Skip to content

Inspecting generated kernel code? #53

Answered by mmacklin
ib00 asked this question in Q&A
Discussion options

You must be logged in to vote

Hi there,

Yes, please take a look in the Kernel Cache location printed at Warp initialization time, e.g.:

   Version: 0.5.0
   Devices:
     "cpu"    | AMD64 Family 25 Model 33 Stepping 0, AuthenticAMD
     "cuda:0" | NVIDIA GeForce RTX 3090
     "cuda:1" | NVIDIA GeForce RTX 2080 Ti
   Kernel cache: C:\Users\mmacklin\AppData\Local\NVIDIA Corporation\warp\Cache\0.5.0

C:\Users\mmacklin\AppData\Local\NVIDIA Corporation\warp\Cache\0.5.0 holds the generated C++/CUDA code and compiled .ptx files that you can inspect. You can also compile / link these into your own existing C++ projects.

Cheers,
Miles

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by ib00
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants