brintos

brintos / llvm-project-archived public Read only

0
0
Text · 20.7 KiB · c47824a Raw
312 lines · plain
1// RUN: mlir-opt -split-input-file -transform-interpreter %s | FileCheck %s2 3///----------------------------------------------------------------------------------------4/// Tests for vectorizing depthwise convolutions (with patterns) with the5/// flattening of the channel dim enabled. This approach is beneficial when the6/// number of channel dimensions is low.7///----------------------------------------------------------------------------------------8 9func.func @depthwise_conv1d_nwc_wc_1x8x3xi8_tensor(%input: tensor<1x8x3xi8>,10                                                   %filter: tensor<1x3xi8>,11                                                   %output: tensor<1x8x3xi8>) -> (tensor<1x8x3xi8>) {12  %res = linalg.depthwise_conv_1d_nwc_wc13    {dilations = dense<1> : vector<1xi64>,14    strides = dense<1> : vector<1xi64>}15    ins(%input, %filter : tensor<1x8x3xi8>, tensor<1x3xi8>)16    outs(%output : tensor<1x8x3xi8>) -> tensor<1x8x3xi8>17  return %res : tensor<1x8x3xi8>18}19 20module attributes {transform.with_named_sequence} {21  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {22    %0 = transform.structured.match ops{["linalg.depthwise_conv_1d_nwc_wc"]} in %arg0 : (!transform.any_op) -> !transform.any_op23    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op24    %2 = transform.structured.vectorize_children_and_apply_patterns %1 {flatten_1d_depthwise_conv} : (!transform.any_op) -> !transform.any_op25    transform.yield26  }27}28// CHECK-LABEL:   func.func @depthwise_conv1d_nwc_wc_1x8x3xi8_tensor29// CHECK-SAME:      %[[INPUT:.*]]: tensor<1x8x3xi8>,30// CHECK-SAME:      %[[FILTER:.*]]: tensor<1x3xi8>,31// CHECK-SAME:      %[[OUTPUT:.*]]: tensor<1x8x3xi8>) -> tensor<1x8x3xi8> {32 33// CHECK-DAG:       %[[C0_IDX:.*]] = arith.constant 0 : index34 35/// Read the whole data in one shot.36// CHECK:           %[[V_INPUT_R:.*]] = vector.transfer_read %[[INPUT]][%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]]37// CHECK:           %[[V_FILTER_R:.*]] = vector.transfer_read %[[FILTER]][%[[C0_IDX]], %[[C0_IDX]]]38// CHECK:           %[[V_OUTPUT_R:.*]] = vector.transfer_read %[[OUTPUT]][%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]]39 40// CHECK:           %[[V_FILTER_0:.*]] = vector.extract %[[V_FILTER_R]][0] : vector<3xi8> from vector<1x3xi8>41 42/// w == 0, kw = 043// CHECK:           %[[SC_INPUT:.*]] = vector.shape_cast %[[V_INPUT_R]] : vector<1x8x3xi8> to vector<1x24xi8>44// CHECK:           %[[SC_OUTPUT:.*]] = vector.shape_cast %[[V_OUTPUT_R]] : vector<1x8x3xi8> to vector<1x24xi8>45// CHECK:           %[[SH_FILTER_0:.*]] = vector.shuffle %[[V_FILTER_0]], %[[V_FILTER_0]]46// CHECK-SAME:        [0, 1, 2, 0, 1, 2, 0, 1, 2, 0, 1, 2, 0, 1, 2, 0, 1, 2, 0, 1, 2, 0, 1, 2] : vector<3xi8>, vector<3xi8>47// CHECK:           %[[B_FILTER:.*]] = vector.broadcast %[[SH_FILTER_0]] : vector<24xi8> to vector<1x24xi8>48// CHECK:           %[[MULI:.*]] = arith.muli %[[SC_INPUT]], %[[B_FILTER]] : vector<1x24xi8>49// CHECK:           %[[ADDI:.