Google Git
Sign in
llvm / llvm-project / 3a62d4fde88544125ce9ceff990db108ee91148a / . / mlir / test / Dialect / SparseTensor / sparse_2d.mlir
blob: 80febcad1c0b17417878539bc0bbcbe40c08c0db [file] [log] [blame]
// NOTE: Assertions have been autogenerated by utils/generate-test-checks.py
// RUN: mlir-opt %s -sparsification | FileCheck %s
#trait_dd = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (i,j)>, // B
affine_map<(i,j) -> (i,j)> // X (out)
],
sparse = [
[ "D", "D" ], // A
[ "D", "D" ], // B
[ "D", "D" ] // X
],
iterator_types = ["parallel", "parallel"],
doc = "X(i,j) = A(i,j) OP B(i,j)"
}
// CHECK-LABEL: func @add_dd(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 32 : index
// CHECK: %[[VAL_4:.*]] = constant 16 : index
// CHECK: %[[VAL_5:.*]] = constant 0 : index
// CHECK: %[[VAL_6:.*]] = constant 1 : index
// CHECK: %[[VAL_7:.*]] = memref.buffer_cast %[[VAL_0]] : memref<32x16xf32>
// CHECK: %[[VAL_8:.*]] = memref.buffer_cast %[[VAL_1]] : memref<32x16xf32>
// CHECK: %[[VAL_9:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_10:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_9]], %[[VAL_10]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] {
// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
// CHECK: %[[VAL_13:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32>
// CHECK: %[[VAL_14:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32>
// CHECK: %[[VAL_15:.*]] = addf %[[VAL_13]], %[[VAL_14]] : f32
// CHECK: store %[[VAL_15]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_16:.*]] = memref.tensor_load %[[VAL_10]] : memref<32x16xf32>
// CHECK: return %[[VAL_16]] : tensor<32x16xf32>
// CHECK: }
func @add_dd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_dd
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = addf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
// CHECK-LABEL: func @mul_dd(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 32 : index
// CHECK: %[[VAL_4:.*]] = constant 16 : index
// CHECK: %[[VAL_5:.*]] = constant 0 : index
// CHECK: %[[VAL_6:.*]] = constant 1 : index
// CHECK: %[[VAL_7:.*]] = memref.buffer_cast %[[VAL_0]] : memref<32x16xf32>
// CHECK: %[[VAL_8:.*]] = memref.buffer_cast %[[VAL_1]] : memref<32x16xf32>
// CHECK: %[[VAL_9:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_10:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_9]], %[[VAL_10]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_6]] {
// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
// CHECK: %[[VAL_13:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32>
// CHECK: %[[VAL_14:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32>
// CHECK: %[[VAL_15:.*]] = mulf %[[VAL_13]], %[[VAL_14]] : f32
// CHECK: store %[[VAL_15]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_12]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_16:.*]] = memref.tensor_load %[[VAL_10]] : memref<32x16xf32>
// CHECK: return %[[VAL_16]] : tensor<32x16xf32>
// CHECK: }
func @mul_dd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_dd
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = mulf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
#trait_ds = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (i,j)>, // B
affine_map<(i,j) -> (i,j)> // X (out)
],
sparse = [
[ "D", "S" ], // A
[ "D", "D" ], // B
[ "D", "D" ] // X
],
iterator_types = ["parallel", "parallel"],
doc = "X(i,j) = A(i,j) OP B(i,j)"
}
// CHECK-LABEL: func @add_ds(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 32 : index
// CHECK: %[[VAL_4:.*]] = constant 16 : index
// CHECK: %[[VAL_5:.*]] = constant 0 : index
// CHECK: %[[VAL_6:.*]] = constant true
// CHECK: %[[VAL_7:.*]] = constant 1 : index
// CHECK: %[[VAL_8:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_7]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_9:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_7]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_10:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_11:.*]] = memref.buffer_cast %[[VAL_1]] : memref<32x16xf32>
// CHECK: %[[VAL_12:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_13:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_12]], %[[VAL_13]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_7]] {
// CHECK: %[[VAL_15:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_14]]] : memref<?xindex>
// CHECK: %[[VAL_16:.*]] = addi %[[VAL_14]], %[[VAL_7]] : index
// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]]:2 = scf.while (%[[VAL_19:.*]] = %[[VAL_15]], %[[VAL_20:.*]] = %[[VAL_5]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_17]] : index
// CHECK: scf.condition(%[[VAL_21]]) %[[VAL_19]], %[[VAL_20]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_22:.*]]: index, %[[VAL_23:.*]]: index):
