Repository navigation
Replies: 1 comment
|
It's not impossible, that's what Nintenfo Switch emulators do |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
I know that SASS isn't fully documented, but there’s a list of disassembled instructions available in NVIDIA's CUDA documentation. However, I’m not sure if that’s a complete list of instructions or just a partial reference.
Does anyone have insights on whether building a compiler or translator that maps NVIDIA GPU ISA to AMD GPU ISA or AMD LLVM IR is technically feasible? What kind of challenges should we expect, especially given the architectural differences between NVIDIA and AMD GPUs? Is there any project out there that’s already working on something similar?
I’d love to hear thoughts or experiences!
All reactions