Skip to content

[flang][OpenMP] Fix reduction of arrays with non-default lower bounds #132228

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.

Sign up for GitHub

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
Mar 24, 2025
Merged

[flang][OpenMP] Fix reduction of arrays with non-default lower bounds #132228

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 17 additions & 8 deletions flang/lib/Lower/OpenMP/PrivateReductionUtils.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,10 +122,9 @@ static void createCleanupRegion(Fortran::lower::AbstractConverter &converter,
typeError();
}

fir::ShapeShiftOp
Fortran::lower::omp::getShapeShift(fir::FirOpBuilder &builder,
mlir::Location loc, mlir::Value box,
bool cannotHaveNonDefaultLowerBounds) {
fir::ShapeShiftOp Fortran::lower::omp::getShapeShift(
fir::FirOpBuilder &builder, mlir::Location loc, mlir::Value box,
bool cannotHaveNonDefaultLowerBounds, bool useDefaultLowerBounds) {
fir::SequenceType sequenceType = mlir::cast<fir::SequenceType>(
hlfir::getFortranElementOrSequenceType(box.getType()));
const unsigned rank = sequenceType.getDimension();
Expand All @@ -134,15 +133,24 @@ Fortran::lower::omp::getShapeShift(fir::FirOpBuilder &builder,
lbAndExtents.reserve(rank * 2);
mlir::Type idxTy = builder.getIndexType();

if (cannotHaveNonDefaultLowerBounds && !sequenceType.hasDynamicExtents()) {
mlir::Value oneVal;
auto one = [&] {
if (!oneVal)
oneVal = builder.createIntegerConstant(loc, idxTy, 1);
return oneVal;
};

if ((cannotHaveNonDefaultLowerBounds || useDefaultLowerBounds) &&
!sequenceType.hasDynamicExtents()) {
// We don't need fir::BoxDimsOp if all of the extents are statically known
// and we can assume default lower bounds. This helps avoids reads from the
// mold arg.
mlir::Value one = builder.createIntegerConstant(loc, idxTy, 1);
// We may also want to use default lower bounds to iterate through array
// elements without having to adjust each index.
for (int64_t extent : sequenceType.getShape()) {
assert(extent != sequenceType.getUnknownExtent());
lbAndExtents.push_back(one());
mlir::Value extentVal = builder.createIntegerConstant(loc, idxTy, extent);
lbAndExtents.push_back(one);
lbAndExtents.push_back(extentVal);
}
} else {
Expand All @@ -153,7 +161,8 @@ Fortran::lower::omp::getShapeShift(fir::FirOpBuilder &builder,
mlir::Value dim = builder.createIntegerConstant(loc, idxTy, i);
auto dimInfo =
builder.create<fir::BoxDimsOp>(loc, idxTy, idxTy, idxTy, box, dim);
lbAndExtents.push_back(dimInfo.getLowerBound());
lbAndExtents.push_back(useDefaultLowerBounds ? one()
: dimInfo.getLowerBound());
lbAndExtents.push_back(dimInfo.getExtent());
}
}
Expand Down
8 changes: 7 additions & 1 deletion flang/lib/Lower/OpenMP/PrivateReductionUtils.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,9 +59,15 @@ void populateByRefInitAndCleanupRegions(
bool cannotHaveNonDefaultLowerBounds = false);

/// Generate a fir::ShapeShift op describing the provided boxed array.
/// `cannotHaveNonDefaultLowerBounds` should be set if `box` is known to have
/// default lower bounds. This can improve code generation.
/// `useDefaultLowerBounds` can be set to force the returned fir::ShapeShiftOp
/// to have default lower bounds, which is useful to iterate through array
/// elements without having to adjust each index.
fir::ShapeShiftOp getShapeShift(fir::FirOpBuilder &builder, mlir::Location loc,
mlir::Value box,
bool cannotHaveNonDefaultLowerBounds = false);
bool cannotHaveNonDefaultLowerBounds = false,
bool useDefaultLowerBounds = false);

} // namespace omp
} // namespace lower
Expand Down
7 changes: 6 additions & 1 deletion flang/lib/Lower/OpenMP/ReductionProcessor.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -337,7 +337,12 @@ static void genBoxCombiner(fir::FirOpBuilder &builder, mlir::Location loc,
return;
}

fir::ShapeShiftOp shapeShift = getShapeShift(builder, loc, lhs);
// Get ShapeShift with default lower bounds. This makes it possible to use
// unmodified LoopNest's indices with ArrayCoorOp.
fir::ShapeShiftOp shapeShift =
getShapeShift(builder, loc, lhs,
/*cannotHaveNonDefaultLowerBounds=*/false,
/*useDefaultLowerBounds=*/true);

// Iterate over array elements, applying the equivalent scalar reduction:

Expand Down
3 changes: 2 additions & 1 deletion flang/test/Lower/OpenMP/parallel-reduction-allocatable-array.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,8 @@ program reduce
! CHECK: %[[VAL_3:.*]] = fir.load %[[VAL_1]] : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>>
! CHECK: %[[VAL_4:.*]] = arith.constant 0 : index
! CHECK: %[[VAL_5:.*]]:3 = fir.box_dims %[[VAL_2]], %[[VAL_4]] : (!fir.box<!fir.heap<!fir.array<?xi32>>>, index) -> (index, index, index)
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[VAL_5]]#0, %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[C1:.*]] = arith.constant 1 : index
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[C1]], %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[VAL_7:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_8:.*]] = %[[VAL_7]] to %[[VAL_5]]#1 step %[[VAL_7]] unordered {
! CHECK: %[[VAL_9:.*]] = fir.array_coor %[[VAL_2]](%[[VAL_6]]) %[[VAL_8]] : (!fir.box<!fir.heap<!fir.array<?xi32>>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
Expand Down
19 changes: 9 additions & 10 deletions flang/test/Lower/OpenMP/parallel-reduction-array-lb.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,16 +38,15 @@ program reduce
! CHECK: ^bb0(%[[VAL_0:.*]]: !fir.ref<!fir.box<!fir.array<3x2xi32>>>, %[[VAL_1:.*]]: !fir.ref<!fir.box<!fir.array<3x2xi32>>>):
! CHECK: %[[VAL_2:.*]] = fir.load %[[VAL_0]] : !fir.ref<!fir.box<!fir.array<3x2xi32>>>
! CHECK: %[[VAL_3:.*]] = fir.load %[[VAL_1]] : !fir.ref<!fir.box<!fir.array<3x2xi32>>>
! CHECK: %[[VAL_4:.*]] = arith.constant 0 : index
! CHECK: %[[VAL_5:.*]]:3 = fir.box_dims %[[VAL_2]], %[[VAL_4]] : (!fir.box<!fir.array<3x2xi32>>, index) -> (index, index, index)
! CHECK: %[[VAL_6:.*]] = arith.constant 1 : index
! CHECK: %[[VAL_7:.*]]:3 = fir.box_dims %[[VAL_2]], %[[VAL_6]] : (!fir.box<!fir.array<3x2xi32>>, index) -> (index, index, index)
! CHECK: %[[VAL_8:.*]] = fir.shape_shift %[[VAL_5]]#0, %[[VAL_5]]#1, %[[VAL_7]]#0, %[[VAL_7]]#1 : (index, index, index, index) -> !fir.shapeshift<2>
! CHECK: %[[VAL_9:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_10:.*]] = %[[VAL_9]] to %[[VAL_7]]#1 step %[[VAL_9]] unordered {
! CHECK: fir.do_loop %[[VAL_11:.*]] = %[[VAL_9]] to %[[VAL_5]]#1 step %[[VAL_9]] unordered {
! CHECK: %[[VAL_12:.*]] = fir.array_coor %[[VAL_2]](%[[VAL_8]]) %[[VAL_11]], %[[VAL_10]] : (!fir.box<!fir.array<3x2xi32>>, !fir.shapeshift<2>, index, index) -> !fir.ref<i32>
! CHECK: %[[VAL_13:.*]] = fir.array_coor %[[VAL_3]](%[[VAL_8]]) %[[VAL_11]], %[[VAL_10]] : (!fir.box<!fir.array<3x2xi32>>, !fir.shapeshift<2>, index, index) -> !fir.ref<i32>
! CHECK: %[[C1:.*]] = arith.constant 1 : index
! CHECK: %[[C3:.*]] = arith.constant 3 : index
! CHECK: %[[C2:.*]] = arith.constant 2 : index
! CHECK: %[[SHAPE_SHIFT:.*]] = fir.shape_shift %[[C1]], %[[C3]], %[[C1]], %[[C2]] : (index, index, index, index) -> !fir.shapeshift<2>
! CHECK: %[[C1_0:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_10:.*]] = %[[C1_0]] to %[[C2]] step %[[C1_0]] unordered {
! CHECK: fir.do_loop %[[VAL_11:.*]] = %[[C1_0]] to %[[C3]] step %[[C1_0]] unordered {
! CHECK: %[[VAL_12:.*]] = fir.array_coor %[[VAL_2]](%[[SHAPE_SHIFT]]) %[[VAL_11]], %[[VAL_10]] : (!fir.box<!fir.array<3x2xi32>>, !fir.shapeshift<2>, index, index) -> !fir.ref<i32>
! CHECK: %[[VAL_13:.*]] = fir.array_coor %[[VAL_3]](%[[SHAPE_SHIFT]]) %[[VAL_11]], %[[VAL_10]] : (!fir.box<!fir.array<3x2xi32>>, !fir.shapeshift<2>, index, index) -> !fir.ref<i32>
! CHECK: %[[VAL_14:.*]] = fir.load %[[VAL_12]] : !fir.ref<i32>
! CHECK: %[[VAL_15:.*]] = fir.load %[[VAL_13]] : !fir.ref<i32>
! CHECK: %[[VAL_16:.*]] = arith.addi %[[VAL_14]], %[[VAL_15]] : i32
Expand Down
14 changes: 7 additions & 7 deletions flang/test/Lower/OpenMP/parallel-reduction-array.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,13 +37,13 @@ program reduce
! CHECK: ^bb0(%[[VAL_0:.*]]: !fir.ref<!fir.box<!fir.array<3xi32>>>, %[[VAL_1:.*]]: !fir.ref<!fir.box<!fir.array<3xi32>>>):
! CHECK: %[[VAL_2:.*]] = fir.load %[[VAL_0]] : !fir.ref<!fir.box<!fir.array<3xi32>>>
! CHECK: %[[VAL_3:.*]] = fir.load %[[VAL_1]] : !fir.ref<!fir.box<!fir.array<3xi32>>>
! CHECK: %[[VAL_4:.*]] = arith.constant 0 : index
! CHECK: %[[VAL_5:.*]]:3 = fir.box_dims %[[VAL_2]], %[[VAL_4]] : (!fir.box<!fir.array<3xi32>>, index) -> (index, index, index)
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[VAL_5]]#0, %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[VAL_7:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_8:.*]] = %[[VAL_7]] to %[[VAL_5]]#1 step %[[VAL_7]] unordered {
! CHECK: %[[VAL_9:.*]] = fir.array_coor %[[VAL_2]](%[[VAL_6]]) %[[VAL_8]] : (!fir.box<!fir.array<3xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
! CHECK: %[[VAL_10:.*]] = fir.array_coor %[[VAL_3]](%[[VAL_6]]) %[[VAL_8]] : (!fir.box<!fir.array<3xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
! CHECK: %[[C1:.*]] = arith.constant 1 : index
! CHECK: %[[C3:.*]] = arith.constant 3 : index
! CHECK: %[[SHAPE_SHIFT:.*]] = fir.shape_shift %[[C1]], %[[C3]] : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[C1_0:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_8:.*]] = %[[C1_0]] to %[[C3]] step %[[C1_0]] unordered {
! CHECK: %[[VAL_9:.*]] = fir.array_coor %[[VAL_2]](%[[SHAPE_SHIFT]]) %[[VAL_8]] : (!fir.box<!fir.array<3xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
! CHECK: %[[VAL_10:.*]] = fir.array_coor %[[VAL_3]](%[[SHAPE_SHIFT]]) %[[VAL_8]] : (!fir.box<!fir.array<3xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
! CHECK: %[[VAL_11:.*]] = fir.load %[[VAL_9]] : !fir.ref<i32>
! CHECK: %[[VAL_12:.*]] = fir.load %[[VAL_10]] : !fir.ref<i32>
! CHECK: %[[VAL_13:.*]] = arith.addi %[[VAL_11]], %[[VAL_12]] : i32
Expand Down
14 changes: 7 additions & 7 deletions flang/test/Lower/OpenMP/parallel-reduction-array2.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,13 +36,13 @@ program reduce
! CHECK: ^bb0(%[[VAL_0:.*]]: !fir.ref<!fir.box<!fir.array<3xi32>>>, %[[VAL_1:.*]]: !fir.ref<!fir.box<!fir.array<3xi32>>>):
! CHECK: %[[VAL_2:.*]] = fir.load %[[VAL_0]] : !fir.ref<!fir.box<!fir.array<3xi32>>>
! CHECK: %[[VAL_3:.*]] = fir.load %[[VAL_1]] : !fir.ref<!fir.box<!fir.array<3xi32>>>
! CHECK: %[[VAL_4:.*]] = arith.constant 0 : index
! CHECK: %[[VAL_5:.*]]:3 = fir.box_dims %[[VAL_2]], %[[VAL_4]] : (!fir.box<!fir.array<3xi32>>, index) -> (index, index, index)
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[VAL_5]]#0, %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[VAL_7:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_8:.*]] = %[[VAL_7]] to %[[VAL_5]]#1 step %[[VAL_7]] unordered {
