[flang-commits] [flang] e5caa0f - [Flang][OpenMP] Add support for real typed reductions in worksharing-loop
Dylan Fleming via flang-commits
flang-commits at lists.llvm.org
Thu Sep 1 04:17:23 PDT 2022
Author: Dylan Fleming
Date: 2022-09-01T11:16:42Z
New Revision: e5caa0f2292d8e2fc4c830625e7ec5809d5b5c42
URL: https://github.com/llvm/llvm-project/commit/e5caa0f2292d8e2fc4c830625e7ec5809d5b5c42
DIFF: https://github.com/llvm/llvm-project/commit/e5caa0f2292d8e2fc4c830625e7ec5809d5b5c42.diff
LOG: [Flang][OpenMP] Add support for real typed reductions in worksharing-loop
Allows addition/multiplication reductions to be used with
real types by adding getReductionOperation() to OpenMP.cpp,
which can select either integer or floating-point instruction.
Reviewed By: kiranchandramohan
Differential Revision: https://reviews.llvm.org/D132459
Added:
flang/test/Lower/OpenMP/wsloop-reduction-add.f90
flang/test/Lower/OpenMP/wsloop-reduction-mul.f90
Modified:
flang/lib/Lower/OpenMP.cpp
Removed:
flang/test/Lower/OpenMP/Todo/reduction-real.f90
flang/test/Lower/OpenMP/wsloop-reduction-int-add.f90
flang/test/Lower/OpenMP/wsloop-reduction-int-mul.f90
################################################################################
diff --git a/flang/lib/Lower/OpenMP.cpp b/flang/lib/Lower/OpenMP.cpp
index cd614321af15b..19ff2d738a4ad 100644
--- a/flang/lib/Lower/OpenMP.cpp
+++ b/flang/lib/Lower/OpenMP.cpp
@@ -855,11 +855,28 @@ static int getOperationIdentity(llvm::StringRef reductionOpName,
static Value getReductionInitValue(mlir::Location loc, mlir::Type type,
llvm::StringRef reductionOpName,
fir::FirOpBuilder &builder) {
+ assert(type.isIntOrIndexOrFloat() && "only integer and float types are currently supported");
+ if (type.isa<FloatType>())
+ return builder.create<mlir::arith::ConstantOp>(
+ loc, type,
+ builder.getFloatAttr(
+ type, (double)getOperationIdentity(reductionOpName, loc)));
+
return builder.create<mlir::arith::ConstantOp>(
loc, type,
builder.getIntegerAttr(type, getOperationIdentity(reductionOpName, loc)));
}
+template <typename FloatOp, typename IntegerOp>
+static Value getReductionOperation(fir::FirOpBuilder &builder, mlir::Type type,
+ mlir::Location loc, mlir::Value op1,
+ mlir::Value op2) {
+ assert(type.isIntOrIndexOrFloat() && "only integer and float types are currently supported");
+ if (type.isIntOrIndex())
+ return builder.create<IntegerOp>(loc, op1, op2);
+ return builder.create<FloatOp>(loc, op1, op2);
+}
+
/// Creates an OpenMP reduction declaration and inserts it into the provided
/// symbol table. The declaration has a constant initializer with the neutral
/// value `initValue`, and the reduction combiner carried over from `reduce`.
@@ -891,19 +908,23 @@ static omp::ReductionDeclareOp createReductionDecl(
mlir::Value op1 = decl.reductionRegion().front().getArgument(0);
mlir::Value op2 = decl.reductionRegion().front().getArgument(1);
- Value res;
+ Value reductionOp;
switch (intrinsicOp) {
case Fortran::parser::DefinedOperator::IntrinsicOperator::Add:
- res = builder.create<mlir::arith::AddIOp>(loc, op1, op2);
+ reductionOp =
+ getReductionOperation<mlir::arith::AddFOp, mlir::arith::AddIOp>(
+ builder, type, loc, op1, op2);
break;
case Fortran::parser::DefinedOperator::IntrinsicOperator::Multiply:
- res = builder.create<mlir::arith::MulIOp>(loc, op1, op2);
+ reductionOp =
+ getReductionOperation<mlir::arith::MulFOp, mlir::arith::MulIOp>(
+ builder, type, loc, op1, op2);
break;
default:
TODO(loc, "Reduction of some intrinsic operators is not supported");
}
- builder.create<omp::YieldOp>(loc, res);
+ builder.create<omp::YieldOp>(loc, reductionOp);
return decl;
}
@@ -1106,7 +1127,7 @@ static void genOMP(Fortran::lower::AbstractConverter &converter,
mlir::Type redType =
symVal.getType().cast<fir::ReferenceType>().getEleTy();
reductionVars.push_back(symVal);
- if (redType.isIntOrIndex()) {
+ if (redType.isIntOrIndexOrFloat()) {
decl = createReductionDecl(
firOpBuilder, getReductionName(intrinsicOp, redType),
intrinsicOp, redType, currentLocation);
@@ -1785,7 +1806,7 @@ void Fortran::lower::genOpenMPReduction(
mlir::Value reductionVal = converter.getSymbolAddress(*symbol);
mlir::Type reductionType =
reductionVal.getType().cast<fir::ReferenceType>().getEleTy();
- if (!reductionType.isIntOrIndex())
+ if (!reductionType.isIntOrIndexOrFloat())
continue;
for (mlir::OpOperand &reductionValUse : reductionVal.getUses()) {
diff --git a/flang/test/Lower/OpenMP/Todo/reduction-real.f90 b/flang/test/Lower/OpenMP/Todo/reduction-real.f90
deleted file mode 100644
index 4b1a25345f15a..0000000000000
--- a/flang/test/Lower/OpenMP/Todo/reduction-real.f90
