================
@@ -69,28 +69,33 @@ class IncrementalCompilerBuilder {
// Offload options
void SetOffloadArch(llvm::StringRef Arch) { OffloadArch = Arch; };
- // CUDA specific
- void SetCudaSDK(llvm::StringRef path) { CudaSDKPath = path; };
+ // The SDK path (CUDA or ROCm) of the device language being offloaded to.
+ void SetDeviceSDK(llvm::StringRef Path) { DeviceSDKPath = Path; }
----------------
vgvassilev wrote:
Can we have a setup where we have both cuda- and hip-based setups and we expect
to be able to work with both of them?
That's probably even more relevant for a multi-interpreter setup..
https://github.com/llvm/llvm-project/pull/231783
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
