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

[Silverforce11]

Did we have that previously? Something like the GTX980TI came in from nowhere for example.

Lol no.

Titan X and 980Ti "GM200 Cut" leaks came out many months before retail.

What terrible memory you have.

Base on that leak, Titan X was ~35% faster than 980 and ~235W. Lots of folks where were up in arms "it can't be that slow!" or "only 35%?" like we didn't see that before with 680 -> Titan. Take a tour back at those old threads.

AIBs have a long chain of supply. As soon as they get it, the usual sites will be all over it with performance leaks.

 

[ShintaiDK]

Lol no.

Titan X and 980Ti "GM200 Cut" leaks came out many months before retail.

What terrible memory you have.

Random rumours sure. But that's not what its about.

AIBs have a long chain of supply. As soon as they get it, the usual sites will be all over it with performance leaks.

Oh the irony. So you are saying AIBs dont even have Polaris yet?

 

[Silverforce11]

Random rumours sure. But that's not what its about.

Oh the irony. So you are saying AIBs dont even have Polaris yet?

That random leak 6 months before Titan X was released was spot on. Guess it could just be lucky.

Did you miss the AIDA64 Polaris benchmarks?

There's more leaks like that out there, take a stroll on ChipHell forums where the usual leakers hang out.

We have a situation where AMD demo working hardware, showing journalists the chip and setup at the start of the year. AMD also say they are releasing Polaris in June.

And nvgpu says it's a paper launch, that AMD got nothing! But whereas NV have said nothing, all false rumors from clickbait sites, it must be a real launch, ahead of AMD for sure...

All that spin, we're less than 2 months out. Not that long for reviews.

 

[Adored]

There is an alternative reason, that is that Polaris 11 is all going to Apple. That could explain the information coming from the Taiwanese OEM's.

From where I'm standing, AMD is at least a month ahead, but I can see why they'd take the opportunity to get into laptops instead of launching desktop GPUs. I just hope both aren't playing a waiting game to see what the other delivers first, though that probably suits Nvidia more.

 

[Silverforce11]

Btw, since these guys got the leak spot on about GP100, the interposer being huge ~1200mm2 which some folks said it was "BS" or simply can't be true...

Let's put this here for context. Leaks from a proven source vs leaks from clickbait sites who claims GTX GP100 in April 2016.

Originally Posted by BitsandChips @ Translate
Our source has informed us of the possible presentation of graphics cards lineup based on the various facets of the architecture of NVIDIA Pascal.

April 2016 - GTC: Tesla (GP100)
June 2016 - Computex: GTX 1080 (GP104) & GTX 1070 (GP104)
4Q 2016 - GP106 & GP107
4Q 2016 or 1Q 2017 - Titan (GP100)
1Q / 2Q 2017 - GP108 (GM108 rebrand ?)

It begins in April, with the Tesla board, based on GPU GP100, and dedicated to the HPC market. 'S Oak Ridge National Laboratory and Lawrence Livermore National Laboratory have already announced that they will make extensive use. The first dedicated to the consumer market cards, will be those with GPU GP104, always produced with FF16 node ++ TSMC. They should be submitted to COMPUTEX in Taipei, but the market should start only from 3Q 2016. Later will be presented the lower-end cards, and the Titan range top.

Source: http://www.bitsandchips.it/9-hardware/6621-rumor-scaletta-di-presentazione-delle-gpu-pascal

 

[96Firebird]

Poor Nvidia, always a day late and a dollar short.

Oh, wait... :sneaky:

 

[Silverforce11]

Poor Nvidia, always a day late and a dollar short.

Oh, wait... :sneaky:

I know right, doesn't matter if NV is late. They can keep selling 28nm stuff for a discount and JHH will still enjoy his wads of $$.

Some people were so shocked to see JHH doesn't want to sell the huge GP100 as a consumer GTX in April (LOL @ rumors). That even the Tesla variant is Q1 2017..

So guys, relax. Not long to go and all shall be revealed.

 

[Arachnotronic]

Why don't you have a quick browse through the recent rumor mongering clickbait articles from Digitimes and see whether they are correct?

Big Pascal GTX in APRIL anyone? They are one of the sites repeating that stupid rumor since last year. -_-

Also you don't have to try so hard to claim AMD is paper launching, it's less than 2 months to go. They've been public saying Polaris will launch in June since the start of this year.

I pay for a DigiTimes subscription and they get a lot of things right, way more than people give them credit for. Not once did DigiTimes AFAIK claim a gaming Pascal GTX card was coming in April.

Stop making up FUD. The AMD Boosters who said that Pascal was "late" and that AMD would have a big lead on NVIDIA were dead wrong. Period.

 

[Headfoot]

I pay for a DigiTimes subscription and they get a lot of things right, way more than people give them credit for. Not once did DigiTimes AFAIK claim a gaming Pascal GTX card was coming in April.

Stop making up FUD. The AMD Boosters who said that Pascal was "late" and that AMD would have a big lead on NVIDIA were dead wrong. Period.

For gaming cards nothing has come out yet so.... a bit premature don't you think?

 

[Silverforce11]

The AMD Boosters who said that Pascal was "late" and that AMD would have a big lead on NVIDIA were dead wrong. Period.

Who?

