390X coming soon few weeks

Rizen said:
It sucks that the wait has been so long, but really I think the problem here is manufacturing processes. AMD is fabless now, and while we could argue over whether or not that was a good decision, the delays on 20nm really impacted both NVIDIA and AMD's road maps.
Click to expand...

But the 390 is still on 28 just like the titan and the 28 process is about as mature as it gets. Seems blaming it on manufacturing issues at this point is far less likely than "oops overestimated 290 demand due to assuming bitcoin bubble would last forever and over produced them to the point that our distribution centers let employees take whole pallets home so their kids can use them to build GPU forts because we don't have enough storage to keep them at the warehouse"

I mean since they've got to have some contractual minimum manufacturing level with their chip makers they're probably stockpiling 3xx parts as we speak so when they do finally launch chances are there will be no shortages.
 
shadow85 said:
Well fine then, there is no king of the hill coming anymore. It will just be a slower card than the titan x if u say so. Ill just go get 2x Titan X then
Click to expand...

Oh, show me where I said the Titan-x would be faster? I never said I knew anything about the performance of the 390x. I don't know what it is going to be like, neither does anyone else.

All I asked was for you to show me where AMD said what the performance would be? Or even show me something from AMD that says the name of the card is going to be called the king of hill?

You were saying that this card better be the fastest because of the way that AMD were claiming how good it was going to be an they would be shooting themselves in the foot if it isn't.

All I am pointing out is that AMD hasn't claimed anything yet, not the name of the card or what the performance is going to be like.
 
Rizen said:
It sucks that the wait has been so long, but really I think the problem here is manufacturing processes. AMD is fabless now, and while we could argue over whether or not that was a good decision, the delays on 20nm really impacted both NVIDIA and AMD's road maps.
Click to expand...

I highly doubt it has anything to do with manufacturing process at this stage, besides Gibbo on overclockers uk has said that it's because AMD are clearing out as much old stock as possible before releasing new cards. .
 
geez, more rumors...

lol

an overclocked titanX with half the memory and the same TDP for $599?

riiiggggghhhhhthtttt

..i want some of what those guys are smoking...
 
The Mac said:
geez, more rumors...

lol

an overclocked titanX with half the memory and the same TDP?

not a chance...
Click to expand...
Nvidia knows they'll need a $700-$800 part to compete with the 390X which is already 10%+ faster than the Titan X. They can save a bit of cash on the VRAM. Factory OC closes the gap in benchmarks -- or maybe passes the 390X, which is what they're hoping for.

For now they continue to milk early adopters with the X. Works out fine in the end.

None of this is surprising in the least.
 
we dont know that the 390x will be 10% over the titanx (well, amd/nvidia might)

If that rumor is true, they would never be able to sell a single additional TitanX
 
shad0w4life said:
That would entirely invalidate the Titan X AND the 980, you'd have to be a moron to buy the Titan X when you get better performance from a card $399 cheaper.
Click to expand...
Meh. The 780 Ti did this to the original Titan with 9 months inbetween. By the time the 980 Ti launches it will be virtually the same scenario.
This time AMD will be more competitive and their release schedule is pushed up relative to the Titan. Summer as opposed to Fall.

Nvidia releases expensive Titan; AMD destroys it 6+ months later; Nvidia obsoletes their own Titan with the Ti. History repeats itself.

The 980's price is going down and the Ti will fit somewhere between $500 and $800 depending how Fiji is priced.
 
^the difference though, was nVidia severely kneecapped the 780 Ti with only 3GB of vram, causing it to become worthless on some games even at 1080p (admittedly all due to beyond shitty optimization, but you get the point), so they very cleverly built in a "gotcha" catch.

If the 980 Ti really does come with 6GB, then the only reason to buy the Titan X would be for surround 4K gaming and that's it. Just seems way too generous on nVidia's part.

shad0w4life said:
That would entirely invalidate the Titan X AND the 980, you'd have to be a moron to buy the Titan X when you get better performance from a card $399 cheaper.
Click to expand...

b-b-but 12GB vram!

Yeah I agree, that rumor is so ridiculous it's not even worth entertaining right now.
 
n=1 said:
If the 980 Ti really does come with 6GB, then the only reason to buy the Titan X would be for surround 4K gaming and that's it. Just seems way too generous on nVidia's part.
Click to expand...
Nvidia has no choice but to be generous when they're competing with 8 GB Fiji's for the same price.
6 months is a long time. We will be living in a different world when September rolls around.

