Pascal = Maxwell + Mixed Precision + 3D Memory + NVLink

Já jen aby tu někteří nečekali nějaké extra novinky v uarch.
Moderátoři: Walker1134, Wilik





Neříkám, že nefixnou nejpalčivější issues, ale zcelá nová uArch to podle nV nebude.Elkim píše:Takže lze čekat i stejnej leakage lock ve scalabilitě s voltáží, fajn no


To říkám přece už dávno, nová architektura je Volta a ta byla posunuta cca o dva roky, takže Pascal nacpali mezi to jako STOP-GAP produkt. Tak rychle se nedá nová architektura vyvinout, na to měli příliš málo času. Velký Maxwell navíc neměl podporu double precision jako předchozí velké čipy Kepler a Fermi, to znamená že Pascal vyplní přesně tuhle chybějící mezeru... už jsme to tu probírali milionkrát tady a tady a tadyKrteq píše:Neříkám, že nefixnou nejpalčivější issues, ale zcelá nová uArch to podle nV nebude.Elkim píše:Takže lze čekat i stejnej leakage lock ve scalabilitě s voltáží, fajn no
Uvidíme jestli budou nějaké změny na front-endu, resp. scheduleru a podpoře Async-Compute.




While we all know that 14/15/16nm class product should become available in the May/June timeframe, an April release feels a little premature



Krteq píše:Jj, poměrně starší, ale pořád dobrý kus![]()
Jinak Charlieho bych sem radši ani nelinkoval, někteří jedinci ho tu nemohou rozdýchat.




It also proves the ‘reports’ of Pascal taping out in June were unquestionably wrong, if it taped out in June there is no way silicon would be getting back to Nvidia in early January, best case. ~7 months is enough for a full production wafer to go through TSMC, a month of debug, and another full production run after that. If you hot lot the silicon as they most assuredly did, there would be room for 3-4 full cycles, more than any GPU in recent memory bar Fermi needed. They would have shown it off months before AMD showed running Polaris’ in early December.
http://semiaccurate.com/2016/02/01/news ... important/So dozens of sites all echoed the June tapeout date, and since it was on so many sites it was definitely true, only it really wasn’t. Pascal likely taped out in early November and wasn’t back from the fabs when Jen-Hsun gave his CES speech, at least that is what the data shows. The only thing the tapeout story really proved is none of the dozens of tech sites has any real sources and will all copy from anyone without bothering to so much as verify a fact. It isn’t news or journalism, it is plagiarism in a socially accepted form. And it is wrong.
The same happened with the Zauba manifests, again assuming they are for Pascal. These manifests unquestionably prove that there is no Pascal silicon in hand, not that Nvidia would be insane enough to ship such valuable parts via commercial cargo anyway, they prove that it didn’t exist at the time of shipping. Once again if the dozens of sites that reported Pascal silicon arrival had any technical knowledge, any sources, or even the most basic urge to do their jobs and verify the data, they would have known it was false. Literally no site other than SemiAccurate did this, they just copied from the nearest source and posted it as fact. And they were once again all wrong.


