[clang] [flang] [llvm] [mlir] [OpenMP][flang] Add initial support for by-ref reductions on the GPU (PR #165714)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Oct 30 06:02:32 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-flang-openmp
Author: Kareem Ergawy (ergawy)
<details>
<summary>Changes</summary>
Adds initial support for GPU by-ref reductions. In particular, this diff adds support for reductions on scalar allocatables where reductions happen on loops nested in `target` regions. For example:
```fortran
integer :: i
real, allocatable :: scalar_alloc
allocate(scalar_alloc)
scalar_alloc = 0
!$omp target map(tofrom: scalar_alloc)
!$omp parallel do reduction(+: scalar_alloc)
do i = 1, 1000000
scalar_alloc = scalar_alloc + 1
end do
!$omp end target
```
This PR supports by-ref reductions on the intra- and inter-warp levels.
So far, there are still steps to be takens for full support of by-ref reductions, for example:
* Support inter-block value combination is still not supported. Therefore, `target teams distribute parallel do` is still not supported.
* Support for dynamically-sized arrays still needs to be added.
* Support for more than one allocatable/array on the same `reduction` clause.
---
Patch is 54.34 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/165714.diff
34 Files Affected:
- (modified) clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp (+2-2)
- (modified) flang/include/flang/Optimizer/Dialect/FIROps.td (+2-1)
- (modified) flang/lib/Lower/Support/ReductionProcessor.cpp (+6-1)
- (modified) flang/lib/Optimizer/OpenMP/DoConcurrentConversion.cpp (+2-1)
- (modified) flang/test/Lower/OpenMP/delayed-privatization-reduction-byref.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/parallel-reduction-allocatable-array.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/parallel-reduction-array-lb.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/parallel-reduction-array.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/parallel-reduction-array2.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/parallel-reduction-pointer-array.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/parallel-reduction3.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/reduction-array-intrinsic.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/sections-array-reduction.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/taskgroup-task-array-reduction.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/wsloop-reduction-allocatable-array-minmax.f90 (+2-2)
- (modified) flang/test/Lower/OpenMP/wsloop-reduction-allocatable.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/wsloop-reduction-array-assumed-shape.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/wsloop-reduction-array-lb.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/wsloop-reduction-array-lb2.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/wsloop-reduction-array.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/wsloop-reduction-array2.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/wsloop-reduction-multiple-clauses.f90 (+1-1)
- (modified) flang/test/Lower/OpenMP/wsloop-reduction-pointer.f90 (+1-1)
- (modified) flang/test/Lower/do_concurrent_reduce_allocatable.f90 (+1-1)
- (modified) llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h (+17-7)
- (modified) llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp (+119-35)
- (modified) mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td (+3-1)
