[flang-commits] [flang] 716fe1c - [Flang][OpenMP] Fix negative array indexing with allocatable derived type array maps (#154193)
via flang-commits
flang-commits at lists.llvm.org
Fri Oct 3 18:12:25 PDT 2025
Author: agozillon
Date: 2025-10-04T03:12:21+02:00
New Revision: 716fe1cbd9496564ac3588069846a52b8539df65
URL: https://github.com/llvm/llvm-project/commit/716fe1cbd9496564ac3588069846a52b8539df65
DIFF: https://github.com/llvm/llvm-project/commit/716fe1cbd9496564ac3588069846a52b8539df65.diff
LOG: [Flang][OpenMP] Fix negative array indexing with allocatable derived type array maps (#154193)
The main problem is that the previous intermediate map generation for
allocatable members wasn't quite handling negative bounds acccesses
correctly, it seems to require slightly more complicated access using
shape_shift/dimension information. So this more closely mimics what
Flang generates in other cases now.
There is still a path for non-Box types to go down the old route for the
moment, so it is possible we may still have issues with negative bounds
in these cases. But, that's better in another PR if we come across it,
instead of too much change in this one.
Added:
flang/test/Lower/OpenMP/map-neg-alloca-derived-type-array.f90
Modified:
flang/lib/Lower/OpenMP/Utils.cpp
flang/test/Integration/OpenMP/map-types-and-sizes.f90
Removed:
################################################################################
diff --git a/flang/lib/Lower/OpenMP/Utils.cpp b/flang/lib/Lower/OpenMP/Utils.cpp
index 29cccbd1bfe5a..37b926e2f23f2 100644
--- a/flang/lib/Lower/OpenMP/Utils.cpp
+++ b/flang/lib/Lower/OpenMP/Utils.cpp
@@ -14,11 +14,12 @@
#include "ClauseFinder.h"
#include "flang/Evaluate/fold.h"
-#include "flang/Lower/OpenMP/Clauses.h"
#include <flang/Lower/AbstractConverter.h>
#include <flang/Lower/ConvertType.h>
#include <flang/Lower/DirectivesCommon.h>
+#include <flang/Lower/OpenMP/Clauses.h>
#include <flang/Lower/PFTBuilder.h>
+#include <flang/Lower/Support/PrivateReductionUtils.h>
#include <flang/Optimizer/Builder/FIRBuilder.h>
#include <flang/Optimizer/Builder/Todo.h>
#include <flang/Parser/openmp-utils.h>
@@ -180,16 +181,11 @@ static void generateArrayIndices(lower::AbstractConverter &converter,
for (auto v : arr->subscript()) {
if (std::holds_alternative<Triplet>(v.u))
TODO(clauseLocation, "Triplet indexing in map clause is unsupported");
-
auto expr = std::get<Fortran::evaluate::IndirectSubscriptIntegerExpr>(v.u);
mlir::Value subscript =
fir::getBase(converter.genExprValue(toEvExpr(expr.value()), stmtCtx));
- mlir::Value one = firOpBuilder.createIntegerConstant(
- clauseLocation, firOpBuilder.getIndexType(), 1);
- subscript = firOpBuilder.createConvert(
- clauseLocation, firOpBuilder.getIndexType(), subscript);
- indices.push_back(mlir::arith::SubIOp::create(firOpBuilder, clauseLocation,
- subscript, one));
+ indices.push_back(firOpBuilder.createConvert(
+ clauseLocation, firOpBuilder.getIndexType(), subscript));
}
}
@@ -322,10 +318,42 @@ mlir::Value createParentSymAndGenIntermediateMaps(
subscriptIndices, objectList[i]);
assert(!subscriptIndices.empty() &&
"missing expected indices for map clause");
- curValue = fir::CoordinateOp::create(
- firOpBuilder, clauseLocation,
- firOpBuilder.getRefType(arrType.getEleTy()), curValue,
- subscriptIndices);
+ if (auto boxTy = llvm::dyn_cast<fir::BaseBoxType>(curValue.getType())) {
+ // To accommodate indexing into box types of all dimensions including
+ // negative dimensions we have to take into consideration the lower
+ // bounds and extents of the data (stored in the box) and convey it
+ // to the ArrayCoorOp so that it can appropriately access the element
+ // utilising the subscript we provide and the runtime sizes stored in
+ // the Box. To do so we need to generate a ShapeShiftOp which combines
+ // both the lb (ShiftOp) and extent (ShapeOp) of the Box, giving the
+ // ArrayCoorOp the spatial information it needs to calculate the
+ // underlying address.
