[flang-commits] [flang] [flang][acc] Generate acc.copyout for the reduction clause on compute constructs (PR #144623)
via flang-commits
flang-commits at lists.llvm.org
Wed Jun 18 00:25:49 PDT 2025
https://github.com/khaki3 updated https://github.com/llvm/llvm-project/pull/144623
>From a509073944186f25f4dab18b474619cc3609da49 Mon Sep 17 00:00:00 2001
From: Kazuaki Matsumura <kmatsumura at nvidia.com>
Date: Tue, 17 Jun 2025 17:39:06 -0700
Subject: [PATCH 1/2] [flang][acc] Generate acc.copyout for the reduction
clause on compute constructs
---
flang/lib/Lower/OpenACC.cpp | 8 +++++++-
.../acc-reduction-unwrap-defaultbounds.f90 | 20 ++++++++++++++++++-
flang/test/Lower/OpenACC/acc-reduction.f90 | 20 ++++++++++++++++++-
3 files changed, 45 insertions(+), 3 deletions(-)
diff --git a/flang/lib/Lower/OpenACC.cpp b/flang/lib/Lower/OpenACC.cpp
index 69e9c53baa740..63a9d1d5616a9 100644
--- a/flang/lib/Lower/OpenACC.cpp
+++ b/flang/lib/Lower/OpenACC.cpp
@@ -2676,7 +2676,8 @@ static Op createComputeOp(
llvm::SmallVector<mlir::Value> waitOperands, attachEntryOperands,
copyEntryOperands, copyinEntryOperands, copyoutEntryOperands,
createEntryOperands, nocreateEntryOperands, presentEntryOperands,
- dataClauseOperands, numGangs, numWorkers, vectorLength, async;
+ reductionEntryOperands, dataClauseOperands, numGangs, numWorkers,
+ vectorLength, async;
llvm::SmallVector<mlir::Attribute> numGangsDeviceTypes, numWorkersDeviceTypes,
vectorLengthDeviceTypes, asyncDeviceTypes, asyncOnlyDeviceTypes,
waitOperandsDeviceTypes, waitOnlyDeviceTypes;
@@ -2912,9 +2913,12 @@ static Op createComputeOp(
// combined construct implies a copy clause so issue an implicit copy
// instead.
if (!combinedConstructs) {
+ auto crtDataStart = reductionOperands.size();
genReductions(reductionClause->v, converter, semanticsContext, stmtCtx,
reductionOperands, reductionRecipes, async,
asyncDeviceTypes, asyncOnlyDeviceTypes);
+ reductionEntryOperands.append(reductionOperands.begin() + crtDataStart,
+ reductionOperands.end());
} else {
auto crtDataStart = dataClauseOperands.size();
genDataOperandOperations<mlir::acc::CopyinOp>(
@@ -3038,6 +3042,8 @@ static Op createComputeOp(
builder, nocreateEntryOperands, /*structured=*/true);
genDataExitOperations<mlir::acc::PresentOp, mlir::acc::DeleteOp>(
builder, presentEntryOperands, /*structured=*/true);
+ genDataExitOperations<mlir::acc::ReductionOp, mlir::acc::CopyoutOp>(
+ builder, reductionEntryOperands, /*structured=*/true);
builder.restoreInsertionPoint(insPt);
return computeOp;
diff --git a/flang/test/Lower/OpenACC/acc-reduction-unwrap-defaultbounds.f90 b/flang/test/Lower/OpenACC/acc-reduction-unwrap-defaultbounds.f90
index 5bb751678ed53..bb76122aaffac 100644
--- a/flang/test/Lower/OpenACC/acc-reduction-unwrap-defaultbounds.f90
+++ b/flang/test/Lower/OpenACC/acc-reduction-unwrap-defaultbounds.f90
@@ -1001,6 +1001,7 @@ subroutine acc_reduction_iand()
! CHECK-LABEL: func.func @_QPacc_reduction_iand()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<i32>) -> !fir.ref<i32> {name = "i"}
! CHECK: acc.parallel reduction(@reduction_iand_ref_i32 -> %[[RED]] : !fir.ref<i32>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<i32>) to varPtr(%{{.*}} : !fir.ref<i32>) {dataClause = #acc<data_clause acc_reduction>, name = "i"}
subroutine acc_reduction_ior()
integer :: i
@@ -1011,6 +1012,7 @@ subroutine acc_reduction_ior()
! CHECK-LABEL: func.func @_QPacc_reduction_ior()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<i32>) -> !fir.ref<i32> {name = "i"}
