[flang][acc] Ensure all acc.loop get a default parallelism mode

This PR updates the flang lowering to explicitly implement the OpenACC
rules:
 - As per OpenACC 3.3 standard section 2.9.6 independent clause:
   A loop construct with no auto or seq clause is treated as if it has
   the independent clause when it is an orphaned loop construct or its
   parent compute construct is a parallel construct.
 - As per OpenACC 3.3 standard section 2.9.7 auto clause:
   When the parent compute construct is a kernels construct, a loop
   construct with no independent or seq clause is treated as if it has
   the auto clause.
 - Loops in serial regions are `seq` if they have no other parallelism
   marking such as gang, worker, vector.

For now the `acc.loop` verifier has not yet been updated to enforce
this.

Author: Razvan Lupusoru

flang/lib/Lower/OpenACC.cpp

@@ -2150,6 +2150,60 @@ privatizeIv(Fortran::lower::AbstractConverter &converter,
   ivPrivate.push_back(privateValue);
 }
 
+static void determineDefaultLoopParMode(
+    Fortran::lower::AbstractConverter &converter, mlir::acc::LoopOp &loopOp,
+    llvm::SmallVector<mlir::Attribute> &seqDeviceTypes,
+    llvm::SmallVector<mlir::Attribute> &independentDeviceTypes,
+    llvm::SmallVector<mlir::Attribute> &autoDeviceTypes) {
+  auto hasDeviceNone = [](mlir::Attribute attr) -> bool {
+    return mlir::dyn_cast<mlir::acc::DeviceTypeAttr>(attr).getValue() ==
+           mlir::acc::DeviceType::None;
+  };
+  bool hasDefaultSeq = llvm::any_of(seqDeviceTypes, hasDeviceNone);
+  bool hasDefaultIndependent =
+      llvm::any_of(independentDeviceTypes, hasDeviceNone);
+  bool hasDefaultAuto = llvm::any_of(autoDeviceTypes, hasDeviceNone);
+  if (hasDefaultSeq || hasDefaultIndependent || hasDefaultAuto)
+    return; // Default loop par mode is already specified.
+
+  mlir::Region *currentRegion =
+      converter.getFirOpBuilder().getBlock()->getParent();
+  mlir::Operation *parentOp = mlir::acc::getEnclosingComputeOp(*currentRegion);
+  const bool isOrphanedLoop = !parentOp;
+  if (isOrphanedLoop ||
+      mlir::isa_and_present<mlir::acc::ParallelOp>(parentOp)) {
+    // As per OpenACC 3.3 standard section 2.9.6 independent clause:
+    // A loop construct with no auto or seq clause is treated as if it has the
+    // independent clause when it is an orphaned loop construct or its parent
+    // compute construct is a parallel construct.
+    independentDeviceTypes.push_back(mlir::acc::DeviceTypeAttr::get(
+        converter.getFirOpBuilder().getContext(), mlir::acc::DeviceType::None));
+  } else if (mlir::isa_and_present<mlir::acc::SerialOp>(parentOp)) {
+    // Serial construct implies `seq` clause on loop. However, this
+    // conflicts with parallelism assignment if already set. Therefore check
+    // that first.
+    bool hasDefaultGangWorkerOrVector =
+        loopOp.hasVector() || loopOp.getVectorValue() || loopOp.hasWorker() ||
+        loopOp.getWorkerValue() || loopOp.hasGang() ||
+        loopOp.getGangValue(mlir::acc::GangArgType::Num) ||
+        loopOp.getGangValue(mlir::acc::GangArgType::Dim) ||
+        loopOp.getGangValue(mlir::acc::GangArgType::Static);
+    if (!hasDefaultGangWorkerOrVector)
+      seqDeviceTypes.push_back(mlir::acc::DeviceTypeAttr::get(
+          converter.getFirOpBuilder().getContext(),
+          mlir::acc::DeviceType::None));
+  } else {
+    // As per OpenACC 3.3 standard section 2.9.7 auto clause:
+    // When the parent compute construct is a kernels construct, a loop
+    // construct with no independent or seq clause is treated as if it has the
+    // auto clause.
+    assert(mlir::isa_and_present<mlir::acc::KernelsOp>(parentOp) &&
+           "Expected kernels construct");
+    autoDeviceTypes.push_back(mlir::acc::DeviceTypeAttr::get(
+        converter.getFirOpBuilder().getContext(), mlir::acc::DeviceType::None));
+  }
+}
+
 static mlir::acc::LoopOp createLoopOp(
     Fortran::lower::AbstractConverter &converter,
     mlir::Location currentLocation,
@@ -2482,6 +2536,9 @@ static mlir::acc::LoopOp createLoopOp(
     loopOp.setTileOperandsSegmentsAttr(
         builder.getDenseI32ArrayAttr(tileOperandsSegments));
 
