[flang] Set lower bounds of array section fir.embox to one

[jeanPerier]

Summary

Do not use the shift of a fir.embox to set lower bounds if there is
a fir.slice operand. This matches Fortran semantics where lower bounds
of array sections are ones.
Note that in case there is a fir.slice, the array shift may be provided
because it is used to calculate the origin/base address of an array slice.

Add a TODO for substring codegen since I noticed it was not upstreamed
yet and would cause some program to silently compile incorrectly.

[clementval]

LGTM

flang/lib/Optimizer/CodeGen/CodeGen.cpp

if (auto memEleTy = fir::dyn_cast_ptrEleTy(xbox.memref().getType()))
             return rewriter.notifyMatchFailure(xbox, "unexpected dynamic type");
           }
         } else {
           constRows = seqTy.getConstantRows();
         }
       }
 
     bool hasSubcomp = !xbox.subcomponent().empty();
+    if (!xbox.substr().empty())
+      TODO(loc, "codegen of fir.embox with substring");
+
     mlir::Value stepExpr;
     if (hasSubcomp) {
       // We have a subcomponent. The step value needs to be the number of
       // bytes per element (which is a derived type).
       mlir::Type ty0 = base.getType();
       [[maybe_unused]] auto ptrTy = ty0.dyn_cast<mlir::LLVM::LLVMPointerType>();
       assert(ptrTy && "expected pointer type");
       mlir::Type memEleTy = fir::dyn_cast_ptrEleTy(xbox.memref().getType());
for (unsigned di = 0, descIdx = 0; di < rank; ++di) {
         // store lower bound (normally 0) for BIND(C) interoperability.
         mlir::Value lb = zero;
         const bool isaPointerOrAllocatable =
             eleTy.isa<fir::PointerType>() || eleTy.isa<fir::HeapType>();
         // Lower bound is defaults to 1 for POINTER, ALLOCATABLE, and
         // denormalized descriptors.
         if (isaPointerOrAllocatable || !normalizedLowerBound(xbox)) {
           lb = one;
-          // If there is a shifted origin and this is not a normalized
-          // descriptor then use the value from the shift op as the lower bound.
-          if (hasShift) {
+          // If there is a shifted origin, and no fir.slice, and this is not
+          // a normalized descriptor then use the value from the shift op as
+          // the lower bound.
+          if (hasShift && !(hasSlice || hasSubcomp)) {
             lb = operands[shiftOffset];
             auto extentIsEmpty = rewriter.create<mlir::LLVM::ICmpOp>(
                 loc, mlir::LLVM::ICmpPredicate::eq, extent, zero);
             lb = rewriter.create<mlir::LLVM::SelectOp>(loc, extentIsEmpty, one,
                                                        lb);
           }
         }
         dest = insertLowerBound(rewriter, loc, dest, descIdx, lb);

