Make the argument -Xcuda-ptxas visible to the driver in cl-mode

It has been noticed that the arguments are being passed twice to ptxas.
This also has been fixed by filtering out the arguments before appending
them to the new DAL created by CudaToolChain::TranslateArgs.

github:#86807

Author: jle-quel

clang/include/clang/Driver/Options.td

@@ -1003,7 +1003,8 @@ def : Joined<["-"], "Xclang=">, Group<CompileOnly_Group>,
 def Xcuda_fatbinary : Separate<["-"], "Xcuda-fatbinary">,
   HelpText<"Pass <arg> to fatbinary invocation">, MetaVarName<"<arg>">;
 def Xcuda_ptxas : Separate<["-"], "Xcuda-ptxas">,
-  HelpText<"Pass <arg> to the ptxas assembler">, MetaVarName<"<arg>">;
+  HelpText<"Pass <arg> to the ptxas assembler">, MetaVarName<"<arg>">,
+  Visibility<[ClangOption, CLOption]>;
 def Xopenmp_target : Separate<["-"], "Xopenmp-target">, Group<CompileOnly_Group>,
   HelpText<"Pass <arg> to the target offloading toolchain.">, MetaVarName<"<arg>">;
 def Xopenmp_target_EQ : JoinedAndSeparate<["-"], "Xopenmp-target=">, Group<CompileOnly_Group>,

clang/lib/Driver/ToolChains/Cuda.cpp

@@ -990,7 +990,10 @@ CudaToolChain::TranslateArgs(const llvm::opt::DerivedArgList &Args,
   }
 
   for (Arg *A : Args) {
-    DAL->append(A);
+    // Make sure flags are not duplicated.
+    if (!llvm::is_contained(*DAL, A)) {
+      DAL->append(A);
+    }
   }
 
   if (!BoundArch.empty()) {

clang/test/Driver/cuda-external-tools.cu

@@ -86,6 +86,12 @@
 // RUN:   -Xcuda-fatbinary -bar1 -Xcuda-ptxas -foo2 -Xcuda-fatbinary -bar2 %s 2>&1 \
 // RUN: | FileCheck -check-prefixes=CHECK,SM35,PTXAS-EXTRA,FATBINARY-EXTRA %s
 
+// Check -Xcuda-ptxas with clang-cl
+// RUN: %clang_cl -### -c -Xcuda-ptxas -foo1 \
+// RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
+// RUN:   -Xcuda-ptxas -foo2 %s 2>&1 \
+// RUN: | FileCheck -check-prefixes=CHECK,SM35,PTXAS-EXTRA %s
+
 // MacOS spot-checks
 // RUN: %clang -### --target=x86_64-apple-macosx -O0 -c %s 2>&1 \
 // RUN:   --offload-arch=sm_35 --cuda-path=%S/Inputs/CUDA/usr/local/cuda \
@@ -140,6 +146,8 @@
 // CHECK-SAME: "[[PTXFILE]]"
 // PTXAS-EXTRA-SAME: "-foo1"
 // PTXAS-EXTRA-SAME: "-foo2"
+// CHECK-NOT: "-foo1"
+// CHECK-NOT: "-foo2"
 // RDC-SAME: "-c"
 // CHECK-NOT: "-c"