| 1 |
// DEFINE: %{tosa-to-linalg-pipeline} = -pass-pipeline="builtin.module(func.func(tosa-infer-shapes,tosa-to-linalg-named,tosa-to-linalg,tosa-to-arith))" |
| 2 |
|
| 3 |
// RUN: mlir-opt %s \ |
| 4 |
// RUN: %{tosa-to-linalg-pipeline} \ |
| 5 |
// RUN: | mlir-opt \ |
| 6 |
// RUN: -one-shot-bufferize="bufferize-function-boundaries" \ |
| 7 |
// RUN: -buffer-deallocation-pipeline \ |
| 8 |
// RUN: -test-lower-to-llvm \ |
| 9 |
// RUN: | mlir-runner \ |
| 10 |
// RUN: -entry-point-result=void \ |
| 11 |
// RUN: -shared-libs=%mlir_runner_utils,%mlir_c_runner_utils \ |
| 12 |
// RUN: | FileCheck %s |
| 13 |
|
| 14 |
// Validate that the TOSA lowering for tosa.max_pool2d produces the same results when |
| 15 |
// for fully static and fully dynamic inputs. |
| 16 |
|
| 17 |
!tensor_type = tensor<1x4x4x1xf32> |
| 18 |
!memref_type = memref<1x4x4x1xf32> |
| 19 |
|
| 20 |
// Utility functions |
| 21 |
func.func private @printMemrefF32(memref<*xf32>) attributes { llvm.emit_c_interface } |
| 22 |
|
| 23 |
func.func @max_pool_static(%arg0: !tensor_type) -> (!tensor_type) { |
| 24 |
%0 = tosa.max_pool2d %arg0 { |
| 25 |
pad = array<i64: 1, 1, 1, 1>, |
| 26 |
kernel = array<i64: 3, 3>, |
| 27 |
stride = array<i64: 1, 1> |
| 28 |
} : (tensor<1x4x4x1xf32>) -> tensor<1x4x4x1xf32> |
| 29 |
return %0 : tensor<1x4x4x1xf32> |
| 30 |
} |
| 31 |
|
| 32 |
func.func @max_pool_dynamic(%arg0: tensor<?x?x?x?xf32>) -> (tensor<?x?x?x?xf32>) { |
| 33 |
%0 = tosa.max_pool2d %arg0 { |
| 34 |
pad = array<i64: 1, 1, 1, 1>, |
| 35 |
kernel = array<i64: 3, 3>, |
| 36 |
stride = array<i64: 1, 1> |
| 37 |
} : (tensor<?x?x?x?xf32>) -> tensor<?x?x?x?xf32> |
| 38 |
return %0 : tensor<?x?x?x?xf32> |
| 39 |
} |
| 40 |
|
| 41 |
// Test harness to compare the results of a fully statically shaped max_pool2d with |
| 42 |
// a fully dynamically shaped max_pool2d on the same inputs. |
| 43 |
func.func @main() { |
| 44 |
%A = arith.constant dense<[[ |
| 45 |
[[0.0], [0.1], [0.2], [0.3]], // H = 0 |
| 46 |
[[1.0], [1.1], [1.2], [1.3]], // H = 1 |
| 47 |
[[2.0], [2.1], [2.2], [2.3]], // H = 2 |
| 48 |
[[3.0], [3.1], [3.2], [3.3]] // H = 3 |
| 49 |
]]> : tensor<1x4x4x1xf32> |
| 50 |
|
| 51 |
%A_dynamic = tensor.cast %A : !tensor_type to tensor<?x?x?x?xf32> |
| 52 |
|
| 53 |
// Call both static and dynamically sized variants |
| 54 |
%result_static = func.call @max_pool_static(%A) : (!tensor_type) -> !tensor_type |
| 55 |
%result_dynamic = func.call @max_pool_dynamic(%A_dynamic) : (tensor<?x?x?x?xf32>) -> tensor<?x?x?x?xf32> |
| 56 |
|
| 57 |
%static_buffer = bufferization.to_buffer %result_static : !tensor_type to !memref_type |
| 58 |
%unranked_static_buffer = memref.cast %static_buffer : !memref_type to memref<*xf32> |
| 59 |
|
| 60 |
// CHECK: Unranked Memref base@ = {{.*}} rank = 4 offset = 0 sizes = [1, 4, 4, 1] strides = [16, 4, 1, 1] data = |
| 61 |
|
| 62 |
// CHECK-NEXT: 1.1 |
| 63 |
// CHECK-NEXT: 1.2 |
| 64 |
// CHECK-NEXT: 1.3 |
| 65 |
// CHECK-NEXT: 1.3 |
| 66 |
|
| 67 |
// CHECK-NEXT: 2.1 |
| 68 |
// CHECK-NEXT: 2.2 |
| 69 |
// CHECK-NEXT: 2.3 |
| 70 |
// CHECK-NEXT: 2.3 |
| 71 |
|
| 72 |
// CHECK-NEXT: 3.1 |
| 73 |
// CHECK-NEXT: 3.2 |
| 74 |
// CHECK-NEXT: 3.3 |
| 75 |
// CHECK-NEXT: 3.3 |
| 76 |
|
| 77 |
// CHECK-NEXT: 3.1 |
| 78 |
// CHECK-NEXT: 3.2 |
| 79 |
// CHECK-NEXT: 3.3 |
| 80 |
// CHECK-NEXT: 3.3 |
| 81 |
|
| 82 |
func.call @printMemrefF32(%unranked_static_buffer) : (memref<*xf32>) -> () |
| 83 |
|
| 84 |
%dynamic_buffer = bufferization.to_buffer %result_dynamic : tensor<?x?x?x?xf32> to memref<?x?x?x?xf32> |
| 85 |
%unranked_dynamic_buffer = memref.cast %dynamic_buffer : memref<?x?x?x?xf32> to memref<*xf32> |
| 86 |
|
| 87 |
// CHECK: Unranked Memref base@ = {{.*}} rank = 4 offset = 0 sizes = [1, 4, 4, 1] strides = [16, 4, 1, 1] data = |
| 88 |
// CHECK-NEXT: 1.1 |
| 89 |
// CHECK-NEXT: 1.2 |
| 90 |
// CHECK-NEXT: 1.3 |
| 91 |
// CHECK-NEXT: 1.3 |
| 92 |
|
| 93 |
// CHECK-NEXT: 2.1 |
| 94 |
// CHECK-NEXT: 2.2 |
| 95 |
// CHECK-NEXT: 2.3 |
| 96 |
// CHECK-NEXT: 2.3 |
| 97 |
|
| 98 |
// CHECK-NEXT: 3.1 |
| 99 |
// CHECK-NEXT: 3.2 |
| 100 |
// CHECK-NEXT: 3.3 |
| 101 |
// CHECK-NEXT: 3.3 |
| 102 |
|
| 103 |
// CHECK-NEXT: 3.1 |
| 104 |
// CHECK-NEXT: 3.2 |
| 105 |
// CHECK-NEXT: 3.3 |
| 106 |
// CHECK-NEXT: 3.3 |
| 107 |
|
| 108 |
func.call @printMemrefF32(%unranked_dynamic_buffer) : (memref<*xf32>) -> () |
| 109 |
|
| 110 |
return |
| 111 |
} |
| 112 |
|