! CHECK: acc.parallel reduction(@reduction_ior_ref_i32 -> %[[RED]] : !fir.ref<i32>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<i32>) to varPtr(%{{.*}} : !fir.ref<i32>) {dataClause = #acc<data_clause acc_reduction>, name = "i"}
subroutine acc_reduction_ieor()
integer :: i
@@ -1021,6 +1023,7 @@ subroutine acc_reduction_ieor()
! CHECK-LABEL: func.func @_QPacc_reduction_ieor()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<i32>) -> !fir.ref<i32> {name = "i"}
! CHECK: acc.parallel reduction(@reduction_xor_ref_i32 -> %[[RED]] : !fir.ref<i32>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<i32>) to varPtr(%{{.*}} : !fir.ref<i32>) {dataClause = #acc<data_clause acc_reduction>, name = "i"}
subroutine acc_reduction_and()
logical :: l
@@ -1033,6 +1036,7 @@ subroutine acc_reduction_and()
! CHECK: %[[DECLL:.*]]:2 = hlfir.declare %[[L]]
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[DECLL]]#0 : !fir.ref<!fir.logical<4>>) -> !fir.ref<!fir.logical<4>> {name = "l"}
! CHECK: acc.parallel reduction(@reduction_land_ref_l32 -> %[[RED]] : !fir.ref<!fir.logical<4>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.logical<4>>) to varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) {dataClause = #acc<data_clause acc_reduction>, name = "l"}
subroutine acc_reduction_or()
logical :: l
@@ -1043,6 +1047,7 @@ subroutine acc_reduction_or()
! CHECK-LABEL: func.func @_QPacc_reduction_or()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) -> !fir.ref<!fir.logical<4>> {name = "l"}
! CHECK: acc.parallel reduction(@reduction_lor_ref_l32 -> %[[RED]] : !fir.ref<!fir.logical<4>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.logical<4>>) to varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) {dataClause = #acc<data_clause acc_reduction>, name = "l"}
subroutine acc_reduction_eqv()
logical :: l
@@ -1053,6 +1058,7 @@ subroutine acc_reduction_eqv()
! CHECK-LABEL: func.func @_QPacc_reduction_eqv()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) -> !fir.ref<!fir.logical<4>> {name = "l"}
! CHECK: acc.parallel reduction(@reduction_eqv_ref_l32 -> %[[RED]] : !fir.ref<!fir.logical<4>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.logical<4>>) to varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) {dataClause = #acc<data_clause acc_reduction>, name = "l"}
subroutine acc_reduction_neqv()
logical :: l
@@ -1063,6 +1069,7 @@ subroutine acc_reduction_neqv()
! CHECK-LABEL: func.func @_QPacc_reduction_neqv()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) -> !fir.ref<!fir.logical<4>> {name = "l"}
! CHECK: acc.parallel reduction(@reduction_neqv_ref_l32 -> %[[RED]] : !fir.ref<!fir.logical<4>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.logical<4>>) to varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) {dataClause = #acc<data_clause acc_reduction>, name = "l"}
subroutine acc_reduction_add_cmplx()
complex :: c
@@ -1073,6 +1080,7 @@ subroutine acc_reduction_add_cmplx()
! CHECK-LABEL: func.func @_QPacc_reduction_add_cmplx()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<complex<f32>>) -> !fir.ref<complex<f32>> {name = "c"}
! CHECK: acc.parallel reduction(@reduction_add_ref_z32 -> %[[RED]] : !fir.ref<complex<f32>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<complex<f32>>) to varPtr(%{{.*}} : !fir.ref<complex<f32>>) {dataClause = #acc<data_clause acc_reduction>, name = "c"}
