Citat:
Ursprungligen inskrivet av
Hardware guy
Det där låter mer som rent skitsnack än några andra rykten jag hört.
"More industry whispers suggest the reason Nvidia's upcoming hope, the GK104, is late to the table is all the redesigns it has had to go through. Parts on the 32nm had to be redesigned for 28nm, but along the way there were challenges with packaging and interconnects. Some industry watchers suggest that Nvidia gave up a lot of space on its chip, trying to buff up Kepler by bringing Ageia to the hardware."
"Ageia hardware" säger tillräckligt mycket om att personen som skriver inte har den blekaste vad han snackar om. Fysik hanteras via GPGPU idag och Ageiahårdvara har inte existerat sedan NVidia köpte upp dem 2008 och skrev om SDKn till att använda x87 och C++ (GPGPU via CUDA). CUDA är heller inget nytt, det har funnits sedan 2006 och har, liksom Stream för AMD, varit grundpelaren i NVidias GPU-arkitekturer ända sedan dess.
Dessutom är Kepler, har alltid varit, designad för 28nm. NVidia var de som redan från början hoppade över 32nm. Det lag som hade bekymmer där var om något AMD, då Northern Islands från början var designad som 32nm och fick göras om till 40nm istället.
"At AMD's Technical Forum and Exhibition 2010, Matt Skynner (AMD VP and General Manager of AMD's GPU Division) admitted that the HD 6000 series was originally set to use TSMC's 32nm process, but that AMD had to opt back to 40nm earlier this year after that process was unceremoniously dumped by TSMC in favour of concentrating on 28nm only. The reason for this was explained to be lackluster interest in the process as several clients, among them NVIDIA, have decided to move directly to the upcoming 28nm process for their next-generation units. The costs of implementing the hardware for the 32nm process would have had to be shared by too few clients to be cost-effective."
"But the murmurs suggest Nvidia has been dedicating a lot of resources to get physics and fluid dynamics operating properly, which has so far, allegedly, taken half of its gaming engineers and six months to get right."
Varför skulle de då ha problem med att implementera PhysX och Fluid Dynamics när det är ren CUDA - en teknik de använt rakt av sedan 8000-serien och G80 och har fungerar utmärkt i fyra år, för att inte tala om integrerad i hur NVidia designar sina GPU-kärnor? PhysX är inte direkt en ny motor och att de skulle behöva designa om den för 600-serien låter ju bara barockt. Återigen, det fungerar redan, så varför skulle de behöva lägga tid på att utveckla det igen?
"One industry watcher said to TechEye the company is in "holy s**t" mode - having been confident that the GK104 would fight off and trounce the competition, but the timing is out of whack. When Nvidia does get its high-end Kepler chip out in the second half of the year, the competition is going to be ready with something else."
Detta är ren spekulation, och att bekämpa antifakta är omöjligt oavsett.
"There are no doubts that full fluid dynamics is going to wow the crowds - on demos specifically catering to fluid dynamics. Writing code for games to get the performance right, though, is trickier. While Nvidia's team is working overtime, its rivals just may be able to clean up.
"Their SDK is great," someone familiar with the matter said to TechEye. "But it was foolish of them to try putting Ageia hardware onto a GPU. The amount of engineering work you have to do to make that useful in games - you get one game every six months that gives you the benefits of that."
Återigen... PhysX är inte direkt något nytt, nej.