*]] = arith.addi %[[MULI]], %[[SC_OUTPUT]] : vector<1x24xi8>50 51// Write the result back in one shot.52// CHECK:           %[[SC_ADDI:.*]] = vector.shape_cast %[[ADDI]] : vector<1x24xi8> to vector<1x8x3xi8>53// CHECK:           vector.transfer_write %[[SC_ADDI]], %[[OUTPUT]][%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]]54 55//------56 57func.func @depthwise_conv1d_nwc_wc_3x5x4xf32_memref_dillation_2(%input: memref<3x5x4xf32>,58                                                                %filter: memref<2x4xf32>,59                                                                %output: memref<3x2x4xf32>) {60  linalg.depthwise_conv_1d_nwc_wc61    {dilations = dense<2> : tensor<1xi64>, strides = dense<1> : tensor<1xi64>}62    ins(%input, %filter : memref<3x5x4xf32>, memref<2x4xf32>)63    outs(%output : memref<3x2x4xf32>)64  return65}66 67//       CHECK: func @depthwise_conv1d_nwc_wc_3x5x4xf32_memref_dillation_268//  CHECK-SAME:   (%[[INPUT:[0-9a-z]+]]: memref<3x5x4xf32>, %[[FILTER:[0-9a-z]+]]: memref<2x4xf32>, %[[OUTPUT:[0-9a-z]+]]: memref<3x2x4xf32>)69 70//   CHECK-DAG:   %[[C0:.+]] = arith.constant 0 : index71//   CHECK-DAG:   %[[F0:.+]] = arith.constant 0.000000e+00 : f3272 73/// Read the whole data in one shot.74//      CHECK-DAG:   %[[V_INPUT_R:.+]] = vector.transfer_read %[[INPUT]][%[[C0]], %[[C0]], %[[C0]]]75//      CHECK-DAG:  %[[V_FILTER_R:.+]] = vector.transfer_read %[[FILTER]][%[[C0]], %[[C0]]]76//      CHECK-DAG:  %[[V_OUTPUT_R:.+]] = vector.transfer_read %[[OUTPUT]][%[[C0]], %[[C0]], %[[C0]]]77 78//      CHECK:   %[[V_INPUT_0:.+]] = vector.extract_strided_slice %[[V_INPUT_R]]79// CHECK-SAME:     {offsets = [0, 0, 0], sizes = [3, 2, 4], strides = [1, 1, 1]} : vector<3x4x4xf32> to vector<3x2x4xf32>80//      CHECK:   %[[V_INPUT_1:.+]] = vector.extract_strided_slice %[[V_INPUT_R]]81// CHECK-SAME:     {offsets = [0, 2, 0], sizes = [3, 2, 4], strides = [1, 1, 1]} : vector<3x4x4xf32> to vector<3x2x4xf32>82 83//      CHECK:  %[[V_FILTER_0:.+]] = vector.extract %[[V_FILTER_R]][0] : vector<4xf32> from vector<2x4xf32>84//      CHECK:  %[[V_FILTER_1:.+]] = vector.extract %[[V_FILTER_R]][1] : vector<4xf32> from vector<2x4xf32>85 86 87/// w == 0, kw = 088// CHECK:           %[[SC_V_INPUT_0:.*]] = vector.shape_cast %[[V_INPUT_0]] : vector<3x2x4xf32> to vector<3x8xf32>89// CHECK:           %[[SC_V_OUTPUT_R:.*]] = vector.shape_cast %[[V_OUTPUT_R]] : vector<3x2x4xf32> to vector<3x8xf32>90// CHECK:           %[[SH_FILTER_0:.*]] = vector.shuffle %[[V_FILTER_0]], %[[V_FILTER_0]] 91// CHECK-SAME:        [0, 1, 2, 3, 0, 1, 2, 3] : vector<4xf32>, vector<4xf32>92// CHECK:           %[[B_FILTER_0:.*]] = vector.broadcast %[[SH_FILTER_0]] : vector<8xf32> to vector<3x8xf32>93// CHECK:           %[[FMA_0:.*]] = vector.fma %[[SC_V_INPUT_0]], %[[B_FILTER_0]], %[[SC_V_OUTPUT_R]] : vector<3x8xf32>94 95/// w == 0, kw = 196// CHECK:           %[[SC_V_INPUT_1:.*]] = vector.shape_cast %[[V_INPUT_1]] : vector<3x2x4xf32> to vector<3x8xf32>97// CHECK:           %[[SH_FILTER_1:.