Page MenuHomePhabricator

[CUDA] updated CompileCudaWithLLVM.rst
ClosedPublic

Authored by tra on Nov 15 2018, 4:49 PM.

Diff Detail

Repository
rL LLVM

Event Timeline

tra created this revision.Nov 15 2018, 4:49 PM
jlebar accepted this revision.Nov 15 2018, 4:52 PM
jlebar added inline comments.
llvm/docs/CompileCudaWithLLVM.rst
27 ↗(On Diff #174300)

Is there a way to query clang (or its source code) to see what versions it supports, so that people don't have to ping us manually? Like, if we write the documentation saying "current release of clang", are we going to update it for every new release?

This revision is now accepted and ready to land.Nov 15 2018, 4:52 PM
tra added inline comments.Nov 15 2018, 5:03 PM
llvm/docs/CompileCudaWithLLVM.rst
27 ↗(On Diff #174300)

There's no convenient way at the moment. The easiest way for the user right now is to check __clang_cuda_runtime_wrapper.h

We could enhance CUDA installation detector to issue a warning if it finds and unsupported CUDA version and list supported versions there.

This revision was automatically updated to reflect the committed changes.
jlebar added inline comments.Nov 15 2018, 5:08 PM
llvm/docs/CompileCudaWithLLVM.rst
27 ↗(On Diff #174300)

Sure, I'm wondering if e.g. we shouldn't point users at __clang_cuda_runtime_wrapper.h?

We could enhance CUDA installation detector to issue a warning if it finds and unsupported CUDA version and list supported versions there.

Something like that might be nice.