1// NOTE: Assertions have been autogenerated by utils/generate-test-checks.py 2// RUN: mlir-opt %s -sparsification | FileCheck %s 3 4#SpVec = #sparse_tensor.encoding<{ dimLevelType = [ "compressed" ] }> 5#CSR = #sparse_tensor.encoding<{ dimLevelType = [ "dense", "compressed" ] }> 6 7#trait1 = { 8 indexing_maps = [ 9 affine_map<(i) -> (i)>, // a 10 affine_map<(i) -> (3)>, // b 11 affine_map<(i) -> (i)> // x (out) 12 ], 13 iterator_types = ["parallel"], 14 doc = "x(i) += a(i) * b(3)" 15} 16 17// CHECK-LABEL: func @mul_inv_dense1d( 18// CHECK-SAME: %[[VAL_0:.*]]: tensor<32xf32, #sparse_tensor.encoding<{{{.*}}}>>, 19// CHECK-SAME: %[[VAL_1:.*]]: tensor<4xf32>, 20// CHECK-SAME: %[[VAL_2:.*]]: tensor<32xf32>) -> tensor<32xf32> { 21// CHECK-DAG: %[[VAL_3:.*]] = arith.constant 0 : index 22// CHECK-DAG: %[[VAL_4:.*]] = arith.constant 3 : index 23// CHECK-DAG: %[[VAL_5:.*]] = arith.constant 1 : index 24// CHECK-DAG: %[[VAL_6:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_3]] : tensor<32xf32, #sparse_tensor.encoding<{{{.*}}}>> 25// CHECK-DAG: %[[VAL_7:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_3]] : tensor<32xf32, #sparse_tensor.encoding<{{{.*}}}>> 26// CHECK-DAG: %[[VAL_8:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32xf32, #sparse_tensor.encoding<{{{.*}}}>> 27// CHECK-DAG: %[[VAL_9:.*]] = bufferization.to_memref %[[VAL_1]] : memref<4xf32> 28// CHECK-DAG: %[[VAL_10:.*]] = bufferization.to_memref %[[VAL_2]] : memref<32xf32> 29// CHECK-DAG: %[[VAL_11:.*]] = memref.alloc() : memref<32xf32> 30// CHECK: memref.copy %[[VAL_10]], %[[VAL_11]] : memref<32xf32> to memref<32xf32> 31// CHECK: %[[VAL_12:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_4]]] : memref<4xf32> 32// CHECK: %[[VAL_13:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_3]]] : memref<?xindex> 33// CHECK: %[[VAL_14:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex> 34// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_13]] to %[[VAL_14]] step %[[VAL_5]] { 35// CHECK: %[[VAL_16:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xindex> 36// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_16]]] : memref<32xf32> 37// CHECK: %[[VAL_18:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref<?xf32> 38// CHECK: %[[VAL_19:.*]] = arith.mulf %[[VAL_18]], %[[VAL_12]] : f32 39// CHECK: %[[VAL_20:.*]] = arith.addf %[[VAL_17]], %[[VAL_19]] : f32 40// CHECK: memref.store %[[VAL_20]], %[[VAL_11]]{{\[}}%[[VAL_16]]] : memref<32xf32> 41// CHECK: } 42// CHECK: %[[VAL_21:.*]] = bufferization.to_tensor %[[VAL_11]] : memref<32xf32> 43// CHECK: return %[[VAL_21]] : tensor<32xf32> 44// CHECK: } 45func.func @mul_inv_dense1d(%arga: tensor<32xf32, #SpVec>, 46 %argb: tensor<4xf32>, 47 %argx: tensor<32xf32>) -> tensor<32xf32> { 48 %0 = linalg.generic #trait1 49 ins(%arga, %argb: tensor<32xf32, #SpVec>, tensor<4xf32>) 50 outs(%argx: tensor<32xf32>) { 51 ^bb(%a: f32, %b: f32, %x: f32): 52 %0 = arith.mulf %a, %b : f32 53 %1 = arith.addf %x, %0 : f32 54 linalg.yield %1 : f32 55 } -> tensor<32xf32> 56 return %0 : tensor<32xf32> 57} 58 59#trait2 = { 60 indexing_maps = [ 61 affine_map<(i) -> (i)>, // a 62 affine_map<(i) -> (i+2)>, // b 63 affine_map<(i) -> (i)> // x (out) 64 ], 65 iterator_types = ["parallel"], 66 doc = "x(i) = a(i) & b(i+2)" 67} 68 69// CHECK-LABEL: func @and_affine_dense1d( 70// CHECK-SAME: %[[VAL_0:.