[OpenMP] Adjust phases for AMDGPU offloading for OpenMP in save-temps mode

Currently, the behaviour of `-save-temps` changes the generated output
when offloading to AMDGPU. This is because we only have a single phase
and it contains the `-disable-llvm-passes` flags which results in
unoptimized bitcode. We need to make sure we generate another phase that
produces both the optimized and unoptimized bitcode. There used to be a
check that turned these phases into a no-op. But I believe it is more
correct to not generate them this way in the first place. Doing this
requires a bit of a hack, replacing an already generated phase action,
but it should be fine.

Reviewed By: JonChesterfield

Differential Revision: https://reviews.llvm.org/D141440

diff --git a/clang/lib/Driver/Action.cpp b/clang/lib/Driver/Action.cpp
index 2fc0b9d..44b4715 100644 (file)
--- a/clang/lib/Driver/Action.cpp
+++ b/clang/lib/Driver/Action.cpp
@@ -221,13 +221,17 @@ OffloadAction::OffloadAction(const HostDependence &HDep,
 
   // Add device inputs and propagate info to the device actions. Do work only if
   // we have dependencies.
-  for (unsigned i = 0, e = DDeps.getActions().size(); i != e; ++i)
+  for (unsigned i = 0, e = DDeps.getActions().size(); i != e; ++i) {
     if (auto *A = DDeps.getActions()[i]) {
       getInputs().push_back(A);
       A->propagateDeviceOffloadInfo(DDeps.getOffloadKinds()[i],
                                     DDeps.getBoundArchs()[i],
                                     DDeps.getToolChains()[i]);
+      // If this action is used to forward single dependency, set the toolchain.
+      if (DDeps.getActions().size() == 1)
+        OffloadingToolChain = DDeps.getToolChains()[i];
     }
+  }
 }
 
 void OffloadAction::doOnHostDependence(const OffloadActionWorkTy &Work) const {

diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index 1c71e71..0194143 100644 (file)
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -4436,6 +4436,9 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
         if (A->getType() == types::TY_Nothing)
           continue;
 
+        // Propagate the ToolChain so we can use it in ConstructPhaseAction.
+        A->propagateDeviceOffloadInfo(Kind, TCAndArch->second.data(),
+                                      TCAndArch->first);
         A = ConstructPhaseAction(C, Args, Phase, A, Kind);
 
         if (isa<CompileJobAction>(A) && isa<CompileJobAction>(HostAction) &&
@@ -4452,6 +4455,7 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
           DDep.add(*A, *TCAndArch->first, TCAndArch->second.data(), Kind);
           A = C.MakeAction<OffloadAction>(HDep, DDep);
         }
+
         ++TCAndArch;
       }
     }
@@ -4623,9 +4627,12 @@ Action *Driver::ConstructPhaseAction(
       return C.MakeAction<BackendJobAction>(Input, Output);
     }
     if (Args.hasArg(options::OPT_emit_llvm) ||
-        (TargetDeviceOffloadKind == Action::OFK_HIP &&
-         Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
-                      false))) {
+        (((Input->getOffloadingToolChain() &&
+           Input->getOffloadingToolChain()->getTriple().isAMDGPU()) ||
+          TargetDeviceOffloadKind == Action::OFK_HIP) &&
+         (Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
+                       false) ||
+          TargetDeviceOffloadKind == Action::OFK_OpenMP))) {
       types::ID Output =
           Args.hasArg(options::OPT_S) ? types::TY_LLVM_IR : types::TY_LLVM_BC;
       return C.MakeAction<BackendJobAction>(Input, Output);
@@ -5304,25 +5311,6 @@ InputInfoList Driver::BuildJobsForActionNoCache(
   if (!T)
     return {InputInfo()};
 
