[acc] acc.loop verifier now requires parallelism determination flag (#143720)

The OpenACC specification for `acc loop` describe that a loop's
parallelism determination mode is either auto, independent, or seq. The
rules are as follows.
- 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.
- Additionally, loops marked with gang, worker, or vector are not
guaranteed to be parallel. Specifically noted in 2.9.7 auto clause: If
not, or if it is unable to make a determination, it must treat the auto
clause as if it is a seq clause, and it must ignore any gang, worker, or
vector clauses on the loop construct.

The verifier for `acc.loop` was updated to enforce this marking because
the context in which a loop appears is not trivially determined once IR
transformations begin. For example, orphaned loops are implicitly
`independent`, but after inlining into an `acc.kernels` region they
would be implicitly considered `auto`. Thus now the verifier requires
that a frontend specifically generates acc dialect with this marking
since it knows the context.

Author: razvanlupusoru

mlir/lib/Dialect/OpenACC/IR/OpenACC.cpp

@@ -2461,10 +2461,34 @@ LogicalResult acc::LoopOp::verify() {
   if (hasDuplicateDeviceTypes(getAuto_(), deviceTypes) ||
       hasDuplicateDeviceTypes(getIndependent(), deviceTypes) ||
       hasDuplicateDeviceTypes(getSeq(), deviceTypes)) {
-    return emitError() << "only one of \"" << acc::LoopOp::getAutoAttrStrName()
-                       << "\", " << getIndependentAttrName() << ", "
-                       << getSeqAttrName()
-                       << " can be present at the same time";
+    return emitError() << "only one of auto, independent, seq can be present "
+                          "at the same time";
+  }
+
+  // Check that at least one of auto, independent, or seq is present
+  // for the device-independent default clauses.
+  auto hasDeviceNone = [](mlir::acc::DeviceTypeAttr attr) -> bool {
+    return attr.getValue() == mlir::acc::DeviceType::None;
+  };
+  bool hasDefaultSeq =
+      getSeqAttr()
+          ? llvm::any_of(getSeqAttr().getAsRange<mlir::acc::DeviceTypeAttr>(),
+                         hasDeviceNone)
+          : false;
+  bool hasDefaultIndependent =
+      getIndependentAttr()
+          ? llvm::any_of(
+                getIndependentAttr().getAsRange<mlir::acc::DeviceTypeAttr>(),
+                hasDeviceNone)
+          : false;
+  bool hasDefaultAuto =
+      getAuto_Attr()
+          ? llvm::any_of(getAuto_Attr().getAsRange<mlir::acc::DeviceTypeAttr>(),
+                         hasDeviceNone)
+          : false;
+  if (!hasDefaultSeq && !hasDefaultIndependent && !hasDefaultAuto) {
+    return emitError()
+           << "at least one of auto, independent, seq must be present";
   }
 
   // Gang, worker and vector are incompatible with seq.
@@ -2482,8 +2506,7 @@ LogicalResult acc::LoopOp::verify() {
                        deviceTypeAttr.getValue()) ||
           getGangValue(mlir::acc::GangArgType::Static,
                        deviceTypeAttr.getValue()))
-        return emitError()
-               << "gang, worker or vector cannot appear with the seq attr";
+        return emitError() << "gang, worker or vector cannot appear with seq";
     }
   }
 

mlir/test/Dialect/OpenACC/canonicalize.mlir

@@ -116,10 +116,10 @@ func.func @testhostdataop(%a: memref<f32>, %ifCond: i1) -> () {
   acc.host_data dataOperands(%0 : memref<f32>) if(%false) {
     acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
       acc.yield
-    } attributes { inclusiveUpperbound = array<i1: true> }
+    } attributes {inclusiveUpperbound = array<i1: true>, independent = [#acc.device_type<none>]}
     acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
       acc.yield
-    } attributes { inclusiveUpperbound = array<i1: true> }
+    } attributes {inclusiveUpperbound = array<i1: true>, independent = [#acc.device_type<none>]}
     acc.terminator
   }
   return

mlir/test/Dialect/OpenACC/invalid.mlir

@@ -2,7 +2,7 @@
 
 %1 = arith.constant 1 : i32
 %2 = arith.constant 10 : i32
-// expected-error@+1 {{gang, worker or vector cannot appear with the seq attr}}
+// expected-error@+1 {{gang, worker or vector cannot appear with seq}}
 acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
   "test.openacc_dummy_op"() : () -> ()
   acc.yield
@@ -12,7 +12,7 @@ acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
 
