• We should now be fully online following an overnight outage. Apologies for any inconvenience, we do not expect there to be any further issues.

Pascal graphics card to launch at Computex 2016 and enter mass shipments in July

Page 3 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

tential

Diamond Member
May 13, 2008
7,348
642
121
Raja Koduri himself mentioned a few months advantage, so that implies ~3+ months ahead of NVIDIA. If DigiTimes is correct he is wrong.
A few months advantage does not imply 3+. A few by definition is "a small number". Go Google it for Christmas sake it even says as one of the Google dictionary synonyms to be "one or two".

So no, you're absolutely wrong. Sorry.

Wow, when asked for hard evidence it seems people really struggle to use quotes or links....
I guess hard evidence now means just throwing out wild accusations now.
 
Last edited:

AtenRa

Lifer
Feb 2, 2009
14,003
3,362
136
Raja Koduri himself mentioned a few months advantage, so that implies ~3+ months ahead of NVIDIA. If DigiTimes is correct he is wrong.

Im not saying he is right or wrong but a few months could be 2 months + 1 day to several months. But at the time he may was thinking of early Q3 vs late Q3.
 

MrTeal

Diamond Member
Dec 7, 2003
3,919
2,708
136
Im not saying he is right or wrong but a few months could be 2 months + 1 day to several months. But at the time he may was thinking of early Q3 vs late Q3.

We're already in early Q2, so if he wasn't thinking of launching early Q2 he'd better hurry.

You could still have a 2+ month gap with both estimates though. We've heard June for Polaris, but is June meant a hard launch at Computex, and nVidia's July mass shipment meant end of July with retail availability in the first week of August, that puts it at a few months.

I doubt that would happen, but you never know.
 

Adored

Senior member
Mar 24, 2016
256
1
16
Just use some logic to figure it out.

AMD showed Polaris 10 in December and GF went into mass production in February. Nvidia probably started P100 production on a very small allocation of wafers in Q3/Q4 last year, but there is no chance of anything else starting then.

Nvidia doesn't have an unlimited amount of wafers at TSMC, AMD does at GF. Nvidia will be putting much more into P100 than anything else because they pay time penalties for late delivery.

TSMC doubled production in March, at which point Nvidia would have been able to start production of their gaming GPUs. They have to be at least 1 month behind and depending on how many GPUs AMD got from the early risk production of Polaris, could be 3 or more, however AMD would likely have to stockpile those GPUs for a harder launch so they would effectively be 2 months ahead.

I say Polaris 11 at the end of May but weak availability until July. The issue as I mentioned was, they could all be going to Apple anyway.
 

AtenRa

Lifer
Feb 2, 2009
14,003
3,362
136
We're already in early Q2, so if he wasn't thinking of launching early Q2 he'd better hurry.

You could still have a 2+ month gap with both estimates though. We've heard June for Polaris, but is June meant a hard launch at Computex, and nVidia's July mass shipment meant end of July with retail availability in the first week of August, that puts it at a few months.

I doubt that would happen, but you never know.

yea i wanted to say early Q3 vs late Q3. And i agree we dont know if actual retail availability will be on release date or later.
 

Sweepr

Diamond Member
May 12, 2006
5,148
1,143
136
A few months advantage does not imply 3+. A few by definition is "a small number".

Doesn't look like 'a small number' of months advantage for AMD either, not if DigiTimes is remotely correct.

So no, you're absolutely wrong. Sorry.

GP100 in production right now and DigiTimes saying Pascal could launch earlier than Polaris, I find it funny to see how much this bothers you.

Go cry in the corner and stop making up stuff, I didn't throw any accusation here.
 
Last edited:

nvgpu

Senior member
Sep 12, 2014
629
202
81
http://www.anandtech.com/show/10075/early-exynos-8890-impressions

One observation I made today which was particularly concerning, was that both with the Snapdragon 820 LG G5 as well as the Exynos 8890 Galaxy S7 got considerably warm after running some heavy workloads. The fact that the Galaxy S7 touts having a heat-pipe thermal dissipation system is a quite worrying characteristic of the phone and should in no way be seen as a positive feature as it points to high power draw figures on the part of the SoC.

