brintos

brintos / llvm-project-archived public Read only

0
0
Text · 5.8 KiB · 75d3c76 Raw
151 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#SV = #sparse_tensor.encoding<{ map = (d0) -> (d0 : compressed) }>35 36#trait_reduction = {37  indexing_maps = [38    affine_map<(i) -> (i)>,  // a39    affine_map<(i) -> ()>    // x (scalar out)40  ],41  iterator_types = ["reduction"],42  doc = "x += MIN_i a(i)"43}44 45// Examples of sparse vector MIN reductions.46module {47 48  // Custom MIN reduction: stored i32 elements only.49  func.func @min1(%arga: tensor<32xi32, #SV>, %argx: tensor<i32>) -> tensor<i32> {50    %c = tensor.extract %argx[] : tensor<i32>51    %0 = linalg.generic #trait_reduction52      ins(%arga: tensor<32xi32, #SV>)53      outs(%argx: tensor<i32>) {54        ^bb(%a: i32, %b: i32):55          %1 = sparse_tensor.reduce %a, %b, %c : i32 {56            ^bb0(%x: i32, %y: i32):57	      %m = arith.minsi %x, %y : i3258              sparse_tensor.yield %m : i3259          }60          linalg.yield %1 : i3261    } -> tensor<i32>62    return %0 : tensor<i32>63  }64 65  // Regular MIN reduction: stored i32 elements AND implicit zeros.66  // Note that dealing with the implicit zeros is taken care of67  // by the sparsifier to preserve semantics of the "original".68  func.func @min2(%arga: tensor<32xi32, #SV>, %argx: tensor<i32>) -> tensor<i32> {69    %c = tensor.extract %argx[] : tensor<i32>70    %0 = linalg.generic #trait_reduction71      ins(%arga: tensor<32xi32, #SV>)72      outs(%argx: tensor<i32>) {73        ^bb(%a: i32, %b: i32):74	  %m = arith.minsi %a, %b : i3275          linalg.yield %m : i3276    } -> tensor<i32>77    return %0 : tensor<i32>78  }79 80  func.func @dump_i32(%arg0 : tensor<i32>) {81    %v = tensor.extract %arg0[] : tensor<i32>82    vector.print %v : i3283    return84  }85 86  func.func @main() {87    %ri = arith.constant dense<999> : tensor<i32>88 89    // Vectors with a few zeros.90    %c_0_i32 = arith.constant dense<[91      2, 2, 7, 2, 2, 2, 2, 2, 0, 2, 2, 2, 2, 2, 2, 2,92      2, 2, 2, 2, 3, 0, 9, 2, 2, 2, 2, 0, 5, 1, 7, 393    ]> : tensor<32xi32>94 95    // Vectors with no zeros.96    %c_1_i32 = arith.constant dense<[97      2, 2, 7, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2,98      2, 2, 2, 2, 3, 2, 7, 2, 2, 2, 2, 2, 2, 1, 7, 399    ]> : tensor<32xi32>100 101    // Convert constants to annotated tensors. Note that this102    // particular conversion only stores nonzero elements,103    // so we will have no explicit zeros, only implicit zeros.104    %sv0 = sparse_tensor.convert %c_0_i32105      : tensor<32xi32> to tensor<32xi32, #SV>106    %sv1 = sparse_tensor.convert %c_1_i32107      : tensor<32xi32> to tensor<32xi32, #SV>108 109    // Special case, construct a sparse vector with an explicit zero.110    %v = arith.constant sparse< [ [1], [7] ], [ 0, 22 ] > : tensor<32xi32>111    %sv2 = sparse_tensor.convert %v: tensor<32xi32> to tensor<32xi32, #SV>112 113    // Call the kernels.114    %0 = call @min1(%sv0, %ri) : (tensor<32xi32, #SV>, tensor<i32>) -> tensor<i32>115    %1 = call @min1(%sv1, %ri) : (tensor<32xi32, #SV>, tensor<i32>) -> tensor<i32>116    %2 = call @min1(%sv2, %ri) : (tensor<32xi32, #SV>, tensor<i32>) -> tensor<i32>117    %3 = call @min2(%sv0, %ri) : (tensor<32xi32, #SV>, tensor<i32>) -> tensor<i32>118    %4 = call @min2(%sv1, %ri) : (tensor<32xi32, #SV>, tensor<i32>) -> tensor<i32>119    %5 = call @min2(%sv2, %ri) : (tensor<32xi32, #SV>, tensor<i32>) -> tensor<i32>120 121    // Verify results.122    //123    // CHECK: 1124    // CHECK: 1125    // CHECK: 0126    // CHECK: 0127    // CHECK: 1128    // CHECK: 0129    //130    call @dump_i32(%0) : (tensor<i32>) -> ()131    call @dump_i32(%1) : (tensor<i32>) -> ()132    call @dump_i32(%2) : (tensor<i32>) -> ()133    call @dump_i32(%3) : (tensor<i32>) -> ()134    call @dump_i32(%4) : (tensor<i32>) -> ()135    call @dump_i32(%5) : (tensor<i32>) -> ()136 137    // Release the resources.138    bufferization.dealloc_tensor %sv0 : tensor<32xi32, #SV>139    bufferization.dealloc_tensor %sv1 : tensor<32xi32, #SV>140    bufferization.dealloc_tensor %sv2 : tensor<32xi32, #SV>141    bufferization.dealloc_tensor %0 : tensor<i32>142    bufferization.dealloc_tensor %1 : tensor<i32>143    bufferization.dealloc_tensor %2 : tensor<i32>144    bufferization.dealloc_tensor %3 : tensor<i32>145    bufferization.dealloc_tensor %4 : tensor<i32>146    bufferization.dealloc_tensor %5 : tensor<i32>147 148    return149  }150}151