// CHECK: %[[VAL_24:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref<?xindex>
// CHECK: %[[VAL_25:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
// CHECK: scf.if %[[VAL_25]] {
// CHECK: %[[VAL_26:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref<?xf32>
// CHECK: %[[VAL_27:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32>
// CHECK: %[[VAL_28:.*]] = addf %[[VAL_26]], %[[VAL_27]] : f32
// CHECK: store %[[VAL_28]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: scf.if %[[VAL_6]] {
// CHECK: %[[VAL_29:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32>
// CHECK: store %[[VAL_29]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_23]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_30:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
// CHECK: %[[VAL_31:.*]] = addi %[[VAL_22]], %[[VAL_7]] : index
// CHECK: %[[VAL_32:.*]] = select %[[VAL_30]], %[[VAL_31]], %[[VAL_22]] : index
// CHECK: %[[VAL_33:.*]] = addi %[[VAL_23]], %[[VAL_7]] : index
// CHECK: scf.yield %[[VAL_32]], %[[VAL_33]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_34:.*]] = %[[VAL_35:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_36:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_14]], %[[VAL_34]]] : memref<32x16xf32>
// CHECK: store %[[VAL_36]], %[[VAL_13]]{{\[}}%[[VAL_14]], %[[VAL_34]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_37:.*]] = memref.tensor_load %[[VAL_13]] : memref<32x16xf32>
// CHECK: return %[[VAL_37]] : tensor<32x16xf32>
// CHECK: }
func @add_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ds
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = addf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
// CHECK-LABEL: func @mul_ds(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 32 : index
// CHECK: %[[VAL_4:.*]] = constant 0 : index
// CHECK: %[[VAL_5:.*]] = constant 1 : index
// CHECK: %[[VAL_6:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_5]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_7:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_5]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_8:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_9:.*]] = memref.buffer_cast %[[VAL_1]] : memref<32x16xf32>
// CHECK: %[[VAL_10:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_11:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_10]], %[[VAL_11]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
// CHECK: %[[VAL_13:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_5]] : index
// CHECK: %[[VAL_15:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_5]] {
// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref<?xf32>
// CHECK: %[[VAL_19:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_12]], %[[VAL_17]]] : memref<32x16xf32>
// CHECK: %[[VAL_20:.*]] = mulf %[[VAL_18]], %[[VAL_19]] : f32
// CHECK: store %[[VAL_20]], %[[VAL_11]]{{\[}}%[[VAL_12]], %[[VAL_17]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_21:.*]] = memref.tensor_load %[[VAL_11]] : memref<32x16xf32>
// CHECK: return %[[VAL_21]] : tensor<32x16xf32>
// CHECK: }
func @mul_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ds
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = mulf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
#trait_sd = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (i,j)>, // B
affine_map<(i,j) -> (i,j)> // X (out)
],
sparse = [
[ "S", "D" ], // A
[ "D", "D" ], // B
[ "D", "D" ] // X
],
iterator_types = ["parallel", "parallel"],
doc = "X(i,j) = A(i,j) OP B(i,j)"
}
// CHECK-LABEL: func @add_sd(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 32 : index
// CHECK: %[[VAL_4:.*]] = constant 16 : index
// CHECK: %[[VAL_5:.*]] = constant true
// CHECK: %[[VAL_6:.*]] = constant 0 : index
// CHECK: %[[VAL_7:.*]] = constant 1 : index
// CHECK: %[[VAL_8:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_6]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_9:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_6]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_10:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_11:.*]] = memref.buffer_cast %[[VAL_1]] : memref<32x16xf32>
// CHECK: %[[VAL_12:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_13:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_12]], %[[VAL_13]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: %[[VAL_14:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref<?xindex>
// CHECK: %[[VAL_15:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref<?xindex>
// CHECK: %[[VAL_16:.*]]:2 = scf.while (%[[VAL_17:.*]] = %[[VAL_14]], %[[VAL_18:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_19:.*]] = cmpi ult, %[[VAL_17]], %[[VAL_15]] : index