Polaris is built on the same bad Samsung 14LPP process and GloFo's track record is pretty much a joke in the industry, just ask AMD about Llano yields.
 

tential

Diamond Member
May 13, 2008
7,348
642
121
Doesn't look like 'a small number' of months advantage for AMD either, not if DigiTimes is remotely correct.



GP100 in production right now and DigiTimes saying Pascal could launch earlier than Polaris, I find it funny to see how much this bothers you.

Go cry in the corner and stop making up stuff, I didn't throw any accusation here.

Raja Koduri himself mentioned a few months advantage, so that implies ~3+ months ahead of NVIDIA. If DigiTimes is correct he is wrong.

XBrvmcK.png


You're the one who states that he is implying 3+ months, despite the definition of the word proving otherwise...

Also again, where is the quote from him saying this? Where is the hard evidence?
What did I make up?
 

tential

Diamond Member
May 13, 2008
7,348
642
121
lol, this is just pure gold. although kinda expected from a guy named after a company.

what's next ? red is a bad color so we shouldn't even look at it ?

Are you saying you have faith in Glo Flo to consistently deliver products when asked?
 

IEC

Elite Member
Super Moderator
Jun 10, 2004
14,600
6,084
136
Interestingly, the retail channels are still stuffed full of Maxwell 2 GPUs while AMD equivalents (esp 390/X) seem to have dried up (at least at reasonable prices).

While the rumors of ending 390/X production are just that, rumors, it does seem like AMD is in a pretty good spot to deliver with Polaris 10 and 11 in the next few months just looking at inventory...

If nV manages to pull a fast one (unlikely, given P100) and beat AMD to a new node for consumer GPUs, I'd expect some big sales on 28nm GPUs in short order.
 

kraatus77

Senior member
Aug 26, 2015
266
59
101
Are you saying you have faith in Glo Flo to consistently deliver products when asked?
nope but this time they are using samsung's tech and i have faith in samsung. since their version of sd810 didn't run as hot as qc's tsmc based sd810. and since AMD already gave a demo with awesome p/w. nothing is sure but atleast wait and see before trashing an unreleased product.
 

Sweepr

Diamond Member
May 12, 2006
5,148
1,143
136
You're the one who states that he is implying 3+ months, despite the definition of the word proving otherwise...

Also again, where is the quote from him saying this? Where is the hard evidence?
What did I make up?

This is very early silicon, by the way. We have much more performance optimization to do in the coming months. But even in this early silicon, we’re seeing numbers versus the best class on the competition running at a heavy workload, like Star Wars—The competing system consumes 140 watts. This is 86 watts. We believe we’re several months ahead of this transition, especially for the notebook and the mainstream market. The competition is talking about chips for cars and stuff, but not the mainstream market.

http://venturebeat.com/2016/01/15/a...h-to-full-graphics-immersion-with-16k-screens

Yes, looks like I was wrong. He didn't say a few months, he said several months ahead of the competition. If DigiTimes is correct then his prediction is way off.
icon14.gif
 
Last edited:

tential

Diamond Member
May 13, 2008
7,348
642
121
http://venturebeat.com/2016/01/15/a...to-full-graphics-immersion-with-16k-screens/2

Yes, looks like I was wrong. He didn't say a few months, he said several months ahead of the competition. If DigiTimes is correct then he was way off with his prediction.
icon14.gif

Your link isn't working, but see, that's why you provide direct quotes....

Although AMD being way off with a prediction would be no surprise to me...
Edit: Actually either company being way off is no surprise to me. I just always give Nvidia more business credit because well, they deserve it.
 
Last edited:

USER8000

Golden Member
Jun 23, 2012
1,542
780
136
The AMD Boosters

Goodness grief,it is only cards,why are you acting like its life and death politics or something???

So,using your own metrics are you an Nvidia or Intel "Booster"??

You might need to step away from the keyboard if you are getting so emotionally entangled in all of this.

It is all rather childish.

Seems like you're the one getting worked up here.


Nope,you are the one getting so emtionally tangled up in all of this now you are calling people "AMD Boosters"??

