I heard there is still trouble to buy consumer grade Nvidia GPU. At this point I am wondering if it is Gaming market demand, AI, or simply a supply issue.
On another note I am waiting for Nvidia's entry to CPU. At some point down the line I expect the CPU will be less important, ( relatively speaking ) and Nvidia could afford to throw a CPU in the system as bonus. Especially when we are expecting ARM X930 to rival Apple's M4 in terms of IPC. CPU design has become somewhat of a commodity.
My understanding is it's the AI demand and willingness to pay crazy money for wafer that makes consumer GPUs a significantly less attractive product to produce.
I don't have really solid evidence, just semi-anecdotal/semi-reliable internet posts:
Nvidia as a whole has been fairly anti-consumer recently with pricing, so I wouldn't be banking on them for a great cpu option. Weirdly Intel is in the position where they have to prove themselves, so hopefully they'll give us some great products in the next 2-5 years - if they survive (think the old lead-up-to-ryzen era for amd)
It feels a bit like the Intel Core Ultra desktop CPU launch where the prices were the critical factor that doomed an otherwise pretty okay product. At least Intel's excuse is that they’re closer to going under than before, even if their GPUs were pretty fairly priced anyways.
It’s almost like everyone complains about their prices and the fact that they’re releasing 8 GB cards… and then still go and give them money anyways.
The same chip as the "proper"[1] 5090 is also used for workstation and some server cards, which go for easy higher price. So it's just an allocation of child to different products, taking into account that with the power demands and design issues in 5090s power supply there isn't all that much demand for 5090 either.
[1] there are now 5090 branded cards that use same chip as 5080
Their Grace datacenter CPU is basically a chip where they put down all the LPDDR5 memory controllers (albeit curiously slow), NVLINK and PCIe IOs they needed around the perimeter, and then filled in the interior with boring off the shelf ARM cores. It's basically an IO and memory expander that happens to run Linux.
GB10 when it ships might be more interesting, since it'll go into systems that need to support use cases other than merely feeding a big GPU ML workloads. But it sounds like the CPU chiplet at least was more or less outsourced to Mediatek.
The whole missing ROPs saga[1][2] didn't help. I bought a 5070 Ti and had to return it due to missing ROPs. Had to get another brand as replacement, as they had so little stock.
Where did you get that from? Pretty sure it's a single planar set of transistors. Those transistors are manufactured using multiple layers of mask.
FinFET transistors are described as 3D or non-planar but crucially this isn't allowing transistor on transistor stacking you've just got the gate structure of the FinFET poking out above the plane of the rest of the transistors.
Silicon on silicon die stacking is a possibility but limits your power and GPUs run very hot so it's not an option for them.
Chips and Cheese GPU analysis are pretty detailed, but they need to be taken with a huge grain of salt because the results only really apply to OpenCL and nobody buying NVIDIA or AMD GPUs for Compute runs OpenCL on them; its either CUDA or HIP, which differ widely in parts of their compilation stack.
After reading the entire analysis, I'm left wondering, what observations in this analysis - if any - actually apply to CUDA?
Does the comparison even makes sense, considering there's (more than) an order of magnitude difference in price between the AMD's Desktop GPU and NVIDIA's Workstation accelerator?
17 comments
[ 4.2 ms ] story [ 49.7 ms ] threadOn another note I am waiting for Nvidia's entry to CPU. At some point down the line I expect the CPU will be less important, ( relatively speaking ) and Nvidia could afford to throw a CPU in the system as bonus. Especially when we are expecting ARM X930 to rival Apple's M4 in terms of IPC. CPU design has become somewhat of a commodity.
I don't have really solid evidence, just semi-anecdotal/semi-reliable internet posts:
Eg. https://www.tomshardware.com/tech-industry/more-than-251-mil...
Nvidia as a whole has been fairly anti-consumer recently with pricing, so I wouldn't be banking on them for a great cpu option. Weirdly Intel is in the position where they have to prove themselves, so hopefully they'll give us some great products in the next 2-5 years - if they survive (think the old lead-up-to-ryzen era for amd)
If they’re swimming in the AI cash and the consumer GPU segment isn’t that important (https://www.visualcapitalist.com/nvidia-revenue-by-product-l...) then why on earth couldn’t they do less price gouging?
It feels a bit like the Intel Core Ultra desktop CPU launch where the prices were the critical factor that doomed an otherwise pretty okay product. At least Intel's excuse is that they’re closer to going under than before, even if their GPUs were pretty fairly priced anyways.
It’s almost like everyone complains about their prices and the fact that they’re releasing 8 GB cards… and then still go and give them money anyways.
[1] there are now 5090 branded cards that use same chip as 5080
Haven't they already started doing this with Grace and GB10?
- https://www.nvidia.com/en-us/data-center/grace-cpu/
- https://nvidianews.nvidia.com/news/nvidia-puts-grace-blackwe...
GB10 when it ships might be more interesting, since it'll go into systems that need to support use cases other than merely feeding a big GPU ML workloads. But it sounds like the CPU chiplet at least was more or less outsourced to Mediatek.
[1]: https://gamersnexus.net/gpus/investigating-nvidias-defective...
[2]: https://nvidia.custhelp.com/app/answers/detail/a_id/5628/~/h...
Where did you get that from? Pretty sure it's a single planar set of transistors. Those transistors are manufactured using multiple layers of mask.
FinFET transistors are described as 3D or non-planar but crucially this isn't allowing transistor on transistor stacking you've just got the gate structure of the FinFET poking out above the plane of the rest of the transistors.
Silicon on silicon die stacking is a possibility but limits your power and GPUs run very hot so it's not an option for them.
It seems there is a huge market for inference.
After reading the entire analysis, I'm left wondering, what observations in this analysis - if any - actually apply to CUDA?