- (modified) mlir/lib/Conversion/SCFToOpenMP/SCFToOpenMP.cpp (+2-1)
- (modified) mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp (+20-4)
- (added) mlir/test/Target/LLVMIR/allocatable_gpu_reduction.mlir (+92)
- (modified) mlir/test/Target/LLVMIR/omptarget-multi-block-reduction.mlir (+2-4)
- (modified) mlir/test/Target/LLVMIR/omptarget-multi-reduction.mlir (+4-4)
- (modified) mlir/test/Target/LLVMIR/omptarget-teams-distribute-reduction.mlir (+1-1)
- (modified) mlir/test/Target/LLVMIR/omptarget-teams-reduction.mlir (+1-1)
``````````diff
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
index fddeba98adccc..9a8c75073aa4c 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -1784,8 +1784,8 @@ void CGOpenMPRuntimeGPU::emitReduction(
llvm::OpenMPIRBuilder::InsertPointTy AfterIP =
cantFail(OMPBuilder.createReductionsGPU(
- OmpLoc, AllocaIP, CodeGenIP, ReductionInfos, false, TeamsReduction,
- llvm::OpenMPIRBuilder::ReductionGenCBKind::Clang,
+ OmpLoc, AllocaIP, CodeGenIP, ReductionInfos, {}, false,
+ TeamsReduction, llvm::OpenMPIRBuilder::ReductionGenCBKind::Clang,
CGF.getTarget().getGridValue(),
C.getLangOpts().OpenMPCUDAReductionBufNum, RTLoc));
CGF.Builder.restoreIP(AfterIP);
diff --git a/flang/include/flang/Optimizer/Dialect/FIROps.td b/flang/include/flang/Optimizer/Dialect/FIROps.td
index 58a317cf5d691..ff4dab1136ee9 100644
--- a/flang/include/flang/Optimizer/Dialect/FIROps.td
+++ b/flang/include/flang/Optimizer/Dialect/FIROps.td
@@ -3743,7 +3743,8 @@ def fir_DeclareReductionOp : fir_Op<"declare_reduction", [IsolatedFromAbove,
}];
let arguments = (ins SymbolNameAttr:$sym_name,
- TypeAttr:$type);
+ TypeAttr:$type,
+ OptionalAttr<TypeAttr>:$byref_element_type);
let regions = (region MaxSizedRegion<1>:$allocRegion,
AnyRegion:$initializerRegion,
diff --git a/flang/lib/Lower/Support/ReductionProcessor.cpp b/flang/lib/Lower/Support/ReductionProcessor.cpp
index 605a5b6b20b94..e02cd8fac823b 100644
--- a/flang/lib/Lower/Support/ReductionProcessor.cpp
+++ b/flang/lib/Lower/Support/ReductionProcessor.cpp
@@ -573,10 +573,15 @@ OpType ReductionProcessor::createDeclareReduction(
mlir::OpBuilder modBuilder(module.getBodyRegion());
mlir::Type valTy = fir::unwrapRefType(type);
+ mlir::TypeAttr boxedTy{};
+
if (!isByRef)
type = valTy;
- decl = OpType::create(modBuilder, loc, reductionOpName, type);
+ if (isByRef)
+ boxedTy = mlir::TypeAttr::get(fir::unwrapPassByRefType(valTy));
+
+ decl = OpType::create(modBuilder, loc, reductionOpName, type, boxedTy);
createReductionAllocAndInitRegions(converter, loc, decl, redId, type,
isByRef);
diff --git a/flang/lib/Optimizer/OpenMP/DoConcurrentConversion.cpp b/flang/lib/Optimizer/OpenMP/DoConcurrentConversion.cpp
index 1229018bd9b3e..11609ea7b6040 100644
--- a/flang/lib/Optimizer/OpenMP/DoConcurrentConversion.cpp
+++ b/flang/lib/Optimizer/OpenMP/DoConcurrentConversion.cpp
@@ -851,7 +851,8 @@ class DoConcurrentConversion
if (!ompReducer) {
ompReducer = mlir::omp::DeclareReductionOp::create(
rewriter, firReducer.getLoc(), ompReducerName,
- firReducer.getTypeAttr().getValue());
+ firReducer.getTypeAttr().getValue(),
+ firReducer.getByrefElementTypeAttr());
cloneFIRRegionToOMP(rewriter, firReducer.getAllocRegion(),
ompReducer.getAllocRegion());
diff --git a/flang/test/Lower/OpenMP/delayed-privatization-reduction-byref.f90 b/flang/test/Lower/OpenMP/delayed-privatization-reduction-byref.f90
index 4b6a643f94059..4c7b6ac5f5f9b 100644
--- a/flang/test/Lower/OpenMP/delayed-privatization-reduction-byref.f90
