Skip to content

[flang][OpenMP][Offloading][AMDGPU] Add test for target update #76355

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 2, 2024

Conversation

ergawy
Copy link
Member

@ergawy ergawy commented Dec 25, 2023

Adds a new test for offloading target update directive to AMD GPUs.

@llvmbot
Copy link
Member

llvmbot commented Dec 25, 2023

@llvm/pr-subscribers-mlir

@llvm/pr-subscribers-mlir-openmp

Author: Kareem Ergawy (ergawy)

Changes

Adds a new test for offloading target update directive to AMD GPUs.


Full diff: https://github.com/llvm/llvm-project/pull/76355.diff

3 Files Affected:

  • (modified) mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp (+6-5)
  • (modified) openmp/libomptarget/test/lit.cfg (+1-1)
  • (added) openmp/libomptarget/test/offloading/fortran/target_update.f90 (+43)
diff --git a/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp b/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp
index cd1cfb3b7686d0..730858ffc67a71 100644
--- a/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp
+++ b/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp
@@ -239,11 +239,11 @@ void mlir::configureOpenMPToLLVMConversionLegality(
   target.addDynamicallyLegalOp<
       mlir::omp::AtomicReadOp, mlir::omp::AtomicWriteOp, mlir::omp::FlushOp,
       mlir::omp::ThreadprivateOp, mlir::omp::YieldOp, mlir::omp::EnterDataOp,
-      mlir::omp::ExitDataOp, mlir::omp::DataBoundsOp, mlir::omp::MapInfoOp>(
-      [&](Operation *op) {
-        return typeConverter.isLegal(op->getOperandTypes()) &&
-               typeConverter.isLegal(op->getResultTypes());
-      });
+      mlir::omp::ExitDataOp, mlir::omp::UpdateDataOp, mlir::omp::DataBoundsOp,
+      mlir::omp::MapInfoOp>([&](Operation *op) {
+    return typeConverter.isLegal(op->getOperandTypes()) &&
+           typeConverter.isLegal(op->getResultTypes());
+  });
   target.addDynamicallyLegalOp<mlir::omp::ReductionOp>([&](Operation *op) {
     return typeConverter.isLegal(op->getOperandTypes());
   });
@@ -282,6 +282,7 @@ void mlir::populateOpenMPToLLVMConversionPatterns(LLVMTypeConverter &converter,
       RegionLessOpConversion<omp::YieldOp>,
       RegionLessOpConversion<omp::EnterDataOp>,
       RegionLessOpConversion<omp::ExitDataOp>,
+      RegionLessOpConversion<omp::UpdateDataOp>,
       RegionLessOpWithVarOperandsConversion<omp::DataBoundsOp>>(converter);
 }
 
diff --git a/openmp/libomptarget/test/lit.cfg b/openmp/libomptarget/test/lit.cfg
index 19c5e5c4572227..dca922dcfc6bce 100644
--- a/openmp/libomptarget/test/lit.cfg
+++ b/openmp/libomptarget/test/lit.cfg
@@ -132,7 +132,7 @@ elif config.operating_system == 'Darwin':
     config.test_flags += " -Wl,-rpath," + config.library_dir
     config.test_flags += " -Wl,-rpath," + config.omp_host_rtl_directory
 else: # Unices
-    if config.libomptarget_current_target != "nvptx64-nvidia-cuda":
+    if config.libomptarget_current_target != "nvptx64-nvidia-cuda" and config.libomptarget_current_target != "amdgcn-amd-amdhsa":
         config.test_flags += " -nogpulib"
     config.test_flags += " -Wl,-rpath," + config.library_dir
     config.test_flags += " -Wl,-rpath," + config.omp_host_rtl_directory
diff --git a/openmp/libomptarget/test/offloading/fortran/target_update.f90 b/openmp/libomptarget/test/offloading/fortran/target_update.f90
new file mode 100644
index 00000000000000..87f0a46f3afe72
--- /dev/null
+++ b/openmp/libomptarget/test/offloading/fortran/target_update.f90
@@ -0,0 +1,43 @@
+! REQUIRES: flang, amdgcn-amd-amdhsa
+
+! RUN: %libomptarget-compile-fortran-run-and-check-generic
+program target_update
+    implicit none
+    integer :: x(1)
+    integer :: host_id
+    integer :: device_id(1)
+
+    INTERFACE
+        FUNCTION omp_get_device_num() BIND(C)
+            USE, INTRINSIC :: iso_c_binding, ONLY: C_INT
+            integer :: omp_get_device_num
+        END FUNCTION omp_get_device_num
+    END INTERFACE
+
+    x(1) = 5
+    host_id = omp_get_device_num()
+
+!$omp target enter data map(to:x, device_id)
+!$omp target
+    x(1) = 42
+!$omp end target
+
+    ! CHECK: After first target regions and before target update: x = 5
+    print *, "After first target regions and before target update: x =", x(1)
+
+!$omp target
+    x(1) = 84
+    device_id(1) = omp_get_device_num()
+!$omp end target
+!$omp target update from(x, device_id)
+
+    ! CHECK: After second target regions and target update: x = 84
+    print *, "After second target regions and target update: x =", x(1)
+
+    ! CHECK: Offloading succeeded!
+    if (host_id /= device_id(1)) then
+        print *, "Offloading succeeded!"
+    else
+        print *, "Offloading failed!"
+    end if
+end program target_update

@llvmbot
Copy link
Member

llvmbot commented Dec 25, 2023

@llvm/pr-subscribers-flang-openmp

Author: Kareem Ergawy (ergawy)

Changes

Adds a new test for offloading target update directive to AMD GPUs.