 %1 = arith.constant 1 : i32
 %2 = arith.constant 10 : i32
-// expected-error@+1 {{gang, worker or vector cannot appear with the seq attr}}
+// expected-error@+1 {{gang, worker or vector cannot appear with seq}}
 acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
   "test.openacc_dummy_op"() : () -> ()
   acc.yield
@@ -22,7 +22,7 @@ acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
 
 %1 = arith.constant 1 : i32
 %2 = arith.constant 10 : i32
-// expected-error@+1 {{gang, worker or vector cannot appear with the seq attr}}
+// expected-error@+1 {{gang, worker or vector cannot appear with seq}}
 acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
   "test.openacc_dummy_op"() : () -> ()
   acc.yield
@@ -32,7 +32,7 @@ acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
 
 %1 = arith.constant 1 : i32
 %2 = arith.constant 10 : i32
-// expected-error@+1 {{gang, worker or vector cannot appear with the seq attr}}
+// expected-error@+1 {{gang, worker or vector cannot appear with seq}}
 acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
   "test.openacc_dummy_op"() : () -> ()
   acc.yield
@@ -42,7 +42,7 @@ acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
 
 %1 = arith.constant 1 : i32
 %2 = arith.constant 10 : i32
-// expected-error@+1 {{gang, worker or vector cannot appear with the seq attr}}
+// expected-error@+1 {{gang, worker or vector cannot appear with seq}}
 acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
   "test.openacc_dummy_op"() : () -> ()
   acc.yield
@@ -52,7 +52,7 @@ acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
 
 %1 = arith.constant 1 : i32
 %2 = arith.constant 10 : i32
-// expected-error@+1 {{gang, worker or vector cannot appear with the seq attr}}
+// expected-error@+1 {{gang, worker or vector cannot appear with seq}}
 acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
   "test.openacc_dummy_op"() : () -> ()
   acc.yield
@@ -62,7 +62,7 @@ acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
 
 %1 = arith.constant 1 : i32
 %2 = arith.constant 10 : i32
-// expected-error@+1 {{gang, worker or vector cannot appear with the seq attr}}
+// expected-error@+1 {{gang, worker or vector cannot appear with seq}}
 acc.loop {
   "test.openacc_dummy_op"() : () -> ()
   acc.yield
@@ -72,7 +72,7 @@ acc.loop {
 
 // expected-error@+1 {{expected non-empty body.}}
 acc.loop {
-}
+} attributes {independent = [#acc.device_type<none>]}
 
 // -----
 
@@ -99,7 +99,7 @@ acc.loop {
 
 %1 = arith.constant 1 : i32
 %2 = arith.constant 10 : i32
-// expected-error@+1 {{only one of "auto", "independent", "seq" can be present at the same time}}
+// expected-error@+1 {{only one of auto, independent, seq can be present at the same time}}
 acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
   acc.yield
 } attributes {auto_ = [#acc.device_type<none>], seq = [#acc.device_type<none>], inclusiveUpperbound = array<i1: true>}
@@ -168,7 +168,7 @@ acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32){
 // expected-error@+1 {{'acc.init' op cannot be nested in a compute operation}}
   acc.init
   acc.yield
-} attributes {inclusiveUpperbound = array<i1: true>}
+} attributes {inclusiveUpperbound = array<i1: true>, independent = [#acc.device_type<none>]}
 
 // -----
 
@@ -186,7 +186,7 @@ acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
 // expected-error@+1 {{'acc.shutdown' op cannot be nested in a compute operation}}
   acc.shutdown
   acc.yield
-} attributes {inclusiveUpperbound = array<i1: true>}
+} attributes {inclusiveUpperbound = array<i1: true>, independent = [#acc.device_type<none>]}
 
 // -----
 
@@ -198,7 +198,7 @@ acc.loop control(%iv : i32) = (%1 : i32) to (%2 : i32) step (%1 : i32) {
     acc.shutdown
   }) : () -> ()
   acc.yield
-} attributes {inclusiveUpperbound = array<i1: true>}
+} attributes {inclusiveUpperbound = array<i1: true>, independent = [#acc.device_type<none>]}
 
 // -----
 
@@ -797,7 +797,7 @@ func.func @acc_loop_container() {
         scf.yield
     }
     acc.yield
-  } attributes { collapse = [2], collapseDeviceType = [#acc.device_type<none>] }
+  } attributes { collapse = [2], collapseDeviceType = [#acc.device_type<none>], independent = [#acc.device_type<none>]}
   return
 }
 