*]] = vector.shuffle %[[V_FILTER_1]], %[[V_FILTER_1]] 98// CHECK-SAME:        [0, 1, 2, 3, 0, 1, 2, 3] : vector<4xf32>, vector<4xf32>99// CHECK:           %[[B_FILTER_1:.*]] = vector.broadcast %[[SH_FILTER_1]] : vector<8xf32> to vector<3x8xf32>100// CHECK:           %[[FMA_1:.*]] = vector.fma %[[SC_V_INPUT_1]], %[[B_FILTER_1]], %[[FMA_0]] : vector<3x8xf32>101 102// Write the result back in one shot.103//      CHECK:   %[[SC_FMA_1:.*]] = vector.shape_cast %[[FMA_1]] : vector<3x8xf32> to vector<3x2x4xf32>104//      CHECK:   vector.transfer_write %[[SC_FMA_1]], %[[OUTPUT]][%[[C0]], %[[C0]], %[[C0]]]105 106 107module attributes {transform.with_named_sequence} {108  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {109    %0 = transform.structured.match ops{["linalg.depthwise_conv_1d_nwc_wc"]} in %arg0 : (!transform.any_op) -> !transform.any_op110    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op111    %2 = transform.structured.vectorize_children_and_apply_patterns %1 {flatten_1d_depthwise_conv} : (!transform.any_op) -> !transform.any_op112    transform.yield113  }114}115 116// -----117 118func.func @depthwise_conv1d_nwc_wc_3x5x4xi8_memref_dilation_2(%input: memref<3x5x4xi8>,119                                                              %filter: memref<2x4xi8>,120                                                              %output: memref<3x2x4xi32>) {121  linalg.depthwise_conv_1d_nwc_wc122    {dilations = dense<2> : tensor<1xi64>, strides = dense<1> : tensor<1xi64>}123    ins(%input, %filter : memref<3x5x4xi8>, memref<2x4xi8>)124    outs(%output : memref<3x2x4xi32>)125  return126}127 128//       CHECK: func @depthwise_conv1d_nwc_wc_3x5x4xi8_memref_dilation_2129//  CHECK-SAME:   (%[[INPUT:[0-9a-z]+]]: memref<3x5x4xi8>, %[[FILTER:[0-9a-z]+]]: memref<2x4xi8>, %[[OUTPUT:[0-9a-z]+]]: memref<3x2x4xi32>)130 131//   CHECK-DAG:   %[[C0:.+]] = arith.constant 0 : index132 133/// Read the whole data in one shot.134//      CHECK-DAG:   %[[V_INPUT_R:.+]] = vector.transfer_read %[[INPUT]][%[[C0]], %[[C0]], %[[C0]]]135//      CHECK-DAG:  %[[V_FILTER_R:.+]] = vector.transfer_read %[[FILTER]][%[[C0]], %[[C0]]]136//      CHECK-DAG:  %[[V_OUTPUT_R:.+]] = vector.transfer_read %[[OUTPUT]][%[[C0]], %[[C0]], %[[C0]]]137 138//      CHECK:   %[[V_INPUT_0:.+]] = vector.extract_strided_slice %[[V_INPUT_R]]139// CHECK-SAME:     {offsets = [0, 0, 0], sizes = [3, 2, 4], strides = [1, 1, 1]} : vector<3x4x4xi8> to vector<3x2x4xi8>140//      CHECK:   %[[V_INPUT_1:.+]] = vector.extract_strided_slice %[[V_INPUT_R]]141// CHECK-SAME:     {offsets = [0, 2, 0], sizes = [3, 2, 4], strides = [1, 1, 1]} : vector<3x4x4xi8> to vector<3x2x4xi8>142 143//      CHECK:  %[[V_FILTER_0:.+]] = vector.extract %[[V_FILTER_R]][0] : vector<4xi8> from vector<2x4xi8>144//      CHECK:  %[[V_FILTER_1:.+]] = vector.extract %[[V_FILTER_R]][1] : vector<4xi8> from vector<2x4xi8>145 146/// w == 0, kw = 0147//      CHECK:  %[[SC_V_INPUT_0:.*]] = vector.shape_cast %[[V_INPUT_0]] : vector<3x2x4xi8> to vector<3x8xi8>148//      CHECK:  %[[SC_V_OUTPUT_R:.*]] = vector.shape_cast %[[V_OUTPUT_R]] : vector<3x2x4xi32> to vector<3x8xi32>149//      CHECK:  %[[EXT_INPUT_0:.