+ mlir::Value shapeShift = Fortran::lower::getShapeShift(
+ firOpBuilder, clauseLocation, curValue);
+ auto addrOp =
+ fir::BoxAddrOp::create(firOpBuilder, clauseLocation, curValue);
+ curValue = fir::ArrayCoorOp::create(
+ firOpBuilder, clauseLocation,
+ firOpBuilder.getRefType(arrType.getEleTy()), addrOp, shapeShift,
+ /*slice=*/mlir::Value{}, subscriptIndices,
+ /*typeparms=*/mlir::ValueRange{});
+ } else {
+ // We're required to negate by one in the non-Box case as I believe
+ // we do not have the shape generated from the dimensions to help
+ // adjust the indexing.
+ // TODO/FIXME: This may need adjusted to support bounds of unusual
+ // dimensions, if that's the case then it is likely best to fold this
+ // branch into the above.
+ mlir::Value one = firOpBuilder.createIntegerConstant(
+ clauseLocation, firOpBuilder.getIndexType(), 1);
+ for (auto &v : subscriptIndices)
+ v = mlir::arith::SubIOp::create(firOpBuilder, clauseLocation, v,
+ one);
+ curValue = fir::CoordinateOp::create(
+ firOpBuilder, clauseLocation,
+ firOpBuilder.getRefType(arrType.getEleTy()), curValue,
+ subscriptIndices);
+ }
}
}
@@ -415,7 +443,6 @@ mlir::Value createParentSymAndGenIntermediateMaps(
currentIndicesIdx++;
}
}
-
return curValue;
}
diff --git a/flang/test/Integration/OpenMP/map-types-and-sizes.f90 b/flang/test/Integration/OpenMP/map-types-and-sizes.f90
index 665be5a8db4d4..44a049f5ac510 100644
--- a/flang/test/Integration/OpenMP/map-types-and-sizes.f90
+++ b/flang/test/Integration/OpenMP/map-types-and-sizes.f90
@@ -785,15 +785,20 @@ end subroutine mapType_common_block_members
!CHECK: %[[BOUNDS_CALC:.*]] = sub i64 %[[BOUNDS_LD_2]], 1
!CHECK: %[[OFF_PTR_CALC_0:.*]] = sub i64 %[[BOUNDS_LD]], 1
!CHECK: %[[OFF_PTR_2:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]], ptr, [1 x i64] }, ptr %[[OFF_PTR_1]], i32 0, i32 0
+!CHECK: %[[GEP_LB:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]], ptr, [1 x i64] }, ptr %[[ALLOCA_0]], i32 0, i32 7, i64 0, i32 0
+!CHECK: %[[LOAD_LB:.*]] = load i64, ptr %[[GEP_LB]], align 8
+!CHECK: %[[GEP_UB:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]], ptr, [1 x i64] }, ptr %[[ALLOCA_0]], i32 0, i32 7, i64 0, i32 1
+!CHECK: %[[LOAD_UB:.*]] = load i64, ptr %[[GEP_UB]], align 8
!CHECK: %[[GEP_DESC_PTR:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]], ptr, [1 x i64] }, ptr %[[ALLOCA_0]], i32 0, i32 0
-!CHECK: %[[LOAD_DESC_PTR:.*]] = load ptr, ptr %[[GEP_DESC_PTR]], align 8
-!CHECK: %[[SZ_CALC_1:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]], ptr, [1 x i64] }, ptr %[[ALLOCA_0]], i32 0, i32 7, i32 0, i32 2
