// RUN: mlir-opt %s --sparse-reinterpret-map -sparsification -cse -sparse-vectorization="vl=8" -cse | \
// RUN:   FileCheck %s

// NOTE: Assertions have been autogenerated by utils/generate-test-checks.py

#SparseVector = #sparse_tensor.encoding<{
  map = (d0) -> (d0 : compressed)
}>

#trait_1d = {
  indexing_maps = [
    affine_map<(i) -> (i)>,  // a
    affine_map<(i) -> (i)>   // x (out)
  ],
  iterator_types = ["parallel"],
  doc = "X(i) = a(i) op i"
}

// CHECK-LABEL: func.func @sparse_index_1d_conj(
// CHECK-SAME:      %[[VAL_0:.*]]: tensor<8xi64, #sparse{{[0-9]*}}>) -> tensor<8xi64> {
// CHECK-DAG:       %[[VAL_1:.*]] = arith.constant 8 : index
// CHECK-DAG:       %[[VAL_2:.*]] = arith.constant dense<0> : vector<8xi64>
// CHECK-DAG:       %[[VAL_3:.*]] = arith.constant dense<0> : vector<8xindex>
// CHECK-DAG:       %[[VAL_4:.*]] = arith.constant 0 : i64
// CHECK-DAG:       %[[VAL_5:.*]] = arith.constant 0 : index
// CHECK-DAG:       %[[VAL_6:.*]] = arith.constant 1 : index
// CHECK-DAG:       %[[VAL_7:.*]] = tensor.empty() : tensor<8xi64>
// CHECK-DAG:       %[[VAL_8:.*]] = sparse_tensor.positions %[[VAL_0]] {level = 0 : index} : tensor<8xi64, #sparse{{[0-9]*}}> to memref<?xindex>
// CHECK-DAG:       %[[VAL_9:.*]] = sparse_tensor.coordinates %[[VAL_0]] {level = 0 : index} : tensor<8xi64, #sparse{{[0-9]*}}> to memref<?xindex>
// CHECK-DAG:       %[[VAL_10:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<8xi64, #sparse{{[0-9]*}}> to memref<?xi64>
// CHECK-DAG:       %[[VAL_11:.*]] = bufferization.to_buffer %[[VAL_7]] : tensor<8xi64> to memref<8xi64>
// CHECK-DAG:       linalg.fill ins(%[[VAL_4]] : i64) outs(%[[VAL_11]] : memref<8xi64>)
// CHECK:           %[[VAL_12:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK:           %[[VAL_13:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref<?xindex>
// CHECK:           scf.for %[[VAL_14:.*]] = %[[VAL_12]] to %[[VAL_13]] step %[[VAL_1]] {
// CHECK:             %[[VAL_15:.*]] = affine.min #map(%[[VAL_13]], %[[VAL_14]]){{\[}}%[[VAL_1]]]
// CHECK:             %[[VAL_16:.*]] = vector.create_mask %[[VAL_15]] : vector<8xi1>
// CHECK:             %[[VAL_17:.*]] = vector.maskedload %[[VAL_9]]{{\[}}%[[VAL_14]]], %[[VAL_16]], %[[VAL_3]] : memref<?xindex>, vector<8xi1>, vector<8xindex> into vector<8xindex>
// CHECK:             %[[VAL_18:.*]] = vector.maskedload %[[VAL_10]]{{\[}}%[[VAL_14]]], %[[VAL_16]], %[[VAL_2]] : memref<?xi64>, vector<8xi1>, vector<8xi64> into vector<8xi64>
// CHECK:             %[[VAL_19:.*]] = arith.index_cast %[[VAL_17]] : vector<8xindex> to vector<8xi64>
// CHECK:             %[[VAL_20:.*]] = arith.muli %[[VAL_18]], %[[VAL_19]] : vector<8xi64>
// CHECK:             vector.scatter %[[VAL_11]]{{\[}}%[[VAL_5]]] {{\[}}%[[VAL_17]]], %[[VAL_16]], %[[VAL_20]] : memref<8xi64>, vector<8xindex>, vector<8xi1>, vector<8xi64>
// CHECK:           } {"Emitted from" = "linalg.generic"}
// CHECK:           %[[VAL_21:.*]] = bufferization.to_tensor %[[VAL_11]] : memref<8xi64>
// CHECK:           return %[[VAL_21]] : tensor<8xi64>
// CHECK:         }
func.func @sparse_index_1d_conj(%arga: tensor<8xi64, #SparseVector>) -> tensor<8xi64> {
  %init = tensor.empty() : tensor<8xi64>
  %r = linalg.generic #trait_1d
      ins(%arga: tensor<8xi64, #SparseVector>)
     outs(%init: tensor<8xi64>) {
      ^bb(%a: i64, %x: i64):
        %i = linalg.index 0 : index
        %ii = arith.index_cast %i : index to i64
        %m1 = arith.muli %a, %ii : i64
        linalg.yield %m1 : i64
  } -> tensor<8xi64>
  return %r : tensor<8xi64>
}