flang/test/Fir/convert-to-llvm.fir

 // CHECK:         %[[ADJUSTED_OFFSET:.*]] = llvm.sub %[[C0]], %[[C0]]  : i64
 // CHECK:         %[[DIM_OFFSET:.*]] = llvm.mul %[[ADJUSTED_OFFSET]], %[[ONE]]  : i64
 // CHECK:         %[[PTR_OFFSET:.*]] = llvm.add %[[DIM_OFFSET]], %[[ZERO]]  : i64
 // CHECK:         %[[EXTENT0:.*]] = llvm.sub %[[C0]], %[[C0]]  : i64
 // CHECK:         %[[EXTENT1:.*]] = llvm.add %[[EXTENT0]], %[[C0]]  : i64
 // CHECK:         %[[EXTENT2:.*]] = llvm.sdiv %[[EXTENT1]], %[[C0]]  : i64
 // CHECK:         %[[EXTENT_CMP:.*]] = llvm.icmp "sgt" %[[EXTENT2]], %[[ZERO]] : i64
 // CHECK:         %[[EXTENT:.*]] = llvm.select %[[EXTENT_CMP]], %[[EXTENT2]], %[[ZERO]] : i1, i64
-// CHECK:         %[[EXTENT_CMP_2:.*]] = llvm.icmp "eq" %[[EXTENT]], %[[ZERO]] : i64
-// CHECK:         %[[LOWER:.*]] = llvm.select %[[EXTENT_CMP_2]], %[[ONE]], %[[C0]] : i1, i64
-// CHECK:         %[[BOX7:.*]] = llvm.insertvalue %[[LOWER]], %[[BOX6]][7 : i32, 0 : i32, 0 : i32] : !llvm.struct<(ptr<i32>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<1 x array<3 x i64>>)>
+// CHECK:         %[[BOX7:.*]] = llvm.insertvalue %[[ONE]], %[[BOX6]][7 : i32, 0 : i32, 0 : i32] : !llvm.struct<(ptr<i32>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<1 x array<3 x i64>>)>
 // CHECK:         %[[BOX8:.*]] = llvm.insertvalue %[[EXTENT]], %[[BOX7]][7 : i32, 0 : i32, 1 : i32] : !llvm.struct<(ptr<i32>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<1 x array<3 x i64>>)>
 // CHECK:         %[[STRIDE:.*]] = llvm.mul %[[ELEM_LEN_I64]], %[[C0]]  : i64
 // CHECK:         %[[BOX9:.*]] = llvm.insertvalue %[[STRIDE]], %[[BOX8]][7 : i32, 0 : i32, 2 : i32] : !llvm.struct<(ptr<i32>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<1 x array<3 x i64>>)>
 // CHECK:         %[[PREV_DIM:.*]] = llvm.mul %[[ELEM_LEN_I64]], %[[C0]]  : i64
 // CHECK:         %[[PREV_PTROFF:.*]] = llvm.mul %[[ONE]], %[[C0]]  : i64
 // CHECK:         %[[BASE_PTR:.*]] = llvm.getelementptr %[[ARG0]][%[[PTR_OFFSET]]] : (!llvm.ptr<i32>, i64) -> !llvm.ptr<i32>
 // CHECK:         %[[ADDR_BITCAST:.*]] = llvm.bitcast %[[BASE_PTR]] : !llvm.ptr<i32> to !llvm.ptr<i32>
 // CHECK:         %[[BOX10:.*]] = llvm.insertvalue %[[ADDR_BITCAST]], %[[BOX9]][0 : i32] : !llvm.struct<(ptr<i32>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<1 x array<3 x i64>>)>