It comes accross as very immature. The problem is using your absurd logic,do you call yourself a "Nvidia Booster" or a "Intel Booster" or a "Apple Booster"?? The problem is you sadly don't understand you are attacking people for having a different view than you,but are no less extreme than the people you feel are wrong.

These are only companies - remember to AMD or Nvidia you are a nobody and neither am I . People like Jen-Hsun Huang or Lisa Su are making much more than most of us,so it is really no point getting into childish name calling.

You are grown adult FFS.
 
Last edited:

xpea

Senior member
Feb 14, 2014
458
156
116
IMHO, all this debate around product availability is mud.
What is important is that both Pascal consumer and Polaris should be announced for Computex. Then most of the customers won't care if one is coming mid June or end of July. Its basically the same time frame and it won't affect buyer's decision (especially after so long 28nm period). What will make the decision is price, performance and (mostly for Nvidia) brand loyalty.
It will also be very interesting to see if Green and Red products will fight on the same category (Polaris 10 competitor to GTX1070 anyone?).

Another objective fact is that Polaris 11 was demoed in December for claimed availability in June. On the other side, no news at all. Nvidia kept totally silent. Of course, it was expected. Nvidia is the market leader and did not wanted to stop selling their products until Pascal will be available. So people shouldn't be surprised if Nvidia keeps cards close to its chest. In fact, last rumors say that only reference models sold directly by Nvidia will be available first. It shows again how Nvidia is secretive (no leak from AIBs)

That will bring me to the last and more personal feeling. I strongly believe that AMD Polaris launch will be screwed by Nvidia. During these last 6 months, I see AMD open communication as a double edge sword and it may be well turns against them when it matters the most...
 
Last edited:
Mar 10, 2006
11,715
2,012
126
Nope,you are the one getting so emtionally tangled up in all of this now you are calling certain people "AMD Boosters"??

You are grown adult FFS.

Not at all. I believe that these forums are slowly being infested by people seemingly with agendas to try to promote AMD products and alleged "superiority." The claims are becoming increasingly fantastical and out-of-touch with reality.
 

kraatus77

Senior member
Aug 26, 2015
266
59
101
One Google click away from you:

http://venturebeat.com/2016/01/15/a...h-to-full-graphics-immersion-with-16k-screens

Now that you're at it try googling the definition of 'several months ahead' of the competition, I'm not an expert but I don't think it matches what current rumours are telling us.

well he also said

"We believe we’re several months ahead of this transition, especially for the notebook and the mainstream market"


anyway. doesn't really matter how much but even if they are ahead by 1 day, it's just that AHEAD. regardless anyone who buys gpu based on who is ahead at launching is just an idiot. always wait for both and after that evaluate and buy. :)
 
Last edited:

tential

Diamond Member
May 13, 2008
7,348
642
121
One Google click away from you:

http://venturebeat.com/2016/01/15/a...h-to-full-graphics-immersion-with-16k-screens

Now that you're at it try googling the definition of 'several months ahead' of the competition, I'm not an expert but I don't think it matches what current rumours are telling us.

This is very early silicon, by the way. We have much more performance optimization to do in the coming months. But even in this early silicon, we’re seeing numbers versus the best class on the competition running at a heavy workload, like Star Wars—The competing system consumes 140 watts. This is 86 watts. We believe we’re several months ahead of this transition, especially for the notebook and the mainstream market.

So I guess now,
competition = transition.

Full context since some people can't learn to quote articles:
Koduri:
When we set to design this GPU, we set a completely different goal than for the usual way the PC road maps go. Those are driven by, the benchmark score this year is X. Next year we need to target 20 percent better at this cost and this power. We decided to do something exciting with this GPU. Let’s spike it so we can accomplish something we hadn’t accomplished before.

The target we set was to do console-class gaming on a thin and light notebook. What does that take for the GPU in terms of power and configuration? I’m proud to say we’ve accomplished that goal with this GPU.

VB: Is that with a generation coming in 2016?

Koduri: Yes. We have two versions of these FinFET GPUs. Both are extremely power efficient. This is Polaris 10 and that’s Polaris 11. In terms of what we’ve done at the high level, it’s our most revolutionary jump in performance so far. We’ve redesigned many blocks in our cores. We’ve redesigned the main processor, a new geometry processor, a completely new fourth-generation Graphics Core Next with a very high increase in performance. We have new multimedia cores, a new display engine.