subroutine acc_reduction_mul_cmplx()
complex :: c
@@ -1083,6 +1091,7 @@ subroutine acc_reduction_mul_cmplx()
! CHECK-LABEL: func.func @_QPacc_reduction_mul_cmplx()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<complex<f32>>) -> !fir.ref<complex<f32>> {name = "c"}
! CHECK: acc.parallel reduction(@reduction_mul_ref_z32 -> %[[RED]] : !fir.ref<complex<f32>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<complex<f32>>) to varPtr(%{{.*}} : !fir.ref<complex<f32>>) {dataClause = #acc<data_clause acc_reduction>, name = "c"}
subroutine acc_reduction_add_alloc()
integer, allocatable :: i
@@ -1098,6 +1107,7 @@ subroutine acc_reduction_add_alloc()
! CHECK: %[[BOX_ADDR:.*]] = fir.box_addr %[[LOAD]] : (!fir.box<!fir.heap<i32>>) -> !fir.heap<i32>
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[BOX_ADDR]] : !fir.heap<i32>) -> !fir.heap<i32> {name = "i"}
! CHECK: acc.parallel reduction(@reduction_add_heap_i32 -> %[[RED]] : !fir.heap<i32>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.heap<i32>) to varPtr(%[[BOX_ADDR]] : !fir.heap<i32>) {dataClause = #acc<data_clause acc_reduction>, name = "i"}
subroutine acc_reduction_add_pointer(i)
integer, pointer :: i
@@ -1112,6 +1122,7 @@ subroutine acc_reduction_add_pointer(i)
! CHECK: %[[BOX_ADDR:.*]] = fir.box_addr %[[LOAD]] : (!fir.box<!fir.ptr<i32>>) -> !fir.ptr<i32>
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[BOX_ADDR]] : !fir.ptr<i32>) -> !fir.ptr<i32> {name = "i"}
! CHECK: acc.parallel reduction(@reduction_add_ptr_i32 -> %[[RED]] : !fir.ptr<i32>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ptr<i32>) to varPtr(%[[BOX_ADDR]] : !fir.ptr<i32>) {dataClause = #acc<data_clause acc_reduction>, name = "i"}
subroutine acc_reduction_add_static_slice(a)
integer :: a(100)
@@ -1129,6 +1140,7 @@ subroutine acc_reduction_add_static_slice(a)
! CHECK: %[[BOUND:.*]] = acc.bounds lowerbound(%[[LB]] : index) upperbound(%[[UB]] : index) extent(%[[C100]] : index) stride(%[[C1]] : index) startIdx(%[[C1]] : index)
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[DECLARG0]]#0 : !fir.ref<!fir.array<100xi32>>) bounds(%[[BOUND]]) -> !fir.ref<!fir.array<100xi32>> {name = "a(11:20)"}
! CHECK: acc.parallel reduction(@reduction_add_section_lb10.ub19_ref_100xi32 -> %[[RED]] : !fir.ref<!fir.array<100xi32>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.array<100xi32>>) bounds(%[[BOUND]]) to varPtr(%[[DECLARG0]]#0 : !fir.ref<!fir.array<100xi32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a(11:20)"}
subroutine acc_reduction_add_dynamic_extent_add(a)
integer :: a(:)
@@ -1141,6 +1153,7 @@ subroutine acc_reduction_add_dynamic_extent_add(a)
! CHECK: %[[DECLARG0:.*]]:2 = hlfir.declare %[[ARG0]]
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<!fir.array<?xi32>>) bounds(%{{.*}}) -> !fir.ref<!fir.array<?xi32>> {name = "a"}
! CHECK: acc.parallel reduction(@reduction_add_box_Uxi32 -> %[[RED:.*]] : !fir.ref<!fir.array<?xi32>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.array<?xi32>>) bounds(%{{.*}}) to varPtr(%{{.*}} : !fir.ref<!fir.array<?xi32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a"}
subroutine acc_reduction_add_assumed_shape_max(a)
real :: a(:)
@@ -1153,6 +1166,7 @@ subroutine acc_reduction_add_assumed_shape_max(a)
! CHECK: %[[DECLARG0:.*]]:2 = hlfir.declare %[[ARG0]]
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<!fir.array<?xf32>>) bounds(%{{.*}}) -> !fir.ref<!fir.array<?xf32>> {name = "a"}
