[Mlir-commits] [mlir] 40340cf - [MLIR][OpenMP][OMPIRBuilder] Use target triple to initialize `IsGPU` flag

Sergio Afonso llvmlistbot at llvm.org
Thu Jul 20 07:08:19 PDT 2023


Author: Sergio Afonso
Date: 2023-07-20T15:07:50+01:00
New Revision: 40340cf91ab9c61ec8c77c0a5063d4e5894e9d07

URL: https://github.com/llvm/llvm-project/commit/40340cf91ab9c61ec8c77c0a5063d4e5894e9d07
DIFF: https://github.com/llvm/llvm-project/commit/40340cf91ab9c61ec8c77c0a5063d4e5894e9d07.diff

LOG: [MLIR][OpenMP][OMPIRBuilder] Use target triple to initialize `IsGPU` flag

This patch modifies the construction of the `OpenMPIRBuilder` in MLIR to
initialize the `IsGPU` flag using target triple information passed down from
the Flang frontend. If not present, it will default to `false`.

This replicates the behavior currently implemented in Clang, where the
`CodeGenModule::createOpenMPRuntime()` method creates a different
`CGOpenMPRuntime` instance depending on the target triple, which in turn has an
effect on the `IsGPU` flag of the `OpenMPIRBuilderConfig` object.

Differential Revision: https://reviews.llvm.org/D151903

Added: 
    flang/test/Lower/OpenMP/omp-is-gpu.f90

Modified: 
    flang/include/flang/Frontend/LangOptions.def
    flang/include/flang/Tools/CrossToolHelpers.h
    flang/lib/Frontend/CompilerInvocation.cpp
    flang/test/Lower/OpenMP/host-ir-flag.f90
    flang/test/Lower/OpenMP/rtl-flags.f90
    flang/test/Lower/OpenMP/target_cpu_features.f90
    flang/tools/bbc/bbc.cpp
    llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
    mlir/include/mlir/Dialect/OpenMP/OpenMPOpsInterfaces.td
    mlir/lib/Target/LLVMIR/ModuleTranslation.cpp

Removed: 
    


################################################################################
diff  --git a/flang/include/flang/Frontend/LangOptions.def b/flang/include/flang/Frontend/LangOptions.def
index 635f640f4db424..b7b244a58253d6 100644
--- a/flang/include/flang/Frontend/LangOptions.def
+++ b/flang/include/flang/Frontend/LangOptions.def
@@ -38,6 +38,8 @@ LANGOPT(ReciprocalMath, 1, false)
 LANGOPT(OpenMPVersion, 32, 0)
 /// Generate code only for OpenMP target device
 LANGOPT(OpenMPIsTargetDevice, 1, false)
+/// Generate OpenMP target code only for GPUs
+LANGOPT(OpenMPIsGPU, 1, false)
 /// Enable debugging in the OpenMP offloading device RTL
 LANGOPT(OpenMPTargetDebug, 32, 0)
 /// Assume work-shared loops do not have more iterations than participating

diff  --git a/flang/include/flang/Tools/CrossToolHelpers.h b/flang/include/flang/Tools/CrossToolHelpers.h
index 52cf721905942a..d43a1fccccb62f 100644
--- a/flang/include/flang/Tools/CrossToolHelpers.h
+++ b/flang/include/flang/Tools/CrossToolHelpers.h
@@ -24,13 +24,13 @@ struct OffloadModuleOpts {
   OffloadModuleOpts(uint32_t OpenMPTargetDebug, bool OpenMPTeamSubscription,
       bool OpenMPThreadSubscription, bool OpenMPNoThreadState,
       bool OpenMPNoNestedParallelism, bool OpenMPIsTargetDevice,
-      uint32_t OpenMPVersion, std::string OMPHostIRFile = {})
+      bool OpenMPIsGPU, uint32_t OpenMPVersion, std::string OMPHostIRFile = {})
       : OpenMPTargetDebug(OpenMPTargetDebug),
         OpenMPTeamSubscription(OpenMPTeamSubscription),
         OpenMPThreadSubscription(OpenMPThreadSubscription),
         OpenMPNoThreadState(OpenMPNoThreadState),
         OpenMPNoNestedParallelism(OpenMPNoNestedParallelism),
-        OpenMPIsTargetDevice(OpenMPIsTargetDevice),
+        OpenMPIsTargetDevice(OpenMPIsTargetDevice), OpenMPIsGPU(OpenMPIsGPU),
         OpenMPVersion(OpenMPVersion), OMPHostIRFile(OMPHostIRFile) {}
 
