[THREAD UFFICIALE] Aspettando Nvidia GTX 480 e GTX 470

[The_SaN]

Originariamente inviato da Felle

Speriamo che il forum "non entri in manutenzione tra poco"

Dovremmo avere ancora mezz'oretta...

[NOOB4EVER]

Originariamente inviato da The_SaN

Dovremmo avere ancora mezz'oretta...

cavoli almeno una notiziuccia o uno slidino prima di dormire non sarebbe poi male speriamo davvero di riuscire a sapere qualcosa e a condividerla prima delle 3:30


va va ..quanti curiosi ancora svegli credevo di essere da solo

[Felle]

Per ora condividiamo la trepidazione!!!!

[The_SaN]

Originariamente inviato da NOOB4EVER

cavoli almeno una notiziuccia o uno slidino prima di dormire non sarebbe poi male speriamo davvero di riuscire a sapere qualcosa e a condividerla prima delle 3:30


va va ..quanti curiosi ancora svegli credevo di essere da solo

Qua é ancora "presto", é mezzanotte

[Rsdj]

Originariamente inviato da The_SaN

Qua é ancora "presto", é mezzanotte

Ah, allora stai più tranquillo

Cmq ancora niente di nuovo...

[NOOB4EVER]

Originariamente inviato da Rsdj

Ah, allora stai più tranquillo

Originariamente inviato da Rsdj

Cmq ancora niente di nuovo...

PS : grrr quanto invidio quei nerd del video di Nemesis da Facebook

[Felle]

Ragazzi ancora nulla???

[Rsdj]

Originariamente inviato da Felle

NOOB4EVER controlla la casella messaggi hai un pvt....

Ragazzi ancora nulla???

Niente di niente.... mi sa che era un'altra presa per il cxxo...

[|Phoenix|]

scusate,sono di passaggio... ma cosa aspettate?

[Rsdj]

Alle 3:00 dovrebbe essere scaduto l'NDA sulle nuove vga nVidia basate su architettura Fermi.

Cmq ho trovato questo:

http://forum.beyond3d.com/showthread.php?p=1381688

"In the R870, if you compare the time it takes to render 1 Million triangles from 250K using the tesselator, it will take a bit longer than running those same 1 Million triangles through without the tesselator. Tesselation takes no shader time, so other than latency and bandwidth, there is essentially zero cost. If ATI implemented things right, and remember, this is generation four of the technology, things should be almost transparent.

Contrast that with the GT300 approach. There is no dedicated tesselator, and if you use that DX11 feature, it will take large amounts of shader time, used inefficiently as is the case with general purpose hardware. You will then need the same shaders again to render the triangles. 250K to 1 Million triangles on the GT300 should be notably slower than straight 1 Million triangles.

The same should hold true for all DX11 features, ATI has dedicated hardware where applicable, Nvidia has general purpose shaders roped into doing things far less efficiently. When you turn on DX11 features, the GT300 will take a performance nosedive, the R870 won't."

[NOOB4EVER]

Originariamente inviato da |Phoenix|

scusate,sono di passaggio... ma cosa aspettate?

un misero slide veritiero su quelle che potrebbero essere le potenzialita' delle nuove nate di casa Nvidia , vedi titolo " FERMI" e qui piu' fermi di cosi' si muore,sono un tutt'uno con la sedia da ormai un bel po'. TriLOL

[NOOB4EVER]

Originariamente inviato da Rsdj

Alle 3:00 dovrebbe essere scaduto l'NDA sulle nuove vga nVidia basate su architettura Fermi.

Cmq ho trovato questo:

http://forum.beyond3d.com/showthread.php?p=1381688

"In the R870, if you compare the time it takes to render 1 Million triangles from 250K using the tesselator, it will take a bit longer than running those same 1 Million triangles through without the tesselator. Tesselation takes no shader time, so other than latency and bandwidth, there is essentially zero cost. If ATI implemented things right, and remember, this is generation four of the technology, things should be almost transparent.

Contrast that with the GT300 approach. There is no dedicated tesselator, and if you use that DX11 feature, it will take large amounts of shader time, used inefficiently as is the case with general purpose hardware. You will then need the same shaders again to render the triangles. 250K to 1 Million triangles on the GT300 should be notably slower than straight 1 Million triangles.