Full diff: https://github.com/llvm/llvm-project/pull/76355.diff

3 Files Affected:

  • (modified) mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp (+6-5)
  • (modified) openmp/libomptarget/test/lit.cfg (+1-1)
  • (added) openmp/libomptarget/test/offloading/fortran/target_update.f90 (+43)
diff --git a/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp b/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp
index cd1cfb3b7686d0..730858ffc67a71 100644
--- a/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp
+++ b/mlir/lib/Conversion/OpenMPToLLVM/OpenMPToLLVM.cpp
@@ -239,11 +239,11 @@ void mlir::configureOpenMPToLLVMConversionLegality(
   target.addDynamicallyLegalOp<
       mlir::omp::AtomicReadOp, mlir::omp::AtomicWriteOp, mlir::omp::FlushOp,
       mlir::omp::ThreadprivateOp, mlir::omp::YieldOp, mlir::omp::EnterDataOp,
-      mlir::omp::ExitDataOp, mlir::omp::DataBoundsOp, mlir::omp::MapInfoOp>(
-      [&](Operation *op) {
-        return typeConverter.isLegal(op->getOperandTypes()) &&
-               typeConverter.isLegal(op->getResultTypes());
-      });
+      mlir::omp::ExitDataOp, mlir::omp::UpdateDataOp, mlir::omp::DataBoundsOp,
+      mlir::omp::MapInfoOp>([&](Operation *op) {
+    return typeConverter.isLegal(op->getOperandTypes()) &&
+           typeConverter.isLegal(op->getResultTypes());
+  });
   target.addDynamicallyLegalOp<mlir::omp::ReductionOp>([&](Operation *op) {
     return typeConverter.isLegal(op->getOperandTypes());
   });
@@ -282,6 +282,7 @@ void mlir::populateOpenMPToLLVMConversionPatterns(LLVMTypeConverter &converter,
       RegionLessOpConversion<omp::YieldOp>,
       RegionLessOpConversion<omp::EnterDataOp>,
       RegionLessOpConversion<omp::ExitDataOp>,
+      RegionLessOpConversion<omp::UpdateDataOp>,
       RegionLessOpWithVarOperandsConversion<omp::DataBoundsOp>>(converter);
 }
 
diff --git a/openmp/libomptarget/test/lit.cfg b/openmp/libomptarget/test/lit.cfg
index 19c5e5c4572227..dca922dcfc6bce 100644
--- a/openmp/libomptarget/test/lit.cfg
+++ b/openmp/libomptarget/test/lit.cfg
@@ -132,7 +132,7 @@ elif config.operating_system == 'Darwin':
     config.test_flags += " -Wl,-rpath," + config.library_dir
     config.test_flags += " -Wl,-rpath," + config.omp_host_rtl_directory
 else: # Unices
-    if config.libomptarget_current_target != "nvptx64-nvidia-cuda":
+    if config.libomptarget_current_target != "nvptx64-nvidia-cuda" and config.libomptarget_current_target != "amdgcn-amd-amdhsa":
         config.test_flags += " -nogpulib"
     config.test_flags += " -Wl,-rpath," + config.library_dir
     config.test_flags += " -Wl,-rpath," + config.omp_host_rtl_directory
diff --git a/openmp/libomptarget/test/offloading/fortran/target_update.f90 b/openmp/libomptarget/test/offloading/fortran/target_update.f90
new file mode 100644
index 00000000000000..87f0a46f3afe72
--- /dev/null
+++ b/openmp/libomptarget/test/offloading/fortran/target_update.f90
@@ -0,0 +1,43 @@
+! REQUIRES: flang, amdgcn-amd-amdhsa
+
+! RUN: %libomptarget-compile-fortran-run-and-check-generic
+program target_update
+    implicit none
+    integer :: x(1)
+    integer :: host_id
+    integer :: device_id(1)
+
+    INTERFACE
+        FUNCTION omp_get_device_num() BIND(C)
+            USE, INTRINSIC :: iso_c_binding, ONLY: C_INT
+            integer :: omp_get_device_num
+        END FUNCTION omp_get_device_num
+    END INTERFACE
+
+    x(1) = 5
+    host_id = omp_get_device_num()
+
+!$omp target enter data map(to:x, device_id)
+!$omp target
+    x(1) = 42
+!$omp end target
+
+    ! CHECK: After first target regions and before target update: x = 5
+    print *, "After first target regions and before target update: x =", x(1)
+
+!$omp target
+    x(1) = 84
+    device_id(1) = omp_get_device_num()
+!$omp end target
+!$omp target update from(x, device_id)
+
+    ! CHECK: After second target regions and target update: x = 84
+    print *, "After second target regions and target update: x =", x(1)
+
+    ! CHECK: Offloading succeeded!
+    if (host_id /= device_id(1)) then
+        print *, "Offloading succeeded!"
+    else
+        print *, "Offloading failed!"
+    end if
+end program target_update

@ergawy ergawy force-pushed the omp_target_upate_4 branch from 4c38828 to 674f5b4 Compare December 25, 2023 08:30
@ergawy ergawy requested review from agozillon and TIFitis December 25, 2023 08:32
Copy link
Contributor

@agozillon agozillon left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

@ergawy ergawy requested review from jdoerfert and jhuber6 December 28, 2023 15:34
…pdate`

Adds a new test for offloading `target update` directive to AMD GPUs.
@ergawy
Copy link
Member Author

ergawy commented Jan 2, 2024

I split the lit.cfg changes to a separate PR: #76702.

@ergawy ergawy merged commit 75be7bb into llvm:main Jan 2, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants