So I'm browsing Steam Summer fest games, and then I come across this:

https://store.steampowered.com/app/2230110/Fae_Farm/

£50... that is one hell of an expensive indie farm sim game, that's for sure.

I guess Square and Sony upping their prices is getting some daring indies to try the same, because that seems beyond reasonable, for what little it offers compared to all the other farming sim indie titles out there. 

That's true for GPU cores, but upscaling and frame generation don't need to read anything from the GPU except for the frame buffer.

In theory, you can fit a ray-tracing solution then although you'd be very limited in terms of shading (like other post-procs done in the ROP) but maybe something clever can be thought of such as path tracing frames on and off and matching in the back buffer.

I keep hoping we'll see that smart stuff like that from AMD or Intel but nope. They just want to fund stuff that can allow them to compete in HPC.

As for 3D SiCs, that feels like an even greater challenge than chiplets ('2.5D') and most of the industry seems to agree.

Would you think this was a render if you didn't know beforehand, let alone a real time one?

Up-scaling and frame generation do need a lot of fast caches to keep data buffered to work from, otherwise it does get expensive.

nVidia could in theory make all the Ray Tracing and Tensor/A.I routines run on the shader engines/Cuda cores as they are capable of 4/8/16INT and Floats to various degrees, but dedicating the hardware and slimming down those units is more space-efficient rather than making each shader pipeline more flexible... Although nVidia did make it's CUDA cores capable of performing Integers and Floating Point numbers concurrently with Turing if I remember correctly.

Many simpler upscaling/Anti-Aliasing methods these days are actually performed on the Shaders/Cuda cores because it's cheap and fast rather than ROPS... Often ROPS will be a bottleneck in a GPU design, hence why the Geforce 760 had such a massive improvement over the 660... It had less CUDA Cores and Teraflops, but much higher ROP throughput. (2.25 Teraflop on the 760 vs 2.45 Teraflops on the 660.)
In some scenarios where AA was done on the Cuda cores, the 660 would be faster than the 760, but once you start leveraging MSAA on the ROPS, the 760 would dwarf the 660. (Re-affirms the idea that Teraflops is also bullshit for determining gaming performance as well.)

So you could in theory run Ray Tracing operations on the Tensor cores rather than the RT cores if you wanted... But we can't couple those operations to ROPS as they just don't have the INT/FP throughput.

3D chip stacking started out with stacked DRAM, then NAND. Now we are doing it with Stacked cache on top of CPU cores.
The next jump will be stacked chiplets. - Yeah it will be a challenge, but so was chiplets once upon a time.

Stacked chips though can actually get around the limited latency and bandwidth issues of Fabric interconnects, so there are inherent benefits... Imagine current Ryzen chips, using the same fabrication, but consuming 50% LESS power than they do currently by stacking the chiplets. (That's how much energy is wasted on the fabric.)

Impressive. But I'd like to know the specs of his system.

I don't disagree that it will eventually be the way to go, just that chiplet will be less of a challenge and become viable first as a mid-step, perhaps even in consumer-grade GPUs. Infinity Link has a thousand times more bandwidth than either Crossfire or SLi, so I'm sure engineers can find a way around any lingering latency issue.

That or most people will be streaming games within ten years or so, so multi-chip GPUs become more desirable to the industry players anyway.

Apple M2 Ultra SoC Isn’t Faster Than AMD & Intel Last Year Desktop CPUs, 50% Slower Than NVIDIA RTX 4080

https://wccftech.com/apple-m2-ultra-soc-isnt-faster-than-amd-intel-last-year-desktop-cpus-50-slower-than-nvidia-rtx-4080/

Performance per watt will be Apples strong suit but when you consider just how much the M2 Ultra costs vs a PC with say a 13900K, the question then becomes how many years of extended use is going to take to make up the difference you are paying cause a base model Mac Studio with M2 Ultra starts at $4000 USD. You can get a 13900K + 4090 for $3000 USD quite easily but a 4090 is over 2x faster. Realistically, the only way these products make sense is if you need to use Apple specific software or need tons of memory for Ai since it's cheaper to spend $6600 USD on 192GB of Unified memory on M2 Ultra than $40,000 on a single Nvidia H100 with 80GB of vram.

Don't forget to tune into the Xbox Showcase here:

Alright it was a good conference. I'll post some of the trailers I am interested in:

Didn't watch from beggining but so many decent games and new IP's shown on there. Also pretty funny that Microsoft just embarrassed Sony with their presentation. And they were on a hiatus for a year.

CP 2077 dlc, I'm super excited for. That Bioshock looking game from IneXile looked promising too.

Fuck me Starfield looks incredible