[clang][Driver][HIP] Change OffloadingActionBuilder to respect the --no-gpu-bundle-output flag

clang/lib/Driver/Driver.cpp

@@ -3853,6 +3853,9 @@ class OffloadingActionBuilder final {
   /// Flag set to true if all valid builders allow file bundling/unbundling.
   bool CanUseBundler;
 
+  /// Flag set to false if an argument turns off bundling.
+  bool ShouldUseBundler;
+
 public:
   OffloadingActionBuilder(Compilation &C, DerivedArgList &Args,
                           const Driver::InputList &Inputs)
@@ -3887,6 +3890,9 @@ class OffloadingActionBuilder final {
     }
     CanUseBundler =
         ValidBuilders && ValidBuilders == ValidBuildersSupportingBundling;
+
+    ShouldUseBundler = Args.hasFlag(options::OPT_gpu_bundle_output,
+                                    options::OPT_no_gpu_bundle_output, true);
   }
 
   ~OffloadingActionBuilder() {
@@ -4038,11 +4044,11 @@ class OffloadingActionBuilder final {
       SB->appendTopLevelActions(OffloadAL);
     }
 
-    // If we can use the bundler, replace the host action by the bundling one in
-    // the resulting list. Otherwise, just append the device actions. For
-    // device only compilation, HostAction is a null pointer, therefore only do
-    // this when HostAction is not a null pointer.
-    if (CanUseBundler && HostAction &&
+    // If we can and should use the bundler, replace the host action by the
+    // bundling one in the resulting list. Otherwise, just append the device
+    // actions. For device only compilation, HostAction is a null pointer,
+    // therefore only do this when HostAction is not a null pointer.
+    if (CanUseBundler && ShouldUseBundler && HostAction &&
         HostAction->getType() != types::TY_Nothing && !OffloadAL.empty()) {
       // Add the host action to the list in order to create the bundling action.
       OffloadAL.push_back(HostAction);

clang/test/Driver/no-gpu-bundle-respected.hip

@@ -0,0 +1,24 @@
+// RUN: %clang -ccc-print-phases -c -emit-llvm \
+// RUN:   --offload-arch=gfx900,gfx1030 -O3 -x hip %s \
+// RUN:   2>&1 | FileCheck %s --check-prefix=BUNDLE
+
+// RUN: %clang -ccc-print-phases -c -emit-llvm \
+// RUN:   --gpu-bundle-output --offload-arch=gfx900,gfx1030 -O3 -x hip %s \
+// RUN:   2>&1 | FileCheck %s --check-prefix=BUNDLE
+
+// RUN: %clang -ccc-print-phases -c -emit-llvm \
+// RUN:   --no-gpu-bundle-output --offload-arch=gfx900,gfx1030 -O3 -x hip %s \
+// RUN:   2>&1 | FileCheck %s --check-prefixes=COMPILER,GFX1030,GFX900,OFFLOAD,NOBUNDLE
+
+// BUNDLE: clang-offload-bundler
+// NOBUNDLE-NOT: clang-offload-bundler
+
+// COM: sanity checks
+// COMPILER: compiler
+// GFX1030: (device-hip, gfx1030)
+// GFX900: (device-hip, gfx900)
+// OFFLOAD: offload
+
+int square(int num) {
+    return num * num;
+}