• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

NVIDIA 4000 Series

mrk said:
www.notebookcheck.net

Nvidia RTX 50 GB102 Blackwell early internal performance gains only in range of Pascal to Turing and not 2.6x from AD102, increased SM counts on the anvil

Nvidia's next gen RTX 50 Blackwell with purported 144 SMs isn't reaching ambitious performance gains in internal testing, according to latest rumors. Apparently, Blackwell's performance gains vis-à-vis AD102 are in the range of what we've seen from Pascal to Turing, but Nvidia wants more. This...
www.notebookcheck.net www.notebookcheck.net

If it stays that way and perf doesn't hit the rumoured targets, then don't expect higher end 40xx prices to drop.
Click to expand...
gpuerrilla said:
While people were ripping into AMD for their shallow RDNA3 gains by going chiplet, it was pointed out by a few tuber nerds that nvidia are going to hit a wall soon. The leap the 4090 did was decent, but the above would make sense; although its quite early to be believing anything tbh.
Click to expand...

Nvidia is already using an improved TSMC 5NM,ie,4N so moving to TSMC 3NM is going to yield less improvements. Ada Lovelace saw a two node jump being on TSMC 5NM 4N from Samsung 8NM,which was more a 10NM class process node.

This generation AMD,no doubt decided to make sure they can get over the teething problems of chiplets.One of them is power and extra die area. You saw that when AMD actually started using MCM Zen/Zen+ commercial designs and it was only with Zen2/Zen3 they managed to finally get over the power problems.
 
Last edited:
JediFragger said:
The 4090 turned out to be an absolute monster, it'll be interesting to see if the 5090 can maintain the leap!
Click to expand...

Yeah but the most gains were because of this:

CAT-THE-FIFTH said:
Nvidia is already using an improved TSMC 5NM,ie,4N
Click to expand...

Might be a good reason to wait for RDNA4 instead of the 'normal' priced msrp stock to return to levels where it needs to be.
 
gpuerrilla said:
While people were ripping into AMD for their shallow RDNA3 gains by going chiplet, it was pointed out by a few tuber nerds that nvidia are going to hit a wall soon. The leap the 4090 did was decent, but the above would make sense; although its quite early to be believing anything tbh.
Click to expand...

It is when chiplets are used to distribute processing that stuff starts getting interesting. What AMD is doing so far isn't that.
 
Last edited:
gpuerrilla said:
Might be a good reason to wait for RDNA4 instead of the 'normal' priced msrp stock to return to levels where it needs to be.
Click to expand...

If dGPU sales stay rubbish for the immediate future we might see the next generation releases get delayed.

Rroff said:
It is when chiplets are used to distribute processing that stuff starts getting interesting. What AMD is doing so far isn't that.
Click to expand...

Which might happen next generation. But they are taking the safe approach ATM.

Power is going to be the bigger issue here.
 
Last edited:
JediFragger said:
The 4090 turned out to be an absolute monster, it'll be interesting to see if the 5090 can maintain the leap!
Click to expand...
I'd say it's unlikely to be as big of a jump because the node difference won't be as stark. Samsung 8nm to TSMC 5nm (4N) was like a doubling in transistor density whereas 5nm->3nm is only supposed to bring a 33% or so improvement as far as I can find out. The only thing that will make up for this will either be a larger die size budget or massive architectural improvements. Although they will probably lean on some next gen DLSS.

Lots of scope to generate excitement at the mid-range if the top end won't scale as well, though...
 
Neil79 said:
Are we getting yearly GPU upgrades?
:eek:
Click to expand...

Highly doubt it, Nvidia said at the latter end of 2022 they are aiming for a new GPU arch every 2 years... plus we're still yet to see the 4080 Ti, There's enough of a gap between the 4080 and 4090 for it to exist... and the 4090 Ti or whatever they call the full fat card.

Q3 next year is when we should be seeing the 5000 series, these tests are done well in advance of a GPU coming out.

From what I've read, Nvidia were testing Ampere around 6 or so months after Turing came out and Ada around 6 or so months after Ampere came out and each of those had a 24 month shelf life.
 
Last edited:

I don't want to unplug my connector to check but am putting trust into Corsair's own 12vHPWR cable. Disconnecting and reconnecting will no doubt put wear on the connector though too. Mine is firmly locked in place.

For ref, the Corsair cable splits into 2x outlets from the PSU and is a much more neater cable solution than the Nvidia 12VHPWR to 3x PSU connectors.
 
Last edited:
You must log in or register to reply here.
Back
Top Bottom