-  if (BuildingForOffloadDevice &&
-      A->getOffloadingDeviceKind() == Action::OFK_OpenMP) {
-    if (TC->getTriple().isAMDGCN()) {
-      // AMDGCN treats backend and assemble actions as no-op because
-      // linker does not support object files.
-      if (const BackendJobAction *BA = dyn_cast<BackendJobAction>(A)) {
-        return BuildJobsForAction(C, *BA->input_begin(), TC, BoundArch,
-                                  AtTopLevel, MultipleArchs, LinkingOutput,
-                                  CachedResults, TargetDeviceOffloadKind);
-      }
-
-      if (const AssembleJobAction *AA = dyn_cast<AssembleJobAction>(A)) {
-        return BuildJobsForAction(C, *AA->input_begin(), TC, BoundArch,
-                                  AtTopLevel, MultipleArchs, LinkingOutput,
-                                  CachedResults, TargetDeviceOffloadKind);
-      }
-    }
-  }
-
   // If we've collapsed action list that contained OffloadAction we
   // need to build jobs for host/device-side inputs it may have held.
   for (const auto *OA : CollapsedOffloadActions)
@@ -5724,15 +5712,18 @@ const char *Driver::GetNamedOutputPath(Compilation &C, const JobAction &JA,
     // When using both -save-temps and -emit-llvm, use a ".tmp.bc" suffix for
     // the unoptimized bitcode so that it does not get overwritten by the ".bc"
     // optimized bitcode output.
-    auto IsHIPRDCInCompilePhase = [](const JobAction &JA,
-                                     const llvm::opt::DerivedArgList &Args) {
-      // The relocatable compilation in HIP implies -emit-llvm. Similarly, use a
-      // ".tmp.bc" suffix for the unoptimized bitcode (generated in the compile
-      // phase.)
+    auto IsHIPRDCInCompilePhase = [&C](const JobAction &JA,
+                                       const llvm::opt::DerivedArgList &Args) {
+      // The relocatable compilation in HIP and OpenMP implies -emit-llvm.
+      // Similarly, use a ".tmp.bc" suffix for the unoptimized bitcode
+      // (generated in the compile phase.)
+      const ToolChain *TC = JA.getOffloadingToolChain();
       return isa<CompileJobAction>(JA) &&
-             JA.getOffloadingDeviceKind() == Action::OFK_HIP &&
-             Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
-                          false);
+             ((JA.getOffloadingDeviceKind() == Action::OFK_HIP &&
+               Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc,
+                            false)) ||
+              (JA.getOffloadingDeviceKind() == Action::OFK_OpenMP && TC &&
+               TC->getTriple().isAMDGPU()));
     };
     if (!AtTopLevel && JA.getType() == types::TY_LLVM_BC &&
         (C.getArgs().hasArg(options::OPT_emit_llvm) ||

diff --git a/clang/test/Driver/amdgpu-openmp-toolchain.c b/clang/test/Driver/amdgpu-openmp-toolchain.c
index ea713b6..77ea2a7 100644 (file)
--- a/clang/test/Driver/amdgpu-openmp-toolchain.c
+++ b/clang/test/Driver/amdgpu-openmp-toolchain.c
@@ -1,9 +1,9 @@
 // REQUIRES: x86-registered-target
 // REQUIRES: amdgpu-registered-target
-// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa \
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa \
 // RUN:          -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 --libomptarget-amdgpu-bc-path=%S/Inputs/hip_dev_lib %s 2>&1 \
 // RUN:   | FileCheck %s
-// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa \
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa \
 // RUN:          --offload-arch=gfx906 --libomptarget-amdgpu-bc-path=%S/Inputs/hip_dev_lib %s 2>&1 \
 // RUN:   | FileCheck %s
 
@@ -13,7 +13,7 @@
 // CHECK: "-cc1" "-triple" "x86_64-unknown-linux-gnu"{{.*}}"-emit-obj"
 // CHECK: clang-linker-wrapper{{.*}}"--"{{.*}} "-o" "a.out"
 
-// RUN:   %clang -ccc-print-phases --target=x86_64-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 %s 2>&1 \
+// RUN:   %clang -ccc-print-phases --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 %s 2>&1 \
 // RUN:   | FileCheck --check-prefix=CHECK-PHASES %s
 // CHECK-PHASES: 0: input, "[[INPUT:.+]]", c, (host-openmp)
 // CHECK-PHASES: 1: preprocessor, {0}, cpp-output, (host-openmp)
@@ -22,39 +22,50 @@
 // CHECK-PHASES: 4: preprocessor, {3}, cpp-output, (device-openmp)
 // CHECK-PHASES: 5: compiler, {4}, ir, (device-openmp)
 // CHECK-PHASES: 6: offload, "host-openmp (x86_64-unknown-linux-gnu)" {2}, "device-openmp (amdgcn-amd-amdhsa)" {5}, ir
-// CHECK-PHASES: 7: backend, {6}, assembler, (device-openmp)
-// CHECK-PHASES: 8: assembler, {7}, object, (device-openmp)
-// CHECK-PHASES: 9: offload, "device-openmp (amdgcn-amd-amdhsa)" {8}, object
-// CHECK-PHASES: 10: clang-offload-packager, {9}, image
-// CHECK-PHASES: 11: offload, "host-openmp (x86_64-unknown-linux-gnu)" {2}, "device-openmp (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)
+// CHECK-PHASES: 7: backend, {6}, ir, (device-openmp)
+// CHECK-PHASES: 8: offload, "device-openmp (amdgcn-amd-amdhsa)" {7}, ir
+// CHECK-PHASES: 9: clang-offload-packager, {8}, image, (device-openmp)
+// CHECK-PHASES: 10: offload, "host-openmp (x86_64-unknown-linux-gnu)" {2}, "device-openmp (x86_64-unknown-linux-gnu)" {9}, ir
+// CHECK-PHASES: 11: backend, {10}, assembler, (host-openmp)
+// CHECK-PHASES: 12: assembler, {11}, object, (host-openmp)
+// CHECK-PHASES: 13: clang-linker-wrapper, {12}, image, (host-openmp)
 