*]] = arith.extsi %[[SC_V_INPUT_0]] : vector<3x8xi8> to vector<3x8xi32>150//      CHECK:  %[[SH_FILTER_0:.*]] = vector.shuffle %[[V_FILTER_0]], %[[V_FILTER_0]]151//      CHECK-SAME:  [0, 1, 2, 3, 0, 1, 2, 3] : vector<4xi8>, vector<4xi8>152//      CHECK:  %[[EXT_FILTER_0:.*]] = arith.extsi %[[SH_FILTER_0]] : vector<8xi8> to vector<8xi32>153//      CHECK:  %[[B_FILTER_0:.*]] = vector.broadcast %[[EXT_FILTER_0]] : vector<8xi32> to vector<3x8xi32>154//      CHECK:  %[[MUL_0:.*]] = arith.muli %[[EXT_INPUT_0]], %[[B_FILTER_0]] : vector<3x8xi32>155//      CHECK:  %[[ADD_0:.*]] = arith.addi %[[MUL_0]], %[[SC_V_OUTPUT_R]] : vector<3x8xi32>156 157/// w == 0, kw = 1158//      CHECK:  %[[SC_V_INPUT_1:.*]] = vector.shape_cast %[[V_INPUT_1]] : vector<3x2x4xi8> to vector<3x8xi8>159//      CHECK:  %[[EXT_INPUT_1:.*]] = arith.extsi %[[SC_V_INPUT_1]] : vector<3x8xi8> to vector<3x8xi32>160//      CHECK:  %[[SH_FILTER_1:.*]] = vector.shuffle %[[V_FILTER_1]], %[[V_FILTER_1]]161//      CHECK-SAME:  [0, 1, 2, 3, 0, 1, 2, 3] : vector<4xi8>, vector<4xi8>162//      CHECK:  %[[EXT_FILTER_1:.*]] = arith.extsi %[[SH_FILTER_1]] : vector<8xi8> to vector<8xi32>163//      CHECK:  %[[B_FILTER_1:.*]] = vector.broadcast %[[EXT_FILTER_1]] : vector<8xi32> to vector<3x8xi32>164//      CHECK:  %[[MUL_1:.*]] = arith.muli %[[EXT_INPUT_1]], %[[B_FILTER_1]] : vector<3x8xi32>165//      CHECK:  %[[ADD_1:.*]] = arith.addi %[[MUL_1]], %[[ADD_0]] : vector<3x8xi32>166 167// Write the result back in one shot.168//      CHECK:   %[[SC_ADD_1:.*]] = vector.shape_cast %[[ADD_1]] : vector<3x8xi32> to vector<3x2x4xi32>169//      CHECK:   vector.transfer_write %[[SC_ADD_1]], %[[OUTPUT]][%[[C0]], %[[C0]], %[[C0]]]170 171module attributes {transform.with_named_sequence} {172  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {173    %0 = transform.structured.match ops{["linalg.depthwise_conv_1d_nwc_wc"]} in %arg0 : (!transform.any_op) -> !transform.any_op174    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op175    %2 = transform.structured.vectorize_children_and_apply_patterns %1 {flatten_1d_depthwise_conv} : (!transform.any_op) -> !transform.any_op176    transform.yield177  }178}179 180// -----181 182func.func @depthwise_conv1d_nwc_wc_3x9x4xi8_tensor_stride_2(%input: tensor<3x9x4xi8>,183                                                            %filter: tensor<3x4xi8>,184                                                            %output: tensor<3x3x4xi8>) -> tensor<3x3x4xi8> {185  %res = linalg.depthwise_conv_1d_nwc_wc186    {dilations = dense<1> : tensor<1xi64>, strides = dense<2> : tensor<1xi64>}187    ins(%input, %filter : tensor<3x9x4xi8>, tensor<3x4xi8>)188    outs(%output : tensor<3x3x4xi8>) -> tensor<3x3x4xi8>189  return %res : tensor<3x3x4xi8>190}191// CHECK-LABEL:   func.func @depthwise_conv1d_nwc_wc_3x9x4xi8_tensor_stride_2192// CHECK-SAME:      %[[INPUT:.*]]: tensor<3x9x4xi8>,193// CHECK-SAME:      %[[FILTER:.*]]: tensor<3x4xi8>,194// CHECK-SAME:      %[[OUTPUT:.*]]: tensor<3x3x4xi8>) -> tensor<3x3x4xi8> {195 196// CHECK-DAG:           %[[C0_IDX:.