[OpenMP] Fix offload packager not writing to temps correctly

[jhuber6]

Summary

The offloading packager doesn't have a normal offloading kind. This
would result in its output being sent to the executable name when in
save-temps mode. This would then get overwritten by the actual output.
This patch adds specific checks to make sure that it gets the correct
name.

[tra]

LGTM overall with a couple of nits.

clang/lib/Driver/Driver.cpp

5420

!! assumes specific values for the mask returned by getOffloadingHostActiveKinds().

(A->getOffloadingHostActiveKinds() != OFK_None && !AtTopLevel) would be a bit easier to understand, IMO.
Maybe even !(A->getOffloadingHostActiveKinds() == OFK_None || AtTopLevel).

5658–5659

bool UseOutExt = IsHIPNoRDC || isa<OffloadPackagerJobAction>(JA);
if (UseOutExt)
  ...

[jhuber6]

Thanks for the review.

clang/lib/Driver/Driver.cpp

5420

That was confusing me as well, might as well change it while I'm here.

[jhuber6]

Addressing nits.

clang/lib/Driver/Driver.cpp

if (auto *UA = dyn_cast<OffloadUnbundlingJobAction>(JA)) {
     Result = CachedResults[ActionTC].front();
   } else if (JA->getType() == types::TY_Nothing)
     Result = {InputInfo(A, BaseInput)};
   else {
     // We only have to generate a prefix for the host if this is not a top-level
     // action.
     std::string OffloadingPrefix = Action::GetOffloadingFileNamePrefix(
         A->getOffloadingDeviceKind(), TC->getTriple().normalize(),
-        /*CreatePrefixForHost=*/!!A->getOffloadingHostActiveKinds() &&
-            !AtTopLevel);
+        /*CreatePrefixForHost=*/isa<OffloadPackagerJobAction>(A) ||
+            !(A->getOffloadingHostActiveKinds() == Action::OFK_None ||
+              AtTopLevel));
     if (isa<OffloadWrapperJobAction>(JA)) {
       if (Arg *FinalOutput = C.getArgs().getLastArg(options::OPT_o))
         BaseInput = FinalOutput->getValue();
       else
         BaseInput = getDefaultImageName();
       BaseInput =
           C.getArgs().MakeArgString(std::string(BaseInput) + "-wrapper");
     }
if (IsCLMode()) {
           MakeCLOutputFilename(C.getArgs(), "", BaseName, types::TY_Image);
     } else {
       SmallString<128> Output(getDefaultImageName());
       // HIP image for device compilation with -fno-gpu-rdc is per compilation
       // unit.
       bool IsHIPNoRDC = JA.getOffloadingDeviceKind() == Action::OFK_HIP &&
                         !C.getArgs().hasFlag(options::OPT_fgpu_rdc,
                                              options::OPT_fno_gpu_rdc, false);
-      if (IsHIPNoRDC) {
+      bool UseOutExtension = IsHIPNoRDC || isa<OffloadPackagerJobAction>(JA);
+      if (UseOutExtension) {
         Output = BaseName;
         llvm::sys::path::replace_extension(Output, "");
       }
       Output += OffloadingPrefix;
       if (MultipleArchs && !BoundArch.empty()) {
         Output += "-";
         Output.append(BoundArch);
       }
-      if (IsHIPNoRDC)
+      if (UseOutExtension)
         Output += ".out";
       NamedOutput = C.getArgs().MakeArgString(Output.c_str());
     }
   } else if (JA.getType() == types::TY_PCH && IsCLMode()) {
     NamedOutput = C.getArgs().MakeArgString(GetClPchPath(C, BaseName));
   } else {
     const char *Suffix = types::getTypeTempSuffix(JA.getType(), IsCLMode());
     assert(Suffix && "All types used for output should have a suffix.");

clang/test/Driver/openmp-offload-gpu-new.c

 // CHECK-PHASES: 9: offload, "device-openmp (nvptx64-nvidia-cuda)" {8}, object
 // CHECK-PHASES: 10: clang-offload-packager, {9}, image
 // CHECK-PHASES: 11: offload, "host-openmp (x86_64-unknown-linux-gnu)" {2}, " (x86_64-unknown-linux-gnu)" {10}, ir
 // CHECK-PHASES: 12: backend, {11}, assembler, (host-openmp)
 // CHECK-PHASES: 13: assembler, {12}, object, (host-openmp)
 // CHECK-PHASES: 14: clang-linker-wrapper, {13}, image, (host-openmp)
 
 // RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-BINDINGS
-// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.*]]"], output: "[[HOST_BC:.*]]"
-// CHECK-BINDINGS: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_BC:.*]]"
-// CHECK-BINDINGS: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_BC]]"], output: "[[DEVICE_OBJ:.*]]"
-// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_OBJ]]"], output: "[[BINARY:.*]]"
-// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]", "[[BINARY]]"], output: "[[HOST_OBJ:.*]]"
+// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[HOST_BC:.+]]"
+// CHECK-BINDINGS: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_BC:.+]]"
+// CHECK-BINDINGS: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_BC]]"], output: "[[DEVICE_OBJ:.+]]"
+// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_OBJ]]"], output: "[[BINARY:.+.out]]"
+// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]", "[[BINARY]]"], output: "[[HOST_OBJ:.+]]"
 // CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[HOST_OBJ]]"], output: "a.out"
 
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_52 -nogpulib -save-temps %s 2>&1 | FileCheck %s --check-prefix=CHECK-TEMP-BINDINGS
+// CHECK-TEMP-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_OBJ:.+]]"], output: "[[BINARY:.+.out]]"
+
 // RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda --offload-arch=sm_52 --offload-arch=sm_70 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-ARCH-BINDINGS
 // CHECK-ARCH-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.*]]"], output: "[[HOST_BC:.*]]"
 // CHECK-ARCH-BINDINGS: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_BC_SM_52:.*]]"
 // CHECK-ARCH-BINDINGS: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_BC_SM_52]]"], output: "[[DEVICE_OBJ_SM_52:.*]]"
 // CHECK-ARCH-BINDINGS: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_BC_SM_70:.*]]"
 // CHECK-ARCH-BINDINGS: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_BC_SM_70]]"], output: "[[DEVICE_OBJ_SM_70:.*]]"
 // CHECK-ARCH-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_OBJ_SM_52]]", "[[DEVICE_OBJ_SM_70]]"], output: "[[BINARY:.*]]"
 // CHECK-ARCH-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]", "[[BINARY]]"], output: "[[HOST_OBJ:.*]]"