+  // Determine the loop's default par mode - either seq, independent, or auto.
+  determineDefaultLoopParMode(converter, loopOp, seqDeviceTypes,
+                              independentDeviceTypes, autoDeviceTypes);
   if (!seqDeviceTypes.empty())
     loopOp.setSeqAttr(builder.getArrayAttr(seqDeviceTypes));
   if (!independentDeviceTypes.empty())

flang/test/Lower/OpenACC/acc-kernels-loop.f90

@@ -47,7 +47,7 @@ subroutine acc_kernels_loop
 ! CHECK:      acc.kernels {
 ! CHECK:        acc.loop private{{.*}} {
 ! CHECK:          acc.yield
-! CHECK-NEXT:   }{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>]{{.*}}}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -59,7 +59,7 @@ subroutine acc_kernels_loop
 ! CHECK:      acc.kernels combined(loop) {
 ! CHECK:        acc.loop combined(kernels) private{{.*}} {
 ! CHECK:          acc.yield
-! CHECK-NEXT:   }{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>]{{.*}}}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -490,7 +490,7 @@ subroutine acc_kernels_loop
 ! CHECK:      acc.kernels {{.*}} {
 ! CHECK:        acc.loop {{.*}} gang {{.*}} {
 ! CHECK:          acc.yield
-! CHECK-NEXT:   } attributes {inclusiveUpperbound = array<i1: true>}{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>], inclusiveUpperbound = array<i1: true>}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -503,7 +503,7 @@ subroutine acc_kernels_loop
 ! CHECK:        [[GANGNUM1:%.*]] = arith.constant 8 : i32
 ! CHECK:        acc.loop {{.*}} gang({num=[[GANGNUM1]] : i32}) {{.*}} {
 ! CHECK:          acc.yield
-! CHECK-NEXT:   }{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>], inclusiveUpperbound = array<i1: true>}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -516,7 +516,7 @@ subroutine acc_kernels_loop
 ! CHECK:        [[GANGNUM2:%.*]] = fir.load %{{.*}} : !fir.ref<i32>
 ! CHECK:        acc.loop {{.*}} gang({num=[[GANGNUM2]] : i32}) {{.*}} {
 ! CHECK:          acc.yield
-! CHECK-NEXT:   }{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>], inclusiveUpperbound = array<i1: true>}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -528,7 +528,7 @@ subroutine acc_kernels_loop
 ! CHECK:      acc.kernels {{.*}} {
 ! CHECK:        acc.loop {{.*}} gang({num=%{{.*}} : i32, static=%{{.*}} : i32})
 ! CHECK:          acc.yield
-! CHECK-NEXT:   }{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>], inclusiveUpperbound = array<i1: true>}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -540,7 +540,7 @@ subroutine acc_kernels_loop
 ! CHECK:      acc.kernels {{.*}} {
 ! CHECK:        acc.loop {{.*}} vector {{.*}} {
 ! CHECK:          acc.yield
-! CHECK-NEXT:   } attributes {inclusiveUpperbound = array<i1: true>}{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>], inclusiveUpperbound = array<i1: true>}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -553,7 +553,7 @@ subroutine acc_kernels_loop
 ! CHECK:        [[CONSTANT128:%.*]] = arith.constant 128 : i32
 ! CHECK:        acc.loop {{.*}} vector([[CONSTANT128]] : i32) {{.*}} {
 ! CHECK:          acc.yield
-! CHECK-NEXT:   }{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>], inclusiveUpperbound = array<i1: true>}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -566,7 +566,7 @@ subroutine acc_kernels_loop
 ! CHECK:        [[VECTORLENGTH:%.*]] = fir.load %{{.*}} : !fir.ref<i32>
 ! CHECK:        acc.loop {{.*}} vector([[VECTORLENGTH]] : i32) {{.*}} {
 ! CHECK:          acc.yield
-! CHECK-NEXT:   }{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>], inclusiveUpperbound = array<i1: true>}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -578,7 +578,7 @@ subroutine acc_kernels_loop
 ! CHECK:      acc.kernels {{.*}} {
 ! CHECK:        acc.loop {{.*}} worker {{.*}} {
 ! CHECK:          acc.yield
-! CHECK-NEXT:   } attributes {inclusiveUpperbound = array<i1: true>}{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>], inclusiveUpperbound = array<i1: true>}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -591,7 +591,7 @@ subroutine acc_kernels_loop
 ! CHECK:        [[WORKER128:%.*]] = arith.constant 128 : i32
 ! CHECK:        acc.loop {{.*}} worker([[WORKER128]] : i32) {{.*}} {
 ! CHECK:          acc.yield
-! CHECK-NEXT:   }{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>], inclusiveUpperbound = array<i1: true>}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -605,7 +605,7 @@ subroutine acc_kernels_loop
 ! CHECK:      acc.kernels {{.*}} {
 ! CHECK:        acc.loop {{.*}} {
 ! CHECK:          acc.yield
-! CHECK-NEXT:   } attributes {collapse = [2], collapseDeviceType = [#acc.device_type<none>], inclusiveUpperbound = array<i1: true, true>}
+! CHECK-NEXT:   } attributes {{{.*}}collapse = [2], collapseDeviceType = [#acc.device_type<none>]{{.*}}}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}
 
@@ -621,9 +621,9 @@ subroutine acc_kernels_loop
 ! CHECK:        acc.loop {{.*}} {
 ! CHECK:            acc.loop {{.*}} {
 ! CHECK:              acc.yield
-! CHECK-NEXT:     }{{$}}
+! CHECK-NEXT:     } attributes {auto_ = [#acc.device_type<none>]{{.*}}}
 ! CHECK:          acc.yield
-! CHECK-NEXT:   }{{$}}
+! CHECK-NEXT:   } attributes {auto_ = [#acc.device_type<none>]{{.*}}}
 ! CHECK:        acc.terminator
 ! CHECK-NEXT: }{{$}}