Horses with blinders, all of you.
 
That still leaves at least 5-8 months of waiting time in between before Pascal comes out, and what will they do with all the imperfect GM200 parts? Literally bin them?
 
Realistically, they need a part to slot between the 390x and the Titan X.

That is assuming the 390x performs less that the TitanX. The latest rumor being the 390x will be 20% faster than the 980.

If the 390x beats the TitanX, they wil need a fster part, so an oced X as a 980ti seems reasonable.

However, im not sure you really want to call it a 980ti as its not 980 silicon.

as a side note, the TitanX yields must be absimal, they are going to have to be pretty good yields to be price competative with the 390x
 
Last edited:
n=1 said:
That still leaves at least 5-8 months of waiting time in between before Pascal comes out, and what will they do with all the imperfect GM200 parts? Literally bin them?
Click to expand...

Rebrand them as the low end solution for DX12 when Pascal comes out.
 
Has that ever happened though? I can't remember the last time nVidia rebranded their big dies as mid-tier cards in the succeeding lineup.

And these big dies are just far too hot and power hungry to convert to mobile parts, and nVidia hasn't tried that again since the 480M debacle.
 
Digital Viper-X- said:
I doubt it, i think the 980TI will have less shaders than the Titan-X as well as 6GB, I don't see them cannibalizing the Titan-X this soon,.
Click to expand...

The gutted the last Titan and Titan-Z with the 780ti. The one constant in technology is that it is ever evolving. I can't wait to see what Pascal can do. Didn't Nvidia's CEO say 10x the performance of the the 900 / Titan X series of cards in 2016? That makes Titan X stillborn on day one in my book. I mean it's really freaking nice for today, but spending $1,000 for 1 year of service is a bit much for my tastes.
 
n=1 said:
Has that ever happened though? I can't remember the last time nVidia rebranded their big dies as mid-tier cards in the succeeding lineup.

And these big dies are just far too hot and power hungry to convert to mobile parts, and nVidia hasn't tried that again since the 480M debacle.
Click to expand...

680 became a 770 I think and the 670 became a 760. I mean they beefed up some of the tech attached to them, and made sure that SLi didn't work with the older cards. But they were effectively the same cards. I might be slightly off on the model numbers though. Sure that someone can correct me. :)
 
cageymaru said:
The gutted the last Titan and Titan-Z with the 780ti. The one constant in technology is that it is ever evolving. I can't wait to see what Pascal can do. Didn't Nvidia's CEO say 10x the performance of the the 900 / Titan X series of cards in 2016? That makes Titan X stillborn on day one in my book. I mean it's really freaking nice for today, but spending $1,000 for 1 year of service is a bit much for my tastes.
Click to expand...

10x in what though? compute?

Anyway, they Did it with the titan / 780TI, which is why I don't see it happening again, the 780ti came out of nowhere, maybe as a knee-jerk response to AMDs 290/290x.

Anyhoo I guess we will see shortly, Also the 780ti had no DP/FP64 performance to speak of, so the Titan still had ( and still has) a useful place in the market, where as the Titan X would like you said, be stillborn.
 
cageymaru said:
680 became a 770 I think and the 670 became a 760. I mean they beefed up some of the tech attached to them, and made sure that SLi didn't work with the older cards. But they were effectively the same cards. I might be slightly off on the model numbers though. Sure that someone can correct me. :)
Click to expand...

No you're correct in what you said, but notice how I said "big dies". GK104 was the mid-sized brother of the GK110 big die.

What I'm saying is if nVidia holds on to these GM200 big dies with defects and rebrands them in the upcoming series, that would definitely be a first for them.
 
Digital Viper-X- said:
10x in what though? compute?

Anyway, they Did it with the titan / 780TI, which is why I don't see it happening again, the 780ti came out of nowhere, maybe as a knee-jerk response to AMDs 290/290x.

Anyhoo I guess we will see shortly, Also the 780ti had no DP/FP64 performance to speak of, so the Titan still had ( and still has) a useful place in the market, where as the Titan X would like you said, be stillborn.
Click to expand...

Prime_1 linked this in the Nvidia forum.
http://hardforum.com/showthread.php?t=1855749

Bullets near the top mention it, but honestly since I'm not in the market for a Titan X, I paid little attention to the presentation.
http://blogs.nvidia.com/blog/2015/03/16/live-gtc/
 
cageymaru said:
Prime_1 linked this in the Nvidia forum.
http://hardforum.com/showthread.php?t=1855749

Bullets near the top mention it, but honestly since I'm not in the market for a Titan X, I paid little attention to the presentation.
http://blogs.nvidia.com/blog/2015/03/16/live-gtc/
Click to expand...

I saw the presentation, and with some digging, we get to the source of the "10x" claim, and what it pertains to, it's not to gaming performance, that's for sure.


The y-axis shows the potential throughput in arithmetic operations/second. The x-axis is “operational intensity” which is the number of operations applied to each data value (in units of operations per byte). The intensity is much lower for sparse operations – e.g. sparse matrix multiply typically involves only a multiply and add for each input datum, while dense matrix multiply uses each datum many times. The horizontal lines reflect the maximum ALU throughput for each type of processor (the graph is drawn for Intel i7 and NVIDIA GeForce GTX 680 processors). GPUs have much higher ALU throughput since the GPU chip area is almost entirely ALU. For dense matrix multiply, GPUs are10x faster thanks to this higher computing area.

The diagonal lines reflect memory bandwidth. Since bandwidth is flow in bytes/second it defines a linear relationship between the x-axis (flops/byte) and the y-axis (in flops/sec). A less well-known feature of GPUs is their higher main-memory bandwidth. This leads to a (potential) 10x gap in sparse matrix operations, which are the most important for many machine learning tasks. CuSparse achieves this ceiling for typical scientific data, but we found it was less well fit to very sparse data (text, web logs etc.). We wrote our own sparse kernels and were able to get them close to the roofline limits over a full range of sparseness. These kernels form the basis for the high throughput in most of BIDMach’s algorithms.
Click to expand...

Source, NV Devblogs
 
Good grief that 10x thing needs to DIAF, just read Lord's post for the full explanation, but in short:

10x assuming 8 way instead of 4 way GPU array using FP16 for specific compute scenarios. Not a goddamn thing at all to do with gaming performance.
 
Nvidia says their cards are 10x faster: "I can't wait to buy a Pascal GPU and multiply my frame rates ten-fold! Thanks Nvidia!"
AMD says their cards are 10x faster: "Sounds like marketing hype, I'll believe it when I see it."

Welcome to the internet.
Nvidia doesn't even understand their own VRAM bandwidth, as if they know how fast Pascal will be over a year in advance.
 
Yep sounds about right. There's just something about that cognitive bias that rubs me the very wrong way, which is why I'm pretty disgusted with the nVidia fanbase in general.
 
n=1 said:
No you're correct in what you said, but notice how I said "big dies". GK104 was the mid-sized brother of the GK110 big die.

What I'm saying is if nVidia holds on to these GM200 big dies with defects and rebrands them in the upcoming series, that would definitely be a first for them.
Click to expand...

Uuuuh the 780 and the 780Ti are BOTH binned and rebranded big-die chips. The Titan came out durring the 600 series, and the 780 was essentially a rebranded Titan, the 770 was a rebranded 680, the 760 was a rebranded 670.

Both companies re-brand. It's a thing.
 
Yes, but both were sold (and priced) as high end parts. It's also debatable whether the vanilla Titan belongs in the 600 or 700 series. I think it's equally arguable the vanilla Titan marked the beginning of the 700 series, and served as its first release. In that sense, the Titan X could either be seen as an extension of the 900 series, or the beginning of the 1000 series, depending on what the next GM200 card will be called.

Regardless, if you follow the paper trail I was responding to this comment:

cageymaru said:
Rebrand them as the low end solution for DX12 when Pascal comes out.
Click to expand...

To which I said:

n=1 said:
Has that ever happened though? I can't remember the last time nVidia rebranded their big dies as mid-tier cards in the succeeding lineup.
Click to expand...

That was the context of me saying it would be a first for nVidia.
 
n=1 said:
Yes, but both were sold (and priced) as high end parts. It's also debatable whether the vanilla Titan belongs in the 600 or 700 series. I think it's equally arguable the vanilla Titan marked the beginning of the 700 series, and served as its first release. In that sense, the Titan X could either be seen as an extension of the 900 series, or the beginning of the 1000 series, depending on what the next GM200 card will be called.

Regardless, if you follow the paper trail I was responding to this comment:



To which I said:



That was the context of me saying it would be a first for nVidia.
Click to expand...

680-770
480-570
 
Again, 680-770 were both based on GK104, a mid-sized die.