! CHECK: acc.parallel reduction(@reduction_max_box_Uxf32 -> %[[RED]] : !fir.ref<!fir.array<?xf32>>) {
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.array<?xf32>>) bounds(%{{.*}}) to varPtr(%{{.*}} : !fir.ref<!fir.array<?xf32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a"}
subroutine acc_reduction_add_dynamic_extent_add_with_section(a)
integer :: a(:)
@@ -1167,6 +1181,7 @@ subroutine acc_reduction_add_dynamic_extent_add_with_section(a)
! CHECK: %[[BOX_ADDR:.*]] = fir.box_addr %[[DECL]]#0 : (!fir.box<!fir.array<?xi32>>) -> !fir.ref<!fir.array<?xi32>>
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[BOX_ADDR]] : !fir.ref<!fir.array<?xi32>>) bounds(%[[BOUND]]) -> !fir.ref<!fir.array<?xi32>> {name = "a(2:4)"}
! CHECK: acc.parallel reduction(@reduction_add_section_lb1.ub3_box_Uxi32 -> %[[RED]] : !fir.ref<!fir.array<?xi32>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.array<?xi32>>) bounds(%[[BOUND]]) to varPtr(%[[BOX_ADDR]] : !fir.ref<!fir.array<?xi32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a(2:4)"}
subroutine acc_reduction_add_allocatable(a)
real, allocatable :: a(:)
@@ -1180,8 +1195,9 @@ subroutine acc_reduction_add_allocatable(a)
! CHECK: %[[BOX:.*]] = fir.load %[[DECL]]#0 : !fir.ref<!fir.box<!fir.heap<!fir.array<?xf32>>>>
! CHECK: %[[BOUND:.*]] = acc.bounds lowerbound(%c0{{.*}} : index) upperbound(%{{.*}} : index) extent(%{{.*}}#1 : index) stride(%{{.*}}#2 : index) startIdx(%{{.*}}#0 : index) {strideInBytes = true}
! CHECK: %[[BOX_ADDR:.*]] = fir.box_addr %[[BOX]] : (!fir.box<!fir.heap<!fir.array<?xf32>>>) -> !fir.heap<!fir.array<?xf32>>
-! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[BOX_ADDR]] : !fir.heap<!fir.array<?xf32>>) bounds(%{{[0-9]+}}) -> !fir.heap<!fir.array<?xf32>> {name = "a"}
+! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[BOX_ADDR]] : !fir.heap<!fir.array<?xf32>>) bounds(%[[BOUND]]) -> !fir.heap<!fir.array<?xf32>> {name = "a"}
! CHECK: acc.parallel reduction(@reduction_max_box_heap_Uxf32 -> %[[RED]] : !fir.heap<!fir.array<?xf32>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.heap<!fir.array<?xf32>>) bounds(%[[BOUND]]) to varPtr(%[[BOX_ADDR]] : !fir.heap<!fir.array<?xf32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a"}
subroutine acc_reduction_add_pointer_array(a)
real, pointer :: a(:)
@@ -1197,6 +1213,7 @@ subroutine acc_reduction_add_pointer_array(a)
! CHECK: %[[BOX_ADDR:.*]] = fir.box_addr %[[BOX]] : (!fir.box<!fir.ptr<!fir.array<?xf32>>>) -> !fir.ptr<!fir.array<?xf32>>
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[BOX_ADDR]] : !fir.ptr<!fir.array<?xf32>>) bounds(%[[BOUND]]) -> !fir.ptr<!fir.array<?xf32>> {name = "a"}
! CHECK: acc.parallel reduction(@reduction_max_box_ptr_Uxf32 -> %[[RED]] : !fir.ptr<!fir.array<?xf32>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ptr<!fir.array<?xf32>>) bounds(%[[BOUND]]) to varPtr(%[[BOX_ADDR]] : !fir.ptr<!fir.array<?xf32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a"}
subroutine acc_reduction_max_dynamic_extent_max(a, n)
integer :: n
@@ -1211,3 +1228,4 @@ subroutine acc_reduction_max_dynamic_extent_max(a, n)
! CHECK: %[[ADDR:.*]] = fir.box_addr %[[DECL_A]]#0 : (!fir.box<!fir.array<?x?xf32>>) -> !fir.ref<!fir.array<?x?xf32>>
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[ADDR]] : !fir.ref<!fir.array<?x?xf32>>) bounds(%{{.*}}, %{{.*}}) -> !fir.ref<!fir.array<?x?xf32>> {name = "a"}
! CHECK: acc.parallel reduction(@reduction_max_box_UxUxf32 -> %[[RED]] : !fir.ref<!fir.array<?x?xf32>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.array<?x?xf32>>) bounds(%{{.*}}) to varPtr(%{{.*}} : !fir.ref<!fir.array<?x?xf32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a"}
diff --git a/flang/test/Lower/OpenACC/acc-reduction.f90 b/flang/test/Lower/OpenACC/acc-reduction.f90
index 20b5ad28f78a1..22a52739171b1 100644
--- a/flang/test/Lower/OpenACC/acc-reduction.f90
+++ b/flang/test/Lower/OpenACC/acc-reduction.f90
@@ -1042,6 +1042,7 @@ subroutine acc_reduction_iand()
! CHECK-LABEL: func.func @_QPacc_reduction_iand()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<i32>) -> !fir.ref<i32> {name = "i"}
! CHECK: acc.parallel reduction(@reduction_iand_ref_i32 -> %[[RED]] : !fir.ref<i32>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<i32>) to varPtr(%{{.*}} : !fir.ref<i32>) {dataClause = #acc<data_clause acc_reduction>, name = "i"}
subroutine acc_reduction_ior()
integer :: i
@@ -1052,6 +1053,7 @@ subroutine acc_reduction_ior()
! CHECK-LABEL: func.func @_QPacc_reduction_ior()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<i32>) -> !fir.ref<i32> {name = "i"}
! CHECK: acc.parallel reduction(@reduction_ior_ref_i32 -> %[[RED]] : !fir.ref<i32>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<i32>) to varPtr(%{{.*}} : !fir.ref<i32>) {dataClause = #acc<data_clause acc_reduction>, name = "i"}
subroutine acc_reduction_ieor()
integer :: i
@@ -1062,6 +1064,7 @@ subroutine acc_reduction_ieor()
! CHECK-LABEL: func.func @_QPacc_reduction_ieor()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<i32>) -> !fir.ref<i32> {name = "i"}
! CHECK: acc.parallel reduction(@reduction_xor_ref_i32 -> %[[RED]] : !fir.ref<i32>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<i32>) to varPtr(%{{.*}} : !fir.ref<i32>) {dataClause = #acc<data_clause acc_reduction>, name = "i"}
subroutine acc_reduction_and()
logical :: l
@@ -1074,6 +1077,7 @@ subroutine acc_reduction_and()
! CHECK: %[[DECLL:.*]]:2 = hlfir.declare %[[L]]
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[DECLL]]#0 : !fir.ref<!fir.logical<4>>) -> !fir.ref<!fir.logical<4>> {name = "l"}
! CHECK: acc.parallel reduction(@reduction_land_ref_l32 -> %[[RED]] : !fir.ref<!fir.logical<4>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.logical<4>>) to varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) {dataClause = #acc<data_clause acc_reduction>, name = "l"}
subroutine acc_reduction_or()
logical :: l
@@ -1084,6 +1088,7 @@ subroutine acc_reduction_or()
! CHECK-LABEL: func.func @_QPacc_reduction_or()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) -> !fir.ref<!fir.logical<4>> {name = "l"}
! CHECK: acc.parallel reduction(@reduction_lor_ref_l32 -> %[[RED]] : !fir.ref<!fir.logical<4>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.logical<4>>) to varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) {dataClause = #acc<data_clause acc_reduction>, name = "l"}
subroutine acc_reduction_eqv()
logical :: l
@@ -1094,6 +1099,7 @@ subroutine acc_reduction_eqv()
! CHECK-LABEL: func.func @_QPacc_reduction_eqv()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) -> !fir.ref<!fir.logical<4>> {name = "l"}
! CHECK: acc.parallel reduction(@reduction_eqv_ref_l32 -> %[[RED]] : !fir.ref<!fir.logical<4>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.logical<4>>) to varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) {dataClause = #acc<data_clause acc_reduction>, name = "l"}
