Monday, October 5th 2020

NVIDIA Unveils RTX A6000 "Ampere" Professional Graphics Card and A40 vGPU

NVIDIA today unveiled its RTX A6000 professional graphics card, the first professional visualization-segment product based on its "Ampere" graphics architecture. With this, the company appears to be deviating from the Quadro brand for the graphics card, while several software-side features retain the brand. The card is based on the same 8 nm "GA102" silicon as the GeForce RTX 3080, but configured differently. For starters, it gets a mammoth 48 GB of GDDR6 memory across the chip's 384-bit wide memory interface, along with ECC support.

The company did not reveal the GPU's CUDA core count, but mentioned that the card's typical board power is 300 W. The card also gets NVLink support, letting you pair up to two A6000 cards for explicit multi-GPU. It also supports GPU virtualization, including NVIDIA GRID, NVIDIA Quadro Virtual Data Center Workstation, and NVIDIA Virtual Compute Server. The card features a conventional lateral blower-type cooling solution, and its most fascinating aspect is its power input configuration, with just the one 8-pin EPS power input. We will update this story with more information as it trickles out.
Update 13:37 UTC: The company also unveiled the A40, a headless professional-visualization graphics card dedicated for virtual-GPU/cloud-GPU applications (deployments at scale in data-centers). The card has similar specs to the RTX A6000.

Update 13:42 UTC: NVIDIA website says that both the A40 and RTX A6000 a 4+4 pin EPS connector (and not 8-pin PCIe) for power input. An 8-pin EPS connector is capable of delivering up to 336 W (4x 7 A @ 12 V).
Add your own comment

25 Comments on NVIDIA Unveils RTX A6000 "Ampere" Professional Graphics Card and A40 vGPU

#1
QUANTUMPHYSICS
MARKETING is everything.

The 3090 is a workstation card that's been marketed as a gaming card. And that's why we rushed out to buy one. NO ONE rushes out to buy Quadro cards because there's far less demand for workstation cards than thereis for gaming.


My question is whether / when a card will get the RTX Titan 3000 badge.
Posted on Reply
#3
ZeppMan217
8 pin? What's the matter, didn't make enough of their proprietary 12 pin connectors?
Posted on Reply
#4
Vya Domus
Yep, that's an 8 pin alright, doesn't add up.
Posted on Reply
#5
N3utro
QUANTUMPHYSICS
MARKETING is everything.

The 3090 is a workstation card that's been marketed as a gaming card. And that's why we rushed out to buy one. NO ONE rushes out to buy Quadro cards because there's far less demand for workstation cards than thereis for gaming.


My question is whether / when a card will get the RTX Titan 3000 badge.
Nvidia retail and quadro cards have always shared the same GPU over the years. The difference are that quadro versions have more vRAM and dedicated drivers designed to perform best with 2D/3D rendering softwares used by professionals like autocad.

Retails cards have drivers optimized for gaming.

If you buy a Quadro cards for gaming, you'll have bad gaming performance since the drivers will not be designed for gaming. That's why no one rushes out to buy Quadro cards for gaming.
Posted on Reply
#6
Oberon
ZeppMan217
8 pin? What's the matter, didn't make enough of their proprietary 12 pin connectors?
EPS12V, not PCIe 8-pin. Four 12V conductors vs three, so it can handle more power.
Posted on Reply
#7
Bubster
In the case of Nvidia ... it is a disastrous Marketing, they really messed this up last month :(
Posted on Reply
#8
roberto888
If you check the pinout on the render, you can see it's EPS 12V connector, not the PCI-e 8-pin.
Posted on Reply
#9
AsRock
TPU addict
ZeppMan217
8 pin? What's the matter, didn't make enough of their proprietary 12 pin connectors?
Not the design does not get any interference from the connector, were it's clear it would of with the 30 FE cards.

Dam that cooler looks pretty dam solid, Nv Might be getting more and more to move away from this plastic shroud crap.
Posted on Reply
#10
btarunr
Editor & Senior Moderator
Turns out, both the A6000 and A40 use 4+4 pin EPS as power source, not 8-pin PCIe.

