Skip to content

[flang] [cuda] Fix CUDA implicit data transfer entity creation #139414

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.

Sign up for GitHub

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 5 commits into from
May 12, 2025
Merged

[flang] [cuda] Fix CUDA implicit data transfer entity creation #139414

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
38d7efc
Fix CUDA implicit data transfer entity creation
wangzpgi May 10, 2025
3347add
fix format; add test
wangzpgi May 10, 2025
470a6b7
update test
wangzpgi May 12, 2025
62da816
Merge branch 'main' into entity
wangzpgi May 12, 2025
a8fe42d
Merge branch 'main' into entity
wangzpgi May 12, 2025
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
9 changes: 8 additions & 1 deletion flang/lib/Lower/Bridge.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4778,7 +4778,14 @@ class FirConverter : public Fortran::lower::AbstractConverter {
nbDeviceResidentObject <= 1 &&
"Only one reference to the device resident object is supported");
auto addr = getSymbolAddress(sym);
hlfir::Entity entity{addr};
mlir::Value baseValue;
if (auto declareOp =
llvm::dyn_cast<hlfir::DeclareOp>(addr.getDefiningOp()))
baseValue = declareOp.getBase();
else
baseValue = addr;

hlfir::Entity entity{baseValue};
auto [temp, cleanup] =
hlfir::createTempFromMold(loc, builder, entity);
auto needCleanup = fir::getIntIfConstant(cleanup);
Expand Down
27 changes: 27 additions & 0 deletions flang/test/Lower/CUDA/cuda-managed.cuf
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
! RUN: bbc -emit-hlfir -fcuda %s -o - | FileCheck %s

subroutine testr2(N1,N2)
real(4), managed :: ai4(N1,N2)
real(4), allocatable :: bRefi4(:)

integer :: i1, i2

do i2 = 1, N2
do i1 = 1, N1
ai4(i1,i2) = i1 + N1*(i2-1)
enddo
enddo

allocate(bRefi4 (N1))
do i1 = 1, N1
bRefi4(i1) = (ai4(i1,1)+ai4(i1,N2))*N2/2
enddo
deallocate(bRefi4)

end subroutine

!CHECK-LABEL: func.func @_QPtestr2
!CHECK: %[[ALLOC:.*]] = cuf.alloc !fir.array<?x?xf32>, %{{.*}}, %{{.*}} : index, index {bindc_name = "ai4", data_attr = #cuf.cuda<managed>, uniq_name = "_QFtestr2Eai4"} -> !fir.ref<!fir.array<?x?xf32>>
!CHECK: %[[DECLARE:.*]]:2 = hlfir.declare %[[ALLOC]](%{{.*}}) {data_attr = #cuf.cuda<managed>, uniq_name = "_QFtestr2Eai4"} : (!fir.ref<!fir.array<?x?xf32>>, !fir.shape<2>) -> (!fir.box<!fir.array<?x?xf32>>, !fir.ref<!fir.array<?x?xf32>>)
!CHECK: %[[DEST:.*]] = hlfir.designate %[[DECLARE]]#0 (%{{.*}}, %{{.*}}) : (!fir.box<!fir.array<?x?xf32>>, i64, i64) -> !fir.ref<f32>
!CHECK: cuf.data_transfer %{{.*}}#0 to %[[DEST]] {transfer_kind = #cuf.cuda_transfer<host_device>} : !fir.ref<f32>, !fir.ref<f32>
Loading