Nvidia Fermi info

to većina govori odkad je nvidia u problemu s izdavanjem fermija.. i općenito s malo lošijim performansama/cijenom

Pa zato je trebalo 5 god.da se ati provuce sa planovima dok je nvidia bila uspavana u zimski san a sad ovo me nista ne cudi....zapravo veci problem ima nvidia sa yieldovima od ati-a.

Aj ljudi jel moze kakav odgovor, plizz! Hvala

nnn da, isplati se kontam sacekat, ako ne odgode naravno .. a sve mi nekak "smrdi" da ce se to dogodit ...  preskupa mi je jos ova 295-ica , al cu je svakako uzet ... jel padnu cijene predhodnika odma nakon dolaska noviih?? .. ps hvala!

Ovisi. Ako je razlika u cijeni 480 i 295 pre velika možda i ne padne, sve ovisi o konkureciji ostalih karata istih performansi. Npr. Ako Nvidija na pocetku izbaci 480 koji ima 20% bolje performance ali košta recimo 70% više onda ATI baš i nema razloga da spusti cijene, a cijene slabijih kartica kao što su 5700 i 5600 serija se nece mijenjat tok Nvidija ne izbaci nešto u tom rangu.

Teško je za rec kako ce se cijena mijenjat kada ni neznamo prave performanse te nove serije i koja ce cijena biti. Najbolje što možeš napraviti je da pricekaš izlazak i onda gledaš kako se cijene mijenjaju.

Pa lijepo ti kaže da se to vrti na kodu starom 2 godine, nemožeš na starom softveru izvuć maximum iz najnovijeg hardvera sa novim mogučnostima...

ja kupujem gtx 485 odma cim dodje makar kostala 5 soma kn

Bilo bi zanimljivo kada je 480 bolja od 5870 a lošija od 5970 a košta ko 5970. A to je lako moguce pošto su cijene Nvidija kartica dosta paprene.

Pa ako malo citaš po netu vecina ljudi isto tako misli. Bolje od 5870 a lošije od 5970 a cijenom tu negdi sa 5970. Kakva ce stvarna cijena biti je upitno, ali vecina ljudi racuna na 599$ startne cijene (to ce naravno porast ako ce biti malen broj karata a velika traženost, isto kao i sa 5970)

lol sorry moj bad, trebalo je pisati 5870 a ne 5780, ispravljeno :P

Pa cijena stvarno ovisi. Ako Nvidija ima još uvijek problema sa yieldom onda ih svaki cip košta masno, a to znaci da cim manja cijena znaci manja zarada. Ja cekam Fermi tako da cijene ATI kartica padneju, jer taj premium za jedine DX11 kartice ne želim placat.

samo procitaj podebljano, ako treba vise puta, u biti prvo ne znamo kako ce biti "jaka" dal ce biti jaca od bilo koje kartice ili pak slabija a pogotovo ne znamo cijenu

Ja i onako mislim za grafu dat 3500-4000kn tak da ću upiknut GTX480.

Process vs. Architecture: The Difference Between ATI and NVIDIA

Ever since NV30 (GeForce FX), NVIDIA hasn’t been first to transition to any new manufacturing process. Instead of dedicating engineers to process technology, NVIDIA chooses to put more of its resources into architecture design. The flipside is true at ATI. ATI is much less afraid of new process nodes and thus devotes more engineering resources to manufacturing. Neither approach is the right one, they both have their tradeoffs.

NVIDIA’s approach means that on a mature process, it can execute frustratingly well. It also means that between major process boundaries (e.g. 55nm to 40nm), NVIDIA won’t be as competitive so it needs to spend more time to make its architecture more competitive. And you can do a lot with just architecture alone. Most of the effort put into RV770 was architecture and look at what it gave ATI compared to the RV670.

NVIDIA has historically believed it should let ATI take all of the risk jumping to a new process. Once the process is mature, NVIDIA would switch over. That’s great for NVIDIA, but it does mean that when it comes to jumping to a brand new process - ATI has more experience. Because ATI puts itself in this situation of having to jump to an unproven process earlier than its competitor, ATI has to dedicate more engineers to process technology in order to mitigate the risk.

