1// RUN: mlir-opt %s -transform-interpreter -test-transform-dialect-erase-schedule -one-shot-bufferize="bufferize-function-boundaries" -buffer-deallocation-pipeline -lower-vector-mask --test-lower-to-llvm | \ 2// RUN: mlir-runner -e main -entry-point-result=void --shared-libs=%mlir_c_runner_utils,%mlir_runner_utils | \ 3// RUN: FileCheck %s 4 5func.func private @printMemrefF32(%ptr : tensor<*xf32>) 6 7func.func @main() { 8 %c4 = arith.constant 4 : index 9 %c8 = arith.constant 8 : index 10 11 %A = arith.constant dense<[ 12 [ 1.1, 2.1 ], 13 [ 1.2, 2.2 ], 14 [ 1.3, 2.3 ], 15 [ 1.4, 2.4 ], 16 [ 1.5, 2.5 ], 17 [ 1.6, 2.6 ], 18 [ 1.7, 2.7 ], 19 [ 1.8, 2.8 ] 20 ]> : tensor<8x2xf32> 21 %B = arith.constant dense<[ 22 [ 10.1, 11.1, 12.1, 13.1 ], 23 [ 10.2, 11.2, 12.2, 13.2 ] 24 ]> : tensor<2x4xf32> 25 %C_dyn = bufferization.alloc_tensor(%c8, %c4) : tensor<?x?xf32> 26 27 %A_dyn = tensor.cast %A : tensor<8x2xf32> to tensor<?x?xf32> 28 %B_dyn = tensor.cast %B : tensor<2x4xf32> to tensor<?x?xf32> 29 30 %c0_i32 = arith.constant 0 : i32 31 %C_init = linalg.fill ins(%c0_i32 : i32) outs(%C_dyn : tensor<?x?xf32>) -> tensor<?x?xf32> 32 33 %res = linalg.matmul ins(%A_dyn, %B_dyn: tensor<?x?xf32>, tensor<?x?xf32>) 34 outs(%C_init: tensor<?x?xf32>) -> tensor<?x?xf32> 35 %xf = tensor.cast %res : tensor<?x?xf32> to tensor<*xf32> 36 37 // CHECK: {{\[}}[32.53, 35.73, 38.93, 42.13], 38 // CHECK-NEXT: [34.56, 37.96, 41.36, 44.76], 39 // CHECK-NEXT: [36.59, 40.19, 43.79, 47.39], 40 // CHECK-NEXT: [38.62, 42.42, 46.22, 50.02], 41 // CHECK-NEXT: [0, 0, 0, 0], 42 // CHECK-NEXT: [0, 0, 0, 0], 43 // CHECK-NEXT: [0, 0, 0, 0], 44 // CHECK-NEXT: [0, 0, 0, 0]] 45 call @printMemrefF32(%xf) : (tensor<*xf32>) -> () 46 47 return 48} 49 50module attributes {transform.with_named_sequence} { 51 transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) { 52 %0 = transform.structured.match ops{["linalg.matmul"]} in %arg1 : (!transform.any_op) -> !transform.any_op 53 %func_op = transform.get_parent_op %0 : (!transform.any_op) -> !transform.op<"func.func"> 54 transform.structured.vectorize %0 vector_sizes [4, 4, 2] : !transform.any_op 55 transform.apply_patterns to %func_op { 56 transform.apply_patterns.vector.lower_multi_reduction lowering_strategy = "innerreduction" 57 } : !transform.op<"func.func"> 58 transform.yield 59 } 60} 61