intel/llvm#17068 changed the semantics for urEnqueueKernelLaunch to make validation optional; Implementations may return either INVALID_ARGS or SUCCESS if the arguments are wrong.
However, the Cuda backend in the InvalidKernelArgs test returns UR_RESULT_ERROR_INVALID_VALUE. This is because cuLaunchKernel returns CUDA_ERROR_INVALID_VALUE for the (incorrect) values in the test.
The implementation of urEnqueueKernelLaunch should be updated to either return INVALID_ARGS or SUCCESS. Note that validation is optional, so if the CUDA driver is unable to perform the validation, it is allowed to report a success even if the args are invalid.
intel/llvm#17068 changed the semantics for
urEnqueueKernelLaunchto make validation optional; Implementations may return eitherINVALID_ARGSorSUCCESSif the arguments are wrong.However, the Cuda backend in the
InvalidKernelArgstest returnsUR_RESULT_ERROR_INVALID_VALUE. This is becausecuLaunchKernelreturnsCUDA_ERROR_INVALID_VALUEfor the (incorrect) values in the test.The implementation of
urEnqueueKernelLaunchshould be updated to either returnINVALID_ARGSorSUCCESS. Note that validation is optional, so if the CUDA driver is unable to perform the validation, it is allowed to report a success even if the args are invalid.