   OffloadModuleOpts(Fortran::frontend::LangOptions &Opts)
@@ -40,7 +40,8 @@ struct OffloadModuleOpts {
         OpenMPNoThreadState(Opts.OpenMPNoThreadState),
         OpenMPNoNestedParallelism(Opts.OpenMPNoNestedParallelism),
         OpenMPIsTargetDevice(Opts.OpenMPIsTargetDevice),
-        OpenMPVersion(Opts.OpenMPVersion), OMPHostIRFile(Opts.OMPHostIRFile) {}
+        OpenMPIsGPU(Opts.OpenMPIsGPU), OpenMPVersion(Opts.OpenMPVersion),
+        OMPHostIRFile(Opts.OMPHostIRFile) {}
 
   uint32_t OpenMPTargetDebug = 0;
   bool OpenMPTeamSubscription = false;
@@ -48,6 +49,7 @@ struct OffloadModuleOpts {
   bool OpenMPNoThreadState = false;
   bool OpenMPNoNestedParallelism = false;
   bool OpenMPIsTargetDevice = false;
+  bool OpenMPIsGPU = false;
   uint32_t OpenMPVersion = 11;
   std::string OMPHostIRFile = {};
 };
@@ -60,6 +62,7 @@ void setOffloadModuleInterfaceAttributes(
   if (auto offloadMod = llvm::dyn_cast<mlir::omp::OffloadModuleInterface>(
           module.getOperation())) {
     offloadMod.setIsTargetDevice(Opts.OpenMPIsTargetDevice);
+    offloadMod.setIsGPU(Opts.OpenMPIsGPU);
     if (Opts.OpenMPIsTargetDevice) {
       offloadMod.setFlags(Opts.OpenMPTargetDebug, Opts.OpenMPTeamSubscription,
           Opts.OpenMPThreadSubscription, Opts.OpenMPNoThreadState,

diff  --git a/flang/lib/Frontend/CompilerInvocation.cpp b/flang/lib/Frontend/CompilerInvocation.cpp
index e76b67ab444cd4..43fecca280c570 100644
--- a/flang/lib/Frontend/CompilerInvocation.cpp
+++ b/flang/lib/Frontend/CompilerInvocation.cpp
@@ -782,6 +782,23 @@ static bool parseDialectArgs(CompilerInvocation &res, llvm::opt::ArgList &args,
           res.getLangOpts().OpenMPTargetDebug = 1;
       }
     }
+
+    switch (llvm::Triple(res.getTargetOpts().triple).getArch()) {
+    case llvm::Triple::nvptx:
+    case llvm::Triple::nvptx64:
+    case llvm::Triple::amdgcn:
+      if (!res.getLangOpts().OpenMPIsTargetDevice) {
+        const unsigned diagID = diags.getCustomDiagID(
+            clang::DiagnosticsEngine::Error,
+            "OpenMP AMDGPU/NVPTX is only prepared to deal with device code.");
+        diags.Report(diagID);
+      }
+      res.getLangOpts().OpenMPIsGPU = 1;
+      break;
+    default:
+      res.getLangOpts().OpenMPIsGPU = 0;
+      break;
+    }
   }
 
   // -pedantic

diff  --git a/flang/test/Lower/OpenMP/host-ir-flag.f90 b/flang/test/Lower/OpenMP/host-ir-flag.f90
index 86d5181d2c45fc..be7a6e77011866 100644
--- a/flang/test/Lower/OpenMP/host-ir-flag.f90
+++ b/flang/test/Lower/OpenMP/host-ir-flag.f90
@@ -1,6 +1,6 @@
 !RUN: %flang_fc1 -emit-llvm-bc -fopenmp -o %t.bc %s 2>&1
 !RUN: %flang_fc1 -emit-mlir -fopenmp -fopenmp-is-target-device -fopenmp-host-ir-file-path %t.bc -o - %s 2>&1 | FileCheck %s
 
