How to emit device-side IR when compiling cuda?

Clang Frontend
1

I’m trying:

clang+±3.8 -I/usr/local/cuda-7.5/include llvm-sample.cu -emit-llvm -S -o llvm-sample.ll

This seems to emit host-side IR only?

2

I think I’m still in the wrong list. I’ll find the right list eventually…

3

Have you tried to pass the right target triple option?

i.e. clang -target …

4

Yes, I figured it out in the end, just need --cuda-device-only, https://github.com/hughperkins/cuda-ir-to-opencl/blob/18833aa40b69859c5ca24f22715ad3be2c029ff9/run-ir-to-opencl-demo.sh#L9