TIL 8-pin EPS is capable of 336 W (7A * 12V * 4), and that any mainstream desktop motherboard with >1 EPS input is a scam.
Posted on Reply
#11
lexluthermiester
QUANTUMPHYSICS
The 3090 is a workstation card that's been marketed as a gaming card.
No, the 3090 is a gaming card that can also do some(not all) workstation type tasks. This card and it's big brothers are the workstation render/compute cards.
Posted on Reply
#12
RH92
Bubster
In the case of Nvidia ... its disastrous Marketing, they really messed this up last month :(
Yeah their GPUs being sold out everywhere really shows how disastrous their marketing is ............ :kookoo: :laugh:
Posted on Reply
#13
Nucleoprotein
lexluthermiester
No, the 3090 is a gaming card that can also do some(not all) workstation type tasks. This card and it's big brothers are the workstation render/compute cards.
Exactly, RTX3090 in CAD/FEM is crap, Quadro/Titan RTX is much better there. Like NV said - RTX 3090 is for gaming and creativity applications like Blender ect. not CAD/professional.
Posted on Reply
#14
fynxer
They can begin by delivering the card released, why release cards with very low NO STOCK anyways.

Still waiting for 3080 i ordered 20 days ago, nvidia said production in full swing and there would be waves of cards every week but i haven't seen any waves coming in.

They said there was good stock at release BUT won't say how much, what an obvious lie, the stock where non existent.

In Sweden it was calculated among all big retailers that there where about 700-800 cards available at release date in the entire country while demand was at least 20x more.
Posted on Reply
#15
BigBonedCartman
Yay I can’t wait to see these show up on Facebook Marketplace for 2.5x MSRP like the 3080 and 3090
Posted on Reply
#16
chief-gunney
fynxer
They can begin by delivering the card released, why release cards with very low NO STOCK anyways.

Still waiting for 3080 i ordered 20 days ago, nvidia said production in full swing and there would be waves of cards every week but i haven't seen any waves coming in.

They said there was good stock at release BUT won't say how much, what an obvious lie, the stock where non existent.

In Sweden it was calculated among all big retailers that there where about 700-800 cards available at release date in the entire country while demand was at least 20x more.
Nvidia don't want to be making many FE cards! Lousey margin on those. They want to hand over card supply to AIB's as quickly as possible as that's where the real money is made. The FE card scam is not new for them and they only use it to look like they're not ripping you off too much when in fact the consumer never gets the FE price. Didn't they release the 2080ti FE for $1000? how many people got a 2080TI for that?
Posted on Reply
#17
Valantar
ZeppMan217
8 pin? What's the matter, didn't make enough of their proprietary 12 pin connectors?
Vya Domus
Yep, that's an 8 pin alright, doesn't add up.
Enterprise GPUs typically use 8-pin EPS power connectors, which are rated for higher power draws than the PCIe 8-pin connector (likely due to having 4 wire pairs rather than 3 + two extra grounds. So unless these GPUs exceed... what is it, something like 400W including the PCIe slot? They should be fine.

Edit: @btarunr beat me to it above. Thx for providing the power rating btw, my two seconds of googling didn't provide it, so I gave up :P
Posted on Reply
#18
jabbadap
chief-gunney
Nvidia don't want to be making many FE cards! Lousey margin on those. They want to hand over card supply to AIB's as quickly as possible as that's where the real money is made. The FE card scam is not new for them and they only use it to look like they're not ripping you off too much when in fact the consumer never gets the FE price. Didn't they release the 2080ti FE for $1000? how many people got a 2080TI for that?
2080ti FE was OC card with msrp of $1199. While "reference" card was said to be $999. Though I'm not sure were there really any with that price and with the reference spec.
Posted on Reply
#19
Nater
Dang. Mid-December?! So we'll be waiting probably well into Februrary for the ~$1000 A4000 version to arrive. Guess I'll stick w/ the M4000 for a while longer.
Posted on Reply
#20
evernessince
RH92
Yeah their GPUs being sold out everywhere really shows how disastrous their marketing is ............ :kookoo: :laugh:
This argument has been used a million times.

Without actual stock numbers, being "sold out" means nothing.

What is a fact is that Nvidia announced there won't be wide availability of their cards until sometime in 2021. Launching a product and then being out of stock for months on end is bad business. People stop caring after a point.
Posted on Reply
#21
Berfs1
Wait a minute, so you are telling me this whole damn time NVIDIA could have just used the freaking 8 pin EPS connector for the RTX 30 series cards.......
btarunr
TIL 8-pin EPS is capable of 336 W (7A * 12V * 4), and that any mainstream desktop motherboard with >1 EPS input is a scam.
I mean, those 10 core CPUs can hit 300W... It might be necessary for the 10 core CPUs and highly overclocked 8 core CPUs, not entirely a scam, but usually not needed for most people as you need really good cooling for that kind of power [on a smaller chip w/ smaller IHS like LGA115x/LGA1200].
Posted on Reply
#22
Valantar
Berfs1
Wait a minute, so you are telling me this whole damn time NVIDIA could have just used the freaking 8 pin EPS connector for the RTX 30 series cards.......
Given that a huge number of PSUs have just one EPS cable included, that would have been just as problematic.
Posted on Reply
#23
RH92
evernessince
This argument has been used a million times.
Because this argument makes sense unlike yours :rolleyes:
evernessince
Without actual stock numbers, being "sold out" means nothing.
What is a fact is that Nvidia announced there won't be wide availability of their cards until sometime in 2021. Launching a product and then being out of stock for months on end is bad business. People stop caring after a point.
Dude you are confused this is not what Huang said , what Huang said is that since the demand has been unprecedented he is not expecting cards to be in stock anytime soon . The part that gets you confused is that lack of stock isn't indicative of GPUs not selling well ( or not selling at all ) but quite the opposite !

You don't need GPUs to be physically in stock in order to move them , all resellers have implemented preordering/queuing systems so as soon as they actually receive some physical stock it disapears since this stock is being used to fulfill those preorders . In other words GPUs move so fast that retailers don't even have time to add them to their inventory ( commonly called stock ) .... now i don't know how good your sense of business is but thats the definition of 3rd world problems !

If anything else Huang also declared in the same statement that Nvidia is expecting a very big Q4 season which when translated means , business couldn't be any better for them ........
Posted on Reply
#24
Berfs1
Valantar
Given that a huge number of PSUs have just one EPS cable included, that would have been just as problematic.
On that note, I am genuinely confused why NVIDIA is using EPS connectors instead of PCIe for the professional cards. I mean yeah it has more power, but there is usually not a leftover EPS cable on normal PSUs. We are lucky to be able to have 2 EPS connectors in our PSUs. btw yes I am aware this kind of contradicts my original statement, as I did not think about the actual number of EPS connectors on typical PSUs.
Posted on Reply
#25
evernessince
RH92
The part that gets you confused is that lack of stock isn't indicative of GPUs not selling well ( or not selling at all ) but quite the opposite !

Dude you are confused this is not what Huang said , what Huang said is that since the demand has been unprecedented he is not expecting cards to be in stock anytime soon . The part that gets you confused is that lack of stock isn't indicative of GPUs not selling well ( or not selling at all ) but quite the opposite !

You don't need GPUs to be physically in stock in order to move them , all resellers have implemented preordering/queuing systems so as soon as they actually receive some physical stock it disapears since this stock is being used to fulfill those preorders . In other words GPUs move so fast that retailers don't even have time to add them to their inventory ( commonly called stock ) .... now i don't know how good your sense of business is but thats the definition of 3rd world problems !

If anything else Huang also declared in the same statement that Nvidia is expecting a very big Q4 season which when translated means , business couldn't be any better for them ........
I'm not saying what you assumed I'm saying. All I pointed out is that your argument has no factual basis. You said:

"Yeah their GPUs being sold out everywhere really shows how disastrous their marketing is ............ :kookoo: "

Given that we have zero data on what exactly constitutes "sold out", it could be anywhere from 0 to 999,999.

I'm not saying sales are good or bad, I'm saying that if you make the argument that sold out = good, you should provide data to back it up.


" all resellers have implemented preordering/queuing systems so as soon as they actually receive some physical stock it disapears since this stock is being used to fulfill those preorders"

It should also be mentioned that pre-ordering and queuing are not the same. Many retailers that accept pre-orders do not queue. Of course it makes sense that they do not, a queue is only useful if you expect an extended period of very low stock. I've pre-ordered plenty of products from Newegg and not once have I seen a queue. I also queued for the index near release and that system was fundamentally different. You'd apply to the queue, be given a time estimate of your product would be ready, and then when it's ready pay for it. If you don't pay for it within 48 hours, you loose your spot. That is the exact same format of queue that EVGA is using. A system like that requires a decent amount of devs hours to create and cannot be done overnight. It makes sense for EVGA to implement a system like that given that Nvidia graphics cards are likely 50% of their business. For others though it may not make sense. I wish it were more common as it can help greatly when new PC parts release.
Posted on Reply
Add your own comment