! CHECK: %[[VAL_9:.*]] = fir.array_coor %[[VAL_2]](%[[VAL_6]]) %[[VAL_8]] : (!fir.box<!fir.array<3xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
! CHECK: %[[VAL_10:.*]] = fir.array_coor %[[VAL_3]](%[[VAL_6]]) %[[VAL_8]] : (!fir.box<!fir.array<3xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
! CHECK: %[[C1:.*]] = arith.constant 1 : index
! CHECK: %[[C3:.*]] = arith.constant 3 : index
! CHECK: %[[SHAPE_SHIFT:.*]] = fir.shape_shift %[[C1]], %[[C3]] : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[C1_0:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_8:.*]] = %[[C1_0]] to %[[C3]] step %[[C1_0]] unordered {
! CHECK: %[[VAL_9:.*]] = fir.array_coor %[[VAL_2]](%[[SHAPE_SHIFT]]) %[[VAL_8]] : (!fir.box<!fir.array<3xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
! CHECK: %[[VAL_10:.*]] = fir.array_coor %[[VAL_3]](%[[SHAPE_SHIFT]]) %[[VAL_8]] : (!fir.box<!fir.array<3xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
! CHECK: %[[VAL_11:.*]] = fir.load %[[VAL_9]] : !fir.ref<i32>
! CHECK: %[[VAL_12:.*]] = fir.load %[[VAL_10]] : !fir.ref<i32>
! CHECK: %[[VAL_13:.*]] = arith.addi %[[VAL_11]], %[[VAL_12]] : i32
Expand Down
3 changes: 2 additions & 1 deletion flang/test/Lower/OpenMP/parallel-reduction-pointer-array.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,8 @@ program reduce
! CHECK: %[[VAL_3:.*]] = fir.load %[[VAL_1]] : !fir.ref<!fir.box<!fir.ptr<!fir.array<?xi32>>>>
! CHECK: %[[VAL_4:.*]] = arith.constant 0 : index
! CHECK: %[[VAL_5:.*]]:3 = fir.box_dims %[[VAL_2]], %[[VAL_4]] : (!fir.box<!fir.ptr<!fir.array<?xi32>>>, index) -> (index, index, index)
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[VAL_5]]#0, %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[C1:.*]] = arith.constant 1 : index
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[C1]], %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[VAL_7:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_8:.*]] = %[[VAL_7]] to %[[VAL_5]]#1 step %[[VAL_7]] unordered {
! CHECK: %[[VAL_9:.*]] = fir.array_coor %[[VAL_2]](%[[VAL_6]]) %[[VAL_8]] : (!fir.box<!fir.ptr<!fir.array<?xi32>>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
Expand Down
3 changes: 2 additions & 1 deletion flang/test/Lower/OpenMP/parallel-reduction3.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,8 @@
! CHECK: %[[VAL_3:.*]] = fir.load %[[VAL_1]] : !fir.ref<!fir.box<!fir.array<?xi32>>>
! CHECK: %[[VAL_4:.*]] = arith.constant 0 : index
! CHECK: %[[VAL_5:.*]]:3 = fir.box_dims %[[VAL_2]], %[[VAL_4]] : (!fir.box<!fir.array<?xi32>>, index) -> (index, index, index)
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[VAL_5]]#0, %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[C1:.*]] = arith.constant 1 : index
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[C1]], %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[VAL_7:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_8:.*]] = %[[VAL_7]] to %[[VAL_5]]#1 step %[[VAL_7]] unordered {
! CHECK: %[[VAL_9:.*]] = fir.array_coor %[[VAL_2]](%[[VAL_6]]) %[[VAL_8]] : (!fir.box<!fir.array<?xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
Expand Down
3 changes: 2 additions & 1 deletion flang/test/Lower/OpenMP/reduction-array-intrinsic.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,8 @@ subroutine max_array_reduction(l, r)
! CHECK: %[[VAL_3:.*]] = fir.load %[[VAL_1]] : !fir.ref<!fir.box<!fir.array<?xi32>>>
! CHECK: %[[VAL_4:.*]] = arith.constant 0 : index
! CHECK: %[[VAL_5:.*]]:3 = fir.box_dims %[[VAL_2]], %[[VAL_4]] : (!fir.box<!fir.array<?xi32>>, index) -> (index, index, index)
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[VAL_5]]#0, %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[C1:.*]] = arith.constant 1 : index