480 was GF100, 580 was GF110, a more refined version of GF100, so it wasn't a straight rebrand.

And goddamn we've gone really OT.
 
n=1 said:
Again, 680-770 were both based on GK104, a mid-sized die.

480 was GF100, 580 was GF110, a more refined version of GF100, so it wasn't a straight rebrand.

And goddamn we've gone really OT.
Click to expand...

What would we say about 970? Is it 780? 780 is still a good card. So if 970 delivers the same performance as 780 with slight refinement, it should be a good card for 1440P resolution?
 
290 series only option for 1440 and up.
Nvidias only viable solution cost two arms and a leg and your first born.
 
So when the 390X comes out, the 980ti will be released not 2 months after which is full maxwell with 6GB and faster clocks than a Titan X and ~$300 less expensive. What is AMD gonna do then, assuming the 390X is even faster than a Titan X it's going to most likely get beaten by the 980ti with a lower price tag.

If all that is true, could that spell the doom for Red Team?
 
shadow85 said:
So when the 390X comes out, the 980ti will be released not 2 months after which is full maxwell with 6GB and faster clocks than a Titan X and ~$300 less expensive. What is AMD gonna do then, assuming the 390X is even faster than a Titan X it's going to most likely get beaten by the 980ti with a lower price tag.

If all that is true, could that spell the doom for Red Team?
Click to expand...

If thats true, Nvidia will end up killing the Titan X and pwn all Titan X buyers. Now there is a card called 980ti thats faster cheaper better.......

I don't think that extra 6GB will make any difference in performance.
 
shadow85 said:
So when the 390X comes out, the 980ti will be released not 2 months after which is full maxwell with 6GB and faster clocks than a Titan X and ~$300 less expensive. What is AMD gonna do then, assuming the 390X is even faster than a Titan X it's going to most likely get beaten by the 980ti with a lower price tag.

If all that is true, could that spell the doom for Red Team?
Click to expand...
You're looking at this backwards.
Nvidia wouldn't be releasing an overclocked Titan X for $800 unless they were provoked by AMD.

The 390X will pass the Titan X just like the original 290X vs Titan, only a few percent but everyone will call the 390X "The Titan X killer". Then a month later Nvidia will release the Titan X GHz Edition which passes the 390X by 5-10% and takes back the performance crown.

If that's not the case, then the 980 Ti has no reason to exist... Certainly not an overclocked Titan X for $300 less.

The 390X will be faster than the Titan X. Assuming the 980 Ti rumor is true, Nvidia just confirmed it for us. Or more specifically, Nvidia is genuinely worried the 390X will be faster than the Titan X.
 
-Dragon- said:
But the 390 is still on 28 just like the titan and the 28 process is about as mature as it gets. Seems blaming it on manufacturing issues at this point is far less likely than "oops overestimated 290 demand due to assuming bitcoin bubble would last forever and over produced them to the point that our distribution centers let employees take whole pallets home so their kids can use them to build GPU forts because we don't have enough storage to keep them at the warehouse"
Click to expand...
I didn't mean problems with 28nm maturity. What I meant was that GPU designs are roadmapped and built for years in advance, and both NVIDIA and AMD planned to be on 20nm already by now. So basically every GPU design we've seen from AMD and NVIDIA in the past couple of years has been a compromise due to 20nm not being available, and you can be sure that some features or improvements have been changed or dropped to accommodate this. My guess is that they had to rework something to produce Fiji on 28nm. Plus if the rumors are true, they switching to GlobalFoundries for producing Fiji, and it can be a long process to get another fab up and running on your GPU designs.
 
Wow. Am I the only one who see's how like the R300X series is to 3DFX Rampage?

Roy@AMD acted like info was coming soon on 300 series since October with his stupid little Churchill quotes. Stocks sunk at under $3 a share, CEO gets replaced 2 weeks before financials for the quarter ending last year, no one wants to really acquire them, Crossfire drivers aren't up to par on game launch day like Nvidia, and mean while back at the ranch; Nvidia keeps releasing cards! Actual fucking cards.

Look I am not saying the ship is sinking, but for fucks sake, look at all of what I posted. This is factual. This is supposed to be the company handling GPU development for a 3 gaming systems and they can't get a stock above $3 a share???? Their next big CPU is what? 3 years away IF they have the funding?

A good editorial piece would be "The State Of AMD". Because right now, they look exactly like 3DFX.
 
You must log in or register to reply here.
Back
Top