This is very early silicon, by the way. We have much more performance optimization to do in the coming months. But even in this early silicon, we’re seeing numbers versus the best class on the competition running at a heavy workload, like Star Wars—The competing system consumes 140 watts. This is 86 watts. We believe we’re several months ahead of this transition, especially for the notebook and the mainstream market. The competition is talking about chips for cars and stuff, but not the mainstream market.

Take it how you will....
But when people are hesitant to give you a full quote ask why? Why won't they just quote/link the relevant information so you can quickly find it? Why are they so vague with their information and then from there, drawing their own further conclusions from their vague information to begin.

Ask for hard facts.
 

USER8000

Golden Member
Jun 23, 2012
1,542
780
136
Not at all. I also believe that these forums are slowly being infested by people seemingly with agendas to try to promote AMD products and alleged "superiority". I will not name these posters publicly as member call-outs are not allowed.

So what about all the people doing the same for Nvidia,Intel,Qualcomm,etc??

I remember,years ago have interactions with people on other forums in the UK,who turned out to be Nvidia Focus Group members. Not once did I go and call them out for that.

In the UK on many review sites you get random low post people belittling AMD in comments sections,when any relevant news is post about them and then they disappear. Could they be astroturfers?? Who knows - but unless you can use facts to disprove what they are saying,trying to lump everybody as some paid astroturfer is just petty. Remember - people might think you are astroturfing for the other side then.

At that point the cohesion of a forum dies and the community dies,since everyone who has an opposite view of somebody will be considered an astroturfer.

Remember,people have the right to disagree with you. You also have the right to use facts to disprove them.

It is the internet - you don't know what allegiances people have at all.

But one thing is that any US or UK based poster cannot do anonymous astroturfing.

It is illegal and a criminal offence.
 
Last edited:

tential

Diamond Member
May 13, 2008
7,348
642
121
Not at all. I believe that these forums are slowly being infested by people seemingly with agendas to try to promote AMD products and alleged "superiority." The claims are becoming increasingly fantastical and out-of-touch with reality.

So now when you have something positive to say you're an "AMD booster" and more and more people are showing these traits.

At the same time as this is happening, AMD is also performing better in games and even gaining marketshare.

Weird right?
A company does better, and then more people talk about it....

However, if you're worried about these forums being "infested" with people with "agendas" to promote AMD products that's fine. Luckily, there is a safe place for you where you never have to hear about AMD:
http://forums.anandtech.com/forumdisplay.php?f=69

And if you want to discuss Pascal in this place:
http://forums.anandtech.com/showthread.php?t=2466949

"AMD Boosters" can not get you there. They can't get ANY of us there.
 
Last edited:
Mar 10, 2006
11,715
2,012
126
So what about all the people doing the same for Nvidia,Intel,Qualcomm,etc??
I remember,years ago have interactions with people on other forums in the UK,who turned out to be Nvidia Focus Group members. Not once did I go and call them out for that.

In the UK on many review sites you get random low post people belittling AMD in comments sections,when any relevant news is post about them and then they dissapear. Could they be astroturfers?? Who knows - but unless you can use facts to disprove what they are saying,trying to lump everybody as some paid astroturfer is just petty.

Remember,people have the right to disagree with you. You also have the right to use facts to disprove them.

It is the internet - you don't know what allegiances people have at all.

But one thing is that any US or UK based poster cannot do anonymous astroturfing.

It is illegal.

Let me be clear. There are many folks around here who prefer AMD/AMD products who are perfectly rational and are absolute joys to have intelligent debates/discussions with. Same goes for NVIDIA, Intel, ASUS, ASRock, whatever.

But then you have those posters who consistently make very far out claims that don't jive with reality. For example, I have seen buyers of the GTX 960 mocked for not purchasing a Radeon R9-whatever in its place. These people have been called "sheep."

In fact, NVIDIA buyers in general on these forums seem to be treated as ignorant fools with more money than brains. It doesn't occur to the "GPU elite" who think AMD is the only sensible choice, who narrowly focus on raw perf/$ that there are perhaps other considerations that are important to buyers.

