> Little of the detail of this path is documented by NVIDIA, at least not to the level that we’d like, so we’ll determine it by running timing experiments on the hardware itself
This is a type of article that is HN worthy and came to HN for initially because I don't even understand a third of content there. Giving me inspiration to dive deeper.
That's the best feeling -- idly clicking through looking for that one rabbit hole to fall down then stumbling upon a gem like this. I noticed this the first time on copetti.org articles about game console architectures: know nothing, look every jargon or acronym up as you read along, end up with 42 tabs and a basic high-level understanding of the topic by the end.
For a long time, the chip manufacturers had an inclination to simplify the hardware and rely on the software adapting and optimizing. But for decades this bid failed. Now we have the unrelenting AI capable of finetuning kernels relatively quickly. Maybe simpler hw will work this time? Note: not sure if TPU/NPU is not only simple but also too limited.
There isn't really an ELI5 version of computer architecture but you could start with the book Inside the Machine by Jon Stokes. Then you can get into SIMT.
> Little of the detail of this path is documented by NVIDIA, at least not to the level that we’d like, so we’ll determine it by running timing experiments on the hardware itself
Or you could just use the AMD isa.
This is a type of article that is HN worthy and came to HN for initially because I don't even understand a third of content there. Giving me inspiration to dive deeper.
SEriously, I don't understand it (yet) lol.
That's the best feeling -- idly clicking through looking for that one rabbit hole to fall down then stumbling upon a gem like this. I noticed this the first time on copetti.org articles about game console architectures: know nothing, look every jargon or acronym up as you read along, end up with 42 tabs and a basic high-level understanding of the topic by the end.
For a long time, the chip manufacturers had an inclination to simplify the hardware and rely on the software adapting and optimizing. But for decades this bid failed. Now we have the unrelenting AI capable of finetuning kernels relatively quickly. Maybe simpler hw will work this time? Note: not sure if TPU/NPU is not only simple but also too limited.
VERY good article, reminds me on:
"what every programmer should know about memory" https://github.com/Ty-Chen/Reading-List/blob/master/What%20e...
That’s somebody’s highlighted copy of the PDF.
Here’s a clean version: https://people.freebsd.org/~lstewart/articles/cpumemory.pdf
Can someone help me understand why I spent 5 minutes reading something that I still don't understand?
Link for the ELI5 version?
There isn't really an ELI5 version of computer architecture but you could start with the book Inside the Machine by Jon Stokes. Then you can get into SIMT.
YMMV; not all GPUs work exactly like this
Ctrl+F PCIe BAR.. nothing.
This is talking about HBM/GDDR
a.k.a. VRAM
Something needs to be transferred from sysmem right?
2 replies →