-!CHECK: %[[SZ_CALC_2:.*]] = load i64, ptr %[[SZ_CALC_1]], align 8
-!CHECK: %[[SZ_CALC_3:.*]] = mul nsw i64 1, %[[SZ_CALC_2]]
-!CHECK: %[[SZ_CALC_4:.*]] = add nsw i64 %[[SZ_CALC_3]], 0
-!CHECK: %[[SZ_CALC_5:.*]] = getelementptr i8, ptr %[[LOAD_DESC_PTR]], i64 %[[SZ_CALC_4]]
-!CHECK: %[[SZ_CALC_6:.*]] = getelementptr %_QFmaptype_nested_derived_type_member_idxTvertexes, ptr %[[SZ_CALC_5]], i32 0, i32 2
-!CHECK: %[[OFF_PTR_4:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]] }, ptr %[[SZ_CALC_6]], i32 0, i32 0
+!CHECK: %[[SZ_CALC_1:.*]] = load ptr, ptr %[[GEP_DESC_PTR]], align 8
+!CHECK: %[[SZ_CALC_2:.*]] = sub nsw i64 2, %[[LOAD_LB]]
+!CHECK: %[[SZ_CALC_3:.*]] = mul nsw i64 %[[SZ_CALC_2]], 1
+!CHECK: %[[SZ_CALC_4:.*]] = mul nsw i64 %[[SZ_CALC_3]], 1
+!CHECK: %[[SZ_CALC_5:.*]] = add nsw i64 %[[SZ_CALC_4]], 0
+!CHECK: %[[SZ_CALC_6:.*]] = mul nsw i64 1, %[[LOAD_UB]]
+!CHECK: %[[SZ_CALC_7:.*]] = getelementptr %_QFmaptype_nested_derived_type_member_idxTvertexes, ptr %[[SZ_CALC_1]], i64 %[[SZ_CALC_5]]
+!CHECK: %[[SZ_CALC_8:.*]] = getelementptr %_QFmaptype_nested_derived_type_member_idxTvertexes, ptr %[[SZ_CALC_7]], i32 0, i32 2
+!CHECK: %[[OFF_PTR_4:.*]] = getelementptr { ptr, i64, i32, i8, i8, i8, i8, [1 x [3 x i64]] }, ptr %[[SZ_CALC_8]], i32 0, i32 0
!CHECK: %[[OFF_PTR_CALC_1:.*]] = sub i64 %[[OFF_PTR_CALC_0]], 0
!CHECK: %[[OFF_PTR_CALC_2:.*]] = add i64 %[[OFF_PTR_CALC_1]], 1
!CHECK: %[[OFF_PTR_CALC_3:.*]] = mul i64 1, %[[OFF_PTR_CALC_2]]
@@ -838,7 +843,7 @@ end subroutine mapType_common_block_members
!CHECK: %[[BASE_PTR_ARR:.*]] = getelementptr inbounds [7 x ptr], ptr %.offload_baseptrs, i32 0, i32 4
!CHECK: store ptr %[[BASE_PTR_1]], ptr %[[BASE_PTR_ARR]], align 8
!CHECK: %[[OFFLOAD_PTR_ARR:.*]] = getelementptr inbounds [7 x ptr], ptr %.offload_ptrs, i32 0, i32 4
-!CHECK: store ptr %[[SZ_CALC_6]], ptr %[[OFFLOAD_PTR_ARR]], align 8
+!CHECK: store ptr %[[SZ_CALC_8]], ptr %[[OFFLOAD_PTR_ARR]], align 8
!CHECK: %[[BASE_PTR_ARR:.*]] = getelementptr inbounds [7 x ptr], ptr %.offload_baseptrs, i32 0, i32 5
!CHECK: store ptr %[[BASE_PTR_1]], ptr %[[BASE_PTR_ARR]], align 8
!CHECK: %[[OFFLOAD_PTR_ARR:.*]] = getelementptr inbounds [7 x ptr], ptr %.offload_ptrs, i32 0, i32 5
diff --git a/flang/test/Lower/OpenMP/map-neg-alloca-derived-type-array.f90 b/flang/test/Lower/OpenMP/map-neg-alloca-derived-type-array.f90
new file mode 100644
index 0000000000000..dd8721b97dccd
--- /dev/null
+++ b/flang/test/Lower/OpenMP/map-neg-alloca-derived-type-array.f90
@@ -0,0 +1,27 @@
+!RUN: %flang_fc1 -emit-hlfir -fopenmp %s -o - | FileCheck %s
+
+subroutine map_negative_bounds_allocatable_dtype()
+ type derived_type
