[clang] [clang][Driver][HIP] Change OffloadingActionBuilder to respect the --no-gpu-bundle-output flag (PR #163834)

[alessandra simmons via cfe-commits]

https://github.com/MixedMatched created https://github.com/llvm/llvm-project/pull/163834

Currently, the command `clang -c -emit-llvm --no-gpu-bundle-output --offload-arch=gfx900,gfx1030 -O3 -x hip square.hip` will lead to a bundled output:
```
❯ ../bin/clang -c -emit-llvm --no-gpu-bundle-output --offload-arch=gfx900,gfx1030 -O3 -x hip square.hip
❯ ls
square.hip
square.bc
```

This doesn't match my expectation of the behavior of `--no-gpu-bundle-output`, so this adds a check into OffloadingActionBuilder for the flag when replacing the host compile action for a bundling action.

>From 0125a69ee8e9ec206c72f64d30b8c13324b7a107 Mon Sep 17 00:00:00 2001
From: alessandra simmons <30960626+MixedMatched at users.noreply.github.com>
Date: Thu, 2 Oct 2025 18:34:34 -0400
Subject: [PATCH] [clang][Driver][HIP] Change OffloadingActionBuilder to
 respect the --no-gpu-bundle-output flag

---
 clang/lib/Driver/Driver.cpp                   | 16 +++++++++++-----
 clang/test/Driver/no-gpu-bundle-respected.hip | 18 ++++++++++++++++++
 2 files changed, 29 insertions(+), 5 deletions(-)
 create mode 100644 clang/test/Driver/no-gpu-bundle-respected.hip

diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index 40ea513e85427..02cfc4314bbc4 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -3844,6 +3844,9 @@ 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)
@@ -3878,6 +3881,9 @@ class OffloadingActionBuilder final {
     }
     CanUseBundler =
         ValidBuilders && ValidBuilders == ValidBuildersSupportingBundling;
+
+    ShouldUseBundler = Args.hasFlag(options::OPT_gpu_bundle_output,
+                                    options::OPT_no_gpu_bundle_output, true);
   }
 
   ~OffloadingActionBuilder() {
@@ -4029,11 +4035,11 @@ 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);
diff --git a/clang/test/Driver/no-gpu-bundle-respected.hip b/clang/test/Driver/no-gpu-bundle-respected.hip
new file mode 100644
index 0000000000000..1587551f0322d
--- /dev/null
+++ b/clang/test/Driver/no-gpu-bundle-respected.hip
@@ -0,0 +1,18 @@
+// RUN: %clang -ccc-print-phases -c -emit-llvm \
+// RUN:   --offload-arch=gfx900,gfx1030 -O3 -x hip %s \
+// RUN:   2>&1 | FileCheck %s --check-prefix=OFFLOAD
+
+// 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=OFFLOAD
+
+// 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-prefix=OFFLOAD2
+
+// OFFLOAD: clang-offload-bundler
+// OFFLOAD2-NOT: clang-offload-bundler
+
+int square(int num) {
+    return num * num;
+}