*]]: tensor<32xi32, #sparse_tensor.encoding<{{{.*}}}>>, 71// CHECK-SAME: %[[VAL_1:.*]]: tensor<34xi32>, 72// CHECK-SAME: %[[VAL_2:.*]]: tensor<32xi32>) -> tensor<32xi32> { 73// CHECK-DAG: %[[VAL_3:.*]] = arith.constant 0 : index 74// CHECK-DAG: %[[VAL_4:.*]] = arith.constant 1 : index 75// CHECK-DAG: %[[VAL_5:.*]] = arith.constant 2 : index 76// CHECK-DAG: %[[VAL_6:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_3]] : tensor<32xi32, #sparse_tensor.encoding<{{{.*}}}>> 77// CHECK-DAG: %[[VAL_7:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_3]] : tensor<32xi32, #sparse_tensor.encoding<{{{.*}}}>> 78// CHECK-DAG: %[[VAL_8:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32xi32, #sparse_tensor.encoding<{{{.*}}}>> 79// CHECK-DAG: %[[VAL_9:.*]] = bufferization.to_memref %[[VAL_1]] : memref<34xi32> 80// CHECK-DAG: %[[VAL_10:.*]] = bufferization.to_memref %[[VAL_2]] : memref<32xi32> 81// CHECK-DAG: %[[VAL_11:.*]] = memref.alloc() : memref<32xi32> 82// CHECK: memref.copy %[[VAL_10]], %[[VAL_11]] : memref<32xi32> to memref<32xi32> 83// CHECK: %[[VAL_12:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_3]]] : memref<?xindex> 84// CHECK: %[[VAL_13:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex> 85// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_12]] to %[[VAL_13]] step %[[VAL_4]] { 86// CHECK: %[[VAL_15:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref<?xindex> 87// CHECK: %[[VAL_16:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_14]]] : memref<?xi32> 88// CHECK: %[[VAL_17:.*]] = arith.addi %[[VAL_15]], %[[VAL_5]] : index 89// CHECK: %[[VAL_18:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_17]]] : memref<34xi32> 90// CHECK: %[[VAL_19:.*]] = arith.andi %[[VAL_16]], %[[VAL_18]] : i32 91// CHECK: memref.store %[[VAL_19]], %[[VAL_11]]{{\[}}%[[VAL_15]]] : memref<32xi32> 92// CHECK: } 93// CHECK: %[[VAL_20:.*]] = bufferization.to_tensor %[[VAL_11]] : memref<32xi32> 94// CHECK: return %[[VAL_20]] : tensor<32xi32> 95// CHECK: } 96func.func @and_affine_dense1d(%arga: tensor<32xi32, #SpVec>, 97 %argb: tensor<34xi32>, 98 %argx: tensor<32xi32>) -> tensor<32xi32> { 99 %0 = linalg.generic #trait2 100 ins(%arga, %argb: tensor<32xi32, #SpVec>, tensor<34xi32>) 101 outs(%argx: tensor<32xi32>) { 102 ^bb(%a: i32, %b: i32, %x: i32): 103 %0 = arith.andi %a, %b : i32 104 linalg.yield %0 : i32 105 } -> tensor<32xi32> 106 return %0 : tensor<32xi32> 107} 108 109#trait3 = { 110 indexing_maps = [ 111 affine_map<(i,j) -> (i,j)>, // a 112 affine_map<(i,j) -> (i+2,j+3)>, // b 113 affine_map<(i,j) -> (i,j)> // x (out) 114 ], 115 iterator_types = ["parallel","parallel"], 116 doc = "x(i,j) += a(i,j) * b(i+2,j+3)" 117} 118 119// CHECK-LABEL: func @mul_affine_dense2d( 120// CHECK-SAME: %[[VAL_0:.*]]: tensor<32x16xf64, #sparse_tensor.encoding<{{{.*}}}>>, 121// CHECK-SAME: %[[VAL_1:.*]]: tensor<34x19xf64>, 122// CHECK-SAME: %[[VAL_2:.*]]: tensor<32x16xf64>) -> tensor<32x16xf64> { 123// CHECK-DAG: %[[VAL_3:.*]] = arith.constant 1 : index 124// CHECK-DAG: %[[VAL_4:.*]] = arith.constant 32 : index 125// CHECK-DAG: %[[VAL_5:.*]] = arith.constant 0 : index 126// CHECK-DAG: %[[VAL_6:.*]] = arith.constant 2 : index 127// CHECK-DAG: %[[VAL_7:.*]] = arith.constant 3 : index 128// CHECK-DAG: %[[VAL_8:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf64, #sparse_tensor.encoding<{{{.*}}}>> 129// CHECK-DAG: %[[VAL_9:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf64, #sparse_tensor.encoding<{{{.*}}}>> 130// CHECK-DAG: %[[VAL_10:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32x16xf64, #sparse_tensor.encoding<{{{.*}}}>> 131// CHECK-DAG: %[[VAL_11:.*]] = bufferization.to_memref %[[VAL_1]] : memref<34x19xf64> 132// CHECK-DAG: %[[VAL_12:.*]] = bufferization.to_memref %[[VAL_2]] : memref<32x16xf64> 133// CHECK-DAG: %[[VAL_13:.*]] = memref.alloc() : memref<32x16xf64> 134// CHECK: memref.copy %[[VAL_12]], %[[VAL_13]] : memref<32x16xf64> to memref<32x16xf64> 135// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_3]] { 136// CHECK: %[[VAL_15:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_14]]] : memref<?xindex> 137// CHECK: %[[VAL_16:.*]] = arith.addi %[[VAL_14]], %[[VAL_3]] : index 138// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref<?xindex> 139// CHECK: scf.for %[[VAL_18:.*]] = %[[VAL_15]] to %[[VAL_17]] step %[[VAL_3]] { 140// CHECK: %[[VAL_19:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref<?xindex> 141// CHECK: %[[VAL_20:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_19]]] : memref<32x16xf64> 142// CHECK: %[[VAL_21:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_18]]] : memref<?xf64> 143// CHECK: %[[VAL_22:.*]] = arith.addi %[[VAL_14]], %[[VAL_6]] : index 144// CHECK: %[[VAL_23:.*]] = arith.addi %[[VAL_19]], %[[VAL_7]] : index 145// CHECK: %[[VAL_24:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_22]], %[[VAL_23]]] : memref<34x19xf64> 146// CHECK: %[[VAL_25:.*]] = arith.mulf %[[VAL_21]], %[[VAL_24]] : f64 147// CHECK: %[[VAL_26:.*]] = arith.addf %[[VAL_20]], %[[VAL_25]] : f64 148// CHECK: memref.store %[[VAL_26]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_19]]] : memref<32x16xf64> 149// CHECK: } 150// CHECK: } 151// CHECK: %[[VAL_27:.*]] = bufferization.to_tensor %[[VAL_13]] : memref<32x16xf64> 152// CHECK: return %[[VAL_27]] : tensor<32x16xf64> 153// CHECK: } 154func.func @mul_affine_dense2d(%arga: tensor<32x16xf64, #CSR>, 155 %argb: tensor<34x19xf64>, 156 %argx: tensor<32x16xf64>) -> tensor<32x16xf64> { 157 %0 = linalg.generic #trait3 158 ins(%arga, %argb: tensor<32x16xf64, #CSR>, tensor<34x19xf64>) 159 outs(%argx: tensor<32x16xf64>) { 160 ^bb(%a: f64, %b: f64, %x: f64): 161 %0 = arith.mulf %a, %b : f64 162 %1 = arith.addf %x, %0 : f64 163 linalg.yield %1 : f64 164 } -> tensor<32x16xf64> 165 return %0 : tensor<32x16xf64> 166} 167