But what if nvidia used those fuses because an A100 had too many fabrication faults so it could only be a cheaper mining card?
(which is the more likely scenario because they can make much more money on enterprise/datacenter products, see DRAM)
phelix001 2 minutes ago [-]
They definitely did, but maybe you can get some good results running your own tests and determining if they really ARE bad or not, or they just overly tagged them out.
stingraycharles 5 minutes ago [-]
Isn’t this how these things are always done? Same with number of cores in a CPU, the higher core and lower core come from the same fabrication process, it’s just that the lower core CPU had more faulty cores that are disabled.
mmo93 3 minutes ago [-]
Depends a lot on when its from in the product cycle, the yield at the end of production runs are usually so good that it turns into artificial product segmentation
amelius 3 minutes ago [-]
Yes, that's why I question the approach here.
Testing hardware is a complicated matter (you can do a PhD on the topic), and nvidia probably does a better job at it than a hacker in their basement who thinks they can upgrade their GPU for free.
On the other hand ... perhaps a few bit errors is not a problem for AI workloads ... but they could also crash your system ...
9 minutes ago [-]
39 minutes ago [-]
roger_ 14 minutes ago [-]
Glad I jumped on these cards, excited to give this a try!
Hard to believe $1k was a deal a few months ago (and $200 before then).
gravypod 2 minutes ago [-]
I really wish I did. I told a friend about how I bet an unlock would come and decided to buy them when I heard about an unlock.
The highs and lows of my predictive capabilities
SillyUsername 33 minutes ago [-]
I just wish they had something like this for older Tesla p100s, p4s...
Savlume 11 minutes ago [-]
[flagged]
samlinnfer 41 minutes ago [-]
Before you get too excited about the CMP 170HX, the prices had already skyrocketed and that card doesn't a cooler on it and is designed for a server cooler that sounds like a jet engine. Also most of the 80GB vram unlocks have bad RAM and that is the reason they were locked in the first place, otherwise they would have became A100s.
Anyways, that's what I tell myself as I taste my bowl of sour grapes.
Rendered at 12:58:54 GMT+0000 (Coordinated Universal Time) with Vercel.
(which is the more likely scenario because they can make much more money on enterprise/datacenter products, see DRAM)
Testing hardware is a complicated matter (you can do a PhD on the topic), and nvidia probably does a better job at it than a hacker in their basement who thinks they can upgrade their GPU for free.
On the other hand ... perhaps a few bit errors is not a problem for AI workloads ... but they could also crash your system ...
Hard to believe $1k was a deal a few months ago (and $200 before then).
The highs and lows of my predictive capabilities
Anyways, that's what I tell myself as I taste my bowl of sour grapes.