What's this big lead?

It's actually Raja Koduri that is saying that. He said a "few months" ahead of the competition.

I wouldn't equate a few months to a big lead.

NV being late doesn't matter anyway, they have a ton of cash reserves in the bank.

 

[tential]

There were some poster who said that Nvidia is 6 months behind AMD.

It was actually the other way around. It was a specific poster who said amd is 6 months behind Nvidia and will launch in December. I can even find the quote if you'd like.

It was because Nvidia was launching in may per the rumor thread that's here and they said 6 months + a little extra for "amd delays".

 

[AtenRa]

NV always introduces GPUs on new nodes 3-6 months after AMD the last 6-7 years, nothing new here.

 

[USER8000]

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.

 

[Sweepr]

Why don't you have a quick browse through the recent rumor mongering clickbait articles from Digitimes and see whether they are correct?

Big Pascal GTX in APRIL anyone? They are one of the sites repeating that stupid rumor since last year. -_-

That doesn't come from DigiTimes, but nice try.

http://techfrag.com/2016/01/25/nvid...t-in-april-gtx-1080-in-june-and-volta-in-2017

 

[tential]

I pay for a DigiTimes subscription and they get a lot of things right, way more than people give them credit for. Not once did DigiTimes AFAIK claim a gaming Pascal GTX card was coming in April.

Stop making up FUD. The AMD Boosters who said that Pascal was "late" and that AMD would have a big lead on NVIDIA were dead wrong. Period.

Wild accusations at random people with no proof.

Who are these "amd boosters"?
Who said pascal was" late"?
Who said amd has a big lead on Nvidia?

Using the logic in your post I'm going to say this:
Jhh himself has said that he isn't using pascal and already has plans for a zen+vega rig. He personally wouldn't touch pascal.

Since we're making wild accusations without any proof or quotes, there ya go.

Sent from my C6833 using Tapatalk

 

[Arachnotronic]

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.

 

[Arachnotronic]

Wild accusations at random people with no proof.

Who are these "amd boosters"?
Who said pascal was" late"?
Who said amd has a big lead on Nvidia?

Using the logic in your post I'm going to say this:
Jhh himself has said that he isn't using pascal and already has plans for a zen+vega rig. He personally wouldn't touch pascal.

Since we're making wild accusations without any proof or quotes, there ya go.

Sent from my C6833 using Tapatalk

Here you go, just one example:

http://semiaccurate.com/2016/01/11/nvidia-pascal-over-a-year-ahead-of-1416nm-competition/

Until the CES unveiling, AMD was widely believed to be 2+ quarters ahead of Nvidia on the process front, their 14nm Polaris GPUs had all the mindshare.

That said, I would not call Charlie an AMD booster, he fairly criticizes them when they screw up. He does hate NVIDIA, though, but he will give credit where it is due.

 

[Silverforce11]

Please, don't quote Charlie and SA when you post here claiming people say this or that. Charlie isn't represented here. We all know it's "semi" accurate.

 

[tential]

Here you go, just one example:

http://semiaccurate.com/2016/01/11/nvidia-pascal-over-a-year-ahead-of-1416nm-competition/



That said, I would not call Charlie an AMD booster, he fairly criticizes them when they screw up. He does hate NVIDIA, though, but he will give credit where it is due.

So then it's not an example.

You said amd boosters said it. Who are the amd boosters and what did they say?

I pay for a DigiTimes subscription and they get a lot of things right, way more than people give them credit for. Not once did DigiTimes AFAIK claim a gaming Pascal GTX card was coming in April.

Stop making up FUD. The AMD Boosters who said that Pascal was "late" and that AMD would have a big lead on NVIDIA were dead wrong. Period.

 

[nvgpu]

Don't bother arguing with these people, they don't have the guts to admit they're wrong because they got too much pride defending the competitor and all the FUD against Nvidia being late pretty much blowing up in their face now.

 

[Despoiler]

There were some poster who said that Nvidia is 6 months behind AMD.

Ahh no. There was a thread started based on an article over @ SemiAccurate where Charlie speculated, tongue and cheek I might add, that Nvidia was 6 months behind because their PX2 board was still using Maxwell chips.

 

[Silverforce11]

Don't bother arguing with these people, they don't have the guts to admit they're wrong because they got too much pride defending the competitor and all the FUD against Nvidia being late pretty much blowing up in their face now.

According to you, AMD is going to paper launch and they're the ones late.

Let's just quote this for prosperity sakes. In a few months, we can revisit.

 

[xthetenth]

Don't bother arguing with these people, they don't have the guts to admit they're wrong because they got too much pride defending the competitor and all the FUD against Nvidia being late pretty much blowing up in their face now.

Huh. Weird. Until I hit the second line where you said Nvidia I agreed entirely with you.

Serious though, it is getting annoying around here, it's like trying to navigate with a stuck compass.

 

[tential]

Don't bother arguing with these people, they don't have the guts to admit they're wrong because they got too much pride defending the competitor and all the FUD against Nvidia being late pretty much blowing up in their face now.

So far no one has been proven wrong about anything. Unless you want to talk about being proven wrong that the gtx 1080 isn't going to be available in may......

Sent from my C6833 using Tapatalk

 

[Sweepr]

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