-!CHECK: module attributes {{{.*}}, omp.host_ir_filepath = "{{.*}}.bc", omp.is_target_device = true{{.*}}}
+!CHECK: module attributes {{{.*}}, omp.host_ir_filepath = "{{.*}}.bc", omp.is_gpu = false, omp.is_target_device = true{{.*}}}
 subroutine omp_subroutine()
 end subroutine omp_subroutine

diff  --git a/flang/test/Lower/OpenMP/omp-is-gpu.f90 b/flang/test/Lower/OpenMP/omp-is-gpu.f90
new file mode 100644
index 00000000000000..eb4e8657f7fa93
--- /dev/null
+++ b/flang/test/Lower/OpenMP/omp-is-gpu.f90
@@ -0,0 +1,12 @@
+!RUN: %flang_fc1 -triple amdgcn-amd-amdhsa -emit-fir -fopenmp -fopenmp-is-target-device %s -o - | FileCheck %s
+!RUN: bbc -fopenmp -fopenmp-is-target-device -fopenmp-is-gpu -emit-fir -o - %s | FileCheck %s
+
+!RUN: not %flang_fc1 -triple amdgcn-amd-amdhsa -emit-fir -fopenmp %s -o - 2>&1 | FileCheck %s --check-prefix=FLANG-ERROR
+!RUN: not bbc -fopenmp -fopenmp-is-gpu -emit-fir %s -o - 2>&1 | FileCheck %s --check-prefix=BBC-ERROR
+
+!CHECK: module attributes {{{.*}}omp.is_gpu = true
+subroutine omp_subroutine()
+end subroutine omp_subroutine
+
+!FLANG-ERROR: error: OpenMP AMDGPU/NVPTX is only prepared to deal with device code.
+!BBC-ERROR: FATAL: -fopenmp-is-gpu can only be set if -fopenmp-is-target-device is also set

diff  --git a/flang/test/Lower/OpenMP/rtl-flags.f90 b/flang/test/Lower/OpenMP/rtl-flags.f90
index 533c3478a26d28..ad8eb9e7321374 100644
--- a/flang/test/Lower/OpenMP/rtl-flags.f90
+++ b/flang/test/Lower/OpenMP/rtl-flags.f90
@@ -20,16 +20,20 @@
 !RUN: bbc -emit-fir -fopenmp -fopenmp-assume-no-nested-parallelism -fopenmp-is-target-device -o - %s | FileCheck %s --check-prefix=NEST-PAR-DEVICE-FIR
 !RUN: bbc -emit-fir -fopenmp -fopenmp-target-debug=1 -fopenmp-assume-teams-oversubscription -fopenmp-assume-no-nested-parallelism -fopenmp-assume-threads-oversubscription -fopenmp-assume-no-thread-state -fopenmp-is-target-device -o - %s | FileCheck %s --check-prefix=ALL-DEVICE-FIR
 
-!DEFAULT-DEVICE-FIR: module attributes {{{.*}}, omp.flags = #omp.flags<openmp_device_version = 11>, omp.is_target_device = true{{.*}}}
-!DEFAULT-DEVICE-FIR-VERSION: module attributes {{{.*}}, omp.flags = #omp.flags<openmp_device_version = 45>, omp.is_target_device = true, omp.version = #omp.version<version = 45>{{.*}}
-!DEFAULT-HOST-FIR: module attributes {{{.*}},  omp.is_target_device = false{{.*}}
-!DEFAULT-HOST-FIR-VERSION: module attributes {{{.*}},  omp.is_target_device = false, omp.version = #omp.version<version = 45>{{.*}}
-!DBG-DEVICE-FIR: module attributes {{{.*}}, omp.flags = #omp.flags<debug_kind = 1, openmp_device_version = 11>{{.*}}}
-!DBG-EQ-DEVICE-FIR: module attributes {{{.*}}, omp.flags = #omp.flags<debug_kind = 111, openmp_device_version = 11>{{.*}}}
-!TEAMS-OSUB-DEVICE-FIR: module attributes {{{.*}}, omp.flags = #omp.flags<assume_teams_oversubscription = true, openmp_device_version = 11>{{.*}}}
-!THREAD-OSUB-DEVICE-FIR: module attributes {{{.*}}, omp.flags = #omp.flags<assume_threads_oversubscription = true, openmp_device_version = 11>{{.*}}}
-!THREAD-STATE-DEVICE-FIR: module attributes {{{.*}}, omp.flags = #omp.flags<assume_no_thread_state = true, openmp_device_version = 11>{{.*}}}
-!NEST-PAR-DEVICE-FIR: module attributes {{{.*}}, omp.flags = #omp.flags<assume_no_nested_parallelism = true, openmp_device_version = 11>{{.*}}}
-!ALL-DEVICE-FIR: module attributes {{{.*}}, omp.flags = #omp.flags<debug_kind = 1, assume_teams_oversubscription = true, assume_threads_oversubscription = true, assume_no_thread_state = true, assume_no_nested_parallelism = true, openmp_device_version = 11>{{.*}}}
+!DEFAULT-DEVICE-FIR: module attributes {{{.*}}omp.flags = #omp.flags<openmp_device_version = 11>
+!DEFAULT-DEVICE-FIR-SAME: omp.is_target_device = true
+!DEFAULT-DEVICE-FIR-VERSION: module attributes {{{.*}}omp.flags = #omp.flags<openmp_device_version = 45>
+!DEFAULT-DEVICE-FIR-VERSION-SAME: omp.is_target_device = true
+!DEFAULT-DEVICE-FIR-VERSION-SAME: omp.version = #omp.version<version = 45>
+!DEFAULT-HOST-FIR: module attributes {{{.*}}omp.is_target_device = false{{.*}}
+!DEFAULT-HOST-FIR-VERSION: module attributes {{{.*}}omp.is_target_device = false
+!DEFAULT-HOST-FIR-VERSION-SAME: omp.version = #omp.version<version = 45>
+!DBG-DEVICE-FIR: module attributes {{{.*}}omp.flags = #omp.flags<debug_kind = 1, openmp_device_version = 11>
+!DBG-EQ-DEVICE-FIR: module attributes {{{.*}}omp.flags = #omp.flags<debug_kind = 111, openmp_device_version = 11>
+!TEAMS-OSUB-DEVICE-FIR: module attributes {{{.*}}omp.flags = #omp.flags<assume_teams_oversubscription = true, openmp_device_version = 11>
+!THREAD-OSUB-DEVICE-FIR: module attributes {{{.*}}omp.flags = #omp.flags<assume_threads_oversubscription = true, openmp_device_version = 11>
+!THREAD-STATE-DEVICE-FIR: module attributes {{{.*}}omp.flags = #omp.flags<assume_no_thread_state = true, openmp_device_version = 11>
+!NEST-PAR-DEVICE-FIR: module attributes {{{.*}}omp.flags = #omp.flags<assume_no_nested_parallelism = true, openmp_device_version = 11>
+!ALL-DEVICE-FIR: module attributes {{{.*}}omp.flags = #omp.flags<debug_kind = 1, assume_teams_oversubscription = true, assume_threads_oversubscription = true, assume_no_thread_state = true, assume_no_nested_parallelism = true, openmp_device_version = 11>
 subroutine omp_subroutine()
 end subroutine omp_subroutine

diff  --git a/flang/test/Lower/OpenMP/target_cpu_features.f90 b/flang/test/Lower/OpenMP/target_cpu_features.f90
index e2d6b9d77f3537..eb87c814ef63e7 100644
--- a/flang/test/Lower/OpenMP/target_cpu_features.f90
+++ b/flang/test/Lower/OpenMP/target_cpu_features.f90
@@ -1,5 +1,5 @@
 !REQUIRES: amdgpu-registered-target
-!RUN: %flang_fc1 -emit-fir -triple amdgcn-amd-amdhsa -target-cpu gfx908 -fopenmp %s -o - | FileCheck %s
+!RUN: %flang_fc1 -emit-fir -triple amdgcn-amd-amdhsa -target-cpu gfx908 -fopenmp -fopenmp-is-target-device %s -o - | FileCheck %s
 
 !===============================================================================
 ! Target_Enter Simple
@@ -10,7 +10,10 @@
 !CHECK-SAME: +16-bit-insts,+s-memrealtime,+dot6-insts,+dl-insts,+image-insts,+wavefrontsize64,
 !CHECK-SAME: +gfx9-insts,+gfx8-insts,+ci-insts,+dot10-insts,+dot7-insts,
 !CHECK-SAME: +dot1-insts,+dot5-insts,+mai-insts,+dpp,+dot2-insts">
-!CHECK-LABEL: func.func @_QPomp_target_simple() {
+!CHECK-LABEL: func.func @_QPomp_target_simple()
 subroutine omp_target_simple
+  ! Directive needed to prevent subroutine from being filtered out when
+  ! compiling for the device.
+  !$omp declare target
 end subroutine omp_target_simple
 

diff  --git a/flang/tools/bbc/bbc.cpp b/flang/tools/bbc/bbc.cpp
index 4048899acb4f46..f617743d932fab 100644
--- a/flang/tools/bbc/bbc.cpp
+++ b/flang/tools/bbc/bbc.cpp
@@ -135,6 +135,11 @@ static llvm::cl::opt<bool>
                        llvm::cl::desc("enable openmp device compilation"),
                        llvm::cl::init(false));
 