The same should hold true for all DX11 features, ATI has dedicated hardware where applicable, Nvidia has general purpose shaders roped into doing things far less efficiently. When you turn on DX11 features, the GT300 will take a performance nosedive, the R870 won't."

beh se questo fattore del tassellatore che grava molto sulle GPU amd piuttosto che sulle Nvidia,qualcosa di positivo ne viene fuori di sicuro,io mi aspetto perlomeno un buon 20 % di prestazioni superiore alle 5870 e gia' il prodotto finale non sarebbe affatto male,perche significherebbe che uno sli di gf100 sarebbe superiore alle 5970 ,da vedere poi il prezzo di vendita che giochera' un altro fattore primario...beh tanta curiosita' e tante speranze,e forza con queste news che comincio a vederci triplo a quest'ora

[Rsdj]

News fresca fresca, ma bruttissime notizie per Fermi:

Nvidia GF100 takes 280W, and is unmanufacturable


"NVIDIA'S GF100 ARCHITECTURE is falling into the same trap that G200 did, shooting for the moon at the cost of the parts that pay the bills. Lets take a look at the architecture and how it stacks up in the market once again.

If you recall, last May, I said a few things about the chip then known as GT300, now called Fermi or GF100. The executive summary at the time was that GF100 was too big, too hot, and wrong product design in almost all areas. Nvidia was shooting for a world-beating GPGPU chip, and they may have achieved that. Unfortunately for them, there isn't a sustainable market for such a beast. The cost of that GPGPU performance was raw GPU performance and manufacturability. While GPUs have a sustainable market for the time being the GPGPU market is another story altogether. A risky management bet at best.

What is going to be delivered? As we have said earlier on tapeout, the GF100/Fermi is a 23.x * 23.x mm chip, we hear it is within a hair of 550mm^2. This compares quite unfavorably to it's main competitor, ATI's Cypress/HD5870 at 334mm^2. ATI gets over 160 chip candidates from a wafer, Nvidia gets only 104. To make matters worse, defective chips go up roughly the square of chip area, meaning Nvidia loses almost three times as many dies to defects as ATI because of the chip size differential.

The raw manufacturing cost of each GF100 to Nvidia is more than double that of ATI's Cypress. If the target product with 512 shaders is real, the recently reported 40% yield rates don't seem to be obtainable. It won't hit half of that based on Nvidia's current 40nm product yields, likely far far less.

Cost aside, the next problem is power. The demo cards at CES were pulling 280W for a single GPU which is perilously close to the 300W max for PCIe cards. Nvidia can choose to break that cap, but they would not be able to call the cards PCIe. OEMs really frown on such things, knowingly selling out of spec parts puts a huge liability burden on their shoulders, and OEMs avoid that at all costs.

280W and 550mm^2 means Nvidia is maxed out on both power use and reticle area for any product from TSMC, there is precious little room to grow on either constraint. The competition on the other hand can grow their part by 60% in die area and over 50% in power while staying below what Nvidia is offering. That puts an upper bound on Nvidia's pricing in a fairly immutable way, barring a massive performance win. If you don't feel like reading to the end, the short story is that they didn't get that win.

Getting back to the architecture itself, Jen-Hsun was mocking Intel's Larrabee as "Laughabee" while making the exact same thing himself. As we stated last May, GF100 has almost no fixed function units, not even the tessellator. Most of the units that were fixed in G200 are now distributed, something that is both good and bad.

How did this come about? Sources in Santa Clara tell SemiAccurate that GF100 was never meant to be a graphics chip, it started life as a GPGPU/compute chip and then abandoned. When the successor to the G200 didn't pan out, the GF100 architecture was pulled off the shelf and tarted up to be a GPU. This is very similar to what happened to ATI's R500/Xenos, but that one seems to have worked out nicely in the end.

How do you go from compute to GPU? Add a bit of logic to each Shader Multiprocessor (SM - a 32-shader unit that the GF100 has 16 of) to do some GPU/DX11 specific tasks. The up side is that this can work fairly well, an advantage of a more general purpose GPGPU chip. The down side is that a chip you wanted to sell for $2500 isn't economically feasible at $500. Given that the competition is fierce in the GPU segment, Nvidia is unable to increase their pricing to meet costs.

Moving on to tessellation we said last May that Nvidia does not have dedicated hardware tessellators. Nvidia said the GF100 has hardware tessellation, even though our sources were adamant that it did not. You can say that Nvidia is lying or that they are splitting hairs, but there is no tessellator.

Instead, they have what they call a 'polymorph engine', and there is one per SM. Basically they added a few features to a subset of the shaders, and that is now what they are calling a tessellator, but it is not. ATI has a single fairly small dedicated tessellator that remains unchanged up and down the Evergreen/HD5xxx stack. On ATI 5xxx cards, tessellation performance takes almost no shader time other than dealing with the output just like any other triangle. On GF100, there is no real dedicated hardware, so the more you crank up the tessellation, the more shaders you co-opt.