+++ b/flang/test/Lower/OpenMP/delayed-privatization-reduction-byref.f90
@@ -22,7 +22,7 @@ subroutine red_and_delayed_private
! CHECK-SAME: @[[PRIVATIZER_SYM:.*]] : i32
! CHECK-LABEL: omp.declare_reduction
-! CHECK-SAME: @[[REDUCTION_SYM:.*]] : !fir.ref<i32> alloc
+! CHECK-SAME: @[[REDUCTION_SYM:.*]] : !fir.ref<i32> attributes {byref_element_type = i32} alloc
! CHECK-LABEL: _QPred_and_delayed_private
! CHECK: omp.parallel
diff --git a/flang/test/Lower/OpenMP/parallel-reduction-allocatable-array.f90 b/flang/test/Lower/OpenMP/parallel-reduction-allocatable-array.f90
index 41c7d69ebb3ba..f56875dcb518b 100644
--- a/flang/test/Lower/OpenMP/parallel-reduction-allocatable-array.f90
+++ b/flang/test/Lower/OpenMP/parallel-reduction-allocatable-array.f90
@@ -18,7 +18,7 @@ program reduce
end program
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_heap_Uxi32 : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_heap_Uxi32 : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>> attributes {byref_element_type = !fir.array<?xi32>} alloc {
! CHECK: %[[VAL_10:.*]] = fir.alloca !fir.box<!fir.heap<!fir.array<?xi32>>>
! CHECK: omp.yield(%[[VAL_10]] : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/parallel-reduction-array-lb.f90 b/flang/test/Lower/OpenMP/parallel-reduction-array-lb.f90
index aa91e1e0e8b15..d9ba3bed464f8 100644
--- a/flang/test/Lower/OpenMP/parallel-reduction-array-lb.f90
+++ b/flang/test/Lower/OpenMP/parallel-reduction-array-lb.f90
@@ -12,7 +12,7 @@ program reduce
end program
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_3x2xi32 : !fir.ref<!fir.box<!fir.array<3x2xi32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_3x2xi32 : !fir.ref<!fir.box<!fir.array<3x2xi32>>> {{.*}} alloc {
! CHECK: %[[VAL_15:.*]] = fir.alloca !fir.box<!fir.array<3x2xi32>>
! CHECK: omp.yield(%[[VAL_15]] : !fir.ref<!fir.box<!fir.array<3x2xi32>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/parallel-reduction-array.f90 b/flang/test/Lower/OpenMP/parallel-reduction-array.f90
index 59595de338d50..636660f279e85 100644
--- a/flang/test/Lower/OpenMP/parallel-reduction-array.f90
+++ b/flang/test/Lower/OpenMP/parallel-reduction-array.f90
@@ -17,7 +17,7 @@ program reduce
print *,i
end program
-! CPU-LABEL: omp.declare_reduction @add_reduction_byref_box_3xi32 : !fir.ref<!fir.box<!fir.array<3xi32>>> alloc {
+! CPU-LABEL: omp.declare_reduction @add_reduction_byref_box_3xi32 : !fir.ref<!fir.box<!fir.array<3xi32>>> attributes {byref_element_type = !fir.array<3xi32>} alloc {
! CPU: %[[VAL_8:.*]] = fir.alloca !fir.box<!fir.array<3xi32>>
! CPU: omp.yield(%[[VAL_8]] : !fir.ref<!fir.box<!fir.array<3xi32>>>)
! CPU-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/parallel-reduction-array2.f90 b/flang/test/Lower/OpenMP/parallel-reduction-array2.f90
index 14338c6f50817..9cf8a63427ed1 100644
--- a/flang/test/Lower/OpenMP/parallel-reduction-array2.f90
+++ b/flang/test/Lower/OpenMP/parallel-reduction-array2.f90
@@ -13,7 +13,7 @@ program reduce
print *,i
end program
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_3xi32 : !fir.ref<!fir.box<!fir.array<3xi32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_3xi32 : !fir.ref<!fir.box<!fir.array<3xi32>>> {{.*}} alloc {
! CHECK: %[[VAL_8:.*]] = fir.alloca !fir.box<!fir.array<3xi32>>
! CHECK: omp.yield(%[[VAL_8]] : !fir.ref<!fir.box<!fir.array<3xi32>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/parallel-reduction-pointer-array.f90 b/flang/test/Lower/OpenMP/parallel-reduction-pointer-array.f90
