When compiling code being offloaded by OpenMP to an NVIDIA GPU, pass the -v to PTXAS if it was passed to the CLANG driver.
Details
Details
Diff Detail
Diff Detail
- Repository
- rL LLVM
Event Timeline
| test/Driver/openmp-offload.c | ||
|---|---|---|
| 607 ↗ | (On Diff #93176) | This path might not be correct on all systems. Do we really need this check? |
Comment Actions
Just noticed that this isn't specific to OpenMP. Could you move the test to Driver/cuda-external-tools.cu where the rest of ptxas is tested?