[HIP] Allow the new driver to compile HIP in non-RDC mode

The new driver primarily allows us to support RDC-mode compilations with
proper linking. This is not needed for non-RDC mode compilation, but we
still would like the new driver to be able to handle this mode so we can
transition away from the old driver in the future. This patch adds the
necessary code to support creating a fatbinary for HIP code generation.

Reviewed By: yaxunl

Differential Revision: https://reviews.llvm.org/D129784

clang/lib/Driver/Driver.cpp

@@ -4478,6 +4478,15 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
       }
     }
 
+    // Compiling HIP in non-RDC mode requires linking each action individually.
+    for (Action *&A : DeviceActions) {
+      if (A->getType() != types::TY_Object || Kind != Action::OFK_HIP ||
+          Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc, false))
+        continue;
+      ActionList LinkerInput = {A};
+      A = C.MakeAction<LinkJobAction>(LinkerInput, types::TY_Image);
+    }
+
     auto TCAndArch = TCAndArchs.begin();
     for (Action *A : DeviceActions) {
       DDeps.add(*A, *TCAndArch->first, TCAndArch->second.data(), Kind);
@@ -4497,12 +4506,21 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
   OffloadAction::DeviceDependences DDep;
   if (C.isOffloadingHostKind(Action::OFK_Cuda) &&
       !Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc, false)) {
-    // If we are not in RDC-mode we just emit the final CUDA fatbinary for each
-    // translation unit without requiring any linking.
+    // If we are not in RDC-mode we just emit the final CUDA fatbinary for
+    // each translation unit without requiring any linking.
     Action *FatbinAction =
         C.MakeAction<LinkJobAction>(OffloadActions, types::TY_CUDA_FATBIN);
     DDep.add(*FatbinAction, *C.getSingleOffloadToolChain<Action::OFK_Cuda>(),
              nullptr, Action::OFK_Cuda);
+  } else if (C.isOffloadingHostKind(Action::OFK_HIP) &&
+             !Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
+                           false)) {
+    // If we are not in RDC-mode we just emit the final HIP fatbinary for each
+    // translation unit, linking each input individually.
+    Action *FatbinAction =
+        C.MakeAction<LinkJobAction>(OffloadActions, types::TY_HIP_FATBIN);
+    DDep.add(*FatbinAction, *C.getSingleOffloadToolChain<Action::OFK_HIP>(),
+             nullptr, Action::OFK_HIP);
   } else {
     // Package all the offloading actions into a single output that can be
     // embedded in the host and linked.
@@ -4511,6 +4529,7 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
     DDep.add(*PackagerAction, *C.getSingleOffloadToolChain<Action::OFK_Host>(),
              nullptr, Action::OFK_None);
   }
+
   OffloadAction::HostDependence HDep(
       *HostAction, *C.getSingleOffloadToolChain<Action::OFK_Host>(),
       /*BoundArch=*/nullptr, isa<CompileJobAction>(HostAction) ? DDep : DDeps);

clang/lib/Driver/ToolChains/Clang.cpp

@@ -7006,7 +7006,7 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
     CmdArgs.push_back("-fcuda-include-gpubinary");
     CmdArgs.push_back(CudaDeviceInput->getFilename());
   } else if (!HostOffloadingInputs.empty()) {
-    if (IsCuda && !IsRDCMode) {
+    if ((IsCuda || IsHIP) && !IsRDCMode) {
       assert(HostOffloadingInputs.size() == 1 && "Only one input expected");
       CmdArgs.push_back("-fcuda-include-gpubinary");
       CmdArgs.push_back(HostOffloadingInputs.front().getFilename());