In talking to me Carrell was quick to point out that moving between manufacturing processes is not a transition. A transition implies a smooth gradient from one technology to another. But moving between any major transistor nodes (e.g. 55nm to 45nm, not 90nm to 80nm) it’s less of a transition and more of a jump. You try to prepare for the jump, you try your best to land exactly where you want to, but once your feet leave the ground there’s very little to control where you end up.

Any process node jump involves a great deal of risk. The trick as a semiconductor manufacturer is how you minimize that risk.

At some point, both manufacturers have to build chips on a new process node otherwise they run the risk of becoming obsolete. If you’re more than one process generation behind, it’s game over for you. The question is, what type of chip do you build on a brand new process?

There are two schools of thought here: big jump or little jump. The size refers to the size of the chip you’re using in the jump.

Proponents of the little jump believe the following. In a new process, the defect density (number of defects per unit area on the wafer) isn’t very good. You’ll have a high number defects spread out all over the wafer. In order to minimize the impact of high defect density, you should use a little die.

If we have a wafer that has 100 defects across the surface of the wafer and can fit 1000 die on the wafer, the chance that any one die will be hit with a defect is only 10%.

The big jump is naturally the opposite. You use a big die on the new process. Now instead of 1000 die sharing 100 defects, you might only have 200 die sharing 100 defects. If there’s an even distribution of defects (which isn’t how it works), the chance of a die being hit with a defect is now 50%.

Based on yields alone, there’s no reason you’d ever want to do a big jump. But there is good to be had from the big jump approach.

The obvious reason to do a big jump is if the things you’re going to be able to do by making huge chips (e.g. outperform the competition) will net you more revenue than if you had more of a smaller chip.

The not so obvious, but even more important reason to do a big jump is actually the reason most don’t like the big jump philosophy. Larger die are more likely to expose process problems because they will fail more often. With more opportunity to fail, you get more opportunity to see shortcomings in the process early on.

This is risky to your product, but it gives you a lot of learning that you can then use for future products based on the same process.

Izvor:Anandtech

Uf, uf, Charlie je ovaj put jos i drzak,

evo nove provokacije

doduse pitanja su mu skroz na mjestu, posebno ce mi biti zanimljivo procitati odgovore na njih, ako ih bude naravno

Zanimljiv clanak, ali mislim da je pre pesimisticno napisan. Ovo što tu piše je od njegovih izvora i mislim da je to više onak "worst case scenario". Istina je, Fermi debelo kasni, i znamo da se dosta grije. Za klokove necemo znati dok karticu ne dobijemo. Ako još uvijek ima problema sa yieldom onda necemo vidjet puno kartica, pogotov ako dosta njih ide za Tesla seriju, na kojima Nvidija puno bolje zarađuje po cipu nego kod Gefroce serije. Da ce Fermi biti skup smo vec i prije mogli znati jer su sve nove high end kartice od Nvidije skupe, a i sam cip je 66% veci od ATIjevog Cypresa, pa se lako zakljuci da ce raditi na dosta vecim temparaturama (ako je istina da je die size Fermia 550mm2). Ako stvarno troši 280W kako je receno na vec niskim klokovima onda ne znam kako ce dual GPU verziju napraviti. Problem nije to što se kartice nece moci napajati strujom, to nikada nije problem, problem ju je dobiti ispod 300W, inace Nvidija ima veliki problem. PCIe je specificiran do 300W, sve iznat toga ne može biti PCIe proizvod, i radi toga se nemože kartica prodavati sa garancijom ili tako nešto. Uglavnom nocna mora za partnere Nvidije.

I bez ovog clanka smo znali da Fermi ima dosta problema, inace ne bi kasnio skoro vec 6 mjeseci, ali kakav ce biti konacni proizvod, njegova cijena i perfomanse cemo tek znat kada kartica vidi svijetlo dana.