index 36344458d1cae..3de2ba8f61f8e 100644
--- a/flang/test/Lower/OpenMP/parallel-reduction-pointer-array.f90
+++ b/flang/test/Lower/OpenMP/parallel-reduction-pointer-array.f90
@@ -19,7 +19,7 @@ program reduce
end program
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_ptr_Uxi32 : !fir.ref<!fir.box<!fir.ptr<!fir.array<?xi32>>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_ptr_Uxi32 : !fir.ref<!fir.box<!fir.ptr<!fir.array<?xi32>>>> attributes {byref_element_type = !fir.array<?xi32>} alloc {
! CHECK: %[[VAL_3:.*]] = fir.alloca !fir.box<!fir.ptr<!fir.array<?xi32>>>
! CHECK: omp.yield(%[[VAL_3]] : !fir.ref<!fir.box<!fir.ptr<!fir.array<?xi32>>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/parallel-reduction3.f90 b/flang/test/Lower/OpenMP/parallel-reduction3.f90
index 9af18378f0ae0..da337378862be 100644
--- a/flang/test/Lower/OpenMP/parallel-reduction3.f90
+++ b/flang/test/Lower/OpenMP/parallel-reduction3.f90
@@ -1,7 +1,7 @@
! RUN: bbc -emit-hlfir -fopenmp -o - %s 2>&1 | FileCheck %s
! RUN: %flang_fc1 -emit-hlfir -fopenmp -o - %s 2>&1 | FileCheck %s
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_Uxi32 : !fir.ref<!fir.box<!fir.array<?xi32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_Uxi32 : !fir.ref<!fir.box<!fir.array<?xi32>>> {{.*}} alloc {
! CHECK: %[[VAL_8:.*]] = fir.alloca !fir.box<!fir.array<?xi32>>
! CHECK: omp.yield(%[[VAL_8]] : !fir.ref<!fir.box<!fir.array<?xi32>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/reduction-array-intrinsic.f90 b/flang/test/Lower/OpenMP/reduction-array-intrinsic.f90
index 8b94d51f986f5..4a0593ff9eca4 100644
--- a/flang/test/Lower/OpenMP/reduction-array-intrinsic.f90
+++ b/flang/test/Lower/OpenMP/reduction-array-intrinsic.f90
@@ -9,7 +9,7 @@ subroutine max_array_reduction(l, r)
!$omp end parallel
end subroutine
-! CHECK-LABEL: omp.declare_reduction @max_byref_box_Uxi32 : !fir.ref<!fir.box<!fir.array<?xi32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @max_byref_box_Uxi32 : !fir.ref<!fir.box<!fir.array<?xi32>>> {{.*}} alloc {
! CHECK: %[[VAL_3:.*]] = fir.alloca !fir.box<!fir.array<?xi32>>
! CHECK: omp.yield(%[[VAL_3]] : !fir.ref<!fir.box<!fir.array<?xi32>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/sections-array-reduction.f90 b/flang/test/Lower/OpenMP/sections-array-reduction.f90
index 2f2808cebfc0c..0dbe9e3673395 100644
--- a/flang/test/Lower/OpenMP/sections-array-reduction.f90
+++ b/flang/test/Lower/OpenMP/sections-array-reduction.f90
@@ -14,7 +14,7 @@ subroutine sectionsReduction(x)
end subroutine
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_Uxf32 : !fir.ref<!fir.box<!fir.array<?xf32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_Uxf32 : !fir.ref<!fir.box<!fir.array<?xf32>>> {{.*}} alloc {
! [...]
! CHECK: omp.yield
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/taskgroup-task-array-reduction.f90 b/flang/test/Lower/OpenMP/taskgroup-task-array-reduction.f90
index 18a4f75b86309..3a63bb09c59de 100644
--- a/flang/test/Lower/OpenMP/taskgroup-task-array-reduction.f90
+++ b/flang/test/Lower/OpenMP/taskgroup-task-array-reduction.f90
@@ -1,7 +1,7 @@
! RUN: bbc -emit-hlfir -fopenmp -fopenmp-version=50 -o - %s 2>&1 | FileCheck %s
! RUN: %flang_fc1 -emit-hlfir -fopenmp -fopenmp-version=50 -o - %s 2>&1 | FileCheck %s
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_Uxf32 : !fir.ref<!fir.box<!fir.array<?xf32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_Uxf32 : !fir.ref<!fir.box<!fir.array<?xf32>>> {{.*}} alloc {
! [...]
