[llvm][mlir][OpenMP] Support translation for linear clause in omp.wsloop and omp.simd (llvm#139386)

This patch adds support for LLVM translation of linear clause on
omp.wsloop (except for linear modifiers).

Author: NimishMishra

flang/lib/Lower/OpenMP/ClauseProcessor.cpp

@@ -1235,6 +1235,49 @@ 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);
+    static std::vector<mlir::Attribute> typeAttrs;
+
+    if (!result.linearVars.size())
+      typeAttrs.clear();
+
+    for (const omp::Object &object : objects) {
+      semantics::Symbol *sym = object.sym();
+      const mlir::Value variable = converter.getSymbolAddress(*sym);
+      result.linearVars.push_back(variable);
+      mlir::Type ty = converter.genType(*sym);
+      typeAttrs.push_back(mlir::TypeAttr::get(ty));
+    }
+    result.linearVarTypes =
+        mlir::ArrayAttr::get(&converter.getMLIRContext(), typeAttrs);
+    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<DeclareTargetCaptureInfo> &result) const {
   return findRepeatableClause<omp::clause::Link>(

flang/lib/Lower/OpenMP/ClauseProcessor.h

@@ -130,6 +130,7 @@ class ClauseProcessor {
   processEnter(llvm::SmallVectorImpl<DeclareTargetCaptureInfo> &result) const;
   bool processIf(omp::clause::If::DirectiveNameModifier directiveName,
                  mlir::omp::IfClauseOps &result) const;
+  bool processLinear(mlir::omp::LinearClauseOps &result) const;
   bool processInReduction(
       mlir::Location currentLocation, mlir::omp::InReductionClauseOps &result,
       llvm::SmallVectorImpl<const semantics::Symbol *> &outReductionSyms) const;

flang/lib/Lower/OpenMP/OpenMP.cpp

@@ -1642,8 +1642,7 @@ static void genSimdClauses(
   cp.processReduction(loc, clauseOps, reductionSyms);
   cp.processSafelen(clauseOps);
   cp.processSimdlen(clauseOps);
-
-  cp.processTODO<clause::Linear>(loc, llvm::omp::Directive::OMPD_simd);
+  cp.processLinear(clauseOps);
 }
 
 static void genSingleClauses(lower::AbstractConverter &converter,
@@ -1839,9 +1838,9 @@ static void genWsloopClauses(
   cp.processOrdered(clauseOps);
   cp.processReduction(loc, clauseOps, reductionSyms);
   cp.processSchedule(stmtCtx, clauseOps);
+  cp.processLinear(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/Todo/omp-do-simd-linear.f90

@@ -0,0 +1,57 @@
+! This test checks lowering of OpenMP SIMD Directive
+! 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.simd linear(%[[X]]#0 = %[[const]] : !fir.ref<i32>) {{.*}}
+    !$omp simd linear(x)
+    !CHECK: %[[LOAD:.*]] = fir.load %[[X]]#0 : !fir.ref<i32>
+    !CHECK: %[[const:.*]] = arith.constant 2 : i32
+    !CHECK: %[[RESULT:.*]] = arith.addi %[[LOAD]], %[[const]] : i32
+    do i = 1, 10
+        y = x + 2
+    end do
+    !CHECK: } {linear_var_types = [i32]}
+end subroutine
+
+
+!CHECK: %[[X_alloca:.*]] = fir.alloca i32 {bindc_name = "x", uniq_name = "_QFlinear_stepEx"}
+!CHECK: %[[X:.*]]:2 = hlfir.declare %[[X_alloca]] {uniq_name = "_QFlinear_stepEx"} : (!fir.ref<i32>) -> (!fir.ref<i32>, !fir.ref<i32>)
+subroutine linear_step
+    implicit none
+    integer :: x, y, i
+    !CHECK: %[[const:.*]] = arith.constant 4 : i32
+    !CHECK: omp.simd linear(%[[X]]#0 = %[[const]] : !fir.ref<i32>) {{.*}}
+    !$omp simd 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
+    !CHECK: } {linear_var_types = [i32]}
+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.simd linear(%[[X]]#0 = %[[LINEAR_EXPR]] : !fir.ref<i32>) {{.*}}
+    !$omp simd linear(x:a+4)
+    do i = 1, 10
+        y = x + 2
+    end do
+    !CHECK: } {linear_var_types = [i32]}
+end subroutine

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

@@ -1,6 +1,6 @@
 ! This test checks lowering of OpenMP DO Directive (Worksharing)
 ! with linear clause
-! XFAIL: *
+
 ! 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"}
@@ -18,6 +18,7 @@ subroutine simple_linear
         y = x + 2
     end do
     !$omp end do
+    !CHECK: } {linear_var_types = [i32]}
 end subroutine
 