 // CHECK:         %[[ADJUSTED_OFFSET:.*]] = llvm.sub %[[C2]], %[[SH1]] : i64
 // CHECK:         %[[DIM_OFFSET:.*]] = llvm.mul %[[ADJUSTED_OFFSET]], %[[ONE]]  : i64
 // CHECK:         %[[PTR_OFFSET:.*]] = llvm.add %[[DIM_OFFSET]], %[[ZERO]]  : i64
 // CHECK:         %[[EXTENT0:.*]] = llvm.sub %[[ARG0]], %[[C2]]  : i64
 // CHECK:         %[[EXTENT1:.*]] = llvm.add %[[EXTENT0]], %[[C1]]  : i64
 // CHECK:         %[[EXTENT2:.*]] = llvm.sdiv %[[EXTENT1]], %[[C1]]  : i64
 // CHECK:         %[[EXTENT_CMP:.*]] = llvm.icmp "sgt" %[[EXTENT2]], %[[ZERO]] : i64
 // CHECK:         %[[EXTENT:.*]] = llvm.select %[[EXTENT_CMP]], %[[EXTENT2]], %[[ZERO]] : i1, i64
-// CHECK:         %[[EXTENT_CMP_2:.*]] = llvm.icmp "eq" %[[EXTENT]], %[[ZERO]] : i64
-// CHECK:         %[[SH1B:.*]] = llvm.select %[[EXTENT_CMP_2]], %[[ONE]], %[[SH1]] : i1, i64
-// CHECK:         %[[BOX7:.*]] = llvm.insertvalue %[[SH1B]], %[[BOX6]][7 : i32, 0 : i32, 0 : i32] : !llvm.struct<(ptr<f64>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<2 x array<3 x i64>>)>
+// CHECK:         %[[BOX7:.*]] = llvm.insertvalue %[[ONE]], %[[BOX6]][7 : i32, 0 : i32, 0 : i32] : !llvm.struct<(ptr<f64>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<2 x array<3 x i64>>)>
 // CHECK:         %[[BOX8:.*]] = llvm.insertvalue %[[EXTENT]], %[[BOX7]][7 : i32, 0 : i32, 1 : i32] : !llvm.struct<(ptr<f64>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<2 x array<3 x i64>>)>
 // CHECK:         %[[STRIDE:.*]] = llvm.mul %[[ELEM_LEN_I64]], %[[C1]]  : i64
 // CHECK:         %[[BOX9:.*]] = llvm.insertvalue %[[STRIDE]], %[[BOX8]][7 : i32, 0 : i32, 2 : i32] : !llvm.struct<(ptr<f64>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<2 x array<3 x i64>>)>
 // CHECK:         %[[PREV_DIM:.*]] = llvm.mul %[[ELEM_LEN_I64]], %[[N1]]  : i64
 // CHECK:         %[[PREV_PTROFF:.*]] = llvm.mul %[[ONE]], %[[N1]]  : i64
 // CHECK:         %[[ADJUSTED_OFFSET:.*]] = llvm.sub %[[C4]], %[[SH2]]  : i64
 // CHECK:         %[[DIM_OFFSET:.*]] = llvm.mul %[[ADJUSTED_OFFSET]], %[[PREV_PTROFF]]  : i64
 // CHECK:         %[[PTR_OFFSET0:.*]] = llvm.add %[[DIM_OFFSET]], %[[PTR_OFFSET]]  : i64
 // CHECK:         %[[EXT_SUB:.*]] = llvm.sub %[[N]], %[[C4]]  : i64
 // CHECK:         %[[EXT_ADD:.*]] = llvm.add %[[EXT_SUB]], %[[C1]]  : i64
 // CHECK:         %[[EXT_SDIV:.*]] = llvm.sdiv %[[EXT_ADD]], %[[C1]]  : i64
 // CHECK:         %[[EXT_ICMP:.*]] = llvm.icmp "sgt" %[[EXT_SDIV]], %[[ZERO]] : i64
 // CHECK:         %[[EXT_SELECT:.*]] = llvm.select %[[EXT_ICMP]], %[[EXT_SDIV]], %[[ZERO]] : i1, i64
-// CHECK:         %[[EXT_ICMP_2:.*]] = llvm.icmp "eq" %[[EXT_SELECT]], %[[ZERO]] : i64
-// CHECK:         %[[SH2B:.*]] = llvm.select %[[EXT_ICMP_2]], %[[ONE]], %[[SH2]] : i1, i64
-// CHECK:         %[[BOX10:.*]] = llvm.insertvalue %[[SH2B]], %[[BOX9]][7 : i32, 1 : i32, 0 : i32] : !llvm.struct<(ptr<f64>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<2 x array<3 x i64>>)>
+// CHECK:         %[[BOX10:.*]] = llvm.insertvalue %[[ONE]], %[[BOX9]][7 : i32, 1 : i32, 0 : i32] : !llvm.struct<(ptr<f64>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<2 x array<3 x i64>>)>
 // CHECK:         %[[BOX11:.*]] = llvm.insertvalue %[[EXT_SELECT]], %[[BOX10]][7 : i32, 1 : i32, 1 : i32] : !llvm.struct<(ptr<f64>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<2 x array<3 x i64>>)>
 // CHECK:         %[[STRIDE_MUL:.*]] = llvm.mul %[[PREV_DIM]], %[[C1]]  : i64
 // CHECK:         %[[BOX12:.*]] = llvm.insertvalue %[[STRIDE_MUL]], %[[BOX11]][7 : i32, 1 : i32, 2 : i32] : !llvm.struct<(ptr<f64>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<2 x array<3 x i64>>)>
 // CHECK:         %[[BASE_PTR:.*]] = llvm.getelementptr %[[ARR]][%[[PTR_OFFSET0]]] : (!llvm.ptr<f64>, i64) -> !llvm.ptr<f64>
 // CHECK:         %[[ADDR_BITCAST:.*]] = llvm.bitcast %[[BASE_PTR]] : !llvm.ptr<f64> to !llvm.ptr<f64>
 // CHECK:         %[[BOX13:.*]] = llvm.insertvalue %[[ADDR_BITCAST]], %[[BOX12]][0 : i32] : !llvm.struct<(ptr<f64>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<2 x array<3 x i64>>)>
 // CHECK:         llvm.store %[[BOX13]], %[[ALLOCA]] : !llvm.ptr<struct<(ptr<f64>, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, i{{.*}}, array<2 x array<3 x i64>>)>>