! CHECK: omp.yield
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-allocatable-array-minmax.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-allocatable-array-minmax.f90
index 2cd953de0dffa..ed81577ecce16 100644
--- a/flang/test/Lower/OpenMP/wsloop-reduction-allocatable-array-minmax.f90
+++ b/flang/test/Lower/OpenMP/wsloop-reduction-allocatable-array-minmax.f90
@@ -32,7 +32,7 @@ program reduce15
print *,"min: ", mins
end program
-! CHECK-LABEL: omp.declare_reduction @min_byref_box_heap_Uxi32 : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @min_byref_box_heap_Uxi32 : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>> {{.*}} alloc {
! CHECK: %[[VAL_3:.*]] = fir.alloca !fir.box<!fir.heap<!fir.array<?xi32>>>
! CHECK: omp.yield(%[[VAL_3]] : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>>)
! CHECK-LABEL: } init {
@@ -93,7 +93,7 @@ program reduce15
! CHECK: omp.yield
! CHECK: }
-! CHECK-LABEL: omp.declare_reduction @max_byref_box_heap_Uxi32 : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @max_byref_box_heap_Uxi32 : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>> {{.*}} alloc {
! CHECK: %[[VAL_3:.*]] = fir.alloca !fir.box<!fir.heap<!fir.array<?xi32>>>
! CHECK: omp.yield(%[[VAL_3]] : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-allocatable.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-allocatable.f90
index 663851cba46c6..d8c0a36db126e 100644
--- a/flang/test/Lower/OpenMP/wsloop-reduction-allocatable.f90
+++ b/flang/test/Lower/OpenMP/wsloop-reduction-allocatable.f90
@@ -18,7 +18,7 @@ program reduce
end program
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_heap_i32 : !fir.ref<!fir.box<!fir.heap<i32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_heap_i32 : !fir.ref<!fir.box<!fir.heap<i32>>> attributes {byref_element_type = i32} alloc {
! CHECK: %[[VAL_2:.*]] = fir.alloca !fir.box<!fir.heap<i32>>
! CHECK: omp.yield(%[[VAL_2]] : !fir.ref<!fir.box<!fir.heap<i32>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-array-assumed-shape.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-array-assumed-shape.f90
index 209ee9a4e0cef..28acb8f19531f 100644
--- a/flang/test/Lower/OpenMP/wsloop-reduction-array-assumed-shape.f90
+++ b/flang/test/Lower/OpenMP/wsloop-reduction-array-assumed-shape.f90
@@ -22,7 +22,7 @@ subroutine reduce(r)
end subroutine
end program
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_Uxf64 : !fir.ref<!fir.box<!fir.array<?xf64>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_Uxf64 : !fir.ref<!fir.box<!fir.array<?xf64>>> {{.*}} alloc {
! CHECK: %[[VAL_8:.*]] = fir.alloca !fir.box<!fir.array<?xf64>>
! CHECK: omp.yield(%[[VAL_8]] : !fir.ref<!fir.box<!fir.array<?xf64>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-array-lb.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-array-lb.f90
index 2233a74600948..ec448cf20f111 100644
--- a/flang/test/Lower/OpenMP/wsloop-reduction-array-lb.f90
+++ b/flang/test/Lower/OpenMP/wsloop-reduction-array-lb.f90
@@ -11,7 +11,7 @@ program reduce
!$omp end parallel do
end program
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_2xi32 : !fir.ref<!fir.box<!fir.array<2xi32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_2xi32 : !fir.ref<!fir.box<!fir.array<2xi32>>> {{.*}} alloc {
! CHECK: } combiner {
! CHECK: ^bb0(%[[ARG0:.*]]: !fir.ref<!fir.box<!fir.array<2xi32>>>, %[[ARG1:.*]]: !fir.ref<!fir.box<!fir.array<2xi32>>>):
! CHECK: %[[ARR0:.*]] = fir.load %[[ARG0]] : !fir.ref<!fir.box<!fir.array<2xi32>>>
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-array-lb2.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-array-lb2.f90
index 211bde19da8db..9da05a290ec21 100644
--- a/flang/test/Lower/OpenMP/wsloop-reduction-array-lb2.f90
+++ b/flang/test/Lower/OpenMP/wsloop-reduction-array-lb2.f90
@@ -19,7 +19,7 @@ subroutine sub(a, lb, ub)
end program
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_Uxi32 : !fir.ref<!fir.box<!fir.array<?xi32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_Uxi32 : !fir.ref<!fir.box<!fir.array<?xi32>>> {{.*}} alloc {
! CHECK: } combiner {
! CHECK: ^bb0(%[[ARG0:.*]]: !fir.ref<!fir.box<!fir.array<?xi32>>>, %[[ARG1:.*]]: !fir.ref<!fir.box<!fir.array<?xi32>>>):
! CHECK: %[[ARR0:.*]] = fir.load %[[ARG0]] : !fir.ref<!fir.box<!fir.array<?xi32>>>