 // handling of --libomptarget-amdgpu-bc-path
-// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 --libomptarget-amdgpu-bc-path=%S/Inputs/hip_dev_lib/libomptarget-amdgpu-gfx803.bc %s 2>&1 | FileCheck %s --check-prefix=CHECK-LIBOMPTARGET
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 --libomptarget-amdgpu-bc-path=%S/Inputs/hip_dev_lib/libomptarget-amdgpu-gfx803.bc %s 2>&1 | FileCheck %s --check-prefix=CHECK-LIBOMPTARGET
 // CHECK-LIBOMPTARGET: "-cc1" "-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx803" "-fcuda-is-device" "-mlink-builtin-bitcode"{{.*}}Inputs/hip_dev_lib/libomptarget-amdgpu-gfx803.bc"{{.*}}
 
-// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-NOGPULIB
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-NOGPULIB
 // CHECK-NOGPULIB-NOT: "-cc1" "-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx803" "-fcuda-is-device" "-mlink-builtin-bitcode"{{.*}}libomptarget-amdgpu-gfx803.bc"{{.*}}
 
-// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-BINDINGS
-// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa --offload-arch=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-BINDINGS
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-BINDINGS
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa --offload-arch=gfx803 -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: "amdgcn-amd-amdhsa" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_BC:.+]]"
 // CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_BC]]"], output: "[[BINARY:.+]]"
 // 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 -emit-llvm -S -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -save-temps -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-BINDINGS-TEMPS
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -save-temps -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa --offload-arch=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-BINDINGS-TEMPS
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[HOST_PP:.+]]"
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_PP]]"], output: "[[HOST_BC:.+]]"
+// CHECK-BINDINGS-TEMPS: "amdgcn-amd-amdhsa" - "clang", inputs: ["[[INPUT]]"], output: "[[DEVICE_PP:.+]]"
+// CHECK-BINDINGS-TEMPS: "amdgcn-amd-amdhsa" - "clang", inputs: ["[[DEVICE_PP]]", "[[HOST_BC]]"], output: "[[DEVICE_TEMP_BC:.+]]"
+// CHECK-BINDINGS-TEMPS: "amdgcn-amd-amdhsa" - "clang", inputs: ["[[DEVICE_TEMP_BC]]"], output: "[[DEVICE_BC:.+]]"
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_BC]]"], output: "[[DEVICE_IMAGE:.+]]"
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]", "[[DEVICE_IMAGE]]"], output: "[[HOST_ASM:.+]]"
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "clang::as", inputs: ["[[HOST_ASM]]"], output: "[[HOST_OBJ:.+]]"
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[HOST_OBJ]]"], output: "a.out"
+
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR
 // CHECK-EMIT-LLVM-IR: "-cc1" "-triple" "amdgcn-amd-amdhsa"{{.*}}"-emit-llvm"
 
-// RUN: %clang -### -target x86_64-pc-linux-gnu -fopenmp=libomp --offload-arch=gfx803 \
+// RUN: %clang -### -target x86_64-pc-linux-gnu -fopenmp --offload-arch=gfx803 \
 // RUN:   --rocm-device-lib-path=%S/Inputs/rocm/amdgcn/bitcode -fopenmp-new-driver %s  2>&1 | \
 // RUN: FileCheck %s --check-prefix=CHECK-LIB-DEVICE
 // CHECK-LIB-DEVICE: "-cc1" {{.*}}ocml.bc"{{.*}}ockl.bc"{{.*}}oclc_daz_opt_on.bc"{{.*}}oclc_unsafe_math_off.bc"{{.*}}oclc_finite_only_off.bc"{{.*}}oclc_correctly_rounded_sqrt_on.bc"{{.*}}oclc_wavefrontsize64_on.bc"{{.*}}oclc_isa_version_803.bc"
 
-// RUN: %clang -### -target x86_64-pc-linux-gnu -fopenmp=libomp --offload-arch=gfx803 -nogpulib \
+// RUN: %clang -### -target x86_64-pc-linux-gnu -fopenmp --offload-arch=gfx803 -nogpulib \
 // RUN:   --rocm-device-lib-path=%S/Inputs/rocm/amdgcn/bitcode -fopenmp-new-driver %s  2>&1 | \
 // RUN: FileCheck %s --check-prefix=CHECK-LIB-DEVICE-NOGPULIB
 // CHECK-LIB-DEVICE-NOGPULIB-NOT: "-cc1" {{.*}}ocml.bc"{{.*}}ockl.bc"{{.*}}oclc_daz_opt_on.bc"{{.*}}oclc_unsafe_math_off.bc"{{.*}}oclc_finite_only_off.bc"{{.*}}oclc_correctly_rounded_sqrt_on.bc"{{.*}}oclc_wavefrontsize64_on.bc"{{.*}}oclc_isa_version_803.bc"