// CHECK: scf.condition(%[[VAL_19]]) %[[VAL_17]], %[[VAL_18]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_20:.*]]: index, %[[VAL_21:.*]]: index):
// CHECK: %[[VAL_22:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref<?xindex>
// CHECK: %[[VAL_23:.*]] = cmpi eq, %[[VAL_22]], %[[VAL_21]] : index
// CHECK: scf.if %[[VAL_23]] {
// CHECK: scf.for %[[VAL_24:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_25:.*]] = muli %[[VAL_20]], %[[VAL_4]] : index
// CHECK: %[[VAL_26:.*]] = addi %[[VAL_25]], %[[VAL_24]] : index
// CHECK: %[[VAL_27:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_26]]] : memref<?xf32>
// CHECK: %[[VAL_28:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_21]], %[[VAL_24]]] : memref<32x16xf32>
// CHECK: %[[VAL_29:.*]] = addf %[[VAL_27]], %[[VAL_28]] : f32
// CHECK: store %[[VAL_29]], %[[VAL_13]]{{\[}}%[[VAL_21]], %[[VAL_24]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: scf.if %[[VAL_5]] {
// CHECK: scf.for %[[VAL_30:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_31:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_21]], %[[VAL_30]]] : memref<32x16xf32>
// CHECK: store %[[VAL_31]], %[[VAL_13]]{{\[}}%[[VAL_21]], %[[VAL_30]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_32:.*]] = cmpi eq, %[[VAL_22]], %[[VAL_21]] : index
// CHECK: %[[VAL_33:.*]] = addi %[[VAL_20]], %[[VAL_7]] : index
// CHECK: %[[VAL_34:.*]] = select %[[VAL_32]], %[[VAL_33]], %[[VAL_20]] : index
// CHECK: %[[VAL_35:.*]] = addi %[[VAL_21]], %[[VAL_7]] : index
// CHECK: scf.yield %[[VAL_34]], %[[VAL_35]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_36:.*]] = %[[VAL_37:.*]]#1 to %[[VAL_3]] step %[[VAL_7]] {
// CHECK: scf.for %[[VAL_38:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_39:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_36]], %[[VAL_38]]] : memref<32x16xf32>
// CHECK: store %[[VAL_39]], %[[VAL_13]]{{\[}}%[[VAL_36]], %[[VAL_38]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_40:.*]] = memref.tensor_load %[[VAL_13]] : memref<32x16xf32>
// CHECK: return %[[VAL_40]] : tensor<32x16xf32>
// CHECK: }
func @add_sd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_sd
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = addf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
// CHECK-LABEL: func @mul_sd(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 16 : index
// CHECK: %[[VAL_4:.*]] = constant 0 : index
// CHECK: %[[VAL_5:.*]] = constant 1 : index
// CHECK: %[[VAL_6:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_7:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_8:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_9:.*]] = memref.buffer_cast %[[VAL_1]] : memref<32x16xf32>
// CHECK: %[[VAL_10:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_11:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_10]], %[[VAL_11]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: %[[VAL_12:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_13:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_12]] to %[[VAL_13]] step %[[VAL_5]] {
// CHECK: %[[VAL_15:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
// CHECK: %[[VAL_17:.*]] = muli %[[VAL_14]], %[[VAL_3]] : index
// CHECK: %[[VAL_18:.*]] = addi %[[VAL_17]], %[[VAL_16]] : index
// CHECK: %[[VAL_19:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref<?xf32>
// CHECK: %[[VAL_20:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_15]], %[[VAL_16]]] : memref<32x16xf32>
// CHECK: %[[VAL_21:.*]] = mulf %[[VAL_19]], %[[VAL_20]] : f32
// CHECK: store %[[VAL_21]], %[[VAL_11]]{{\[}}%[[VAL_15]], %[[VAL_16]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_22:.*]] = memref.tensor_load %[[VAL_11]] : memref<32x16xf32>
// CHECK: return %[[VAL_22]] : tensor<32x16xf32>
// CHECK: }
func @mul_sd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_sd
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = mulf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
#trait_ss = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (i,j)>, // B
affine_map<(i,j) -> (i,j)> // X (out)
],
sparse = [
[ "S", "S" ], // A
[ "D", "D" ], // B
[ "D", "D" ] // X
],
iterator_types = ["parallel", "parallel"],
doc = "X(i,j) = A(i,j) OP B(i,j)"
}
// CHECK-LABEL: func @add_ss(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 32 : index
// CHECK: %[[VAL_4:.*]] = constant 16 : index
// CHECK: %[[VAL_5:.*]] = constant true
// CHECK: %[[VAL_6:.*]] = constant 0 : index
// CHECK: %[[VAL_7:.*]] = constant 1 : index
// CHECK: %[[VAL_8:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_6]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_9:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_6]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_10:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_7]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_11:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_7]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_12:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_13:.*]] = memref.buffer_cast %[[VAL_1]] : memref<32x16xf32>
