// CHECK:         }
func.func @broadcast_add(%arg0: tensor<1x1xf32>, %arg1: tensor<1x1000xf32>) -> (tensor<1x1000xf32>, tensor<1x1000xf32>) {
  %0 = "mhlo.broadcast_in_dim"(%arg0) <{broadcast_dimensions = dense<[0, 1]> : tensor<2xi64>}> : (tensor<1x1xf32>) -> tensor<1x1000xf32>
  %1 = mhlo.add %0, %arg1 : tensor<1x1000xf32>
  %2 = mhlo.add %arg1, %0 : tensor<1x1000xf32>
  func.return %1, %2 : tensor<1x1000xf32>, tensor<1x1000xf32>
}

//        start_indices = dense<0> : tensor<2xi64>,
//        strides = dense<1> : tensor<2xi64>} :
//        (tensor<4x6xf32>) -> tensor<4x1xf32>
// %1 = "mhlo.slice"(%input) {
//        limit_indices = dense<[4, 3]> : tensor<2xi64>,
//        start_indices = dense<[0, 1]> : tensor<2xi64>,
//        strides = dense<1> : tensor<2xi64>} :
//        (tensor<4x6xf32>) -> tensor<4x2xf32>

  func.return %0#0 : tensor<8x8x8x8xf32>
}

// -----

// CHECK-LABEL: fusedBatchNormV3_noTraining_mixedPrecision