+++ /dev/null
@@ -1,16 +0,0 @@
-! RUN: %not_todo_cmd bbc -emit-fir -fopenmp -o - %s 2>&1 | FileCheck %s
-! RUN: %not_todo_cmd %flang_fc1 -emit-fir -fopenmp -o - %s 2>&1 | FileCheck %s
-
-! CHECK: not yet implemented: Reduction of some types is not supported
-subroutine reduction_real
- real :: x
- x = 0.0
- !$omp parallel
- !$omp do reduction(+:x)
- do i=1, 100
- x = x + 1.0
- end do
- !$omp end do
- !$omp end parallel
- print *, x
-end subroutine
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-add.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-add.f90
new file mode 100644
index 0000000000000..870cc0e114b55
--- /dev/null
+++ b/flang/test/Lower/OpenMP/wsloop-reduction-add.f90
@@ -0,0 +1,273 @@
+! RUN: bbc -emit-fir -fopenmp %s -o - | FileCheck %s
+! RUN: %flang_fc1 -emit-fir -fopenmp %s -o - | FileCheck %s
+
+!CHECK-LABEL: omp.reduction.declare
+!CHECK-SAME: @[[RED_F64_NAME:.*]] : f64 init {
+!CHECK: ^bb0(%{{.*}}: f64):
+!CHECK: %[[C0_1:.*]] = arith.constant 0.000000e+00 : f64
+!CHECK: omp.yield(%[[C0_1]] : f64)
+!CHECK: } combiner {
+!CHECK: ^bb0(%[[ARG0:.*]]: f64, %[[ARG1:.*]]: f64):
+!CHECK: %[[RES:.*]] = arith.addf %[[ARG0]], %[[ARG1]] : f64
+!CHECK: omp.yield(%[[RES]] : f64)
+!CHECK: }
+
+!CHECK-LABEL: omp.reduction.declare
+!CHECK-SAME: @[[RED_I64_NAME:.*]] : i64 init {
+!CHECK: ^bb0(%{{.*}}: i64):
+!CHECK: %[[C0_1:.*]] = arith.constant 0 : i64
+!CHECK: omp.yield(%[[C0_1]] : i64)
+!CHECK: } combiner {
+!CHECK: ^bb0(%[[ARG0:.*]]: i64, %[[ARG1:.*]]: i64):
+!CHECK: %[[RES:.*]] = arith.addi %[[ARG0]], %[[ARG1]] : i64
+!CHECK: omp.yield(%[[RES]] : i64)
+!CHECK: }
+
+!CHECK-LABEL: omp.reduction.declare
+!CHECK-SAME: @[[RED_F32_NAME:.*]] : f32 init {
+!CHECK: ^bb0(%{{.*}}: f32):
+!CHECK: %[[C0_1:.*]] = arith.constant 0.000000e+00 : f32
+!CHECK: omp.yield(%[[C0_1]] : f32)
+!CHECK: } combiner {
+!CHECK: ^bb0(%[[ARG0:.*]]: f32, %[[ARG1:.*]]: f32):
+!CHECK: %[[RES:.*]] = arith.addf %[[ARG0]], %[[ARG1]] : f32
+!CHECK: omp.yield(%[[RES]] : f32)
+!CHECK: }
+
+!CHECK-LABEL: omp.reduction.declare
+!CHECK-SAME: @[[RED_I32_NAME:.*]] : i32 init {
+!CHECK: ^bb0(%{{.*}}: i32):
+!CHECK: %[[C0_1:.*]] = arith.constant 0 : i32
+!CHECK: omp.yield(%[[C0_1]] : i32)
+!CHECK: } combiner {
+!CHECK: ^bb0(%[[ARG0:.*]]: i32, %[[ARG1:.*]]: i32):
+!CHECK: %[[RES:.*]] = arith.addi %[[ARG0]], %[[ARG1]] : i32
+!CHECK: omp.yield(%[[RES]] : i32)
+!CHECK: }
+
+!CHECK-LABEL: func.func @_QPsimple_int_reduction
+!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFsimple_int_reductionEx"}
+!CHECK: %[[C0_2:.*]] = arith.constant 0 : i32
+!CHECK: fir.store %[[C0_2]] to %[[XREF]] : !fir.ref<i32>
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
+!CHECK: %[[C100:.*]] = arith.constant 100 : i32
+!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
+!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C100]]) inclusive step (%[[C1_2]])
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL]], %[[XREF]] : !fir.ref<i32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine simple_int_reduction
+ integer :: x
+ x = 0
+ !$omp parallel
+ !$omp do reduction(+:x)
+ do i=1, 100
+ x = x + i
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPsimple_real_reduction
+!CHECK: %[[XREF:.*]] = fir.alloca f32 {bindc_name = "x", uniq_name = "_QFsimple_real_reductionEx"}
+!CHECK: %[[C0_2:.*]] = arith.constant 0.000000e+00 : f32
+!CHECK: fir.store %[[C0_2]] to %[[XREF]] : !fir.ref<f32>
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
+!CHECK: %[[C100:.*]] = arith.constant 100 : i32
+!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
+!CHECK: omp.wsloop reduction(@[[RED_F32_NAME]] -> %[[XREF]] : !fir.ref<f32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C100]]) inclusive step (%[[C1_2]])
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL_i32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL_f32:.*]] = fir.convert %[[I_PVT_VAL_i32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL_f32]], %[[XREF]] : !fir.ref<f32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine simple_real_reduction
+ real :: x
+ x = 0.0
+ !$omp parallel
+ !$omp do reduction(+:x)
+ do i=1, 100
+ x = x + i
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPsimple_int_reduction_switch_order
+!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFsimple_int_reduction_switch_orderEx"}
+!CHECK: %[[C0_2:.*]] = arith.constant 0 : i32
+!CHECK: fir.store %[[C0_2]] to %[[XREF]] : !fir.ref<i32>
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
+!CHECK: %[[C100:.*]] = arith.constant 100 : i32
+!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
+!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C100]]) inclusive step (%[[C1_2]])
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL]], %[[XREF]] : !fir.ref<i32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine simple_int_reduction_switch_order
+ integer :: x
+ x = 0
+ !$omp parallel
+ !$omp do reduction(+:x)
+ do i=1, 100
+ x = i + x
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPsimple_real_reduction_switch_order
+!CHECK: %[[XREF:.*]] = fir.alloca f32 {bindc_name = "x", uniq_name = "_QFsimple_real_reduction_switch_orderEx"}
+!CHECK: %[[C0_2:.*]] = arith.constant 0.000000e+00 : f32
+!CHECK: fir.store %[[C0_2]] to %[[XREF]] : !fir.ref<f32>
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
+!CHECK: %[[C100:.*]] = arith.constant 100 : i32
+!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
+!CHECK: omp.wsloop reduction(@[[RED_F32_NAME]] -> %[[XREF]] : !fir.ref<f32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C100]]) inclusive step (%[[C1_2]])
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL_i32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL_f32:.*]] = fir.convert %[[I_PVT_VAL_i32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL_f32]], %[[XREF]] : !fir.ref<f32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine simple_real_reduction_switch_order
+ real :: x
+ x = 0.0
+ !$omp parallel
+ !$omp do reduction(+:x)
+ do i=1, 100
+ x = i + x
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPmultiple_int_reductions_same_type
+!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFmultiple_int_reductions_same_typeEx"}
+!CHECK: %[[YREF:.*]] = fir.alloca i32 {bindc_name = "y", uniq_name = "_QFmultiple_int_reductions_same_typeEy"}
+!CHECK: %[[ZREF:.*]] = fir.alloca i32 {bindc_name = "z", uniq_name = "_QFmultiple_int_reductions_same_typeEz"}
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>, @[[RED_I32_NAME]] -> %[[YREF]] : !fir.ref<i32>, @[[RED_I32_NAME]] -> %[[ZREF]] : !fir.ref<i32>) for (%[[IVAL]]) : i32
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL1:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL1]], %[[XREF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL2:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL2]], %[[YREF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL3:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL3]], %[[ZREF]] : !fir.ref<i32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine multiple_int_reductions_same_type
+ integer :: x,y,z
+ x = 0
+ y = 0
+ z = 0
+ !$omp parallel
+ !$omp do reduction(+:x,y,z)
+ do i=1, 100
+ x = x + i
+ y = y + i
+ z = z + i
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPmultiple_real_reductions_same_type
+!CHECK: %[[XREF:.*]] = fir.alloca f32 {bindc_name = "x", uniq_name = "_QFmultiple_real_reductions_same_typeEx"}
+!CHECK: %[[YREF:.*]] = fir.alloca f32 {bindc_name = "y", uniq_name = "_QFmultiple_real_reductions_same_typeEy"}
+!CHECK: %[[ZREF:.*]] = fir.alloca f32 {bindc_name = "z", uniq_name = "_QFmultiple_real_reductions_same_typeEz"}
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: omp.wsloop reduction(@[[RED_F32_NAME]] -> %[[XREF]] : !fir.ref<f32>, @[[RED_F32_NAME]] -> %[[YREF]] : !fir.ref<f32>, @[[RED_F32_NAME]] -> %[[ZREF]] : !fir.ref<f32>) for (%[[IVAL]]) : i32
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL1_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL1_F32:.*]] = fir.convert %[[I_PVT_VAL1_I32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL1_F32]], %[[XREF]] : !fir.ref<f32>
+!CHECK: %[[I_PVT_VAL2_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL2_F32:.*]] = fir.convert %[[I_PVT_VAL2_I32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL2_F32]], %[[YREF]] : !fir.ref<f32>
+!CHECK: %[[I_PVT_VAL3_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL3_F32:.*]] = fir.convert %[[I_PVT_VAL3_I32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL3_F32]], %[[ZREF]] : !fir.ref<f32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine multiple_real_reductions_same_type
+ real :: x,y,z
+ x = 0.0
+ y = 0.0
+ z = 0.0
+ !$omp parallel
+ !$omp do reduction(+:x,y,z)
+ do i=1, 100
+ x = x + i
+ y = y + i
+ z = z + i
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPmultiple_reductions_
diff erent_type
+!CHECK: %[[WREF:.*]] = fir.alloca f64 {bindc_name = "w", uniq_name = "_QFmultiple_reductions_
diff erent_typeEw"}
+!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFmultiple_reductions_
diff erent_typeEx"}
+!CHECK: %[[YREF:.*]] = fir.alloca i64 {bindc_name = "y", uniq_name = "_QFmultiple_reductions_
diff erent_typeEy"}
+!CHECK: %[[ZREF:.*]] = fir.alloca f32 {bindc_name = "z", uniq_name = "_QFmultiple_reductions_
diff erent_typeEz"}
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>, @[[RED_I64_NAME]] -> %[[YREF]] : !fir.ref<i64>, @[[RED_F32_NAME]] -> %[[ZREF]] : !fir.ref<f32>, @[[RED_F64_NAME]] -> %[[WREF]] : !fir.ref<f64>) for (%[[IVAL:.*]]) : i32
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL1_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL1_I32]], %[[XREF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL2_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL2_I64:.*]] = fir.convert %[[I_PVT_VAL2_I32]] : (i32) -> i64
+!CHECK: omp.reduction %[[I_PVT_VAL2_I64]], %[[YREF]] : !fir.ref<i64>
+!CHECK: %[[I_PVT_VAL3_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL3_F32:.*]] = fir.convert %[[I_PVT_VAL3_I32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL3_F32]], %[[ZREF]] : !fir.ref<f32>
+!CHECK: %[[I_PVT_VAL4_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL4_F64:.*]] = fir.convert %[[I_PVT_VAL4_I32]] : (i32) -> f64
+!CHECK: omp.reduction %[[I_PVT_VAL4_F64]], %[[WREF]] : !fir.ref<f64>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine multiple_reductions_
diff erent_type
+ integer :: x
+ integer(kind=8) :: y
+ real :: z
+ real(kind=8) :: w
+ x = 0
+ y = 0
+ z = 0.0
+ w = 0.0
+ !$omp parallel
+ !$omp do reduction(+:x,y,z,w)
+ do i=1, 100
+ x = x + i
+ y = y + i
+ z = z + i
+ w = w + i
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-int-add.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-int-add.f90
deleted file mode 100644
index bd7102d725250..0000000000000
--- a/flang/test/Lower/OpenMP/wsloop-reduction-int-add.f90
+++ /dev/null
@@ -1,144 +0,0 @@
-! RUN: bbc -emit-fir -fopenmp %s -o - | FileCheck %s
-! RUN: %flang_fc1 -emit-fir -fopenmp %s -o - | FileCheck %s
-
-!CHECK-LABEL: omp.reduction.declare
-!CHECK-SAME: @[[RED_I64_NAME:.*]] : i64 init {
-!CHECK: ^bb0(%{{.*}}: i64):
-!CHECK: %[[C0_1:.*]] = arith.constant 0 : i64
-!CHECK: omp.yield(%[[C0_1]] : i64)
-!CHECK: } combiner {
-!CHECK: ^bb0(%[[ARG0:.*]]: i64, %[[ARG1:.*]]: i64):
-!CHECK: %[[RES:.*]] = arith.addi %[[ARG0]], %[[ARG1]] : i64
-!CHECK: omp.yield(%[[RES]] : i64)
-!CHECK: }
-
-!CHECK-LABEL: omp.reduction.declare
-!CHECK-SAME: @[[RED_I32_NAME:.*]] : i32 init {
-!CHECK: ^bb0(%{{.*}}: i32):
-!CHECK: %[[C0_1:.*]] = arith.constant 0 : i32
-!CHECK: omp.yield(%[[C0_1]] : i32)
-!CHECK: } combiner {
-!CHECK: ^bb0(%[[ARG0:.*]]: i32, %[[ARG1:.*]]: i32):
-!CHECK: %[[RES:.*]] = arith.addi %[[ARG0]], %[[ARG1]] : i32
-!CHECK: omp.yield(%[[RES]] : i32)
-!CHECK: }
-
-!CHECK-LABEL: func.func @_QPsimple_reduction
-!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFsimple_reductionEx"}
-!CHECK: %[[C0_2:.*]] = arith.constant 0 : i32
-!CHECK: fir.store %[[C0_2]] to %[[XREF]] : !fir.ref<i32>
-!CHECK: omp.parallel
-!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
-!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
-!CHECK: %[[C100:.*]] = arith.constant 100 : i32
-!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
-!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C100]]) inclusive step (%[[C1_2]])
-!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: %[[I_PVT_VAL:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: omp.reduction %[[I_PVT_VAL]], %[[XREF]] : !fir.ref<i32>
-!CHECK: omp.yield
-!CHECK: omp.terminator
-!CHECK: return
-
-subroutine simple_reduction
- integer :: x
- x = 0
- !$omp parallel
- !$omp do reduction(+:x)
- do i=1, 100
- x = x + i
- end do
- !$omp end do
- !$omp end parallel
-end subroutine
-
-!CHECK-LABEL: func.func @_QPsimple_reduction_switch_order
-!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFsimple_reduction_switch_orderEx"}
-!CHECK: %[[C0_2:.*]] = arith.constant 0 : i32
-!CHECK: fir.store %[[C0_2]] to %[[XREF]] : !fir.ref<i32>
-!CHECK: omp.parallel
-!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
-!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
-!CHECK: %[[C100:.*]] = arith.constant 100 : i32
-!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
-!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C100]]) inclusive step (%[[C1_2]])
-!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: %[[I_PVT_VAL:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: omp.reduction %[[I_PVT_VAL]], %[[XREF]] : !fir.ref<i32>
-!CHECK: omp.yield
-!CHECK: omp.terminator
-!CHECK: return
-
-subroutine simple_reduction_switch_order
- integer :: x
- x = 0
- !$omp parallel
- !$omp do reduction(+:x)
- do i=1, 100
- x = i + x
- end do
- !$omp end do
- !$omp end parallel
-end subroutine
-
-!CHECK-LABEL: func.func @_QPmultiple_reductions_same_type
-!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFmultiple_reductions_same_typeEx"}
-!CHECK: %[[YREF:.*]] = fir.alloca i32 {bindc_name = "y", uniq_name = "_QFmultiple_reductions_same_typeEy"}
-!CHECK: %[[ZREF:.*]] = fir.alloca i32 {bindc_name = "z", uniq_name = "_QFmultiple_reductions_same_typeEz"}
-!CHECK: omp.parallel
-!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
-!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>, @[[RED_I32_NAME]] -> %[[YREF]] : !fir.ref<i32>, @[[RED_I32_NAME]] -> %[[ZREF]] : !fir.ref<i32>) for (%[[IVAL]]) : i32
-!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: %[[I_PVT_VAL1:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: omp.reduction %[[I_PVT_VAL1]], %[[XREF]] : !fir.ref<i32>
-!CHECK: %[[I_PVT_VAL2:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: omp.reduction %[[I_PVT_VAL2]], %[[YREF]] : !fir.ref<i32>
-!CHECK: %[[I_PVT_VAL3:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: omp.reduction %[[I_PVT_VAL3]], %[[ZREF]] : !fir.ref<i32>
-!CHECK: omp.yield
-!CHECK: omp.terminator
-!CHECK: return
-
-subroutine multiple_reductions_same_type
- integer :: x,y,z
- x = 0
- y = 0
- z = 0
- !$omp parallel
- !$omp do reduction(+:x,y,z)
- do i=1, 100
- x = x + i
- y = y + i
- z = z + i
- end do
- !$omp end do
- !$omp end parallel
-end subroutine
-
-!CHECK-LABEL: func.func @_QPmultiple_reductions_
diff erent_type
-!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFmultiple_reductions_
diff erent_typeEx"}
-!CHECK: %[[YREF:.*]] = fir.alloca i64 {bindc_name = "y", uniq_name = "_QFmultiple_reductions_
diff erent_typeEy"}
-!CHECK: omp.parallel
-!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
-!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>, @[[RED_I64_NAME]] -> %[[YREF]] : !fir.ref<i64>) for (%[[IVAL:.*]]) : i32
-!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: %[[C1_32:.*]] = arith.constant 1 : i32
-!CHECK: omp.reduction %[[C1_32]], %[[XREF]] : !fir.ref<i32>
-!CHECK: %[[C1_64:.*]] = arith.constant 1 : i64
-!CHECK: omp.reduction %[[C1_64]], %[[YREF]] : !fir.ref<i64>
-!CHECK: omp.yield
-!CHECK: omp.terminator
-!CHECK: return
-
-subroutine multiple_reductions_
diff erent_type
- integer :: x
- integer(kind=8) :: y
- !$omp parallel
- !$omp do reduction(+:x,y)
- do i=1, 100
- x = x + 1_4
- y = y + 1_8
- end do
- !$omp end do
- !$omp end parallel
-end subroutine
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-int-mul.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-int-mul.f90
deleted file mode 100644
index 74245d11acbd8..0000000000000
--- a/flang/test/Lower/OpenMP/wsloop-reduction-int-mul.f90
+++ /dev/null
@@ -1,144 +0,0 @@
-! RUN: bbc -emit-fir -fopenmp %s -o - | FileCheck %s
-! RUN: %flang_fc1 -emit-fir -fopenmp %s -o - | FileCheck %s
-
-!CHECK-LABEL: omp.reduction.declare
-!CHECK-SAME: @[[RED_I64_NAME:.*]] : i64 init {
-!CHECK: ^bb0(%{{.*}}: i64):
-!CHECK: %[[C1_1:.*]] = arith.constant 1 : i64
-!CHECK: omp.yield(%[[C1_1]] : i64)
-!CHECK: } combiner {
-!CHECK: ^bb0(%[[ARG0:.*]]: i64, %[[ARG1:.*]]: i64):
-!CHECK: %[[RES:.*]] = arith.muli %[[ARG0]], %[[ARG1]] : i64
-!CHECK: omp.yield(%[[RES]] : i64)
-!CHECK: }
-
-!CHECK-LABEL: omp.reduction.declare
-!CHECK-SAME: @[[RED_I32_NAME:.*]] : i32 init {
-!CHECK: ^bb0(%{{.*}}: i32):
-!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
-!CHECK: omp.yield(%[[C1_1]] : i32)
-!CHECK: } combiner {
-!CHECK: ^bb0(%[[ARG0:.*]]: i32, %[[ARG1:.*]]: i32):
-!CHECK: %[[RES:.*]] = arith.muli %[[ARG0]], %[[ARG1]] : i32
-!CHECK: omp.yield(%[[RES]] : i32)
-!CHECK: }
-
-!CHECK-LABEL: func.func @_QPsimple_reduction
-!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFsimple_reductionEx"}
-!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
-!CHECK: fir.store %[[C1_2]] to %[[XREF]] : !fir.ref<i32>
-!CHECK: omp.parallel
-!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
-!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
-!CHECK: %[[C10:.*]] = arith.constant 10 : i32
-!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
-!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C10]]) inclusive step (%[[C1_2]])
-!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: %[[I_PVT_VAL:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: omp.reduction %[[I_PVT_VAL]], %[[XREF]] : !fir.ref<i32>
-!CHECK: omp.yield
-!CHECK: omp.terminator
-!CHECK: return
-
-subroutine simple_reduction
- integer :: x
- x = 1
- !$omp parallel
- !$omp do reduction(*:x)
- do i=1, 10
- x = x * i
- end do
- !$omp end do
- !$omp end parallel
-end subroutine
-
-!CHECK-LABEL: func.func @_QPsimple_reduction_switch_order
-!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFsimple_reduction_switch_orderEx"}
-!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
-!CHECK: fir.store %[[C1_2]] to %[[XREF]] : !fir.ref<i32>
-!CHECK: omp.parallel
-!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
-!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
-!CHECK: %[[C10:.*]] = arith.constant 10 : i32
-!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
-!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C10]]) inclusive step (%[[C1_2]])
-!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: %[[I_PVT_VAL:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: omp.reduction %[[I_PVT_VAL]], %[[XREF]] : !fir.ref<i32>
-!CHECK: omp.yield
-!CHECK: omp.terminator
-!CHECK: return
-
-subroutine simple_reduction_switch_order
- integer :: x
- x = 1
- !$omp parallel
- !$omp do reduction(*:x)
- do i=1, 10
- x = i * x
- end do
- !$omp end do
- !$omp end parallel
-end subroutine
-
-!CHECK-LABEL: func.func @_QPmultiple_reductions_same_type
-!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFmultiple_reductions_same_typeEx"}
-!CHECK: %[[YREF:.*]] = fir.alloca i32 {bindc_name = "y", uniq_name = "_QFmultiple_reductions_same_typeEy"}
-!CHECK: %[[ZREF:.*]] = fir.alloca i32 {bindc_name = "z", uniq_name = "_QFmultiple_reductions_same_typeEz"}
-!CHECK: omp.parallel
-!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
-!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>, @[[RED_I32_NAME]] -> %[[YREF]] : !fir.ref<i32>, @[[RED_I32_NAME]] -> %[[ZREF]] : !fir.ref<i32>) for (%[[IVAL]]) : i32
-!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: %[[I_PVT_VAL1:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: omp.reduction %[[I_PVT_VAL1]], %[[XREF]] : !fir.ref<i32>
-!CHECK: %[[I_PVT_VAL2:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: omp.reduction %[[I_PVT_VAL2]], %[[YREF]] : !fir.ref<i32>
-!CHECK: %[[I_PVT_VAL3:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: omp.reduction %[[I_PVT_VAL3]], %[[ZREF]] : !fir.ref<i32>
-!CHECK: omp.yield
-!CHECK: omp.terminator
-!CHECK: return
-
-subroutine multiple_reductions_same_type
- integer :: x,y,z
- x = 1
- y = 1
- z = 1
- !$omp parallel
- !$omp do reduction(*:x,y,z)
- do i=1, 10
- x = x * i
- y = y * i
- z = z * i
- end do
- !$omp end do
- !$omp end parallel
-end subroutine
-
-!CHECK-LABEL: func.func @_QPmultiple_reductions_
diff erent_type
-!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFmultiple_reductions_
diff erent_typeEx"}
-!CHECK: %[[YREF:.*]] = fir.alloca i64 {bindc_name = "y", uniq_name = "_QFmultiple_reductions_
diff erent_typeEy"}
-!CHECK: omp.parallel
-!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
-!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>, @[[RED_I64_NAME]] -> %[[YREF]] : !fir.ref<i64>) for (%[[IVAL:.*]]) : i32
-!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
-!CHECK: %[[C2_32:.*]] = arith.constant 2 : i32
-!CHECK: omp.reduction %[[C2_32]], %[[XREF]] : !fir.ref<i32>
-!CHECK: %[[C2_64:.*]] = arith.constant 2 : i64
-!CHECK: omp.reduction %[[C2_64]], %[[YREF]] : !fir.ref<i64>
-!CHECK: omp.yield
-!CHECK: omp.terminator
-!CHECK: return
-
-subroutine multiple_reductions_
diff erent_type
- integer :: x
- integer(kind=8) :: y
- !$omp parallel
- !$omp do reduction(*:x,y)
- do i=1, 10
- x = x * 2_4
- y = y * 2_8
- end do
- !$omp end do
- !$omp end parallel
-end subroutine
diff --git a/flang/test/Lower/OpenMP/wsloop-reduction-mul.f90 b/flang/test/Lower/OpenMP/wsloop-reduction-mul.f90
new file mode 100644
index 0000000000000..5e1423e6cc836
--- /dev/null
+++ b/flang/test/Lower/OpenMP/wsloop-reduction-mul.f90
@@ -0,0 +1,274 @@
+! RUN: bbc -emit-fir -fopenmp %s -o - | FileCheck %s
+! RUN: %flang_fc1 -emit-fir -fopenmp %s -o - | FileCheck %s
+
+!CHECK-LABEL: omp.reduction.declare
+!CHECK-SAME: @[[RED_F64_NAME:.*]] : f64 init {
+!CHECK: ^bb0(%{{.*}}: f64):
+!CHECK: %[[C0_1:.*]] = arith.constant 1.000000e+00 : f64
+!CHECK: omp.yield(%[[C0_1]] : f64)
+!CHECK: } combiner {
+!CHECK: ^bb0(%[[ARG0:.*]]: f64, %[[ARG1:.*]]: f64):
+!CHECK: %[[RES:.*]] = arith.mulf %[[ARG0]], %[[ARG1]] : f64
+!CHECK: omp.yield(%[[RES]] : f64)
+!CHECK: }
+
+!CHECK-LABEL: omp.reduction.declare
+!CHECK-SAME: @[[RED_I64_NAME:.*]] : i64 init {
+!CHECK: ^bb0(%{{.*}}: i64):
+!CHECK: %[[C1_1:.*]] = arith.constant 1 : i64
+!CHECK: omp.yield(%[[C1_1]] : i64)
+!CHECK: } combiner {
+!CHECK: ^bb0(%[[ARG0:.*]]: i64, %[[ARG1:.*]]: i64):
+!CHECK: %[[RES:.*]] = arith.muli %[[ARG0]], %[[ARG1]] : i64
+!CHECK: omp.yield(%[[RES]] : i64)
+!CHECK: }
+
+!CHECK-LABEL: omp.reduction.declare
+!CHECK-SAME: @[[RED_F32_NAME:.*]] : f32 init {
+!CHECK: ^bb0(%{{.*}}: f32):
+!CHECK: %[[C0_1:.*]] = arith.constant 1.000000e+00 : f32
+!CHECK: omp.yield(%[[C0_1]] : f32)
+!CHECK: } combiner {
+!CHECK: ^bb0(%[[ARG0:.*]]: f32, %[[ARG1:.*]]: f32):
+!CHECK: %[[RES:.*]] = arith.mulf %[[ARG0]], %[[ARG1]] : f32
+!CHECK: omp.yield(%[[RES]] : f32)
+!CHECK: }
+
+!CHECK-LABEL: omp.reduction.declare
+!CHECK-SAME: @[[RED_I32_NAME:.*]] : i32 init {
+!CHECK: ^bb0(%{{.*}}: i32):
+!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
+!CHECK: omp.yield(%[[C1_1]] : i32)
+!CHECK: } combiner {
+!CHECK: ^bb0(%[[ARG0:.*]]: i32, %[[ARG1:.*]]: i32):
+!CHECK: %[[RES:.*]] = arith.muli %[[ARG0]], %[[ARG1]] : i32
+!CHECK: omp.yield(%[[RES]] : i32)
+!CHECK: }
+
+!CHECK-LABEL: func.func @_QPsimple_int_reduction
+!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFsimple_int_reductionEx"}
+!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
+!CHECK: fir.store %[[C1_2]] to %[[XREF]] : !fir.ref<i32>
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
+!CHECK: %[[C10:.*]] = arith.constant 10 : i32
+!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
+!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C10]]) inclusive step (%[[C1_2]])
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL]], %[[XREF]] : !fir.ref<i32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+
+subroutine simple_int_reduction
+ integer :: x
+ x = 1
+ !$omp parallel
+ !$omp do reduction(*:x)
+ do i=1, 10
+ x = x * i
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPsimple_real_reduction
+!CHECK: %[[XREF:.*]] = fir.alloca f32 {bindc_name = "x", uniq_name = "_QFsimple_real_reductionEx"}
+!CHECK: %[[C0_2:.*]] = arith.constant 1.000000e+00 : f32
+!CHECK: fir.store %[[C0_2]] to %[[XREF]] : !fir.ref<f32>
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
+!CHECK: %[[C100:.*]] = arith.constant 10 : i32
+!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
+!CHECK: omp.wsloop reduction(@[[RED_F32_NAME]] -> %[[XREF]] : !fir.ref<f32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C100]]) inclusive step (%[[C1_2]])
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL_i32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL_f32:.*]] = fir.convert %[[I_PVT_VAL_i32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL_f32]], %[[XREF]] : !fir.ref<f32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine simple_real_reduction
+ real :: x
+ x = 1.0
+ !$omp parallel
+ !$omp do reduction(*:x)
+ do i=1, 10
+ x = x * i
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPsimple_int_reduction_switch_order
+!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFsimple_int_reduction_switch_orderEx"}
+!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
+!CHECK: fir.store %[[C1_2]] to %[[XREF]] : !fir.ref<i32>
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
+!CHECK: %[[C10:.*]] = arith.constant 10 : i32
+!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
+!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C10]]) inclusive step (%[[C1_2]])
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL]], %[[XREF]] : !fir.ref<i32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine simple_int_reduction_switch_order
+ integer :: x
+ x = 1
+ !$omp parallel
+ !$omp do reduction(*:x)
+ do i=1, 10
+ x = i * x
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPsimple_real_reduction_switch_order
+!CHECK: %[[XREF:.*]] = fir.alloca f32 {bindc_name = "x", uniq_name = "_QFsimple_real_reduction_switch_orderEx"}
+!CHECK: %[[C0_2:.*]] = arith.constant 1.000000e+00 : f32
+!CHECK: fir.store %[[C0_2]] to %[[XREF]] : !fir.ref<f32>
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: %[[C1_1:.*]] = arith.constant 1 : i32
+!CHECK: %[[C100:.*]] = arith.constant 10 : i32
+!CHECK: %[[C1_2:.*]] = arith.constant 1 : i32
+!CHECK: omp.wsloop reduction(@[[RED_F32_NAME]] -> %[[XREF]] : !fir.ref<f32>) for (%[[IVAL:.*]]) : i32 = (%[[C1_1]]) to (%[[C100]]) inclusive step (%[[C1_2]])
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL_i32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL_f32:.*]] = fir.convert %[[I_PVT_VAL_i32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL_f32]], %[[XREF]] : !fir.ref<f32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine simple_real_reduction_switch_order
+ real :: x
+ x = 1.0
+ !$omp parallel
+ !$omp do reduction(*:x)
+ do i=1, 10
+ x = i * x
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPmultiple_int_reductions_same_type
+!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFmultiple_int_reductions_same_typeEx"}
+!CHECK: %[[YREF:.*]] = fir.alloca i32 {bindc_name = "y", uniq_name = "_QFmultiple_int_reductions_same_typeEy"}
+!CHECK: %[[ZREF:.*]] = fir.alloca i32 {bindc_name = "z", uniq_name = "_QFmultiple_int_reductions_same_typeEz"}
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %[[XREF]] : !fir.ref<i32>, @[[RED_I32_NAME]] -> %[[YREF]] : !fir.ref<i32>, @[[RED_I32_NAME]] -> %[[ZREF]] : !fir.ref<i32>) for (%[[IVAL]]) : i32
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL1:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL1]], %[[XREF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL2:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL2]], %[[YREF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL3:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL3]], %[[ZREF]] : !fir.ref<i32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine multiple_int_reductions_same_type
+ integer :: x,y,z
+ x = 1
+ y = 1
+ z = 1
+ !$omp parallel
+ !$omp do reduction(*:x,y,z)
+ do i=1, 10
+ x = x * i
+ y = y * i
+ z = z * i
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPmultiple_real_reductions_same_type
+!CHECK: %[[XREF:.*]] = fir.alloca f32 {bindc_name = "x", uniq_name = "_QFmultiple_real_reductions_same_typeEx"}
+!CHECK: %[[YREF:.*]] = fir.alloca f32 {bindc_name = "y", uniq_name = "_QFmultiple_real_reductions_same_typeEy"}
+!CHECK: %[[ZREF:.*]] = fir.alloca f32 {bindc_name = "z", uniq_name = "_QFmultiple_real_reductions_same_typeEz"}
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: omp.wsloop reduction(@[[RED_F32_NAME]] -> %[[XREF]] : !fir.ref<f32>, @[[RED_F32_NAME]] -> %[[YREF]] : !fir.ref<f32>, @[[RED_F32_NAME]] -> %[[ZREF]] : !fir.ref<f32>) for (%[[IVAL]]) : i32
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL1_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL1_F32:.*]] = fir.convert %[[I_PVT_VAL1_I32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL1_F32]], %[[XREF]] : !fir.ref<f32>
+!CHECK: %[[I_PVT_VAL2_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL2_F32:.*]] = fir.convert %[[I_PVT_VAL2_I32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL2_F32]], %[[YREF]] : !fir.ref<f32>
+!CHECK: %[[I_PVT_VAL3_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL3_F32:.*]] = fir.convert %[[I_PVT_VAL3_I32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL3_F32]], %[[ZREF]] : !fir.ref<f32>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine multiple_real_reductions_same_type
+ real :: x,y,z
+ x = 1
+ y = 1
+ z = 1
+ !$omp parallel
+ !$omp do reduction(*:x,y,z)
+ do i=1, 10
+ x = x * i
+ y = y * i
+ z = z * i
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
+
+!CHECK-LABEL: func.func @_QPmultiple_reductions_
diff erent_type
+!CHECK: %[[WREF:.*]] = fir.alloca f64 {bindc_name = "w", uniq_name = "_QFmultiple_reductions_
diff erent_typeEw"}
+!CHECK: %[[XREF:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFmultiple_reductions_
diff erent_typeEx"}
+!CHECK: %[[YREF:.*]] = fir.alloca i64 {bindc_name = "y", uniq_name = "_QFmultiple_reductions_
diff erent_typeEy"}
+!CHECK: %[[ZREF:.*]] = fir.alloca f32 {bindc_name = "z", uniq_name = "_QFmultiple_reductions_
diff erent_typeEz"}
+!CHECK: omp.parallel
+!CHECK: %[[I_PVT_REF:.*]] = fir.alloca i32 {adapt.valuebyref, pinned}
+!CHECK: omp.wsloop reduction(@[[RED_I32_NAME]] -> %2 : !fir.ref<i32>, @[[RED_I64_NAME]] -> %3 : !fir.ref<i64>, @[[RED_F32_NAME]] -> %4 : !fir.ref<f32>, @[[RED_F64_NAME]] -> %1 : !fir.ref<f64>) for (%[[IVAL:.*]]) : i32
+!CHECK: fir.store %[[IVAL]] to %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL1_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: omp.reduction %[[I_PVT_VAL1_I32]], %[[XREF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL2_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL2_I64:.*]] = fir.convert %[[I_PVT_VAL2_I32]] : (i32) -> i64
+!CHECK: omp.reduction %[[I_PVT_VAL2_I64]], %[[YREF]] : !fir.ref<i64>
+!CHECK: %[[I_PVT_VAL3_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL3_F32:.*]] = fir.convert %[[I_PVT_VAL3_I32]] : (i32) -> f32
+!CHECK: omp.reduction %[[I_PVT_VAL3_F32]], %[[ZREF]] : !fir.ref<f32>
+!CHECK: %[[I_PVT_VAL4_I32:.*]] = fir.load %[[I_PVT_REF]] : !fir.ref<i32>
+!CHECK: %[[I_PVT_VAL4_F64:.*]] = fir.convert %[[I_PVT_VAL4_I32]] : (i32) -> f64
+!CHECK: omp.reduction %[[I_PVT_VAL4_F64]], %[[WREF]] : !fir.ref<f64>
+!CHECK: omp.yield
+!CHECK: omp.terminator
+!CHECK: return
+subroutine multiple_reductions_
diff erent_type
+ integer :: x
+ integer(kind=8) :: y
+ real :: z
+ real(kind=8) :: w
+ x = 1
+ y = 1
+ z = 1
+ w = 1
+ !$omp parallel
+ !$omp do reduction(*:x,y,z,w)
+ do i=1, 10
+ x = x * i
+ y = y * i
+ z = z * i
+ w = w * i
+ end do
+ !$omp end do
+ !$omp end parallel
+end subroutine
More information about the flang-commits
mailing list