+static llvm::cl::opt<bool>
+    enableOpenMPGPU("fopenmp-is-gpu",
+                    llvm::cl::desc("enable openmp GPU target codegen"),
+                    llvm::cl::init(false));
+
 // A simplified subset of the OpenMP RTL Flags from Flang, only the primary
 // positive options are available, no negative options e.g. fopen_assume* vs
 // fno_open_assume*
@@ -288,10 +293,16 @@ static mlir::LogicalResult convertFortranSourceToMLIR(
   burnside.lower(parseTree, semanticsContext);
   mlir::ModuleOp mlirModule = burnside.getModule();
   if (enableOpenMP) {
-    auto offloadModuleOpts = OffloadModuleOpts(
-        setOpenMPTargetDebug, setOpenMPTeamSubscription,
-        setOpenMPThreadSubscription, setOpenMPNoThreadState,
-        setOpenMPNoNestedParallelism, enableOpenMPDevice, setOpenMPVersion);
+    if (enableOpenMPGPU && !enableOpenMPDevice) {
+      llvm::errs() << "FATAL: -fopenmp-is-gpu can only be set if "
+                      "-fopenmp-is-target-device is also set";
+      return mlir::failure();
+    }
+    auto offloadModuleOpts =
+        OffloadModuleOpts(setOpenMPTargetDebug, setOpenMPTeamSubscription,
+                          setOpenMPThreadSubscription, setOpenMPNoThreadState,
+                          setOpenMPNoNestedParallelism, enableOpenMPDevice,
+                          enableOpenMPGPU, setOpenMPVersion);
     setOffloadModuleInterfaceAttributes(mlirModule, offloadModuleOpts);
     setOpenMPVersionAttribute(mlirModule, setOpenMPVersion);
   }

diff  --git a/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp b/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
index b15b30ad38d240..f6889cd5f074a5 100644
--- a/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
+++ b/llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp
@@ -5871,4 +5871,46 @@ TEST_F(OpenMPIRBuilderTest, registerTargetGlobalVariable) {
   }
 }
 
+TEST_F(OpenMPIRBuilderTest, createGPUOffloadEntry) {
+  OpenMPIRBuilder OMPBuilder(*M);
+  OMPBuilder.initialize();
+  OpenMPIRBuilderConfig Config(/* IsTargetDevice = */ true,
+                               /* IsGPU = */ true,
+                               /* HasRequiresUnifiedSharedMemory = */ false,
+                               /* OpenMPOffloadMandatory = */ false);
+  OMPBuilder.setConfig(Config);
+
+  FunctionCallee FnTypeAndCallee =
+      M->getOrInsertFunction("test_kernel", Type::getVoidTy(Ctx));
+
+  auto *Fn = cast<Function>(FnTypeAndCallee.getCallee());
+  OMPBuilder.createOffloadEntry(/* ID = */ nullptr, Fn,
+                                /* Size = */ 0,
+                                /* Flags = */ 0, GlobalValue::WeakAnyLinkage);
+
+  // Check nvvm.annotations only created for GPU kernels
+  NamedMDNode *MD = M->getNamedMetadata("nvvm.annotations");
+  EXPECT_NE(MD, nullptr);
+  EXPECT_EQ(MD->getNumOperands(), 1u);
+
+  MDNode *Annotations = MD->getOperand(0);
+  EXPECT_EQ(Annotations->getNumOperands(), 3u);
+
+  Constant *ConstVal =
+      dyn_cast<ConstantAsMetadata>(Annotations->getOperand(0))->getValue();
+  EXPECT_TRUE(isa<Function>(Fn));
+  EXPECT_EQ(ConstVal, cast<Function>(Fn));
+
+  EXPECT_TRUE(Annotations->getOperand(1).equalsStr("kernel"));
+
+  EXPECT_TRUE(mdconst::hasa<ConstantInt>(Annotations->getOperand(2)));
+  APInt IntVal =
+      mdconst::extract<ConstantInt>(Annotations->getOperand(2))->getValue();
+  EXPECT_EQ(IntVal, 1);
+
+  // Check kernel attributes
+  EXPECT_TRUE(Fn->hasFnAttribute("kernel"));
+  EXPECT_TRUE(Fn->hasFnAttribute(Attribute::MustProgress));
+}
+
 } // namespace

