[PATCH] D120272: [CUDA] Add driver support for compiling CUDA with the new driver

Joseph Huber via Phabricator via cfe-commits cfe-commits at lists.llvm.org
Fri Apr 22 10:27:45 PDT 2022

jhuber6 added inline comments.

Comment at: clang/lib/Driver/ToolChains/Clang.cpp:6223-6224
   if (IsCuda || IsHIP) {
-    if (Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc, false))
+    if (Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc, false) ||
+        Args.hasArg(options::OPT_foffload_new_driver))
tra wrote:
> If user specifies both `-fno-gpu-rdc` and `-foffload-new-driver` we would still enable RDC compilation.
> We may want to at least issue a warning. 
> Considering that  we have multiple places where we may check for `-f[no]gpu-rdc` we should make sure we don't get different ideas whether RDC has been enabled.
> I think it may make sense to provide a common way to figure it out. Either via a helper function that would process CLI arguments or calculate it once and save it somewhere.
I haven't quite finalized how to handle this. The new driver should be compatible with a non-RDC build since we simply wouldn't embed the device image or create offloading entries. It's a little bit more difficult here since the new method is opt-in so it requires a flag. We should definitely emit a warning if both are enabled (I'm assuming there's one for passing both `fgpu-rdc` and `fno-gpu-rdc`). I'll add one in.

Also we could consider the new driver *the* RDC in the future which would be the easiest. The problem is if we want to support CUDA's method of RDC considering how other build systems seem to expect it. I could see us embedding the fatbinary in the object file, even if unused, just so that cuobjdump works. However we couldn't support the generation of `__cudaRegisterFatBinary_nv....` functions because then those would cause linker errors. WDYT?

  rG LLVM Github Monorepo



More information about the cfe-commits mailing list