+ real(4), pointer :: data(:,:,:) => null()
+ end type
+ type(derived_type), allocatable :: dtype(:,:)
+
+ !$omp target map(tofrom: dtype(-1,1)%data)
+ dtype(-1,1)%data(1,1,1) = 10
+ !$omp end target
+end subroutine
+
+! CHECK: %[[VAL_1:.*]] = arith.constant -1 : i64
+! CHECK: %[[VAL_2:.*]] = fir.convert %[[VAL_1]] : (i64) -> index
+! CHECK: %[[VAL_3:.*]] = arith.constant 1 : i64
+! CHECK: %[[VAL_4:.*]] = fir.convert %[[VAL_3]] : (i64) -> index
+! CHECK: %[[VAL_5:.*]] = arith.constant 0 : index
+! CHECK: %[[VAL_6:.*]]:3 = fir.box_dims %{{.*}}, %[[VAL_5]] : (!fir.box<!fir.heap<!fir.array<?x?x!fir.type<_QFmap_negative_bounds_allocatable_dtypeTderived_type{data:!fir.box<!fir.ptr<!fir.array<?x?x?xf32>>>}>>>>, index) -> (index, index, index)
+! CHECK: %[[VAL_7:.*]] = arith.constant 1 : index
+! CHECK: %[[VAL_8:.*]]:3 = fir.box_dims %{{.*}}, %[[VAL_7]] : (!fir.box<!fir.heap<!fir.array<?x?x!fir.type<_QFmap_negative_bounds_allocatable_dtypeTderived_type{data:!fir.box<!fir.ptr<!fir.array<?x?x?xf32>>>}>>>>, index) -> (index, index, index)
+! CHECK: %[[VAL_9:.*]] = fir.shape_shift %[[VAL_6]]#0, %[[VAL_6]]#1, %[[VAL_8]]#0, %[[VAL_8]]#1 : (index, index, index, index) -> !fir.shapeshift<2>
+! CHECK: %[[VAL_10:.*]] = fir.array_coor %{{.*}}(%[[VAL_9]]) %[[VAL_2]], %[[VAL_4]] : (!fir.heap<!fir.array<?x?x!fir.type<_QFmap_negative_bounds_allocatable_dtypeTderived_type{data:!fir.box<!fir.ptr<!fir.array<?x?x?xf32>>>}>>>, !fir.shapeshift<2>, index, index) -> !fir.ref<!fir.type<_QFmap_negative_bounds_allocatable_dtypeTderived_type{data:!fir.box<!fir.ptr<!fir.array<?x?x?xf32>>>}>>
+! CHECK: %[[VAL_11:.*]] = fir.coordinate_of %[[VAL_10]], data : (!fir.ref<!fir.type<_QFmap_negative_bounds_allocatable_dtypeTderived_type{data:!fir.box<!fir.ptr<!fir.array<?x?x?xf32>>>}>>) -> !fir.ref<!fir.box<!fir.ptr<!fir.array<?x?x?xf32>>>>
+! CHECK: %[[VAL_12:.*]] = fir.box_offset %[[VAL_11]] base_addr : (!fir.ref<!fir.box<!fir.ptr<!fir.array<?x?x?xf32>>>>) -> !fir.llvm_ptr<!fir.ref<!fir.array<?x?x?xf32>>>
+! CHECK: %[[VAL_13:.*]] = omp.map.info var_ptr(%[[VAL_11]] : !fir.ref<!fir.box<!fir.ptr<!fir.array<?x?x?xf32>>>>, f32) map_clauses(tofrom) capture(ByRef) var_ptr_ptr(%[[VAL_12]] : !fir.llvm_ptr<!fir.ref<!fir.array<?x?x?xf32>>>) bounds({{.*}}) -> !fir.llvm_ptr<!fir.ref<!fir.array<?x?x?xf32>>> {name = ""}
+! CHECK: %[[VAL_14:.*]] = omp.map.info var_ptr(%[[VAL_11]] : !fir.ref<!fir.box<!fir.ptr<!fir.array<?x?x?xf32>>>>, !fir.box<!fir.ptr<!fir.array<?x?x?xf32>>>) map_clauses(to) capture(ByRef) -> !fir.ref<!fir.box<!fir.ptr<!fir.array<?x?x?xf32>>>> {name = {{.*}}}
More information about the flang-commits
mailing list