clang/test/Driver/hip-binding.hip

@@ -4,6 +4,9 @@
 // RUN: %clang -ccc-print-bindings -target x86_64-linux-gnu \
 // RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
 // RUN:   -c 2>&1 | FileCheck -check-prefix=NRDCS %s
+// RUN: %clang -ccc-print-bindings -target x86_64-linux-gnu --offload-new-driver \
+// RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -c 2>&1 | FileCheck -check-prefix=NRDCS %s
 // NRDCS: # "amdgcn-amd-amdhsa" - "clang", inputs: ["[[IN:.*hip-binding.hip]]"], output: "[[OBJ1:.*o]]"
 // NRDCS: # "amdgcn-amd-amdhsa" - "AMDGCN::Linker", inputs: ["[[OBJ1]]"], output: "[[IMG1:.*]]"
 // NRDCS: # "amdgcn-amd-amdhsa" - "clang", inputs: ["[[IN:.*hip-binding.hip]]"], output: "[[OBJ2:.*o]]"
@@ -19,6 +22,14 @@
 // RDCS: # "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[IN]]"], output: "[[HOSTOBJ:.*o]]"
 // RDCS: # "x86_64-unknown-linux-gnu" - "offload bundler", inputs: ["[[BC1]]", "[[BC2]]", "[[HOSTOBJ]]"], output: "{{.*}}"
 
+// RUN: %clang -ccc-print-bindings -target x86_64-linux-gnu --offload-new-driver \
+// RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
+// RUN:   -c -fgpu-rdc 2>&1 | FileCheck -check-prefix=RDCS-NEW %s
+// RDCS-NEW: # "amdgcn-amd-amdhsa" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[HIP803:.+]]"
+// RDCS-NEW: # "amdgcn-amd-amdhsa" - "clang", inputs: ["[[INPUT]]"], output: "[[HIP900:.+]]"
+// RDCS-NEW: # "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[HIP803]]", "[[HIP900]]"], output: "[[HIPFB:.+]]"
+// RDCS-NEW: # "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT]]", "[[HIPFB]]"], output: "{{.*}}"
+
 // RUN: touch %t.o
 // RUN: %clang --hip-link -ccc-print-bindings -target x86_64-linux-gnu \
 // RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 -fgpu-rdc %t.o\

clang/test/Driver/hip-phases.hip

@@ -11,7 +11,10 @@
 //
 // RUN: %clang -x hip -target x86_64-unknown-linux-gnu -ccc-print-phases \
 // RUN: --cuda-gpu-arch=gfx803 %s 2>&1 \
-// RUN: | FileCheck -check-prefixes=BIN,NRD %s
+// RUN: | FileCheck -check-prefixes=BIN,NRD,OLD %s
+// RUN: %clang -x hip -target x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --offload-new-driver --cuda-gpu-arch=gfx803 %s 2>&1 \
+// RUN: | FileCheck -check-prefixes=BIN,NRD,NEW %s
 //
 // RUN: %clang -x hip -target x86_64-unknown-linux-gnu -ccc-print-phases \
 // RUN: --cuda-gpu-arch=gfx803 -fgpu-rdc %s 2>&1 \
@@ -38,7 +41,8 @@
 // RDC-DAG: [[P11:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa)" {[[P10]]}, object
 // NRD-DAG: [[P12:[0-9]+]]: backend, {[[P11]]}, assembler, (host-[[T]])
 // NRD-DAG: [[P13:[0-9]+]]: assembler, {[[P12]]}, object, (host-[[T]])
-// NRD-DAG: [[P14:[0-9]+]]: linker, {[[P13]]}, image, (host-[[T]])
+// OLD-DAG: [[P14:[0-9]+]]: linker, {[[P13]]}, image, (host-[[T]])
+// NEW-DAG: [[P14:[0-9]+]]: clang-linker-wrapper, {[[P13]]}, image, (host-[[T]])
 // RDC-DAG: [[P14:[0-9]+]]: linker, {[[P13]], [[P11]]}, image, (host-[[T]])
 
 //

clang/test/Driver/hip-toolchain-no-rdc.hip

@@ -21,6 +21,16 @@
 // RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
 // RUN: 2>&1 | FileCheck -check-prefixes=CHECK %s
 
+// RUN: %clang -### -target x86_64-linux-gnu -fno-gpu-rdc \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   --hip-device-lib=lib1.bc --hip-device-lib=lib2.bc \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/lib1 \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/lib2 \
+// RUN:   -fuse-ld=lld -nogpuinc --offload-new-driver -c \
+// RUN:   %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip \
+// RUN: 2>&1 | FileCheck -check-prefixes=CHECK %s
+
 // RUN: touch %T/a.o
 // RUN: touch %T/b.o
 // RUN: %clang -### -target x86_64-linux-gnu \