Nvidia GeForce RTX 30X0 series (Ampere)

[JuiceBox]

Tema za nadolazecu 30X0 seriju i sve vezano za nju


NVIDIA GeForce RTX 3080 Pictured?

[The Exiled]

nVidia's Next-Gen reference cooler Costs $150 by itself, to feature in three SKUs

Pictures of alleged next-generation GeForce "Ampere" graphics cards emerged over the weekend, which many of our readers found hard to believe. It features a dual-fan cooling solution, in which one of the two fans is on the reverse side of the card, blowing air outward from the cooling solution, while the PCB extends two-thirds the length of the card. Since then, there have been several fan-made 3D renders of the card. nVidia is not happy with the leak, and started an investigation into two of its contractors responsible for manufacturing Founders Edition (reference design) GeForce graphics cards, Foxconn and BYD (Build Your Dreams), according to a report by Igor's Lab.

According to the report, the cooling solution, which looks a lot more overengineered than the company's RTX 20-series Founders Edition cooler, costs a hefty USD $150, or roughly the price of a 280 mm AIO CLC. The cooler consists of several interconnected heatsink elements with the PCB in the middle. Igor's Lab reports that the card is estimated to be 21.9 cm in length. Given its cost, nVidia is reserving this cooler for only the top three SKUs in the lineup, the TITAN RTX successor, the RTX 2080 Ti successor, and the RTX 2080/SUPER successor. All three will use the same cooling solution, and a common PCB design codenamed PG132. Further, all three cards will be based on a common ASIC, codenamed "GA102," with varying hardware specs. When launched, "Ampere" could be the first implementation of the new GDDR6X memory standard, which could come with data-rates above even the 16 Gbps of today's GDDR6, likely in the 18-20 Gbps range, if not more. Lesser SKUs could use current-gen GDDR6 memory at data-rates of up to 16 Gbps.

• The "SKU10" could ditch the TITAN brand to carry the model name "GeForce RTX 3090," max out the 384-bit wide memory bus of the GA102 ASIC, and feature a whopping 24 GB of GDDR6X memory, with 350 W typical board power.

• The next SKU, the SK20 will likely feature the RTX 3080 Ti brandingr, will be cut down from SKU10. It will feature 11 GB of GDDR6X memory across a 352-bit wide memory interface, and have a 320 W typical board power rating.

• Lastly, there's the SKU30, which is further cut-down, features 10 GB of GDDR6X memory across a 320-bit wide memory interface, and it bears the RTX 3080 model number, succeeding the RTX 2080 / RTX 2080 Super.

Izvor: TechPowerUp

[JuiceBox]

150 bucksa ne kosta taman da su mu pozlaceni finovi. Klasicni maocetung koznati marketing. Pa 25$ ne kosta vodeno u izradi a ne ova skalamerija. Ali kao sto je netko napisao u komentarima, joj belaja proizvodacima vodenih blokova za ovaj PCB Koja je uopce poanta zasebnog PCB za power delivery ?

[Tajl3r]

Referentno gofno

Sent from my Redmi Note 5 using Tapatalk

[Manuel Calavera]

U početku mi je djelovalo fake, no glasina se uhvatila kao činjenica + još nova glasina iz igors lab...

[DuHc]

GTX1650 MSRP $150
RTX3080 MSRP $150 (Cooler only. Graphics card not included)

[Mommistake]

Šta neće treća serija biti jeftinija od druge?

Kao što rekoh onda i kažem sada "In your dreams".

[Blue Spirit]

Autor xulos

Koja je uopce poanta zasebnog PCB za power delivery ?

"GeForce RTX 3090," max out the 384-bit wide memory bus of the GA102 ASIC, and feature a whopping 24 GB of GDDR6X memory, with 350 W typical board power.

https://www.techpowerup.com/268278/n...-in-three-skus

Nvida Ampere rađena je na 7nm litografiji od TSMC -a u istoj tvornici koja radi Ryzene 3000 i nove Ryzene 4000 serije.

Ako ce Ampere biti na istom proizvodnom procesu kao i Ryzeni 3000;

mislim da postoji šansa da ce imati isti "problem" sa zagrijavanjem kao i Ryzeni 3000.

This large difference in heat-density is the reason why newer Ryzen 3000 processors become much warmer at similar heatloads than their predecessors.

https://noctua.at/en/why-is-my-ryzen...with-my-cooler

We’re getting to the point where performance gains on new nodes are actually slowing down because the transistors are getting packed closer and closer together while consuming the same amount of power and thus producing the same amount of heat. Less surface area is going to mean less area to spread heat from, and consequentially that hurts thermal performance.

https://adoredtv.com/ryzen-3000-ther...-best-and-why/

više o tome smo pisali tu
http://forum.pcekspert.com/showpost....postcount=2658


Pretpostavljam da zbog 7nm litografije bit ce teže odvest toplinu sa cipa kao i na Ryzenima 3000 te ima smisla toplinski odvojit sam cip od naponskog djela grafe i tako omoguciti niže radne temperature samog cipa.

Ako se ne varam VRM ovi mogu raditi max do nekih 100 - 110 stupnjeva.

Autor scarzz

Kako onda misle hladit efikasno 5nm,3nm,2nm?

Autor Gigi1

TEC hladnjenje kod stackinga...stavljao sam linkove i slike međuostalim i na TEC patente od AMD-a (upravo zbog ove problematike disipacije topline sa prelaskom na manje proiz.procese) u temi nadolazeci procesori, međutim nije nikad bilo pinnano.

S obzirom da je interes bio skoro pa nikakav odustao sam od daljneg postanja patenata, a dobar dio ce ih se na ovaj ili onaj nacin implementirati u buduće proizvode kako bi riješili neke od postojecih limitacija.

[guerra]

Iskreno se nadam da ce AMD stisnuti u segmentu kartica kao sto je to napravio sa procesorima tako da mozemo jeftinije kupiti Nvidiju

[The Exiled]

Moglo bi i tak ispasti, jer nVidia ovaj put odmah ide s najjačim čipovima, da što više ublaži potencijalni udarac.

[dada-as]

Konacno ce ovi rudari koji se nisu rjesili onih 1000W plus bjesnih napajanja moci prodat to, samo tko ce kupit polovno napajanje kad ce za GPU skipat tolike pare.

[rokonja]

Autor dada-as

Konacno ce ovi rudari koji se nisu rjesili onih 1000W plus bjesnih napajanja moci prodat to, samo tko ce kupit polovno napajanje kad ce za GPU skipat tolike pare.

A neće valjda i AMD ić u tom visko buđetnom smjeru.

[Manuel Calavera]

Autor The Exiled

Moglo bi i tak ispasti, jer nVidia ovaj put odmah ide s najjačim čipovima, da što više ublaži potencijalni udarac.

Pa i ovu 2000 generaciju su odmah izbacili najjače, dok AMD nije bio nigdje sa high endom...

Radeon VII i 5700XT još nisu skinuli ni 1080Ti koja ima 4 god.

Tako da sam skeptičan da će AMD moći u utrku sa najjačom nvidijom, no ako ništa konzole su me barem uvjerile da mogu prebaciti 2080Ti. Prije toga sam mislio (ekstrapolacijom RDNA 1) da im je plafon skinuti 2080S sa gpu do 300w

[The Exiled]

Ma je, ali mogli su komotno dodatno razvodniti taj GA102 čip i opet bi kartice bile jake. Ovak odmah u startu ide najjača konfiguracija čipa s tri modela bazirana oko istog, pa kud puklo da puklo, ako AMD slučajno ima kakvu konkurenciju.

[Manuel Calavera]