@@ -816,6 +816,6 @@ func.func @acc_loop_container() {
       scf.yield
     }
     acc.yield
-  } attributes { collapse = [3], collapseDeviceType = [#acc.device_type<none>] }
+  } attributes { collapse = [3], collapseDeviceType = [#acc.device_type<none>], independent = [#acc.device_type<none>]}
   return
 }

mlir/test/Dialect/OpenACC/legalize-data.mlir

@@ -96,7 +96,7 @@ func.func @test(%a: memref<10xf32>) {
     acc.loop control(%i : index) = (%lb : index) to (%c10 : index) step (%st : index) {
       %ci = memref.load %a[%i] : memref<10xf32>
       acc.yield
-    }
+    } attributes {independent = [#acc.device_type<none>]}
     acc.yield
   }
   return
@@ -109,7 +109,7 @@ func.func @test(%a: memref<10xf32>) {
 // CHECK:   acc.loop control(%[[I:.*]] : index) = (%{{.*}} : index) to (%{{.*}} : index)  step (%{{.*}} : index) {
 // DEVICE:    %{{.*}} = memref.load %[[CREATE:.*]][%[[I]]] : memref<10xf32>
 // CHECK:     acc.yield
-// CHECK:   }
+// CHECK:   } attributes {independent = [#acc.device_type<none>]}
 // CHECK:   acc.yield
 // CHECK: }
 
@@ -134,7 +134,7 @@ func.func @test(%a: memref<10xf32>) {
     acc.loop control(%i : index) = (%lb : index) to (%c10 : index) step (%st : index) {
       %ci = memref.load %a[%i] : memref<10xf32>
       acc.yield
-    }
+    } attributes {independent = [#acc.device_type<none>]}
     acc.yield
   }
   return
@@ -147,7 +147,7 @@ func.func @test(%a: memref<10xf32>) {
 // CHECK:   acc.loop control(%[[I:.*]] : index) = (%{{.*}} : index) to (%{{.*}} : index)  step (%{{.*}} : index) {
 // DEVICE:    %{{.*}} = memref.load %[[PRIVATE:.*]][%[[I]]] : memref<10xf32>
 // CHECK:     acc.yield
-// CHECK:   }
+// CHECK:   } attributes {independent = [#acc.device_type<none>]}
 // CHECK:   acc.yield
 // CHECK: }
 
@@ -172,7 +172,7 @@ func.func @test(%a: memref<10xf32>) {
     acc.loop private(@privatization_memref_10_f32 -> %p1 : memref<10xf32>) control(%i : index) = (%lb : index) to (%c10 : index) step (%st : index) {
       %ci = memref.load %a[%i] : memref<10xf32>
       acc.yield
-    }
+    } attributes {independent = [#acc.device_type<none>]}
     acc.yield
   }
   return
@@ -185,7 +185,7 @@ func.func @test(%a: memref<10xf32>) {
 // CHECK:   acc.loop private(@privatization_memref_10_f32 -> %[[PRIVATE]] : memref<10xf32>) control(%[[I:.*]] : index) = (%{{.*}} : index) to (%{{.*}} : index)  step (%{{.*}} : index) {
 // DEVICE:    %{{.*}} = memref.load %[[PRIVATE:.*]][%[[I]]] : memref<10xf32>
 // CHECK:     acc.yield
-// CHECK:   }
+// CHECK:   } attributes {independent = [#acc.device_type<none>]}
 // CHECK:   acc.yield
 // CHECK: }
 
@@ -210,7 +210,7 @@ func.func @test(%a: memref<10xf32>) {
     acc.loop control(%i : index) = (%lb : index) to (%c10 : index) step (%st : index) {
       %ci = memref.load %a[%i] : memref<10xf32>
       acc.yield
-    }
+    } attributes {seq = [#acc.device_type<none>]}
     acc.yield
   }
   return
@@ -223,7 +223,7 @@ func.func @test(%a: memref<10xf32>) {
 // CHECK:   acc.loop control(%[[I:.*]] : index) = (%{{.*}} : index) to (%{{.*}} : index)  step (%{{.*}} : index) {
 // DEVICE:    %{{.*}} = memref.load %[[PRIVATE:.*]][%[[I]]] : memref<10xf32>
 // CHECK:     acc.yield
-// CHECK:   }
+// CHECK:   } attributes {seq = [#acc.device_type<none>]}
 // CHECK:   acc.yield
 // CHECK: }