[flang-commits] [flang] e67a666 - [flang][cuda] Avoid extra load in c_f_pointer lowering with c_devptr (#108090)

[via flang-commits]

Author: Valentin Clement (バレンタイン クレメン)
Date: 2024-09-10T19:33:33-07:00
New Revision: e67a6667dc2b46ece983321af89ae40ca7986b16

URL: https://github.com/llvm/llvm-project/commit/e67a6667dc2b46ece983321af89ae40ca7986b16
DIFF: https://github.com/llvm/llvm-project/commit/e67a6667dc2b46ece983321af89ae40ca7986b16.diff

LOG: [flang][cuda] Avoid extra load in c_f_pointer lowering with c_devptr (#108090)

Remove unnecessary load of the `cptr` component when getting the
`__address`. `fir.coordinate_of` operation can be chained so the load is
not needed.

Added: 
    

Modified: 
    flang/lib/Optimizer/Builder/FIRBuilder.cpp
    flang/test/Lower/CUDA/cuda-devptr.cuf

Removed: 
    


################################################################################
diff  --git a/flang/lib/Optimizer/Builder/FIRBuilder.cpp b/flang/lib/Optimizer/Builder/FIRBuilder.cpp
index c5a135a189e8dc..d786d79ba8701b 100644
--- a/flang/lib/Optimizer/Builder/FIRBuilder.cpp
+++ b/flang/lib/Optimizer/Builder/FIRBuilder.cpp
@@ -1594,8 +1594,7 @@ mlir::Value fir::factory::genCPtrOrCFunptrValue(fir::FirOpBuilder &builder,
       cPtrCoor = builder.create<fir::ExtractValueOp>(loc, addrFieldTy, cPtr,
                                                      arrayAttr);
     }
-    mlir::Value cptr = builder.create<fir::LoadOp>(loc, cPtrCoor);
-    return genCPtrOrCFunptrValue(builder, loc, cptr);
+    return genCPtrOrCFunptrValue(builder, loc, cPtrCoor);
   }
 
   if (fir::isa_ref_type(cPtr.getType())) {

diff  --git a/flang/test/Lower/CUDA/cuda-devptr.cuf b/flang/test/Lower/CUDA/cuda-devptr.cuf
index 21c5088b640fc7..2eac890970d52b 100644
--- a/flang/test/Lower/CUDA/cuda-devptr.cuf
+++ b/flang/test/Lower/CUDA/cuda-devptr.cuf
@@ -40,8 +40,9 @@ end
 ! CHECK: %[[X:.*]]:2 = hlfir.declare %{{.*}} {data_attr = #cuf.cuda<device>, fortran_attrs = #fir.var_attrs<pointer>, uniq_name = "_QFsub2Ex"} : (!fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>>) -> (!fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>>, !fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>>)
 ! CHECK: %[[CPTR:.*]] = fir.field_index cptr, !fir.type<_QM__fortran_builtinsT__builtin_c_devptr{cptr:!fir.type<_QM__fortran_builtinsT__builtin_c_ptr{__address:i64}>}>
 ! CHECK: %[[CPTR_COORD:.*]] = fir.coordinate_of %{{.*}}#1, %[[CPTR]] : (!fir.ref<!fir.type<_QM__fortran_builtinsT__builtin_c_devptr{cptr:!fir.type<_QM__fortran_builtinsT__builtin_c_ptr{__address:i64}>}>>, !fir.field) -> !fir.ref<!fir.type<_QM__fortran_builtinsT__builtin_c_ptr{__address:i64}>>
-! CHECK: %[[CPTR_LOAD:.*]] = fir.load %[[CPTR_COORD]] : !fir.ref<!fir.type<_QM__fortran_builtinsT__builtin_c_ptr{__address:i64}>>
-! CHECK: %[[ADDRESS:.*]] = fir.extract_value %[[CPTR_LOAD]], [0 : index] : (!fir.type<_QM__fortran_builtinsT__builtin_c_ptr{__address:i64}>) -> i64
-! CHECK: %[[ADDRESS_IDX:.*]] = fir.convert %[[ADDRESS]] : (i64) -> !fir.ptr<!fir.array<?xf32>>
+! CHECK: %[[ADDRESS:.*]] = fir.field_index __address, !fir.type<_QM__fortran_builtinsT__builtin_c_ptr{__address:i64}>
+! CHECK: %[[ADDRESS_COORD:.*]] = fir.coordinate_of %[[CPTR_COORD]], %[[ADDRESS]] : (!fir.ref<!fir.type<_QM__fortran_builtinsT__builtin_c_ptr{__address:i64}>>, !fir.field) -> !fir.ref<i64>
+! CHECK: %[[ADDRESS_LOADED:.*]] = fir.load %[[ADDRESS_COORD]] : !fir.ref<i64>
+! CHECK: %[[ADDRESS_IDX:.*]] = fir.convert %[[ADDRESS_LOADED]] : (i64) -> !fir.ptr<!fir.array<?xf32>>
 ! CHECK: %[[EMBOX:.*]] = fir.embox %[[ADDRESS_IDX]](%{{.*}}) : (!fir.ptr<!fir.array<?xf32>>, !fir.shape<1>) -> !fir.box<!fir.ptr<!fir.array<?xf32>>>
 ! CHECK: fir.store %[[EMBOX]] to %[[X]]#1 : !fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>>