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-array.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-array.f90
index afaeba27c5eae..14b657c8e180d 100644
--- a/flang/test/Lower/OpenMP/wsloop-reduction-array.f90
+++ b/flang/test/Lower/OpenMP/wsloop-reduction-array.f90
@@ -14,7 +14,7 @@ program reduce
print *,r
end program
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_2xi32 : !fir.ref<!fir.box<!fir.array<2xi32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_2xi32 : !fir.ref<!fir.box<!fir.array<2xi32>>> attributes {byref_element_type = !fir.array<2xi32>} alloc {
! CHECK: %[[VAL_8:.*]] = fir.alloca !fir.box<!fir.array<2xi32>>
! CHECK: omp.yield(%[[VAL_8]] : !fir.ref<!fir.box<!fir.array<2xi32>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-array2.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-array2.f90
index 25b2e97a1b7f7..d0a0c38e4ccb1 100644
--- a/flang/test/Lower/OpenMP/wsloop-reduction-array2.f90
+++ b/flang/test/Lower/OpenMP/wsloop-reduction-array2.f90
@@ -14,7 +14,7 @@ program reduce
print *,r
end program
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_2xi32 : !fir.ref<!fir.box<!fir.array<2xi32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_2xi32 : !fir.ref<!fir.box<!fir.array<2xi32>>> {{.*}} alloc {
! CHECK: %[[VAL_8:.*]] = fir.alloca !fir.box<!fir.array<2xi32>>
! CHECK: omp.yield(%[[VAL_8]] : !fir.ref<!fir.box<!fir.array<2xi32>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-multiple-clauses.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-multiple-clauses.f90
index edd2bcb1d6be8..60a162d8f8002 100644
--- a/flang/test/Lower/OpenMP/wsloop-reduction-multiple-clauses.f90
+++ b/flang/test/Lower/OpenMP/wsloop-reduction-multiple-clauses.f90
@@ -24,7 +24,7 @@ program main
endprogram
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_3x3xf64 : !fir.ref<!fir.box<!fir.array<3x3xf64>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_3x3xf64 : !fir.ref<!fir.box<!fir.array<3x3xf64>>> {{.*}} alloc {
! CHECK: %[[VAL_3:.*]] = fir.alloca !fir.box<!fir.array<3x3xf64>>
! CHECK: omp.yield(%[[VAL_3]] : !fir.ref<!fir.box<!fir.array<3x3xf64>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-pointer.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-pointer.f90
index 27b726376fbeb..f640f5caddf76 100644
--- a/flang/test/Lower/OpenMP/wsloop-reduction-pointer.f90
+++ b/flang/test/Lower/OpenMP/wsloop-reduction-pointer.f90
@@ -18,7 +18,7 @@ program reduce_pointer
deallocate(v)
end program
-! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_ptr_i32 : !fir.ref<!fir.box<!fir.ptr<i32>>> alloc {
+! CHECK-LABEL: omp.declare_reduction @add_reduction_byref_box_ptr_i32 : !fir.ref<!fir.box<!fir.ptr<i32>>> {{.*}} alloc {
! CHECK: %[[VAL_3:.*]] = fir.alloca !fir.box<!fir.ptr<i32>>
! CHECK: omp.yield(%[[VAL_3]] : !fir.ref<!fir.box<!fir.ptr<i32>>>)
! CHECK-LABEL: } init {
diff --git a/flang/test/Lower/do_concurrent_reduce_allocatable.f90 b/flang/test/Lower/do_concurrent_reduce_allocatable.f90
index 873fd10dd1b97..4fb67c094b594 100644
--- a/flang/test/Lower/do_concurrent_reduce_allocatable.f90
+++ b/flang/test/Lower/do_concurrent_reduce_allocatable.f90
@@ -8,7 +8,7 @@ subroutine do_concurrent_allocatable
end do
end subroutine
-! CHECK: fir.declare_reduction @[[RED_OP:.*]] : ![[RED_TYPE:.*]] alloc {
+! CHECK: fir.declare_reduction @[[RED_OP:.*]] : ![[RED_TYPE:.*]] attributes {byref_element_type = !fir.array<?x?xf32>} alloc {
! CHECK: %[[ALLOC:.*]] = fir.alloca
! CHECK: fir.yield(%[[ALLOC]] : ![[RED_TYPE]])
! CHECK: } init {
diff --git a/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h b/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
index 5331cb5abdc6f..f4192f9b49fd9 100644
--- a/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
+++ b/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
@@ -1448,11 +1448,15 @@ class OpenMPIRBuilder {
ReductionInfo(Type *ElementType, Value *Variable, Value *PrivateVariable,
EvalKind EvaluationKind, ReductionGenCBTy ReductionGen,
ReductionGenClangCBTy ReductionGenClang,
- ReductionGenAtomicCBTy AtomicReductionGen)
+ ReductionGenAtomicCBTy AtomicReductionGen,
+ Type *ByRefAllocatedType = nullptr,
+ Type *ByRefElementType = nullptr)
: ElementType(ElementType), Vari...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/165714
More information about the llvm-commits
mailing list