*]] = arith.constant 0 : index197// CHECK-DAG:           %[[C0_I8:.*]] = arith.constant 0 : i8198 199/// Read the whole data in one shot.200// CHECK:           %[[V_INPUT_R:.*]] = vector.transfer_read %[[INPUT]][%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]], %[[C0_I8]]201// CHECK:           %[[V_FILTER_R:.*]] = vector.transfer_read %[[FILTER]][%[[C0_IDX]], %[[C0_IDX]]], %[[C0_I8]]202// CHECK:           %[[V_OUTPUT_R:.*]] = vector.transfer_read %[[OUTPUT]][%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]], %[[C0_I8]]203 204// CHECK:           %[[V_INPUT_0:.*]] = vector.extract_strided_slice %[[V_INPUT_R]]205// CHECK-SAME:        {offsets = [0, 0, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x7x4xi8> to vector<3x1x4xi8>206// CHECK:           %[[V_INPUT_1:.*]] = vector.extract_strided_slice %[[V_INPUT_R]]207// CHECK-SAME:        {offsets = [0, 2, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x7x4xi8> to vector<3x1x4xi8>208// CHECK:           %[[V_INPUT_2:.*]] = vector.extract_strided_slice %[[V_INPUT_R]] 209// CHECK-SAME:        {offsets = [0, 4, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x7x4xi8> to vector<3x1x4xi8>210// CHECK:           %[[V_INPUT_3:.*]] = vector.extract_strided_slice %[[V_INPUT_R]]211// CHECK-SAME:        {offsets = [0, 1, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x7x4xi8> to vector<3x1x4xi8>212// CHECK:           %[[V_INPUT_4:.*]] = vector.extract_strided_slice %[[V_INPUT_R]]213// CHECK-SAME:        {offsets = [0, 3, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x7x4xi8> to vector<3x1x4xi8>214// CHECK:           %[[V_INPUT_5:.*]] = vector.extract_strided_slice %[[V_INPUT_R]]215// CHECK-SAME:        {offsets = [0, 5, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x7x4xi8> to vector<3x1x4xi8>216// CHECK:           %[[V_INPUT_6:.*]] = vector.extract_strided_slice %[[V_INPUT_R]]217// CHECK-SAME:        {offsets = [0, 2, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x7x4xi8> to vector<3x1x4xi8>218// CHECK:           %[[V_INPUT_7:.*]] = vector.extract_strided_slice %[[V_INPUT_R]]219// CHECK-SAME:        {offsets = [0, 4, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x7x4xi8> to vector<3x1x4xi8>220// CHECK:           %[[V_INPUT_8:.*]] = vector.extract_strided_slice %[[V_INPUT_R]]221// CHECK-SAME:        {offsets = [0, 6, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x7x4xi8> to vector<3x1x4xi8>222 223// CHECK:           %[[V_FILTER_0:.*]] = vector.extract %[[V_FILTER_R]][0] : vector<4xi8> from vector<3x4xi8>224// CHECK:           %[[V_FILTER_1:.*]] = vector.extract %[[V_FILTER_R]][1] : vector<4xi8> from vector<3x4xi8>225// CHECK:           %[[V_FILTER_2:.*]] = vector.extract %[[V_FILTER_R]][2] : vector<4xi8> from vector<3x4xi8>226 227// CHECK:           %[[V_OUTPUT_0:.*]] = vector.extract_strided_slice %[[V_OUTPUT_R]]228// CHECK-SAME:        {offsets = [0, 0, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x3x4xi8> to vector<3x1x4xi8>229// CHECK:           %[[V_OUTPUT_1:.