produce because of the wide memory systems they offer. RV770 was a smaller die and yields were a good deal higher both at launch and today, i just can't remember exactly how much higher they were. I remember G200 on 65nm being below 40%, however. The 4870 pricing at launch was due in part to the stir it caused and it generated a spike in demand for GDDR5 when we were in a shortage. The world's supply of GDDR5 has caught up with demand and prices have subsided as a result. TSMC 55GP is more mature and prices have subsided as a result.

We've never had any numbers to prove, or disprove this. As s44 stated, it's all assumption.
I'd agree though that the cards themselves are more complex and more costly to make, but then again, consider the volume. Anyway, until you can show AMD's and Nvidia's accounts payable statements and a BOM, it's hot air.