 
@@ -31,11 +32,12 @@ subroutine linear_step
     !$omp do linear(x:4)
     !CHECK: %[[LOAD:.*]] = fir.load %[[X]]#0 : !fir.ref<i32>
     !CHECK: %[[const:.*]] = arith.constant 2 : i32
-    !CHECK: %[[RESULT:.*]] = arith.addi %[[LOAD]], %[[const]] : i32   
+    !CHECK: %[[RESULT:.*]] = arith.addi %[[LOAD]], %[[const]] : i32
     do i = 1, 10
         y = x + 2
     end do
     !$omp end do
+    !CHECK: } {linear_var_types = [i32]}
 end subroutine
 
 !CHECK: %[[A_alloca:.*]] = fir.alloca i32 {bindc_name = "a", uniq_name = "_QFlinear_exprEa"}
@@ -54,4 +56,5 @@ subroutine linear_expr
         y = x + 2
     end do
     !$omp end do
+    !CHECK: } {linear_var_types = [i32]}
 end subroutine

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

@@ -22,6 +22,7 @@
 include "mlir/Dialect/OpenMP/OpenMPOpBase.td"
 include "mlir/Interfaces/SideEffectInterfaces.td"
 include "mlir/IR/SymbolInterfaces.td"
+include "mlir/IR/BuiltinAttributes.td"
 
 //===----------------------------------------------------------------------===//
 // V5.2: [6.3] `align` clause
@@ -776,10 +777,9 @@ class OpenMP_LinearClauseSkip<
     bit description = false, bit extraClassDeclaration = false
   > : OpenMP_Clause<traits, arguments, assemblyFormat, description,
                     extraClassDeclaration> {
-  let arguments = (ins
-    Variadic<AnyType>:$linear_vars,
-    Variadic<I32>:$linear_step_vars
-  );
+  let arguments = (ins Variadic<AnyType>:$linear_vars,
+      Variadic<I32>:$linear_step_vars,
+      OptionalAttr<ArrayAttr>:$linear_var_types);
 
   let optAssemblyFormat = [{
     `linear` `(`

mlir/include/mlir/Dialect/OpenMP/OpenMPClauses.td

@@ -2862,6 +2862,7 @@ void WsloopOp::build(OpBuilder &builder, OperationState &state,
                      ArrayRef<NamedAttribute> attributes) {
   build(builder, state, /*allocate_vars=*/{}, /*allocator_vars=*/{},
         /*linear_vars=*/ValueRange(), /*linear_step_vars=*/ValueRange(),
+        /*linear_var_types*/ nullptr,
         /*nowait=*/false, /*order=*/nullptr, /*order_mod=*/nullptr,
         /*ordered=*/nullptr, /*private_vars=*/{}, /*private_syms=*/nullptr,
         /*private_needs_barrier=*/false,
@@ -2880,8 +2881,8 @@ void WsloopOp::build(OpBuilder &builder, OperationState &state,
   WsloopOp::build(
       builder, state,
       /*allocate_vars=*/{}, /*allocator_vars=*/{}, clauses.linearVars,
-      clauses.linearStepVars, clauses.nowait, clauses.order, clauses.orderMod,
-      clauses.ordered, clauses.privateVars,
+      clauses.linearStepVars, clauses.linearVarTypes, clauses.nowait,
+      clauses.order, clauses.orderMod, clauses.ordered, clauses.privateVars,
       makeArrayAttr(ctx, clauses.privateSyms), clauses.privateNeedsBarrier,
       clauses.reductionMod, clauses.reductionVars,
       makeDenseBoolArrayAttr(ctx, clauses.reductionByref),
@@ -2926,17 +2927,16 @@ LogicalResult WsloopOp::verifyRegions() {
 void SimdOp::build(OpBuilder &builder, OperationState &state,
                    const SimdOperands &clauses) {
   MLIRContext *ctx = builder.getContext();
-  // TODO Store clauses in op: linearVars, linearStepVars
-  SimdOp::build(builder, state, clauses.alignedVars,
-                makeArrayAttr(ctx, clauses.alignments), clauses.ifExpr,
-                /*linear_vars=*/{}, /*linear_step_vars=*/{},
-                clauses.nontemporalVars, clauses.order, clauses.orderMod,
-                clauses.privateVars, makeArrayAttr(ctx, clauses.privateSyms),
-                clauses.privateNeedsBarrier, clauses.reductionMod,
-                clauses.reductionVars,
-                makeDenseBoolArrayAttr(ctx, clauses.reductionByref),
-                makeArrayAttr(ctx, clauses.reductionSyms), clauses.safelen,
-                clauses.simdlen);
+  SimdOp::build(
+      builder, state, clauses.alignedVars,
+      makeArrayAttr(ctx, clauses.alignments), clauses.ifExpr,
+      clauses.linearVars, clauses.linearStepVars, clauses.linearVarTypes,
+      clauses.nontemporalVars, clauses.order, clauses.orderMod,
+      clauses.privateVars, makeArrayAttr(ctx, clauses.privateSyms),
+      clauses.privateNeedsBarrier, clauses.reductionMod, clauses.reductionVars,
+      makeDenseBoolArrayAttr(ctx, clauses.reductionByref),
+      makeArrayAttr(ctx, clauses.reductionSyms), clauses.safelen,
+      clauses.simdlen);
 }
 
 LogicalResult SimdOp::verify() {