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[C1]], %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[VAL_7:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_8:.*]] = %[[VAL_7]] to %[[VAL_5]]#1 step %[[VAL_7]] unordered {
! CHECK: %[[VAL_9:.*]] = fir.array_coor %[[VAL_2]](%[[VAL_6]]) %[[VAL_8]] : (!fir.box<!fir.array<?xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
Expand Down
6 changes: 4 additions & 2 deletions flang/test/Lower/OpenMP/wsloop-reduction-allocatable-array-minmax.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,8 @@ program reduce15
! CHECK: %[[VAL_3:.*]] = fir.load %[[VAL_1]] : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>>
! CHECK: %[[VAL_4:.*]] = arith.constant 0 : index
! CHECK: %[[VAL_5:.*]]:3 = fir.box_dims %[[VAL_2]], %[[VAL_4]] : (!fir.box<!fir.heap<!fir.array<?xi32>>>, index) -> (index, index, index)
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[VAL_5]]#0, %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[C1:.*]] = arith.constant 1 : index
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[C1]], %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[VAL_7:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_8:.*]] = %[[VAL_7]] to %[[VAL_5]]#1 step %[[VAL_7]] unordered {
! CHECK: %[[VAL_9:.*]] = fir.array_coor %[[VAL_2]](%[[VAL_6]]) %[[VAL_8]] : (!fir.box<!fir.heap<!fir.array<?xi32>>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
Expand Down Expand Up @@ -130,7 +131,8 @@ program reduce15
! CHECK: %[[VAL_3:.*]] = fir.load %[[VAL_1]] : !fir.ref<!fir.box<!fir.heap<!fir.array<?xi32>>>>
! CHECK: %[[VAL_4:.*]] = arith.constant 0 : index
! CHECK: %[[VAL_5:.*]]:3 = fir.box_dims %[[VAL_2]], %[[VAL_4]] : (!fir.box<!fir.heap<!fir.array<?xi32>>>, index) -> (index, index, index)
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[VAL_5]]#0, %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[C1:.*]] = arith.constant 1 : index
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[C1]], %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[VAL_7:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_8:.*]] = %[[VAL_7]] to %[[VAL_5]]#1 step %[[VAL_7]] unordered {
! CHECK: %[[VAL_9:.*]] = fir.array_coor %[[VAL_2]](%[[VAL_6]]) %[[VAL_8]] : (!fir.box<!fir.heap<!fir.array<?xi32>>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
Expand Down
3 changes: 2 additions & 1 deletion flang/test/Lower/OpenMP/wsloop-reduction-array-assumed-shape.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,8 @@ subroutine reduce(r)
! CHECK: %[[VAL_3:.*]] = fir.load %[[VAL_1]] : !fir.ref<!fir.box<!fir.array<?xf64>>>
! CHECK: %[[VAL_4:.*]] = arith.constant 0 : index
! CHECK: %[[VAL_5:.*]]:3 = fir.box_dims %[[VAL_2]], %[[VAL_4]] : (!fir.box<!fir.array<?xf64>>, index) -> (index, index, index)
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[VAL_5]]#0, %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[C1:.*]] = arith.constant 1 : index
! CHECK: %[[VAL_6:.*]] = fir.shape_shift %[[C1]], %[[VAL_5]]#1 : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[VAL_7:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[VAL_8:.*]] = %[[VAL_7]] to %[[VAL_5]]#1 step %[[VAL_7]] unordered {
! CHECK: %[[VAL_9:.*]] = fir.array_coor %[[VAL_2]](%[[VAL_6]]) %[[VAL_8]] : (!fir.box<!fir.array<?xf64>>, !fir.shapeshift<1>, index) -> !fir.ref<f64>
Expand Down
35 changes: 35 additions & 0 deletions flang/test/Lower/OpenMP/wsloop-reduction-array-lb.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
! RUN: bbc -emit-hlfir -fopenmp -o - %s 2>&1 | FileCheck %s
! RUN: %flang_fc1 -emit-hlfir -fopenmp -o - %s 2>&1 | FileCheck %s