Nvidia is going to tout the 'scaling' of their tessellation capabilities, but since they are kicking off the GF100 line at the top, scaling is only going down from there. ATI's 5xxx parts don't lose anything when going down, nor do they lose die area when going up.

When showing off the tessellation capabilities last week, Nvidia was very careful to show the Unigine/Heaven benchmark with the dragon statue, claiming it beat the ATI 5870 by 60%. While technically true, this number is purposely misleading on two accounts. First is that this is a best case for showing off tessellation and and only tessellation. If they were to show off any of the other Heaven tests, the margins would narrow significantly.

Secondly, the test is very light on other parts of the system, so any use of system resources for the tessellator would likely be masked. It is unlikely that this performance would carry over to a real world scenario, which is exactly why it was chosen. Synthetic benchmarks are usually used as a best case scenario, and in this instance, they are.

The last bit is that our sources were reporting that Nvidia was comparing GF100 to a Radeon HD5870, a much cheaper card. If they had compared it to a comparably priced ATI HD5970/Hemlock card, which coincidentally uses almost the exact same power, the results would not have been pretty. Hemlock doubles the tessellation power of 5870, so it is pretty obvious why that comparison was not made.

Moving along, another interesting bit is that the GF100 has upgraded their ROPs (Rendering Output units) from 32 on G200/GTX280/GTX285 to 48. While this looks bad on the surface, the raw count of the ROPs does not take into account any gains in efficiency between the two architectures. The ROPs per shader ratio has gone down dramatically which speaks volumes about the intended target market of the GF100 line.

On a slightly less positive note, the texture unit count has gone from 80 on the G200 line to 64 on the GF100 parts. Again, without numbers on efficiency of the units, they are not necessarily comparable, but smart money from insiders was on 128 texture units last spring. So instead of improving performance it would seem to be a decrease in performance between their current line and their upcoming release.

Both cases point in the direction of Nvidia doing the bare minimum to keep GF100 in the graphics game. The GPU functions appear to be bolted on to a GPGPU oriented 'generalist' chip, something strongly supported by the die size : performance ratio.

Nvidia's GF100 starts out with it's back against the wall and there is little room to grow from there. They can not scale it up in die area, can not scale it up in power use, and as it stands, the part is basically unmanufacturable from a balance sheet perspective. This would be acceptable if the competition was vastly slower, allowing Nvidia to charge a 'sucker premium', or there was a ready market for them at $2500 and up, but neither appears to be the case anymore.

The performance numbers so far, both in DX10 games and DX11 demos show that it at best has a 60% lead on some very specific benchmarks over a much cheaper and more efficient HD5870. Given that GF100 is more than 60% larger than that part, 60% should be the minimum, not the maximum performance lead. The more direct comparison to an ATI 5970 was curiously neglected at CES, mainly because the GF100 is about on par, best case for Nvidia, with that part.

This caps the price Nvidia can charge for GF100 cards at the price of Hemlock, or less. Since GF100 silicon at 40% yields will cost about $125 for the raw unpackaged silicon vs a consensus number of <$50 for ATI's Cypress, ATI can likely make a dual card for less than Nvidia can make a single GF100. The 280W power draw means it is almost impossible for Nvidia to put out a dual card with all units active, leaving the slippery slope of fused off shaders and downclocked parts to hold the fort.

Nvidia has been telling their AIBs (Add In Board makers) that the initial GF100 chips they will receive are going to be massively cut down and downclocked, likely at the same 448 shaders and rough clocks as the Fermi compute board. There will be a handful of 512 shader chips at 'full clocks' distributed to the press and for PR stunts, but yields will not support this as a real product.

To make matters worse, SemiAccurate's sources in the far east are saying that the current A3 silicon is 'a mess'. Last spring, we were told that the chip was targeted for a top clock of 1500-1600MHz. The current silicon coming out of TSMC, defects aside, are not binning past 1400MHz in anything resembling quantity, with 1200MHz being the 'volume' bin. Even at 75% of intended clocks, the numbers of chips produced are not economically viable.

One of the main causes here is that clocks are, according on one source, 'all over the place', and there is no single problem to fix on the chip. Intra-die variation is huge, no surprise given TSMC's 40nm process and the 550mm^2 or so that GF100 takes up. Each individual part tends to have different problems, and Nvidia's unfinished homework did not help.