*]] = vector.extract_strided_slice %[[V_OUTPUT_R]]230// CHECK-SAME:       {offsets = [0, 1, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x3x4xi8> to vector<3x1x4xi8>231// CHECK:           %[[V_OUTPUT_2:.*]] = vector.extract_strided_slice %[[V_OUTPUT_R]]232// CHECK-SAME:        {offsets = [0, 2, 0], sizes = [3, 1, 4], strides = [1, 1, 1]} : vector<3x3x4xi8> to vector<3x1x4xi8>233 234/// w == 0, kw == 0235// CHECK:           %[[VAL_23:.*]] = vector.shape_cast %[[V_INPUT_0]] : vector<3x1x4xi8> to vector<3x4xi8>236// CHECK:           %[[VAL_24:.*]] = vector.shape_cast %[[V_OUTPUT_0]] : vector<3x1x4xi8> to vector<3x4xi8>237// CHECK:           %[[B_FILTER_0:.*]] = vector.broadcast %[[V_FILTER_0]] : vector<4xi8> to vector<3x4xi8>238// CHECK:           %[[VAL_27:.*]] = arith.muli %[[VAL_23]], %[[B_FILTER_0]] : vector<3x4xi8>239// CHECK:           %[[VAL_28:.*]] = arith.addi %[[VAL_27]], %[[VAL_24]] : vector<3x4xi8>240 241/// w == 1, kw == 0242// CHECK:           %[[VAL_29:.*]] = vector.shape_cast %[[V_INPUT_1]] : vector<3x1x4xi8> to vector<3x4xi8>243// CHECK:           %[[VAL_30:.*]] = vector.shape_cast %[[V_OUTPUT_1]] : vector<3x1x4xi8> to vector<3x4xi8>244// CHECK:           %[[B_FILTER_0_1:.*]] = vector.broadcast %[[V_FILTER_0]] : vector<4xi8> to vector<3x4xi8>245// CHECK:           %[[VAL_33:.*]] = arith.muli %[[VAL_29]], %[[B_FILTER_0_1]] : vector<3x4xi8>246// CHECK:           %[[VAL_34:.*]] = arith.addi %[[VAL_33]], %[[VAL_30]] : vector<3x4xi8>247 248/// w == 2, kw == 0249// CHECK:           %[[VAL_35:.*]] = vector.shape_cast %[[V_INPUT_2]] : vector<3x1x4xi8> to vector<3x4xi8>250// CHECK:           %[[VAL_36:.*]] = vector.shape_cast %[[V_OUTPUT_2]] : vector<3x1x4xi8> to vector<3x4xi8>251// CHECK:           %[[B_FILTER_0_2:.*]] = vector.broadcast %[[V_FILTER_0]] : vector<4xi8> to vector<3x4xi8>252// CHECK:           %[[VAL_39:.*]] = arith.muli %[[VAL_35]], %[[B_FILTER_0_2]] : vector<3x4xi8>253// CHECK:           %[[VAL_40:.*]] = arith.addi %[[VAL_39]], %[[VAL_36]] : vector<3x4xi8>254 255/// w == 3, kw == 1256// CHECK:           %[[VAL_41:.*]] = vector.shape_cast %[[V_INPUT_3]] : vector<3x1x4xi8> to vector<3x4xi8>257// CHECK:           %[[B_FILTER_1:.*]] = vector.broadcast %[[V_FILTER_1]] : vector<4xi8> to vector<3x4xi8>258// CHECK:           %[[VAL_44:.*]] = arith.muli %[[VAL_41]], %[[B_FILTER_1]] : vector<3x4xi8>259// CHECK:           %[[VAL_45:.*]] = arith.addi %[[VAL_44]], %[[VAL_28]] : vector<3x4xi8>260 261/// w == 4, kw == 1262// CHECK:           %[[VAL_46:.*]] = vector.shape_cast %[[V_INPUT_4]] : vector<3x1x4xi8> to vector<3x4xi8>263// CHECK:           %[[B_FILTER_1_1:.*]] = vector.broadcast %[[V_FILTER_1]] : vector<4xi8> to vector<3x4xi8>264// CHECK:           %[[VAL_49:.*]] = arith.muli %[[VAL_46]], %[[B_FILTER_1_1]] : vector<3x4xi8>265// CHECK:           %[[VAL_50:.*]] = arith.addi %[[VAL_49]], %[[VAL_34]] : vector<3x4xi8>266 267/// w == 5, kw == 1268// CHECK:           %[[VAL_51:.*]] = vector.shape_cast %[[V_INPUT_5]] : vector<3x1x4xi8> to vector<3x4xi8>269// CHECK:           %[[B_FILTER_1_2:.*]] = vector.broadcast %[[V_FILTER_1]] : vector<4xi8> to vector<3x4xi8>270// CHECK:           %[[VAL_54:.