program reduce
integer a(0:1)

!$omp parallel do reduction(+:a)
do i = 1, 10
a(0) = a(0) + 1
end do
!$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: } 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>>>
! CHECK: %[[ARR1:.*]] = fir.load %[[ARG1]] : !fir.ref<!fir.box<!fir.array<2xi32>>>
! CHECK: %[[C1:.*]] = arith.constant 1 : index
! CHECK: %[[C2:.*]] = arith.constant 2 : index
! CHECK: %[[SHAPE_SHIFT:.*]] = fir.shape_shift %[[C1]], %[[C2]] : (index, index) -> !fir.shapeshift<1>
! CHECK: %[[C1_0:.*]] = arith.constant 1 : index
! CHECK: fir.do_loop %[[ARG2:.*]] = %[[C1_0]] to %[[C2]] step %[[C1_0]] unordered {
! CHECK: %[[COOR0:.*]] = fir.array_coor %[[ARR0]](%[[SHAPE_SHIFT]]) %[[ARG2]] : (!fir.box<!fir.array<2xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
! CHECK: %[[COOR1:.*]] = fir.array_coor %[[ARR1]](%[[SHAPE_SHIFT]]) %[[ARG2]] : (!fir.box<!fir.array<2xi32>>, !fir.shapeshift<1>, index) -> !fir.ref<i32>
! CHECK: %[[ELEM0:.*]] = fir.load %[[COOR0]] : !fir.ref<i32>
! CHECK: %[[ELEM1:.*]] = fir.load %[[COOR1]] : !fir.ref<i32>
! CHECK: %[[SUM:.*]] = arith.addi %[[ELEM0]], %[[ELEM1]] : i32
! CHECK: fir.store %[[SUM]] to %[[COOR0]] : !fir.ref<i32>
! CHECK: }
! CHECK: omp.yield(%[[ARG0]] : !fir.ref<!fir.box<!fir.array<2xi32>>>)
! CHECK: }

! CHECK-LABEL: func.func @_QQmain() attributes {fir.bindc_name = "reduce"} {
! CHECK: omp.wsloop {{.*}} reduction(byref @add_reduction_byref_box_2xi32 %{{.*}} -> %{{.*}} : !fir.ref<!fir.box<!fir.array<2xi32>>>)
Loading