Skip to content

[flang][cuda] Avoid extra load in c_f_pointer lowering with c_devptr #108090

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.

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
Sep 11, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
3 changes: 1 addition & 2 deletions flang/lib/Optimizer/Builder/FIRBuilder.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -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())) {
Expand Down
7 changes: 4 additions & 3 deletions flang/test/Lower/CUDA/cuda-devptr.cuf
Original file line number Diff line number Diff line change
Expand Up @@ -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>>>>
Loading