// CHECK: %[[VAL_14:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_15:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_14]], %[[VAL_15]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: %[[VAL_16:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref<?xindex>
// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]]:2 = scf.while (%[[VAL_19:.*]] = %[[VAL_16]], %[[VAL_20:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_21:.*]] = cmpi ult, %[[VAL_19]], %[[VAL_17]] : index
// CHECK: scf.condition(%[[VAL_21]]) %[[VAL_19]], %[[VAL_20]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_22:.*]]: index, %[[VAL_23:.*]]: index):
// CHECK: %[[VAL_24:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_22]]] : memref<?xindex>
// CHECK: %[[VAL_25:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
// CHECK: scf.if %[[VAL_25]] {
// CHECK: %[[VAL_26:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_22]]] : memref<?xindex>
// CHECK: %[[VAL_27:.*]] = addi %[[VAL_22]], %[[VAL_7]] : index
// CHECK: %[[VAL_28:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_29:.*]]:2 = scf.while (%[[VAL_30:.*]] = %[[VAL_26]], %[[VAL_31:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_32:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_28]] : index
// CHECK: scf.condition(%[[VAL_32]]) %[[VAL_30]], %[[VAL_31]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_33:.*]]: index, %[[VAL_34:.*]]: index):
// CHECK: %[[VAL_35:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_33]]] : memref<?xindex>
// CHECK: %[[VAL_36:.*]] = cmpi eq, %[[VAL_35]], %[[VAL_34]] : index
// CHECK: scf.if %[[VAL_36]] {
// CHECK: %[[VAL_37:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: %[[VAL_38:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32>
// CHECK: %[[VAL_39:.*]] = addf %[[VAL_37]], %[[VAL_38]] : f32
// CHECK: store %[[VAL_39]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: scf.if %[[VAL_5]] {
// CHECK: %[[VAL_40:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32>
// CHECK: store %[[VAL_40]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_34]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_41:.*]] = cmpi eq, %[[VAL_35]], %[[VAL_34]] : index
// CHECK: %[[VAL_42:.*]] = addi %[[VAL_33]], %[[VAL_7]] : index
// CHECK: %[[VAL_43:.*]] = select %[[VAL_41]], %[[VAL_42]], %[[VAL_33]] : index
// CHECK: %[[VAL_44:.*]] = addi %[[VAL_34]], %[[VAL_7]] : index
// CHECK: scf.yield %[[VAL_43]], %[[VAL_44]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_45:.*]] = %[[VAL_46:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_47:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_23]], %[[VAL_45]]] : memref<32x16xf32>
// CHECK: store %[[VAL_47]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_45]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: scf.if %[[VAL_5]] {
// CHECK: scf.for %[[VAL_48:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_49:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_23]], %[[VAL_48]]] : memref<32x16xf32>
// CHECK: store %[[VAL_49]], %[[VAL_15]]{{\[}}%[[VAL_23]], %[[VAL_48]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_50:.*]] = cmpi eq, %[[VAL_24]], %[[VAL_23]] : index
// CHECK: %[[VAL_51:.*]] = addi %[[VAL_22]], %[[VAL_7]] : index
// CHECK: %[[VAL_52:.*]] = select %[[VAL_50]], %[[VAL_51]], %[[VAL_22]] : index
// CHECK: %[[VAL_53:.*]] = addi %[[VAL_23]], %[[VAL_7]] : index
// CHECK: scf.yield %[[VAL_52]], %[[VAL_53]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_54:.*]] = %[[VAL_55:.*]]#1 to %[[VAL_3]] step %[[VAL_7]] {
// CHECK: scf.for %[[VAL_56:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_57:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_54]], %[[VAL_56]]] : memref<32x16xf32>
// CHECK: store %[[VAL_57]], %[[VAL_15]]{{\[}}%[[VAL_54]], %[[VAL_56]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_58:.*]] = memref.tensor_load %[[VAL_15]] : memref<32x16xf32>
// CHECK: return %[[VAL_58]] : tensor<32x16xf32>
// CHECK: }
func @add_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = addf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
// CHECK-LABEL: func @mul_ss(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_6:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_7:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_8:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_9:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_10:.*]] = memref.buffer_cast %[[VAL_1]] : memref<32x16xf32>