// CHECK-LABEL: func.func @sparse_index_1d_disj(
// CHECK-SAME:      %[[VAL_0:.*]]: tensor<8xi64, #sparse{{[0-9]*}}>) -> tensor<8xi64> {
// CHECK-DAG:       %[[VAL_1:.*]] = arith.constant 8 : index
// CHECK-DAG:       %[[VAL_2:.*]] = arith.constant dense<[0, 1, 2, 3, 4, 5, 6, 7]> : vector<8xindex>
// CHECK-DAG:       %[[VAL_3:.*]] = arith.constant 0 : i64
// CHECK-DAG:       %[[VAL_4:.*]] = arith.constant 0 : index
// CHECK-DAG:       %[[VAL_5:.*]] = arith.constant 1 : index
// CHECK-DAG:       %[[VAL_6:.*]] = arith.constant true
// CHECK-DAG:       %[[VAL_7:.*]] = tensor.empty() : tensor<8xi64>
// CHECK-DAG:       %[[VAL_8:.*]] = sparse_tensor.positions %[[VAL_0]] {level = 0 : index} : tensor<8xi64, #sparse{{[0-9]*}}> to memref<?xindex>
// CHECK-DAG:       %[[VAL_9:.*]] = sparse_tensor.coordinates %[[VAL_0]] {level = 0 : index} : tensor<8xi64, #sparse{{[0-9]*}}> to memref<?xindex>
// CHECK-DAG:       %[[VAL_10:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<8xi64, #sparse{{[0-9]*}}> to memref<?xi64>
// CHECK-DAG:       %[[VAL_11:.*]] = bufferization.to_buffer %[[VAL_7]] : tensor<8xi64> to memref<8xi64>
// CHECK-DAG:       linalg.fill ins(%[[VAL_3]] : i64) outs(%[[VAL_11]] : memref<8xi64>)
// CHECK:           %[[VAL_12:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK:           %[[VAL_13:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK:           %[[VAL_14:.*]]:2 = scf.while (%[[VAL_15:.*]] = %[[VAL_12]], %[[VAL_16:.*]] = %[[VAL_4]]) : (index, index) -> (index, index) {
// CHECK:             %[[VAL_17:.*]] = arith.cmpi ult, %[[VAL_15]], %[[VAL_13]] : index
// CHECK:             scf.condition(%[[VAL_17]]) %[[VAL_15]], %[[VAL_16]] : index, index
// CHECK:           } do {
// CHECK:           ^bb0(%[[VAL_18:.*]]: index, %[[VAL_19:.*]]: index):
// CHECK:             %[[VAL_20:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref<?xindex>
// CHECK:             %[[VAL_21:.*]] = arith.cmpi eq, %[[VAL_20]], %[[VAL_19]] : index
// CHECK:             scf.if %[[VAL_21]] {
// CHECK:               %[[VAL_22:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_18]]] : memref<?xi64>
// CHECK:               %[[VAL_23:.*]] = arith.index_cast %[[VAL_19]] : index to i64
// CHECK:               %[[VAL_24:.*]] = arith.addi %[[VAL_22]], %[[VAL_23]] : i64
// CHECK:               memref.store %[[VAL_24]], %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref<8xi64>
// CHECK:             } else {
// CHECK:               scf.if %[[VAL_6]] {
// CHECK:                 %[[VAL_25:.*]] = arith.index_cast %[[VAL_19]] : index to i64
// CHECK:                 memref.store %[[VAL_25]], %[[VAL_11]]{{\[}}%[[VAL_19]]] : memref<8xi64>
// CHECK:               } else {
// CHECK:               }
// CHECK:             }
// CHECK:             %[[VAL_26:.*]] = arith.addi %[[VAL_18]], %[[VAL_5]] : index
// CHECK:             %[[VAL_27:.*]] = arith.select %[[VAL_21]], %[[VAL_26]], %[[VAL_18]] : index
// CHECK:             %[[VAL_28:.*]] = arith.addi %[[VAL_19]], %[[VAL_5]] : index
// CHECK:             scf.yield %[[VAL_27]], %[[VAL_28]] : index, index
// CHECK:           } attributes {"Emitted from" = "linalg.generic"}
// CHECK:           scf.for %[[VAL_29:.*]] = %[[VAL_30:.*]]#1 to %[[VAL_1]] step %[[VAL_1]] {
// CHECK:             %[[VAL_31:.*]] = affine.min #map(%[[VAL_1]], %[[VAL_29]]){{\[}}%[[VAL_1]]]
// CHECK:             %[[VAL_32:.*]] = vector.create_mask %[[VAL_31]] : vector<8xi1>
// CHECK:             %[[VAL_33:.*]] = vector.broadcast %[[VAL_29]] : index to vector<8xindex>
// CHECK:             %[[VAL_34:.*]] = arith.addi %[[VAL_33]], %[[VAL_2]] : vector<8xindex>
// CHECK:             %[[VAL_35:.*]] = arith.index_cast %[[VAL_34]] : vector<8xindex> to vector<8xi64>
// CHECK:             vector.maskedstore %[[VAL_11]]{{\[}}%[[VAL_29]]], %[[VAL_32]], %[[VAL_35]] : memref<8xi64>, vector<8xi1>, vector<8xi64>
// CHECK:           } {"Emitted from" = "linalg.generic"}
// CHECK:           %[[VAL_36:.*]] = bufferization.to_tensor %[[VAL_11]] : memref<8xi64>
// CHECK:           return %[[VAL_36]] : tensor<8xi64>
// CHECK:         }
func.func @sparse_index_1d_disj(%arga: tensor<8xi64, #SparseVector>) -> tensor<8xi64> {
  %init = tensor.empty() : tensor<8xi64>
  %r = linalg.generic #trait_1d
      ins(%arga: tensor<8xi64, #SparseVector>)
     outs(%init: tensor<8xi64>) {
      ^bb(%a: i64, %x: i64):
        %i = linalg.index 0 : index
        %ii = arith.index_cast %i : index to i64
        %m1 = arith.addi %a, %ii : i64
        linalg.yield %m1 : i64
  } -> tensor<8xi64>
  return %r : tensor<8xi64>
}