subroutine acc_reduction_neqv()
logical :: l
@@ -1104,6 +1110,7 @@ subroutine acc_reduction_neqv()
! CHECK-LABEL: func.func @_QPacc_reduction_neqv()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) -> !fir.ref<!fir.logical<4>> {name = "l"}
! CHECK: acc.parallel reduction(@reduction_neqv_ref_l32 -> %[[RED]] : !fir.ref<!fir.logical<4>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.logical<4>>) to varPtr(%{{.*}} : !fir.ref<!fir.logical<4>>) {dataClause = #acc<data_clause acc_reduction>, name = "l"}
subroutine acc_reduction_add_cmplx()
complex :: c
@@ -1114,6 +1121,7 @@ subroutine acc_reduction_add_cmplx()
! CHECK-LABEL: func.func @_QPacc_reduction_add_cmplx()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<complex<f32>>) -> !fir.ref<complex<f32>> {name = "c"}
! CHECK: acc.parallel reduction(@reduction_add_ref_z32 -> %[[RED]] : !fir.ref<complex<f32>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<complex<f32>>) to varPtr(%{{.*}} : !fir.ref<complex<f32>>) {dataClause = #acc<data_clause acc_reduction>, name = "c"}
subroutine acc_reduction_mul_cmplx()
complex :: c
@@ -1124,6 +1132,7 @@ subroutine acc_reduction_mul_cmplx()
! CHECK-LABEL: func.func @_QPacc_reduction_mul_cmplx()
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%{{.*}} : !fir.ref<complex<f32>>) -> !fir.ref<complex<f32>> {name = "c"}
! CHECK: acc.parallel reduction(@reduction_mul_ref_z32 -> %[[RED]] : !fir.ref<complex<f32>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<complex<f32>>) to varPtr(%{{.*}} : !fir.ref<complex<f32>>) {dataClause = #acc<data_clause acc_reduction>, name = "c"}
subroutine acc_reduction_add_alloc()
integer, allocatable :: i
@@ -1137,6 +1146,7 @@ subroutine acc_reduction_add_alloc()
! CHECK: %[[DECL:.*]]:2 = hlfir.declare %[[ALLOCA]]
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[DECL]]#0 : !fir.ref<!fir.box<!fir.heap<i32>>>) -> !fir.ref<!fir.box<!fir.heap<i32>>> {name = "i"}
! CHECK: acc.parallel reduction(@reduction_add_ref_box_heap_i32 -> %[[RED]] : !fir.ref<!fir.box<!fir.heap<i32>>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.box<!fir.heap<i32>>>) to varPtr(%[[DECL]]#0 : !fir.ref<!fir.box<!fir.heap<i32>>>) {dataClause = #acc<data_clause acc_reduction>, name = "i"}
subroutine acc_reduction_add_pointer(i)
integer, pointer :: i
@@ -1149,6 +1159,7 @@ subroutine acc_reduction_add_pointer(i)
! CHECK: %[[DECLARG0:.*]]:2 = hlfir.declare %[[ARG0]]
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[DECLARG0]]#0 : !fir.ref<!fir.box<!fir.ptr<i32>>>) -> !fir.ref<!fir.box<!fir.ptr<i32>>> {name = "i"}
! CHECK: acc.parallel reduction(@reduction_add_ref_box_ptr_i32 -> %[[RED]] : !fir.ref<!fir.box<!fir.ptr<i32>>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.box<!fir.ptr<i32>>>) to varPtr(%[[DECLARG0]]#0 : !fir.ref<!fir.box<!fir.ptr<i32>>>) {dataClause = #acc<data_clause acc_reduction>, name = "i"}
subroutine acc_reduction_add_static_slice(a)
integer :: a(100)
@@ -1166,6 +1177,7 @@ subroutine acc_reduction_add_static_slice(a)
! CHECK: %[[BOUND:.*]] = acc.bounds lowerbound(%[[LB]] : index) upperbound(%[[UB]] : index) extent(%[[C100]] : index) stride(%[[C1]] : index) startIdx(%[[C1]] : index)
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[DECLARG0]]#0 : !fir.ref<!fir.array<100xi32>>) bounds(%[[BOUND]]) -> !fir.ref<!fir.array<100xi32>> {name = "a(11:20)"}
! CHECK: acc.parallel reduction(@reduction_add_section_lb10.ub19_ref_100xi32 -> %[[RED]] : !fir.ref<!fir.array<100xi32>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.array<100xi32>>) bounds(%[[BOUND]]) to varPtr(%[[DECLARG0]]#0 : !fir.ref<!fir.array<100xi32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a(11:20)"}
subroutine acc_reduction_add_dynamic_extent_add(a)
integer :: a(:)
@@ -1178,6 +1190,7 @@ subroutine acc_reduction_add_dynamic_extent_add(a)
! CHECK: %[[DECLARG0:.*]]:2 = hlfir.declare %[[ARG0]]
! CHECK: %[[RED:.*]] = acc.reduction var(%{{.*}} : !fir.box<!fir.array<?xi32>>) -> !fir.box<!fir.array<?xi32>> {name = "a"}
! CHECK: acc.parallel reduction(@reduction_add_box_Uxi32 -> %[[RED:.*]] : !fir.box<!fir.array<?xi32>>)
+! CHECK: acc.copyout accVar(%[[RED]] : !fir.box<!fir.array<?xi32>>) to var(%{{.*}} : !fir.box<!fir.array<?xi32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a"}
subroutine acc_reduction_add_assumed_shape_max(a)
real :: a(:)
@@ -1190,6 +1203,7 @@ subroutine acc_reduction_add_assumed_shape_max(a)
! CHECK: %[[DECLARG0:.*]]:2 = hlfir.declare %[[ARG0]]
! CHECK: %[[RED:.*]] = acc.reduction var(%{{.*}} : !fir.box<!fir.array<?xf32>>) -> !fir.box<!fir.array<?xf32>> {name = "a"}
! CHECK: acc.parallel reduction(@reduction_max_box_Uxf32 -> %[[RED]] : !fir.box<!fir.array<?xf32>>) {
+! CHECK: acc.copyout accVar(%[[RED]] : !fir.box<!fir.array<?xf32>>) to var(%{{.*}} : !fir.box<!fir.array<?xf32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a"}
subroutine acc_reduction_add_dynamic_extent_add_with_section(a)
integer :: a(:)
@@ -1202,7 +1216,8 @@ subroutine acc_reduction_add_dynamic_extent_add_with_section(a)
! CHECK: %[[DECL:.*]]:2 = hlfir.declare %[[ARG0]] dummy_scope %{{[0-9]+}} {uniq_name = "_QFacc_reduction_add_dynamic_extent_add_with_sectionEa"} : (!fir.box<!fir.array<?xi32>>, !fir.dscope) -> (!fir.box<!fir.array<?xi32>>, !fir.box<!fir.array<?xi32>>)
! CHECK: %[[BOUND:.*]] = acc.bounds lowerbound(%c1{{.*}} : index) upperbound(%c3{{.*}} : index) extent(%{{.*}}#1 : index) stride(%{{.*}}#2 : index) startIdx(%{{.*}} : index) {strideInBytes = true}
! CHECK: %[[RED:.*]] = acc.reduction var(%[[DECL]]#0 : !fir.box<!fir.array<?xi32>>) bounds(%[[BOUND]]) -> !fir.box<!fir.array<?xi32>> {name = "a(2:4)"}
-! CHECK: acc.parallel reduction(@reduction_add_section_lb1.ub3_box_Uxi32 -> %[[RED]] : !fir.box<!fir.array<?xi32>>)
+! CHECK: acc.parallel reduction(@reduction_add_section_lb1.ub3_box_Uxi32 -> %[[RED]] : !fir.box<!fir.array<?xi32>>
+! CHECK: acc.copyout accVar(%[[RED]] : !fir.box<!fir.array<?xi32>>) bounds(%[[BOUND]]) to var(%[[DECL]]#0 : !fir.box<!fir.array<?xi32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a(2:4)"}
subroutine acc_reduction_add_allocatable(a)
real, allocatable :: a(:)
@@ -1215,6 +1230,7 @@ subroutine acc_reduction_add_allocatable(a)
! CHECK: %[[DECL:.*]]:2 = hlfir.declare %[[ARG0]] dummy_scope %{{[0-9]+}} {fortran_attrs = #fir.var_attrs<allocatable>, uniq_name = "_QFacc_reduction_add_allocatableEa"} : (!fir.ref<!fir.box<!fir.heap<!fir.array<?xf32>>>>, !fir.dscope) -> (!fir.ref<!fir.box<!fir.heap<!fir.array<?xf32>>>>, !fir.ref<!fir.box<!fir.heap<!fir.array<?xf32>>>>)
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[DECL]]#0 : !fir.ref<!fir.box<!fir.heap<!fir.array<?xf32>>>>) -> !fir.ref<!fir.box<!fir.heap<!fir.array<?xf32>>>> {name = "a"}
! CHECK: acc.parallel reduction(@reduction_max_ref_box_heap_Uxf32 -> %[[RED]] : !fir.ref<!fir.box<!fir.heap<!fir.array<?xf32>>>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.box<!fir.heap<!fir.array<?xf32>>>>) to varPtr(%[[DECL]]#0 : !fir.ref<!fir.box<!fir.heap<!fir.array<?xf32>>>>) {dataClause = #acc<data_clause acc_reduction>, name = "a"}
subroutine acc_reduction_add_pointer_array(a)
real, pointer :: a(:)
@@ -1227,6 +1243,7 @@ subroutine acc_reduction_add_pointer_array(a)
! CHECK: %[[DECL:.*]]:2 = hlfir.declare %[[ARG0]] dummy_scope %{{[0-9]+}} {fortran_attrs = #fir.var_attrs<pointer>, uniq_name = "_QFacc_reduction_add_pointer_arrayEa"} : (!fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>>, !fir.dscope) -> (!fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>>, !fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>>)
! CHECK: %[[RED:.*]] = acc.reduction varPtr(%[[DECL]]#0 : !fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>>) -> !fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>> {name = "a"}
! CHECK: acc.parallel reduction(@reduction_max_ref_box_ptr_Uxf32 -> %[[RED]] : !fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>>)
+! CHECK: acc.copyout accPtr(%[[RED]] : !fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>>) to varPtr(%[[DECL]]#0 : !fir.ref<!fir.box<!fir.ptr<!fir.array<?xf32>>>>) {dataClause = #acc<data_clause acc_reduction>, name = "a"}
subroutine acc_reduction_max_dynamic_extent_max(a, n)
integer :: n
@@ -1240,3 +1257,4 @@ subroutine acc_reduction_max_dynamic_extent_max(a, n)
! CHECK: %[[DECL_A:.*]]:2 = hlfir.declare %[[ARG0]](%{{.*}}) dummy_scope %{{[0-9]+}} {uniq_name = "_QFacc_reduction_max_dynamic_extent_maxEa"} : (!fir.ref<!fir.array<?x?xf32>>, !fir.shape<2>, !fir.dscope) -> (!fir.box<!fir.array<?x?xf32>>, !fir.ref<!fir.array<?x?xf32>>)
! CHECK: %[[RED:.*]] = acc.reduction var(%[[DECL_A]]#0 : !fir.box<!fir.array<?x?xf32>>) -> !fir.box<!fir.array<?x?xf32>> {name = "a"}
! CHECK: acc.parallel reduction(@reduction_max_box_UxUxf32 -> %[[RED]] : !fir.box<!fir.array<?x?xf32>>)
+! CHECK: acc.copyout accVar(%[[RED]] : !fir.box<!fir.array<?x?xf32>>) to var(%[[DECL_A]]#0 : !fir.box<!fir.array<?x?xf32>>) {dataClause = #acc<data_clause acc_reduction>, name = "a"}
>From acbc6cdc22d4742cd3748dd0137168ba3124c0cc Mon Sep 17 00:00:00 2001
From: Kazuaki Matsumura <kmatsumura at nvidia.com>
Date: Wed, 18 Jun 2025 00:25:00 -0700
Subject: [PATCH 2/2] [flang][acc] Reorder the generation of data exit
---
flang/lib/Lower/OpenACC.cpp | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/flang/lib/Lower/OpenACC.cpp b/flang/lib/Lower/OpenACC.cpp
index 63a9d1d5616a9..3ad726b068bb4 100644
--- a/flang/lib/Lower/OpenACC.cpp
+++ b/flang/lib/Lower/OpenACC.cpp
@@ -3028,6 +3028,8 @@ static Op createComputeOp(
builder.setInsertionPointAfter(computeOp);
// Create the exit operations after the region.
+ genDataExitOperations<mlir::acc::ReductionOp, mlir::acc::CopyoutOp>(
+ builder, reductionEntryOperands, /*structured=*/true);
genDataExitOperations<mlir::acc::CopyinOp, mlir::acc::CopyoutOp>(
builder, copyEntryOperands, /*structured=*/true);
genDataExitOperations<mlir::acc::CopyinOp, mlir::acc::DeleteOp>(
@@ -3042,8 +3044,6 @@ static Op createComputeOp(
builder, nocreateEntryOperands, /*structured=*/true);
genDataExitOperations<mlir::acc::PresentOp, mlir::acc::DeleteOp>(
builder, presentEntryOperands, /*structured=*/true);
- genDataExitOperations<mlir::acc::ReductionOp, mlir::acc::CopyoutOp>(
- builder, reductionEntryOperands, /*structured=*/true);
builder.restoreInsertionPoint(insPt);
return computeOp;
More information about the flang-commits
mailing list