147 lines · plain
1//--------------------------------------------------------------------------------------------------2// WHEN CREATING A NEW TEST, PLEASE JUST COPY & PASTE WITHOUT EDITS.3//4// Set-up that's shared across all tests in this directory. In principle, this5// config could be moved to lit.local.cfg. However, there are downstream users that6// do not use these LIT config files. Hence why this is kept inline.7//8// DEFINE: %{sparsifier_opts} = enable-runtime-library=true9// DEFINE: %{sparsifier_opts_sve} = enable-arm-sve=true %{sparsifier_opts}10// DEFINE: %{compile} = mlir-opt %s --sparsifier="%{sparsifier_opts}"11// DEFINE: %{compile_sve} = mlir-opt %s --sparsifier="%{sparsifier_opts_sve}"12// DEFINE: %{run_libs} = -shared-libs=%mlir_c_runner_utils,%mlir_runner_utils13// DEFINE: %{run_libs_sve} = -shared-libs=%native_mlir_runner_utils,%native_mlir_c_runner_utils14// DEFINE: %{run_opts} = -e main -entry-point-result=void15// DEFINE: %{run} = mlir-runner %{run_opts} %{run_libs}16// DEFINE: %{run_sve} = %mcr_aarch64_cmd --march=aarch64 --mattr="+sve" %{run_opts} %{run_libs_sve}17//18// DEFINE: %{env} =19//--------------------------------------------------------------------------------------------------20 21// REDEFINE: %{sparsifier_opts} = enable-runtime-library=false22// RUN: %{compile} | %{run} | FileCheck %s23//24// Do the same run, but now with vectorization.25// REDEFINE: %{sparsifier_opts} = enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true26// RUN: %{compile} | %{run} | FileCheck %s27//28// Do the same run, but now with VLA vectorization.29// RUN: %if mlir_arm_sve_tests %{ %{compile_sve} | %{run_sve} | FileCheck %s %}30 31#TensorCSR = #sparse_tensor.encoding<{32 map = (d0, d1, d2) -> (d0 : compressed, d1 : dense, d2 : compressed)33}>34 35#TensorRow = #sparse_tensor.encoding<{36 map = (d0, d1, d2) -> (d0 : compressed, d1 : compressed, d2 : dense)37}>38 39#CCoo = #sparse_tensor.encoding<{40 map = (d0, d1, d2) -> (d0 : compressed, d1 : compressed(nonunique), d2 : singleton)41}>42 43#DCoo = #sparse_tensor.encoding<{44 map = (d0, d1, d2) -> (d0 : dense, d1 : compressed(nonunique), d2 : singleton)45}>46 47 48module {49 //50 // Main driver.51 //52 func.func @main() {53 %c0 = arith.constant 0 : index54 %c1 = arith.constant 1 : index55 %c2 = arith.constant 2 : index56 %c3 = arith.constant 3 : index57 %c4 = arith.constant 4 : index58 %f1 = arith.constant 1.1 : f6459 %f2 = arith.constant 2.2 : f6460 %f3 = arith.constant 3.3 : f6461 %f4 = arith.constant 4.4 : f6462 %f5 = arith.constant 5.5 : f6463 64 // CHECK: ---- Sparse Tensor ----65 // CHECK-NEXT: nse = 566 // CHECK-NEXT: dim = ( 5, 4, 3 )67 // CHECK-NEXT: lvl = ( 5, 4, 3 )68 // CHECK-NEXT: pos[0] : ( 0, 2 )69 // CHECK-NEXT: crd[0] : ( 3, 4 )70 // CHECK-NEXT: pos[2] : ( 0, 2, 2, 2, 3, 3, 3, 4, 5 )71 // CHECK-NEXT: crd[2] : ( 1, 2, 1, 2, 2 )72 // CHECK-NEXT: values : ( 1.1, 2.2, 3.3, 4.4, 5.5 )73 // CHECK-NEXT: ----74 %tensora = tensor.empty() : tensor<5x4x3xf64, #TensorCSR>75 %tensor1 = tensor.insert %f1 into %tensora[%c3, %c0, %c1] : tensor<5x4x3xf64, #TensorCSR>76 %tensor2 = tensor.insert %f2 into %tensor1[%c3, %c0, %c2] : tensor<5x4x3xf64, #TensorCSR>77 %tensor3 = tensor.insert %f3 into %tensor2[%c3, %c3, %c1] : tensor<5x4x3xf64, #TensorCSR>78 %tensor4 = tensor.insert %f4 into %tensor3[%c4, %c2, %c2] : tensor<5x4x3xf64, #TensorCSR>79 %tensor5 = tensor.insert %f5 into %tensor4[%c4, %c3, %c2] : tensor<5x4x3xf64, #TensorCSR>80 %tensorm = sparse_tensor.load %tensor5 hasInserts : tensor<5x4x3xf64, #TensorCSR>81 sparse_tensor.print %tensorm : tensor<5x4x3xf64, #TensorCSR>82 83 // CHECK-NEXT: ---- Sparse Tensor ----84 // CHECK-NEXT: nse = 1285 // CHECK-NEXT: dim = ( 5, 4, 3 )86 // CHECK-NEXT: lvl = ( 5, 4, 3 )87 // CHECK-NEXT: pos[0] : ( 0, 2 )88 // CHECK-NEXT: crd[0] : ( 3, 4 )89 // CHECK-NEXT: pos[1] : ( 0, 2, 4 )90 // CHECK-NEXT: crd[1] : ( 0, 3, 2, 3 )91 // CHECK-NEXT: values : ( 0, 1.1, 2.2, 0, 3.3, 0, 0, 0, 4.4, 0, 0, 5.5 )92 // CHECK-NEXT: ----93 %rowa = tensor.empty() : tensor<5x4x3xf64, #TensorRow>94 %row1 = tensor.insert %f1 into %rowa[%c3, %c0, %c1] : tensor<5x4x3xf64, #TensorRow>95 %row2 = tensor.insert %f2 into %row1[%c3, %c0, %c2] : tensor<5x4x3xf64, #TensorRow>96 %row3 = tensor.insert %f3 into %row2[%c3, %c3, %c1] : tensor<5x4x3xf64, #TensorRow>97 %row4 = tensor.insert %f4 into %row3[%c4, %c2, %c2] : tensor<5x4x3xf64, #TensorRow>98 %row5 = tensor.insert %f5 into %row4[%c4, %c3, %c2] : tensor<5x4x3xf64, #TensorRow>99 %rowm = sparse_tensor.load %row5 hasInserts : tensor<5x4x3xf64, #TensorRow>100 sparse_tensor.print %rowm : tensor<5x4x3xf64, #TensorRow>101 102 // CHECK-NEXT: ---- Sparse Tensor ----103 // CHECK-NEXT: nse = 5104 // CHECK-NEXT: dim = ( 5, 4, 3 )105 // CHECK-NEXT: lvl = ( 5, 4, 3 )106 // CHECK-NEXT: pos[0] : ( 0, 2 )107 // CHECK-NEXT: crd[0] : ( 3, 4 )108 // CHECK-NEXT: pos[1] : ( 0, 3, 5 )109 // CHECK-NEXT: crd[1] : ( 0, 1, 0, 2, 3, 1, 2, 2, 3, 2 )110 // CHECK-NEXT: values : ( 1.1, 2.2, 3.3, 4.4, 5.5 )111 // CHECK-NEXT: ----112 %ccoo = tensor.empty() : tensor<5x4x3xf64, #CCoo>113 %ccoo1 = tensor.insert %f1 into %ccoo[%c3, %c0, %c1] : tensor<5x4x3xf64, #CCoo>114 %ccoo2 = tensor.insert %f2 into %ccoo1[%c3, %c0, %c2] : tensor<5x4x3xf64, #CCoo>115 %ccoo3 = tensor.insert %f3 into %ccoo2[%c3, %c3, %c1] : tensor<5x4x3xf64, #CCoo>116 %ccoo4 = tensor.insert %f4 into %ccoo3[%c4, %c2, %c2] : tensor<5x4x3xf64, #CCoo>117 %ccoo5 = tensor.insert %f5 into %ccoo4[%c4, %c3, %c2] : tensor<5x4x3xf64, #CCoo>118 %ccoom = sparse_tensor.load %ccoo5 hasInserts : tensor<5x4x3xf64, #CCoo>119 sparse_tensor.print %ccoom : tensor<5x4x3xf64, #CCoo>120 121 // CHECK-NEXT: ---- Sparse Tensor ----122 // CHECK-NEXT: nse = 5123 // CHECK-NEXT: dim = ( 5, 4, 3 )124 // CHECK-NEXT: lvl = ( 5, 4, 3 )125 // CHECK-NEXT: pos[1] : ( 0, 0, 0, 0, 3, 5 )126 // CHECK-NEXT: crd[1] : ( 0, 1, 0, 2, 3, 1, 2, 2, 3, 2 )127 // CHECK-NEXT: values : ( 1.1, 2.2, 3.3, 4.4, 5.5 )128 // CHECK-NEXT: ----129 %dcoo = tensor.empty() : tensor<5x4x3xf64, #DCoo>130 %dcoo1 = tensor.insert %f1 into %dcoo[%c3, %c0, %c1] : tensor<5x4x3xf64, #DCoo>131 %dcoo2 = tensor.insert %f2 into %dcoo1[%c3, %c0, %c2] : tensor<5x4x3xf64, #DCoo>132 %dcoo3 = tensor.insert %f3 into %dcoo2[%c3, %c3, %c1] : tensor<5x4x3xf64, #DCoo>133 %dcoo4 = tensor.insert %f4 into %dcoo3[%c4, %c2, %c2] : tensor<5x4x3xf64, #DCoo>134 %dcoo5 = tensor.insert %f5 into %dcoo4[%c4, %c3, %c2] : tensor<5x4x3xf64, #DCoo>135 %dcoom = sparse_tensor.load %dcoo5 hasInserts : tensor<5x4x3xf64, #DCoo>136 sparse_tensor.print %dcoom : tensor<5x4x3xf64, #DCoo>137 138 // Release resources.139 bufferization.dealloc_tensor %tensorm : tensor<5x4x3xf64, #TensorCSR>140 bufferization.dealloc_tensor %rowm : tensor<5x4x3xf64, #TensorRow>141 bufferization.dealloc_tensor %ccoom : tensor<5x4x3xf64, #CCoo>142 bufferization.dealloc_tensor %dcoom : tensor<5x4x3xf64, #DCoo>143 144 return145 }146}147