forked from OSchip/llvm-project
34 lines
1.4 KiB
MLIR
34 lines
1.4 KiB
MLIR
// RUN: mlir-opt %s \
|
|
// RUN: -async-parallel-for=async-dispatch=true \
|
|
// RUN: -canonicalize -inline -symbol-dce \
|
|
// RUN: | FileCheck %s
|
|
|
|
// RUN: mlir-opt %s \
|
|
// RUN: -async-parallel-for=async-dispatch=false \
|
|
// RUN: -canonicalize -inline -symbol-dce \
|
|
// RUN: | FileCheck %s
|
|
|
|
// Check that if we statically know that the parallel operation has a single
|
|
// block then all async operations will be canonicalized away and we will
|
|
// end up with a single synchonous compute function call.
|
|
|
|
// CHECK-LABEL: @loop_1d(
|
|
// CHECK: %[[MEMREF:.*]]: memref<?xf32>
|
|
func @loop_1d(%arg0: memref<?xf32>) {
|
|
// CHECK-DAG: %[[C0:.*]] = constant 0 : index
|
|
// CHECK-DAG: %[[C1:.*]] = constant 1 : index
|
|
// CHECK-DAG: %[[C100:.*]] = constant 100 : index
|
|
// CHECK-DAG: %[[ONE:.*]] = constant 1.000000e+00 : f32
|
|
// CHECK: scf.for %[[I:.*]] = %[[C0]] to %[[C100]] step %[[C1]]
|
|
// CHECK: memref.store %[[ONE]], %[[MEMREF]][%[[I]]]
|
|
%lb = constant 0 : index
|
|
%ub = constant 100 : index
|
|
%st = constant 1 : index
|
|
scf.parallel (%i) = (%lb) to (%ub) step (%st) {
|
|
%one = constant 1.0 : f32
|
|
memref.store %one, %arg0[%i] : memref<?xf32>
|
|
}
|
|
|
|
return
|
|
}
|