diff  --git a/mlir/include/mlir/Dialect/OpenMP/OpenMPOpsInterfaces.td b/mlir/include/mlir/Dialect/OpenMP/OpenMPOpsInterfaces.td
index 909529e44955cc..77001fc816cf91 100644
--- a/mlir/include/mlir/Dialect/OpenMP/OpenMPOpsInterfaces.td
+++ b/mlir/include/mlir/Dialect/OpenMP/OpenMPOpsInterfaces.td
@@ -149,6 +149,31 @@ def OffloadModuleInterface : OpInterface<"OffloadModuleInterface"> {
            return isTargetDevice.dyn_cast<BoolAttr>().getValue();
         return false;
       }]>,
+    InterfaceMethod<
+      /*description=*/[{
+      Set the attribute on the current module with the specified boolean
+      argument.
+      }],
+      /*retTy=*/"void",
+      /*methodName=*/"setIsGPU",
+      (ins "bool":$isGPU), [{}], [{
+        $_op->setAttr(
+          mlir::StringAttr::get($_op->getContext(), "omp.is_gpu"),
+            mlir::BoolAttr::get($_op->getContext(), isGPU));
+      }]>,
+    InterfaceMethod<
+      /*description=*/[{
+        Get the attribute on the current module if it exists and
+        return its value, if it doesn't exist it returns false by default.
+      }],
+      /*retTy=*/"bool",
+      /*methodName=*/"getIsGPU",
+      (ins), [{}], [{
+        if (Attribute isTargetCGAttr = $_op->getAttr("omp.is_gpu"))
+          if (auto isTargetCGVal = isTargetCGAttr.dyn_cast<BoolAttr>())
+           return isTargetCGVal.getValue();
+        return false;
+      }]>,
     InterfaceMethod<
       /*description=*/[{
         Get the FlagsAttr attribute on the current module if it exists

diff  --git a/mlir/lib/Target/LLVMIR/ModuleTranslation.cpp b/mlir/lib/Target/LLVMIR/ModuleTranslation.cpp
index cd3a645a18c686..caf10302e7204a 100644
--- a/mlir/lib/Target/LLVMIR/ModuleTranslation.cpp
+++ b/mlir/lib/Target/LLVMIR/ModuleTranslation.cpp
@@ -1283,24 +1283,25 @@ llvm::OpenMPIRBuilder *ModuleTranslation::getOpenMPBuilder() {
   if (!ompBuilder) {
     ompBuilder = std::make_unique<llvm::OpenMPIRBuilder>(*llvmModule);
 
-    bool isTargetDevice = false;
+    bool isTargetDevice = false, isGPU = false;
     llvm::StringRef hostIRFilePath = "";
 
-    if (Attribute deviceAttr = mlirModule->getAttr("omp.is_target_device"))
-      if (::llvm::isa<mlir::BoolAttr>(deviceAttr))
-        isTargetDevice =
-            ::llvm::dyn_cast<mlir::BoolAttr>(deviceAttr).getValue();
+    if (auto deviceAttr =
+            mlirModule->getAttrOfType<mlir::BoolAttr>("omp.is_target_device"))
+      isTargetDevice = deviceAttr.getValue();
 
-    if (Attribute filepath = mlirModule->getAttr("omp.host_ir_filepath"))
-      if (::llvm::isa<mlir::StringAttr>(filepath))
-        hostIRFilePath =
-            ::llvm::dyn_cast<mlir::StringAttr>(filepath).getValue();
+    if (auto gpuAttr = mlirModule->getAttrOfType<mlir::BoolAttr>("omp.is_gpu"))
+      isGPU = gpuAttr.getValue();
+
+    if (auto filepathAttr =
+            mlirModule->getAttrOfType<mlir::StringAttr>("omp.host_ir_filepath"))
+      hostIRFilePath = filepathAttr.getValue();
 
     ompBuilder->initialize(hostIRFilePath);
 
     // TODO: set the flags when available
     llvm::OpenMPIRBuilderConfig config(
-        isTargetDevice, /* IsGPU */ false,
+        isTargetDevice, isGPU,
         /* HasRequiresUnifiedSharedMemory */ false,
         /* OpenMPOffloadMandatory */ false);
     ompBuilder->setConfig(config);


        


More information about the Mlir-commits mailing list