// CHECK-SAME: (%[[A:.*]]: tensor<5x7xf32>, %[[B:.*]]: tensor<7x11xf32>)
func.func @matmul_notranspose(%a: tensor<5x7xf32>, %b: tensor<7x11xf32>) -> tensor<5x11xf32> {
  // CHECK: "mhlo.dot"(%[[A]], %[[B]])
  %0 = "tf.MatMul"(%a, %b) {transpose_a = false, transpose_b = false} : (tensor<5x7xf32>, tensor<7x11xf32>) -> tensor<5x11xf32>

  func.return %0 : tensor<5x11xf32>
}

// -----

func.func @torch_index_select(%arg0: tensor<2x1xf32>, %arg1: tensor<2xi32>) -> tensor<2x1xf32> {
  %0 = "mhlo.torch_index_select"(%arg0, %arg1) {
    batch_dims = 0 : i64, dim = 0 : i64
  } : (tensor<2x1xf32>, tensor<2xi32>) -> tensor<2x1xf32>
  func.return %0 : tensor<2x1xf32>
}

// CHECK-LABEL:   func @lowered_cumsum(
// CHECK-SAME:      %[[VAL_0:.*]]: tensor<4x12xf32>) -> tensor<4x12xf32> {

func.func @fuseTileWithBinaryOp1(%arg0: tensor<1x1xf32>, %arg1: tensor<1x128xf32>) -> tensor<1x128xf32> {
  %cst_0 = arith.constant dense<1.0> : tensor<f32>
  %cst_1 = arith.constant dense<[1, 128]> : tensor<2xi32>
  %0 = "tfl.add"(%arg0, %cst_0) {fused_activation_function = "NONE"} : (tensor<1x1xf32>, tensor<f32>) -> tensor<1x1xf32>
  %1 = "tfl.sqrt"(%0) : (tensor<1x1xf32>) -> tensor<1x1xf32>

//                   (tensor<4x1xf32>, tensor<4x2xf32>, tensor<4x3xf32>)
//
// We will generate slices following slices:
// %0 = "mhlo.slice"(%input) {
//        limit_indices = dense<[4, 1]> : tensor<2xi64>,
//        start_indices = dense<0> : tensor<2xi64>,
//        strides = dense<1> : tensor<2xi64>} :
//        (tensor<4x6xf32>) -> tensor<4x1xf32>
// %1 = "mhlo.slice"(%input) {