[Flang][OpenMP] Fix allocatable -ve bounds mapping issue found in SWDEV-548635 (llvm#3571)

Author: ronlieb

flang/lib/Lower/OpenMP/Utils.cpp

@@ -13,7 +13,6 @@
 #include <flang/Lower/OpenMP/Utils.h>
 
 #include "ClauseFinder.h"
-#include "flang/Lower/OpenMP/Clauses.h"
 #include <flang/Lower/AbstractConverter.h>
 #include <flang/Lower/ConvertExprToHLFIR.h>
 #include <flang/Lower/ConvertType.h>
@@ -196,16 +195,11 @@ 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));
   }
 }
 
@@ -338,10 +332,41 @@ 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())) {
+          fir::ExtendedValue exv =
+              hlfir::translateToExtendedValue(clauseLocation, firOpBuilder,
+                                              hlfir::Entity{curValue},
+                                              /*contiguousHint=*/
+                                              true)
+                  .first;
+
+          mlir::Type idxTy = firOpBuilder.getIndexType();
+          llvm::SmallVector<mlir::Value> shiftOperands;
+          for (unsigned dim = 0; dim < exv.rank(); ++dim) {
+            mlir::Value d =
+                firOpBuilder.createIntegerConstant(clauseLocation, idxTy, dim);
+            auto dimInfo = fir::BoxDimsOp::create(
+                firOpBuilder, clauseLocation, idxTy, idxTy, idxTy, curValue, d);
+            shiftOperands.push_back(dimInfo.getLowerBound());
+            shiftOperands.push_back(dimInfo.getExtent());
+          }
+          auto shapeShiftType =
+              fir::ShapeShiftType::get(firOpBuilder.getContext(), exv.rank());
+          mlir::Value shapeShift = fir::ShapeShiftOp::create(
+              firOpBuilder, clauseLocation, shapeShiftType, shiftOperands);
+          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 {
+          curValue = fir::CoordinateOp::create(
+              firOpBuilder, clauseLocation,
+              firOpBuilder.getRefType(arrType.getEleTy()), curValue,
+              subscriptIndices);
+        }
       }
     }
 
@@ -431,7 +456,6 @@ mlir::Value createParentSymAndGenIntermediateMaps(
       currentIndicesIdx++;
     }
   }
-
   return curValue;
 }
 

flang/test/Integration/OpenMP/map-types-and-sizes.f90

@@ -786,15 +786,20 @@ 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]]
@@ -839,7 +844,7 @@ 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