[HIP]: Add -fhip-emit-relocatable to override link job creation for -…

…fno-gpu-rdc

Differential Revision: https://reviews.llvm.org/D153667

Change-Id: Idcc5c7c25dc350b8dc9a1865fd67982904d06ecd

clang/include/clang/Driver/Options.td

@@ -1124,6 +1124,10 @@ def gpu_bundle_output : Flag<["--"], "gpu-bundle-output">,
   Group<f_Group>, HelpText<"Bundle output files of HIP device compilation">;
 def no_gpu_bundle_output : Flag<["--"], "no-gpu-bundle-output">,
   Group<f_Group>, HelpText<"Do not bundle output files of HIP device compilation">;
+def fhip_emit_relocatable : Flag<["-"], "fhip-emit-relocatable">, Group<f_Group>,
+  HelpText<"Compile HIP source to relocatable">;
+def fno_hip_emit_relocatable : Flag<["-"], "fno-hip-emit-relocatable">, Group<f_Group>,
+  HelpText<"Do not override toolchain to compile HIP source to relocatable">;
 def cuid_EQ : Joined<["-"], "cuid=">, Flags<[CC1Option]>,
   HelpText<"An ID for compilation unit, which should be the same for the same "
            "compilation unit but different for different compilation units. "

clang/lib/Driver/Driver.cpp

@@ -2946,7 +2946,12 @@ class OffloadingActionBuilder final {
     CudaActionBuilderBase(Compilation &C, DerivedArgList &Args,
                           const Driver::InputList &Inputs,
                           Action::OffloadKind OFKind)
-        : DeviceActionBuilder(C, Args, Inputs, OFKind) {}
+        : DeviceActionBuilder(C, Args, Inputs, OFKind) {
+
+      CompileDeviceOnly = C.getDriver().offloadDeviceOnly();
+      Relocatable = Args.hasFlag(options::OPT_fgpu_rdc,
+                                 options::OPT_fno_gpu_rdc, /*Default=*/false);
+    }
 
     ActionBuilderReturnCode addDeviceDependences(Action *HostAction) override {
       // While generating code for CUDA, we only depend on the host input action
@@ -3099,9 +3104,6 @@ class OffloadingActionBuilder final {
           !C.hasOffloadToolChain<Action::OFK_HIP>())
         return false;
 
-      Relocatable = Args.hasFlag(options::OPT_fgpu_rdc,
-                                 options::OPT_fno_gpu_rdc, /*Default=*/false);
-
       const ToolChain *HostTC = C.getSingleOffloadToolChain<Action::OFK_Host>();
       assert(HostTC && "No toolchain for host compilation.");
       if (HostTC->getTriple().isNVPTX() ||
@@ -3120,7 +3122,6 @@ class OffloadingActionBuilder final {
               : C.getSingleOffloadToolChain<Action::OFK_HIP>());
 
       CompileHostOnly = C.getDriver().offloadHostOnly();
-      CompileDeviceOnly = C.getDriver().offloadDeviceOnly();
       EmitLLVM = Args.getLastArg(options::OPT_emit_llvm);
       EmitAsm = Args.getLastArg(options::OPT_S);
       FixedCUID = Args.getLastArgValue(options::OPT_cuid_EQ);
@@ -3352,16 +3353,40 @@ class OffloadingActionBuilder final {
     // only compilation. Bundle other type of output files only if
     // --gpu-bundle-output is specified for device only compilation.
     std::optional<bool> BundleOutput;
+    std::optional<bool> EmitReloc;
 
   public:
     HIPActionBuilder(Compilation &C, DerivedArgList &Args,
                      const Driver::InputList &Inputs)
         : CudaActionBuilderBase(C, Args, Inputs, Action::OFK_HIP) {
+
       DefaultCudaArch = CudaArch::GFX906;
+
+      if (Args.hasArg(options::OPT_fhip_emit_relocatable,
+                      options::OPT_fno_hip_emit_relocatable)) {
+        EmitReloc = Args.hasFlag(options::OPT_fhip_emit_relocatable,
+                                 options::OPT_fno_hip_emit_relocatable, false);
+
+        if (*EmitReloc) {
+          if (Relocatable) {
+            C.getDriver().Diag(diag::err_opt_not_valid_with_opt)
+                << "-fhip-emit-relocatable"
+                << "-fgpu-rdc";
+          }
+
+          if (!CompileDeviceOnly) {
+            C.getDriver().Diag(diag::err_opt_not_valid_without_opt)
+                << "-fhip-emit-relocatable"
+                << "--cuda-device-only";
+          }
+        }
+      }
+
       if (Args.hasArg(options::OPT_gpu_bundle_output,
                       options::OPT_no_gpu_bundle_output))
         BundleOutput = Args.hasFlag(options::OPT_gpu_bundle_output,
-                                    options::OPT_no_gpu_bundle_output, true);
+                                    options::OPT_no_gpu_bundle_output, true) &&
+                       (!EmitReloc || !*EmitReloc);
     }
 
     bool canUseBundlerUnbundler() const override { return true; }
@@ -3408,8 +3433,10 @@ class OffloadingActionBuilder final {
       assert(!CompileHostOnly &&
              "Not expecting HIP actions in host-only compilation.");
 
+      bool ShouldLink = !EmitReloc || !*EmitReloc;
+
       if (!Relocatable && CurPhase == phases::Backend && !EmitLLVM &&
-          !EmitAsm) {
+          !EmitAsm && ShouldLink) {
         // If we are in backend phase, we attempt to generate the fat binary.
         // We compile each arch to IR and use a link action to generate code
         // object containing ISA. Then we use a special "link" action to create
@@ -3485,6 +3512,8 @@ class OffloadingActionBuilder final {
 
         return CompileDeviceOnly ? ABRT_Ignore_Host : ABRT_Success;
       } else if (CurPhase == phases::Link) {
+        if (!ShouldLink)
+          return ABRT_Success;
         // Save CudaDeviceActions to DeviceLinkerInputs for each GPU subarch.
         // This happens to each device action originated from each input file.
         // Later on, device actions in DeviceLinkerInputs are used to create
@@ -3522,8 +3551,11 @@ class OffloadingActionBuilder final {
         CudaDeviceActions.clear();
       }
 
-      return (CompileDeviceOnly && CurPhase == FinalPhase) ? ABRT_Ignore_Host
-                                                           : ABRT_Success;
+      return (CompileDeviceOnly &&
+              (CurPhase == FinalPhase ||
+               (!ShouldLink && CurPhase == phases::Assemble)))
+                 ? ABRT_Ignore_Host
+                 : ABRT_Success;
     }
 
     void appendLinkDeviceActions(ActionList &AL) override {
@@ -3674,7 +3706,6 @@ class OffloadingActionBuilder final {
         ++InactiveBuilders;
         continue;
       }
-
       auto RetCode =
           SB->getDeviceDependences(DDeps, CurPhase, FinalPhase, Phases);
 

clang/test/Driver/hip-dependent-options.hip

@@ -0,0 +1,17 @@
+// RUN: %clang -### --target=x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   -c -fhip-emit-relocatable -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
+// RUN:   %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output \
+// RUN: 2>&1 | FileCheck -check-prefixes=RELOCRDC %s
+
+// RELOCRDC: error: option '-fhip-emit-relocatable' cannot be specified with '-fgpu-rdc'
+
+// RUN: %clang -### --target=x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   -c -fhip-emit-relocatable -nogpuinc -nogpulib \
+// RUN:   %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output \
+// RUN: 2>&1 | FileCheck -check-prefixes=RELOCHOST %s
+
+// RELOCHOST: error: option '-fhip-emit-relocatable' cannot be specified without '--cuda-device-only'

clang/test/Driver/hip-device-compile.hip

@@ -45,6 +45,14 @@
 // RUN:   %S/Inputs/hip_multiple_inputs/a.cu \
 // RUN: 2>&1 | FileCheck -check-prefixes=CHECK,ASM,NBUN %s
 