To compound this, the chip was made to run at a low voltage with a relatively high amperage. If you up the voltage, it disproportionately increases the net wattage used compared to other chips, HD5870 included. If Nvidia increases their voltage, they blow through their wattage/TDP limit and burn traces. If they don't, there are a few SMs that have a 'weak' transistor or two which won't run at the lower voltages.

Unfortunately for Nvidia, the architecture is badly designed, the best granularity for fusing off units loses 32 shaders. In it's Fermi guise, the GF100 sells as a $2500-4000 Tesla board, and that is a downclocked 448 shader chip. It is quite telling that they are unable to cherry pick enough fully working parts to support the meager numbers that the Tesla volume requires, especially in light of the margins on those parts.

Nvidia has promised AIBs chips in late February, so the March release seems feasible. The AIBs were cautioned at CES that they would only receive low quantities of the fused off parts, and fewer if any of the 'full' 512 shader parts. If you are waiting in line for the chips Nvidia showed off or the chips that the press will be given, it will be a very long wait, but you will have lots of company.

GF100 as it stands is exactly what we were told last spring. It is too hot, too big, too compute focused, not graphics focused, and economically unmanufacturable. Nvidia is more than capable of winning cherry picked benchmarks against a much cheaper card, but they are eerily quite against the comparably priced HD5970. Quite the green 'Laughabee'.

Look for a lot of FUD coming out of Santa Clara over the next few weeks, they have nothing to sell but are desperate to keep ATI from booming in the GPU market. ATI on the other hand has multiple lines of DX11 parts on the market in all but the lowest price tier, and those will come in very short order.

Until they can 'launch' parts in barely above PR stunt quantities, all Nvidia can do is spin. In the mean time, ATI is fast approaching the 6-month window traditionally needed for launching derivative parts, and will likely have the next full generation finished before any GF100 derivatives launch, if they ever make financial sense at all. When you don't have product, spin, and Nvidia is putting most ice skaters to shame with their current hot-shoe dance. S|A"

[halduemilauno]

sono le sei(+ o -)ed ecco il primo articolo...
http://www.guru3d.com/article/nvidia...ology-preview/

[halduemilauno]

un'altro...
http://www.techpowerup.com/reviews/N...tecture/1.html

[halduemilauno]

e un'altro ancora...
http://firingsquad.com/hardware/nvid...ture_overview/

[halduemilauno]

http://alienbabeltech.com/main/?p=14600
Per riassumere, Fermi GF100 è:

•512 core CUDA
•16 Geometria Unità
•4 raster unità
•64 unità di texture
•48 unità ROP
•384-bit GDDR5

[molochgrifone]

Ne ho letti due poi mi sono rotto (intanto non è che ci capisca granché) però le slides fatte vedere da nVidia darebbero fermi con tesselletion on più veloce della 5870 di circa 1,5 volte, grazie a questo polymorph engine che immagino sia il tessellatore hardware di cui tanto avete discusso l'esistenza (mi pare di aver capito che non se ne conoscesse l'esistenza fino ad ora); nel caso le slides di nVidia fossero veritiere sarebbe ottimo

http://www.techpowerup.com/reviews/N...s/GF100_18.jpg
http://www.techpowerup.com/reviews/N...s/GF100_17.jpg
http://www.techpowerup.com/reviews/N...s/GF100_19.jpg

PS: non ho fatto nottata, semplicemente mi sono svegliato per andare a lavorare e visto che non ho grande voglia di leggere i quotidiani sportivi online questa mattina ho preferito leggere di GF100

[betha]

letti, grazie hal, sembra promettere molto bene, speriamo di sapere qualcosa in + sui consumi e le fasce di prezzo a breve

[halduemilauno]

prime impressioni, come detto per la versione geforce i 512 sono presenti, il numero delle unità texture sono diminuite ma ora vanno alla metà della velocità degli shader e non come prima del core e poi l'unità polymorfa(cosi definita)che fa da tessellation, queste mi paiono le prime novità interessanti da dire. poi non si fa accenno alle frequenze e questo può significare che esse possono ancora fluttuare in base a diversi fattori quali consumo, temperature e rese. per il resto si sapeva che non sarebbero state delle rece ma appunto articoli ma cmq mi aspettavo le classiche slide di presentazione ma i motivi credo che siano dovuti alle frequenze non ancora fissate definitivamente(indicativamente dovrebbero essere 648 per i core e 1476 per la versione 448 e 1584 per la 512 questo per gli shader).
approfitto e aggiungo questo ennesimo articolo...

http://www.hardwarecanucks.com/forum...oscope-17.html