176 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 VLA vectorization.29// RUN: %if mlir_arm_sve_tests %{ %{compile_sve} | %{run_sve} | FileCheck %s %}30 31#Dense = #sparse_tensor.encoding<{32 map = (d0, d1) -> (d0 : dense, d1 : dense)33}>34 35#SortedCOO = #sparse_tensor.encoding<{36 map = (d0, d1) -> (d0 : compressed(nonunique), d1 : singleton(soa))37}>38 39#CSR = #sparse_tensor.encoding<{40 map = (d0, d1) -> (d0 : dense, d1 : compressed)41}>42 43#DCSR = #sparse_tensor.encoding<{44 map = (d0, d1) -> (d0 : compressed, d1 : compressed)45}>46 47#Row = #sparse_tensor.encoding<{48 map = (d0, d1) -> (d0 : compressed, d1 : dense)49}>50 51module {52 //53 // Main driver. We test the contents of various sparse tensor54 // schemes when they are still empty and after a few insertions.55 //56 func.func @main() {57 %c0 = arith.constant 0 : index58 %c2 = arith.constant 2 : index59 %c3 = arith.constant 3 : index60 %f1 = arith.constant 1.0 : f6461 %f2 = arith.constant 2.0 : f6462 %f3 = arith.constant 3.0 : f6463 %f4 = arith.constant 4.0 : f6464 65 //66 // Dense case.67 //68 // CHECK: ---- Sparse Tensor ----69 // CHECK-NEXT: nse = 1270 // CHECK-NEXT: dim = ( 4, 3 )71 // CHECK-NEXT: lvl = ( 4, 3 )72 // CHECK-NEXT: values : ( 1, 0, 0, 0, 0, 0, 0, 0, 2, 3, 0, 4 )73 // CHECK-NEXT: ----74 //75 %densea = tensor.empty() : tensor<4x3xf64, #Dense>76 %dense1 = tensor.insert %f1 into %densea[%c0, %c0] : tensor<4x3xf64, #Dense>77 %dense2 = tensor.insert %f2 into %dense1[%c2, %c2] : tensor<4x3xf64, #Dense>78 %dense3 = tensor.insert %f3 into %dense2[%c3, %c0] : tensor<4x3xf64, #Dense>79 %dense4 = tensor.insert %f4 into %dense3[%c3, %c2] : tensor<4x3xf64, #Dense>80 %densem = sparse_tensor.load %dense4 hasInserts : tensor<4x3xf64, #Dense>81 sparse_tensor.print %densem : tensor<4x3xf64, #Dense>82 83 //84 // COO case.85 //86 // CHECK-NEXT: ---- Sparse Tensor ----87 // CHECK-NEXT: nse = 488 // CHECK-NEXT: dim = ( 4, 3 )89 // CHECK-NEXT: lvl = ( 4, 3 )90 // CHECK-NEXT: pos[0] : ( 0, 4 )91 // CHECK-NEXT: crd[0] : ( 0, 2, 3, 3 )92 // CHECK-NEXT: crd[1] : ( 0, 2, 0, 2 )93 // CHECK-NEXT: values : ( 1, 2, 3, 4 )94 // CHECK-NEXT: ----95 //96 %cooa = tensor.empty() : tensor<4x3xf64, #SortedCOO>97 %coo1 = tensor.insert %f1 into %cooa[%c0, %c0] : tensor<4x3xf64, #SortedCOO>98 %coo2 = tensor.insert %f2 into %coo1[%c2, %c2] : tensor<4x3xf64, #SortedCOO>99 %coo3 = tensor.insert %f3 into %coo2[%c3, %c0] : tensor<4x3xf64, #SortedCOO>100 %coo4 = tensor.insert %f4 into %coo3[%c3, %c2] : tensor<4x3xf64, #SortedCOO>101 %coom = sparse_tensor.load %coo4 hasInserts : tensor<4x3xf64, #SortedCOO>102 sparse_tensor.print %coom : tensor<4x3xf64, #SortedCOO>103 104 //105 // CSR case.106 //107 // CHECK-NEXT: ---- Sparse Tensor ----108 // CHECK-NEXT: nse = 4109 // CHECK-NEXT: dim = ( 4, 3 )110 // CHECK-NEXT: lvl = ( 4, 3 )111 // CHECK-NEXT: pos[1] : ( 0, 1, 1, 2, 4 )112 // CHECK-NEXT: crd[1] : ( 0, 2, 0, 2 )113 // CHECK-NEXT: values : ( 1, 2, 3, 4 )114 // CHECK-NEXT: ----115 //116 %csra = tensor.empty() : tensor<4x3xf64, #CSR>117 %csr1 = tensor.insert %f1 into %csra[%c0, %c0] : tensor<4x3xf64, #CSR>118 %csr2 = tensor.insert %f2 into %csr1[%c2, %c2] : tensor<4x3xf64, #CSR>119 %csr3 = tensor.insert %f3 into %csr2[%c3, %c0] : tensor<4x3xf64, #CSR>120 %csr4 = tensor.insert %f4 into %csr3[%c3, %c2] : tensor<4x3xf64, #CSR>121 %csrm = sparse_tensor.load %csr4 hasInserts : tensor<4x3xf64, #CSR>122 sparse_tensor.print %csrm : tensor<4x3xf64, #CSR>123 124 //125 // DCSR case.126 //127 // CHECK-NEXT: ---- Sparse Tensor ----128 // CHECK-NEXT: nse = 4129 // CHECK-NEXT: dim = ( 4, 3 )130 // CHECK-NEXT: lvl = ( 4, 3 )131 // CHECK-NEXT: pos[0] : ( 0, 3 )132 // CHECK-NEXT: crd[0] : ( 0, 2, 3 )133 // CHECK-NEXT: pos[1] : ( 0, 1, 2, 4 )134 // CHECK-NEXT: crd[1] : ( 0, 2, 0, 2 )135 // CHECK-NEXT: values : ( 1, 2, 3, 4 )136 // CHECK-NEXT: ----137 //138 %dcsra = tensor.empty() : tensor<4x3xf64, #DCSR>139 %dcsr1 = tensor.insert %f1 into %dcsra[%c0, %c0] : tensor<4x3xf64, #DCSR>140 %dcsr2 = tensor.insert %f2 into %dcsr1[%c2, %c2] : tensor<4x3xf64, #DCSR>141 %dcsr3 = tensor.insert %f3 into %dcsr2[%c3, %c0] : tensor<4x3xf64, #DCSR>142 %dcsr4 = tensor.insert %f4 into %dcsr3[%c3, %c2] : tensor<4x3xf64, #DCSR>143 %dcsrm = sparse_tensor.load %dcsr4 hasInserts : tensor<4x3xf64, #DCSR>144 sparse_tensor.print %dcsrm : tensor<4x3xf64, #DCSR>145 146 //147 // Row case.148 //149 // CHECK-NEXT: ---- Sparse Tensor ----150 // CHECK-NEXT: nse = 9151 // CHECK-NEXT: dim = ( 4, 3 )152 // CHECK-NEXT: lvl = ( 4, 3 )153 // CHECK-NEXT: pos[0] : ( 0, 3 )154 // CHECK-NEXT: crd[0] : ( 0, 2, 3 )155 // CHECK-NEXT: values : ( 1, 0, 0, 0, 0, 2, 3, 0, 4 )156 // CHECK-NEXT: ----157 //158 %rowa = tensor.empty() : tensor<4x3xf64, #Row>159 %row1 = tensor.insert %f1 into %rowa[%c0, %c0] : tensor<4x3xf64, #Row>160 %row2 = tensor.insert %f2 into %row1[%c2, %c2] : tensor<4x3xf64, #Row>161 %row3 = tensor.insert %f3 into %row2[%c3, %c0] : tensor<4x3xf64, #Row>162 %row4 = tensor.insert %f4 into %row3[%c3, %c2] : tensor<4x3xf64, #Row>163 %rowm = sparse_tensor.load %row4 hasInserts : tensor<4x3xf64, #Row>164 sparse_tensor.print %rowm : tensor<4x3xf64, #Row>165 166 // Release resources.167 bufferization.dealloc_tensor %densem : tensor<4x3xf64, #Dense>168 bufferization.dealloc_tensor %coom : tensor<4x3xf64, #SortedCOO>169 bufferization.dealloc_tensor %csrm : tensor<4x3xf64, #CSR>170 bufferization.dealloc_tensor %dcsrm : tensor<4x3xf64, #DCSR>171 bufferization.dealloc_tensor %rowm : tensor<4x3xf64, #Row>172 173 return174 }175}176