[openacc] Attach Parallelism Levels to Auto Loops (llvm#200884)

Auto loops are analyzed by the compiler in later compilation stages to
determine whether they can be parallelized. These loops may carry
parallelism levels (this does not guarantee that they are parallelizable, 
compiler should still analyze them). However, if the loop is parallelized, 
the parallelism levels specified in the source should be respected. This 
change attaches the parallelism level to auto loops, which enables their 
propagation through next compilation steps.

Author: delaram-talaashrafi

mlir/lib/Dialect/OpenACC/Transforms/ACCComputeLowering.cpp

@@ -314,6 +314,13 @@ class ACCLoopConversion : public OpRewritePattern<LoopOp> {
           convertACCLoopToSCFFor(loopOp, rewriter, /*enableCollapse=*/true);
       if (!forOp)
         return failure();
+      SmallVector<GPUParallelDimAttr> parDims =
+          getParallelDimensions(loopOp, policy, deviceType);
+      if (!parDims.empty()) {
+        auto parDimsAttr =
+            GPUParallelDimsAttr::get(loopOp->getContext(), parDims);
+        setParDimsAttr(forOp, parDimsAttr);
+      }
       rewriter.replaceOp(loopOp, forOp);
     } else if (!isOpInComputeRegion(loopOp) &&
                !isSpecializedAccRoutine(

mlir/test/Dialect/OpenACC/acc-compute-lowering-loop.mlir

@@ -174,3 +174,32 @@ func.func @device_routine_vector_with_loop(%buf: memref<8xi32>) attributes {acc.
   } attributes {independent = [#acc.device_type<none>], vector = [#acc.device_type<none>]}
   return
 }
+
+// -----
+
+// Auto loop with gang: lowered to scf.for with predetermined par_dims.
+// CHECK-LABEL: func.func @parallel_loop_auto_gang
+func.func @parallel_loop_auto_gang(%buf: memref<1xi32>) {
+  %c0 = arith.constant 0 : index
+  %c1_i32 = arith.constant 1 : i32
+  %c10_i32 = arith.constant 10 : i32
+  %c100_i32 = arith.constant 100 : i32
+
+  %dev = acc.copyin varPtr(%buf : memref<1xi32>) -> memref<1xi32>
+  // CHECK-NOT: acc.parallel
+  // CHECK: acc.kernel_environment
+  // CHECK: acc.par_width {{.*}} {par_dim = #acc.par_dim<block_x>}
+  // CHECK: acc.compute_region launch(
+  // CHECK: scf.for
+  // CHECK-NOT: scf.parallel
+  // CHECK: acc.par_dims = #acc<par_dims[block_x]>
+  acc.parallel num_gangs({%c10_i32 : i32}) dataOperands(%dev : memref<1xi32>) {
+    acc.loop gang control(%arg0 : i32) = (%c1_i32 : i32) to (%c100_i32 : i32) step (%c1_i32 : i32) {
+      memref.store %arg0, %dev[%c0] : memref<1xi32>
+      acc.yield
+    } attributes {auto_ = [#acc.device_type<none>]}
+    acc.yield
+  }
+  acc.copyout accPtr(%dev : memref<1xi32>) to varPtr(%buf : memref<1xi32>)
+  return
+}