*]] = arith.muli %[[VAL_51]], %[[B_FILTER_1_2]] : vector<3x4xi8>271// CHECK:           %[[VAL_55:.*]] = arith.addi %[[VAL_54]], %[[VAL_40]] : vector<3x4xi8>272 273/// w == 6, kw == 2274// CHECK:           %[[VAL_56:.*]] = vector.shape_cast %[[V_INPUT_6]] : vector<3x1x4xi8> to vector<3x4xi8>275// CHECK:           %[[B_FILTER_2:.*]] = vector.broadcast %[[V_FILTER_2]] : vector<4xi8> to vector<3x4xi8>276// CHECK:           %[[VAL_59:.*]] = arith.muli %[[VAL_56]], %[[B_FILTER_2]] : vector<3x4xi8>277// CHECK:           %[[VAL_60:.*]] = arith.addi %[[VAL_59]], %[[VAL_45]] : vector<3x4xi8>278 279/// w == 7, kw == 2280// CHECK:           %[[VAL_61:.*]] = vector.shape_cast %[[VAL_60]] : vector<3x4xi8> to vector<3x1x4xi8>281// CHECK:           %[[VAL_62:.*]] = vector.shape_cast %[[V_INPUT_7]] : vector<3x1x4xi8> to vector<3x4xi8>282// CHECK:           %[[B_FILTER_2_1:.*]] = vector.broadcast %[[V_FILTER_2]] : vector<4xi8> to vector<3x4xi8>283// CHECK:           %[[VAL_65:.*]] = arith.muli %[[VAL_62]], %[[B_FILTER_2_1]] : vector<3x4xi8>284// CHECK:           %[[VAL_66:.*]] = arith.addi %[[VAL_65]], %[[VAL_50]] : vector<3x4xi8>285 286/// w == 8, kw == 2287// CHECK:           %[[VAL_67:.*]] = vector.shape_cast %[[VAL_66]] : vector<3x4xi8> to vector<3x1x4xi8>288// CHECK:           %[[VAL_68:.*]] = vector.shape_cast %[[V_INPUT_8]] : vector<3x1x4xi8> to vector<3x4xi8>289// CHECK:           %[[B_FILTER_2_2:.*]] = vector.broadcast %[[V_FILTER_2]] : vector<4xi8> to vector<3x4xi8>290// CHECK:           %[[VAL_71:.*]] = arith.muli %[[VAL_68]], %[[B_FILTER_2_2]] : vector<3x4xi8>291// CHECK:           %[[VAL_72:.*]] = arith.addi %[[VAL_71]], %[[VAL_55]] : vector<3x4xi8>292 293// Write the result back.294// CHECK:           %[[VAL_73:.*]] = vector.shape_cast %[[VAL_72]] : vector<3x4xi8> to vector<3x1x4xi8>295// CHECK:           %[[VAL_74:.*]] = vector.insert_strided_slice %[[VAL_61]], %[[V_OUTPUT_R]]296// CHECK-SAME:        {offsets = [0, 0, 0], strides = [1, 1, 1]} : vector<3x1x4xi8> into vector<3x3x4xi8>297// CHECK:           %[[VAL_75:.*]] = vector.insert_strided_slice %[[VAL_67]], %[[VAL_74]]298// CHECK-SAME:        {offsets = [0, 1, 0], strides = [1, 1, 1]} : vector<3x1x4xi8> into vector<3x3x4xi8>299// CHECK:           %[[VAL_76:.*]] = vector.insert_strided_slice %[[VAL_73]], %[[VAL_75]]300// CHECK-SAME:        {offsets = [0, 2, 0], strides = [1, 1, 1]} : vector<3x1x4xi8> into vector<3x3x4xi8>301// CHECK:           %[[VAL_77:.*]] = vector.transfer_write %[[VAL_76]], %[[OUTPUT]][%[[C0_IDX]], %[[C0_IDX]], %[[C0_IDX]]]302 303module attributes {transform.with_named_sequence} {304  transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {305    %0 = transform.structured.match ops{["linalg.depthwise_conv_1d_nwc_wc"]} in %arg0 : (!transform.any_op) -> !transform.any_op306    %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op307    %2 = transform.structured.vectorize_children_and_apply_patterns %1 {flatten_1d_depthwise_conv} : (!transform.any_op) -> !transform.any_op308    transform.yield309  }310}311 312