brintos

brintos / llvm-project-archived public Read only

0
0
Text · 8.9 KiB · 407c060 Raw
224 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// RUN: %{compile} | %{run} | FileCheck %s22//23// Do the same run, but now with direct IR generation.24// REDEFINE: %{sparsifier_opts} = enable-runtime-library=false25// RUN: %{compile} | %{run} | FileCheck %s26//27// Do the same run, but now with direct IR generation and vectorization.28// REDEFINE: %{sparsifier_opts} = enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true29// RUN: %{compile} | %{run} | FileCheck %s30//31// Do the same run, but now with direct IR generation and VLA vectorization.32// RUN: %if mlir_arm_sve_tests %{ %{compile_sve} | %{run_sve} | FileCheck %s %}33 34#SparseVector = #sparse_tensor.encoding<{35  map = (d0) -> (d0 : compressed)36}>37 38#SparseMatrix = #sparse_tensor.encoding<{39  map = (d0, d1) -> (d0 : compressed, d1 : compressed)40}>41 42#trait_1d = {43  indexing_maps = [44    affine_map<(i) -> (i)>,  // a45    affine_map<(i) -> (i)>   // x (out)46  ],47  iterator_types = ["parallel"],48  doc = "X(i) = a(i) op i"49}50 51#trait_2d = {52  indexing_maps = [53    affine_map<(i,j) -> (i,j)>,  // A54    affine_map<(i,j) -> (i,j)>   // X (out)55  ],56  iterator_types = ["parallel", "parallel"],57  doc = "X(i,j) = A(i,j) op i op j"58}59 60//61// Test with indices and sparse inputs. All outputs are dense.62//63module {64 65  //66  // Kernel that uses index in the index notation (conjunction).67  //68  func.func @sparse_index_1d_conj(%arga: tensor<8xi64, #SparseVector>)69      -> tensor<8xi64> {70    %out = tensor.empty() : tensor<8xi64>71    %r = linalg.generic #trait_1d72        ins(%arga: tensor<8xi64, #SparseVector>)73       outs(%out: tensor<8xi64>) {74        ^bb(%a: i64, %x: i64):75          %i = linalg.index 0 : index76          %ii = arith.index_cast %i : index to i6477          %m1 = arith.muli %a, %ii : i6478          linalg.yield %m1 : i6479    } -> tensor<8xi64>80    return %r : tensor<8xi64>81  }82 83  //84  // Kernel that uses index in the index notation (disjunction).85  //86  func.func @sparse_index_1d_disj(%arga: tensor<8xi64, #SparseVector>)87      -> tensor<8xi64> {88    %out = tensor.empty() : tensor<8xi64>89    %r = linalg.generic #trait_1d90        ins(%arga: tensor<8xi64, #SparseVector>)91       outs(%out: tensor<8xi64>) {92        ^bb(%a: i64, %x: i64):93          %i = linalg.index 0 : index94          %ii = arith.index_cast %i : index to i6495          %m1 = arith.addi %a, %ii : i6496          linalg.yield %m1 : i6497    } -> tensor<8xi64>98    return %r : tensor<8xi64>99  }100 101  //102  // Kernel that uses indices in the index notation (conjunction).103  //104  func.func @sparse_index_2d_conj(%arga: tensor<3x4xi64, #SparseMatrix>)105      -> tensor<3x4xi64> {106    %out = tensor.empty() : tensor<3x4xi64>107    %r = linalg.generic #trait_2d108        ins(%arga: tensor<3x4xi64, #SparseMatrix>)109       outs(%out: tensor<3x4xi64>) {110        ^bb(%a: i64, %x: i64):111          %i = linalg.index 0 : index112          %j = linalg.index 1 : index113          %ii = arith.index_cast %i : index to i64114          %jj = arith.index_cast %j : index to i64115          %m1 = arith.muli %ii, %a : i64116          %m2 = arith.muli %jj, %m1 : i64117          linalg.yield %m2 : i64118    } -> tensor<3x4xi64>119    return %r : tensor<3x4xi64>120  }121 122  //123  // Kernel that uses indices in the index notation (disjunction).124  //125  func.func @sparse_index_2d_disj(%arga: tensor<3x4xi64, #SparseMatrix>)126      -> tensor<3x4xi64> {127    %out = tensor.empty() : tensor<3x4xi64>128    %r = linalg.generic #trait_2d129        ins(%arga: tensor<3x4xi64, #SparseMatrix>)130       outs(%out: tensor<3x4xi64>) {131        ^bb(%a: i64, %x: i64):132          %i = linalg.index 0 : index133          %j = linalg.index 1 : index134          %ii = arith.index_cast %i : index to i64135          %jj = arith.index_cast %j : index to i64136          %m1 = arith.addi %ii, %a : i64137          %m2 = arith.addi %jj, %m1 : i64138          linalg.yield %m2 : i64139    } -> tensor<3x4xi64>140    return %r : tensor<3x4xi64>141  }142 143  //144  // Main driver.145  //146  func.func @main() {147    %c0 = arith.constant 0 : index148    %du = arith.constant -1 : i64149 150    // Setup input sparse vector.151    %v1 = arith.constant sparse<[[2], [4]], [ 10, 20]> : tensor<8xi64>152    %sv = sparse_tensor.convert %v1 : tensor<8xi64> to tensor<8xi64, #SparseVector>153 154    // Setup input "sparse" vector.155    %v2 = arith.constant dense<[ 1,  2,  4,  8,  16,  32,  64,  128 ]> : tensor<8xi64>156    %dv = sparse_tensor.convert %v2 : tensor<8xi64> to tensor<8xi64, #SparseVector>157 158    // Setup input sparse matrix.159    %m1 = arith.constant sparse<[[1,1], [2,3]], [10, 20]> : tensor<3x4xi64>160    %sm = sparse_tensor.convert %m1 : tensor<3x4xi64> to tensor<3x4xi64, #SparseMatrix>161 162    // Setup input "sparse" matrix.163    %m2 = arith.constant dense <[ [ 1,  1,  1,  1 ],164                                  [ 1,  2,  1,  1 ],165                                  [ 1,  1,  3,  4 ] ]> : tensor<3x4xi64>166    %dm = sparse_tensor.convert %m2 : tensor<3x4xi64> to tensor<3x4xi64, #SparseMatrix>167 168    // Call the kernels.169    %0 = call @sparse_index_1d_conj(%sv) : (tensor<8xi64, #SparseVector>) -> tensor<8xi64>170    %1 = call @sparse_index_1d_disj(%sv) : (tensor<8xi64, #SparseVector>) -> tensor<8xi64>171    %2 = call @sparse_index_1d_conj(%dv) : (tensor<8xi64, #SparseVector>) -> tensor<8xi64>172    %3 = call @sparse_index_1d_disj(%dv) : (tensor<8xi64, #SparseVector>) -> tensor<8xi64>173    %4 = call @sparse_index_2d_conj(%sm) : (tensor<3x4xi64, #SparseMatrix>) -> tensor<3x4xi64>174    %5 = call @sparse_index_2d_disj(%sm) : (tensor<3x4xi64, #SparseMatrix>) -> tensor<3x4xi64>175    %6 = call @sparse_index_2d_conj(%dm) : (tensor<3x4xi64, #SparseMatrix>) -> tensor<3x4xi64>176    %7 = call @sparse_index_2d_disj(%dm) : (tensor<3x4xi64, #SparseMatrix>) -> tensor<3x4xi64>177 178    //179    // Verify result.180    //181    // CHECK:      ( 0, 0, 20, 0, 80, 0, 0, 0 )182    // CHECK-NEXT: ( 0, 1, 12, 3, 24, 5, 6, 7 )183    // CHECK-NEXT: ( 0, 2, 8, 24, 64, 160, 384, 896 )184    // CHECK-NEXT: ( 1, 3, 6, 11, 20, 37, 70, 135 )185    // CHECK-NEXT: ( ( 0, 0, 0, 0 ), ( 0, 10, 0, 0 ), ( 0, 0, 0, 120 ) )186    // CHECK-NEXT: ( ( 0, 1, 2, 3 ), ( 1, 12, 3, 4 ), ( 2, 3, 4, 25 ) )187    // CHECK-NEXT: ( ( 0, 0, 0, 0 ), ( 0, 2, 2, 3 ), ( 0, 2, 12, 24 ) )188    // CHECK-NEXT: ( ( 1, 2, 3, 4 ), ( 2, 4, 4, 5 ), ( 3, 4, 7, 9 ) )189    //190    %vv0 = vector.transfer_read %0[%c0], %du: tensor<8xi64>, vector<8xi64>191    %vv1 = vector.transfer_read %1[%c0], %du: tensor<8xi64>, vector<8xi64>192    %vv2 = vector.transfer_read %2[%c0], %du: tensor<8xi64>, vector<8xi64>193    %vv3 = vector.transfer_read %3[%c0], %du: tensor<8xi64>, vector<8xi64>194    %vv4 = vector.transfer_read %4[%c0,%c0], %du: tensor<3x4xi64>, vector<3x4xi64>195    %vv5 = vector.transfer_read %5[%c0,%c0], %du: tensor<3x4xi64>, vector<3x4xi64>196    %vv6 = vector.transfer_read %6[%c0,%c0], %du: tensor<3x4xi64>, vector<3x4xi64>197    %vv7 = vector.transfer_read %7[%c0,%c0], %du: tensor<3x4xi64>, vector<3x4xi64>198    vector.print %vv0 : vector<8xi64>199    vector.print %vv1 : vector<8xi64>200    vector.print %vv2 : vector<8xi64>201    vector.print %vv3 : vector<8xi64>202    vector.print %vv4 : vector<3x4xi64>203    vector.print %vv5 : vector<3x4xi64>204    vector.print %vv6 : vector<3x4xi64>205    vector.print %vv7 : vector<3x4xi64>206 207    // Release resources.208    bufferization.dealloc_tensor %sv : tensor<8xi64, #SparseVector>209    bufferization.dealloc_tensor %dv : tensor<8xi64, #SparseVector>210    bufferization.dealloc_tensor %sm : tensor<3x4xi64, #SparseMatrix>211    bufferization.dealloc_tensor %dm : tensor<3x4xi64, #SparseMatrix>212    bufferization.dealloc_tensor %0 : tensor<8xi64>213    bufferization.dealloc_tensor %1 : tensor<8xi64>214    bufferization.dealloc_tensor %2 : tensor<8xi64>215    bufferization.dealloc_tensor %3 : tensor<8xi64>216    bufferization.dealloc_tensor %4 : tensor<3x4xi64>217    bufferization.dealloc_tensor %5 : tensor<3x4xi64>218    bufferization.dealloc_tensor %6 : tensor<3x4xi64>219    bufferization.dealloc_tensor %7 : tensor<3x4xi64>220 221    return222  }223}224