+// Output relocatable.
+// RUN: %clang -c --cuda-device-only -### --target=x86_64-linux-gnu \
+// RUN:   -o a.o -x hip --cuda-gpu-arch=gfx900 -fhip-emit-relocatable \
+// RUN:   --hip-device-lib=lib1.bc \
+// RUN:   --hip-device-lib-path=%S/Inputs/hip_multiple_inputs/lib1 \
+// RUN:   %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN: 2>&1 | FileCheck -check-prefixes=CHECK,NBUN,RELOC %s
+
 // Output bundled assembly.
 // RUN: %clang -c -S --cuda-device-only -### --target=x86_64-linux-gnu \
 // RUN:   -o a.s -x hip --cuda-gpu-arch=gfx900 --no-gpu-bundle-output \
@@ -68,6 +76,7 @@
 // LLBUN-SAME: "-o" "{{.*}}.ll"
 // ASM-SAME: "-o" "a.s"
 // ASMBUN-SAME: "-o" "{{.*}}.s"
+// RELOC-SAME: "-o" "a.o"
 // CHECK-SAME: {{".*a.cu"}}
 
 // CHECK-NOT: {{"*.llvm-link"}}

clang/test/Driver/hip-phases.hip

@@ -244,6 +244,43 @@
 // DASM-NOT: clang-offload-bundler
 // DASM-NOT: host
 
+//
+// Test single gpu architecture with compile to relocatable in device-only
+// compilation mode.
+//
+// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --cuda-gpu-arch=gfx803 %s --cuda-device-only -fhip-emit-relocatable 2>&1 \
+// RUN: | FileCheck -check-prefixes=RELOC %s
+// RELOC-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
+// RELOC-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
+// RELOC-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
+// RELOC-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
+// RELOC-DAG: [[P4:[0-9]+]]: assembler, {[[P3]]}, object, (device-[[T]], [[ARCH]])
+// RELOC-NOT: linker
+// RELOC-DAG: [[P5:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P4]]}, object
+
+//
+// Test two gpu architectures with compile to relocatable in device-only
+// compilation mode.
+//
+// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s --cuda-device-only -fhip-emit-relocatable 2>&1 \
+// RUN: | FileCheck -check-prefixes=RELOC2 %s
+// RELOC2-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
+// RELOC2-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
+// RELOC2-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
+// RELOC2-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
+// RELOC2-DAG: [[P4:[0-9]+]]: assembler, {[[P3]]}, object, (device-[[T]], [[ARCH]])
+// RELOC2-NOT: [[P5:[0-9]+]]: linker, {[[P4]]}, image, (device-[[T]], [[ARCH]])
+// RELOC2-DAG: [[P5:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P4]]}, object
+// RELOC2-DAG: [[P6:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH2:gfx900]])
+// RELOC2-DAG: [[P7:[0-9]+]]: preprocessor, {[[P6]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH2]])
+// RELOC2-DAG: [[P8:[0-9]+]]: compiler, {[[P7]]}, ir, (device-[[T]], [[ARCH2]])
+// RELOC2-DAG: [[P9:[0-9]+]]: backend, {[[P8]]}, assembler, (device-[[T]], [[ARCH2]])
+// RELOC2-DAG: [[P10:[0-9]+]]: assembler, {[[P9]]}, object, (device-[[T]], [[ARCH2]])
+// RELOC2-NOT: linker
+// RELOC2-DAG: [[P11:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH2]])" {[[P10]]}, object
+
 //
 // Test two gpu architectures with complete compilation in device-only
 // compilation mode.

clang/test/Driver/hip-rdc-device-only.hip

@@ -18,6 +18,16 @@
 // RUN:   %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output \
 // RUN: 2>&1 | FileCheck -check-prefixes=COMMON,EMITBC %s
 
+// With `-fno-hip-emit-relocatable`, the output should be the same as the aforementioned line
+// as `-fgpu-rdc` in HIP implies `-fno-hip-emit-relocatable`.
+
+// RUN: %clang -### --target=x86_64-linux-gnu \
+// RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   -c -fno-hip-emit-relocatable -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \
+// RUN:   %S/Inputs/hip_multiple_inputs/a.cu \
+// RUN:   %S/Inputs/hip_multiple_inputs/b.hip --gpu-bundle-output \
+// RUN: 2>&1 | FileCheck -check-prefixes=COMMON,EMITBC %s
+
 // RUN: %clang -### --target=x86_64-linux-gnu \
 // RUN:   -x hip --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
 // RUN:   -S -nogpuinc -nogpulib --cuda-device-only -fgpu-rdc \