If you want good gaming performance in a system where a high wattage PSU is not realistically an option, something like the GTX 950 or GTX 960 makes a ton of sense, even if it's not the best perf/$ option from an upfront acquisition perspective.

Then let's talk about say, a GTX 980 Ti buyer. The 980 Ti, by-and-large, is objectively viewed as the superior ultra-high end GPU in terms of both raw performance in a wide swath of games as well as in power efficiency. It's also something of an "overclocker's dream."

Yet, what I am finding is that people are now trying to dissuade others from purchasing a high-end NVIDIA card because of the "DX12 boogeyman." The value prop? Forget all of the games you want to play today, the games of "the future" will all magically run better on AMD because...[Async Compute, GCN is the most advanced GPU architecture in the history of ever, AMD first to HBM, ...].

It's getting old.
 

USER8000

Golden Member
Jun 23, 2012
1,542
780
136
Looking back at all the years I have been a PC enthusiast,I can remember times when ATI destroyed Nvidia with the 9700 PRO and Nvidia destroying ATI with the 8800GTX and so on. Then AMD coming out of the blue with the HD4000 and HD5000 series giving Nvidia some real competition and then Nvidia releasing Maxwell which gave AMD a decent hiding in sales.

I don't see why it would be considered unusual that AMD might bounce back and do better now,and then Nvidia doing the same to AMD and so on.

It is a cycle.
 

USER8000

Golden Member
Jun 23, 2012
1,542
780
136
Let me be clear. There are many folks around here who prefer AMD/AMD products who are perfectly rational and are absolute joys to have intelligent debates/discussions with. Same goes for NVIDIA, Intel, ASUS, ASRock, whatever.

But then you have those posters who consistently make very far out claims that don't jive with reality. For example, I have seen buyers of the GTX 960 mocked for not purchasing a Radeon R9-whatever in its place. These people have been called "sheep."

In fact, NVIDIA buyers in general on these forums seem to be treated as ignorant fools with more money than brains. It doesn't occur to these people, who narrowly focus on raw perf/$ that there are perhaps other considerations that are important to buyers.

If you want good gaming performance in a system where a high wattage PSU is not realistically an option, something like the GTX 950 or GTX 960 makes a ton of sense, even if it's not the best perf/$ option from an upfront acquisition perspective.

Then let's talk about say, a GTX 980 Ti buyer. The 980 Ti, by-and-large, is objectively viewed as the superior ultra-high end GPU in terms of both raw performance in a wide swath of games as well as in power efficiency. It's also something of an "overclocker's dream."

Yet, what I am finding is that people are now trying to dissuade others from purchasing a high-end NVIDIA card because of the "DX12 boogeyman." The value prop? Forget all of the games you want to play today, the games of "the future" will all magically run better on AMD because...[Async Compute, GCN is the most advanced GPU architecture in the history of ever, AMD first to HBM, ...].

It's getting old.

I am one of those GTX960 owners and at the same price I would tell them to get an R9 380. My GTX960 is in a mini-ITX system with a XFX 450W PSU,which will have no problems running an R9 380 either.

I have had no problems running cards such as an HD5850 or 8800GTS 512MB off SFX 450W PSUs in Shuttles,etc.

People overstate PSUs required for an average system - Valve was running a Core i7 4770 and a Geforce Titan in the prototype SteamBoxes off a Silverstone SFX 450W which is a Group Regulated design(I think) and is not as good as larger PSUs(but still a decent PSU).

I got my GTX960 cheaper and at the time,they seemed more evenly matched. Fast forward a few months and not so sure now.

The R9 380 is a better card on average and it will be longer lived IMHO.

But if somebody needed HDMI2.0,ie,an HTPC card I would tell them a GTX960 is better,or if they use Linux,AMD driver performance is not as good as Nvidia or if they ran a game which tended to run much better on Nvidia to get the Nvidia card.

Cards are fickle things - it only takes software changes and changes in what games use,to change the relative position of things.

It is what is called being an enthusiast. It is to appreciate things are fickle - performance changes and PRICING changes do occur and we need to consider those metrics when making a recommendation.
 
Last edited: