[flang][OpenMP] Support MLIR lowering of linear clause for omp.wsloop

Author: NimishMishra

flang/lib/Lower/OpenMP/ClauseProcessor.cpp

@@ -1060,6 +1060,40 @@ bool ClauseProcessor::processIsDevicePtr(
       });
 }
 
+bool ClauseProcessor::processLinear(mlir::omp::LinearClauseOps &result) const {
+  lower::StatementContext stmtCtx;
+  return findRepeatableClause<
+      omp::clause::Linear>([&](const omp::clause::Linear &clause,
+                               const parser::CharBlock &) {
+    auto &objects = std::get<omp::ObjectList>(clause.t);
+    for (const omp::Object &object : objects) {
+      semantics::Symbol *sym = object.sym();
+      const mlir::Value variable = converter.getSymbolAddress(*sym);
+      result.linearVars.push_back(variable);
+    }
+    if (objects.size()) {
+      if (auto &mod =
+              std::get<std::optional<omp::clause::Linear::StepComplexModifier>>(
+                  clause.t)) {
+        mlir::Value operand =
+            fir::getBase(converter.genExprValue(toEvExpr(*mod), stmtCtx));
+        result.linearStepVars.append(objects.size(), operand);
+      } else if (std::get<std::optional<omp::clause::Linear::LinearModifier>>(
+                     clause.t)) {
+        mlir::Location currentLocation = converter.getCurrentLocation();
+        TODO(currentLocation, "Linear modifiers not yet implemented");
+      } else {
+        // If nothing is present, add the default step of 1.
+        fir::FirOpBuilder &firOpBuilder = converter.getFirOpBuilder();
+        mlir::Location currentLocation = converter.getCurrentLocation();
+        mlir::Value operand = firOpBuilder.createIntegerConstant(
+            currentLocation, firOpBuilder.getI32Type(), 1);
+        result.linearStepVars.append(objects.size(), operand);
+      }
+    }
+  });
+}
+
 bool ClauseProcessor::processLink(
     llvm::SmallVectorImpl<DeclareTargetCapturePair> &result) const {
   return findRepeatableClause<omp::clause::Link>(

flang/lib/Lower/OpenMP/ClauseProcessor.h

@@ -122,6 +122,7 @@ class ClauseProcessor {
   bool processIsDevicePtr(
       mlir::omp::IsDevicePtrClauseOps &result,
       llvm::SmallVectorImpl<const semantics::Symbol *> &isDeviceSyms) const;
+  bool processLinear(mlir::omp::LinearClauseOps &result) const;
   bool
   processLink(llvm::SmallVectorImpl<DeclareTargetCapturePair> &result) const;
 

flang/lib/Lower/OpenMP/DataSharingProcessor.cpp

@@ -213,14 +213,15 @@ void DataSharingProcessor::collectSymbolsForPrivatization() {
   // so, we won't need to explicitely handle block objects (or forget to do
   // so).
   for (auto *sym : explicitlyPrivatizedSymbols)
-    allPrivatizedSymbols.insert(sym);
+    if (!sym->test(Fortran::semantics::Symbol::Flag::OmpLinear))
+      allPrivatizedSymbols.insert(sym);
 }
 
 bool DataSharingProcessor::needBarrier() {
   // Emit implicit barrier to synchronize threads and avoid data races on
   // initialization of firstprivate variables and post-update of lastprivate
   // variables.
-  // Emit implicit barrier for linear clause. Maybe on somewhere else.
+  // Emit implicit barrier for linear clause in the OpenMPIRBuilder.
   for (const semantics::Symbol *sym : allPrivatizedSymbols) {
     if (sym->test(semantics::Symbol::Flag::OmpLastPrivate) &&
         (sym->test(semantics::Symbol::Flag::OmpFirstPrivate) ||

flang/lib/Lower/OpenMP/OpenMP.cpp

@@ -1841,13 +1841,13 @@ static void genWsloopClauses(
     llvm::SmallVectorImpl<const semantics::Symbol *> &reductionSyms) {
   ClauseProcessor cp(converter, semaCtx, clauses);
   cp.processNowait(clauseOps);
+  cp.processLinear(clauseOps);
   cp.processOrder(clauseOps);
   cp.processOrdered(clauseOps);
   cp.processReduction(loc, clauseOps, reductionSyms);
   cp.processSchedule(stmtCtx, clauseOps);
 
-  cp.processTODO<clause::Allocate, clause::Linear>(
-      loc, llvm::omp::Directive::OMPD_do);
+  cp.processTODO<clause::Allocate>(loc, llvm::omp::Directive::OMPD_do);
 }
 
 //===----------------------------------------------------------------------===//

flang/test/Lower/OpenMP/wsloop-linear.f90

@@ -0,0 +1,57 @@
+! This test checks lowering of OpenMP DO Directive (Worksharing)
+! with linear clause
+
+! RUN: %flang_fc1 -fopenmp -emit-hlfir %s -o - 2>&1 | FileCheck %s
+
+!CHECK: %[[X_alloca:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFsimple_linearEx"}
+!CHECK: %[[X:.*]]:2 = hlfir.declare %[[X_alloca]] {uniq_name = "_QFsimple_linearEx"} : (!fir.ref<i32>) -> (!fir.ref<i32>, !fir.ref<i32>)
+!CHECK: %[[const:.*]] = arith.constant 1 : i32
+subroutine simple_linear
+    implicit none
+    integer :: x, y, i
+    !CHECK: omp.wsloop linear(%[[X]]#0 = %[[const]] : !fir.ref<i32>) {{.*}}
+    !$omp do linear(x)
+    !CHECK: %[[LOAD:.*]] = fir.load %[[X]]#0 : !fir.ref<i32>
+    !CHECK: %[[const:.*]] = arith.constant 2 : i32
+    !CHECK: %[[RESULT:.*]] = arith.addi %[[LOAD]], %[[const]] : i32
+    do i = 1, 10
+        y = x + 2
+    end do
+    !$omp end do
+end subroutine
+
+
+!CHECK: %[[X_alloca:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFlinear_stepEx"}
+!CHECK: %[[X:.*]]:2 = hlfir.declare %[[X_alloca]] {uniq_name = "_QFlinear_stepEx"} : (!fir.ref<i32>) -> (!fir.ref<i32>, !fir.ref<i32>)
+subroutine linear_step
+    implicit none
+    integer :: x, y, i
+    !CHECK: %[[const:.*]] = arith.constant 4 : i32
+    !CHECK: omp.wsloop linear(%[[X]]#0 = %[[const]] : !fir.ref<i32>) {{.*}}
+    !$omp do linear(x:4)
+    !CHECK: %[[LOAD:.*]] = fir.load %[[X]]#0 : !fir.ref<i32>
+    !CHECK: %[[const:.*]] = arith.constant 2 : i32
+    !CHECK: %[[RESULT:.*]] = arith.addi %[[LOAD]], %[[const]] : i32   
+    do i = 1, 10
+        y = x + 2
+    end do
+    !$omp end do
+end subroutine
+
+!CHECK: %[[A_alloca:.*]] = fir.alloca i32 {bindc_name = "a", uniq_name = "_QFlinear_exprEa"}
+!CHECK: %[[A:.*]]:2 = hlfir.declare %[[A_alloca]] {uniq_name = "_QFlinear_exprEa"} : (!fir.ref<i32>) -> (!fir.ref<i32>, !fir.ref<i32>)
+!CHECK: %[[X_alloca:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFlinear_exprEx"}
+!CHECK: %[[X:.*]]:2 = hlfir.declare %[[X_alloca]] {uniq_name = "_QFlinear_exprEx"} : (!fir.ref<i32>) -> (!fir.ref<i32>, !fir.ref<i32>)
+subroutine linear_expr
+    implicit none
+    integer :: x, y, i, a
+    !CHECK: %[[LOAD_A:.*]] = fir.load %[[A]]#0 : !fir.ref<i32>
+    !CHECK: %[[const:.*]] = arith.constant 4 : i32
+    !CHECK: %[[LINEAR_EXPR:.*]] = arith.addi %[[LOAD_A]], %[[const]] : i32
+    !CHECK: omp.wsloop linear(%[[X]]#0 = %[[LINEAR_EXPR]] : !fir.ref<i32>) {{.*}}
+    !$omp do linear(x:a+4)
+    do i = 1, 10
+        y = x + 2
+    end do
+    !$omp end do
+end subroutine