// CHECK: %[[VAL_11:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_12:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_11]], %[[VAL_12]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: %[[VAL_13:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_13]] to %[[VAL_14]] step %[[VAL_4]] {
// CHECK: %[[VAL_16:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_15]]] : memref<?xindex>
// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]] = addi %[[VAL_15]], %[[VAL_4]] : index
// CHECK: %[[VAL_19:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_18]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_20:.*]] = %[[VAL_17]] to %[[VAL_19]] step %[[VAL_4]] {
// CHECK: %[[VAL_21:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref<?xindex>
// CHECK: %[[VAL_22:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref<?xf32>
// CHECK: %[[VAL_23:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_16]], %[[VAL_21]]] : memref<32x16xf32>
// CHECK: %[[VAL_24:.*]] = mulf %[[VAL_22]], %[[VAL_23]] : f32
// CHECK: store %[[VAL_24]], %[[VAL_12]]{{\[}}%[[VAL_16]], %[[VAL_21]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_25:.*]] = memref.tensor_load %[[VAL_12]] : memref<32x16xf32>
// CHECK: return %[[VAL_25]] : tensor<32x16xf32>
// CHECK: }
func @mul_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = mulf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
#trait_ss_ss = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (i,j)>, // B
affine_map<(i,j) -> (i,j)> // X (out)
],
sparse = [
[ "S", "S" ], // A
[ "S", "S" ], // B
[ "D", "D" ] // X
],
iterator_types = ["parallel", "parallel"],
doc = "X(i,j) = A(i,j) OP B(i,j)"
}
// CHECK-LABEL: func @add_ss_ss(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_6:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_7:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_8:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_9:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_10:.*]] = sparse_tensor.pointers %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_11:.*]] = sparse_tensor.indices %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_12:.*]] = sparse_tensor.pointers %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_13:.*]] = sparse_tensor.indices %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_14:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_15:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_16:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_15]], %[[VAL_16]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_19:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_20:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index
// CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index
// CHECK: %[[VAL_26:.*]] = and %[[VAL_24]], %[[VAL_25]] : i1
// CHECK: scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index):
// CHECK: %[[VAL_29:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_30:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref<?xindex>
// CHECK: %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index
// CHECK: %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index
// CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
// CHECK: %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
// CHECK: %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1
// CHECK: scf.if %[[VAL_35]] {
// CHECK: %[[VAL_36:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_38:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_37]]] : memref<?xindex>
// CHECK: %[[VAL_39:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<?xindex>
// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index
// CHECK: %[[VAL_41:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_40]]] : memref<?xindex>
// CHECK: %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index
// CHECK: %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index
// CHECK: %[[VAL_47:.*]] = and %[[VAL_45]], %[[VAL_46]] : i1
// CHECK: scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index):
// CHECK: %[[VAL_50:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_48]]] : memref<?xindex>
// CHECK: %[[VAL_51:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_49]]] : memref<?xindex>
// CHECK: %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index
// CHECK: %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index
// CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
// CHECK: %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
// CHECK: %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1
// CHECK: scf.if %[[VAL_56]] {
// CHECK: %[[VAL_57:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: %[[VAL_58:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref<?xf32>
// CHECK: %[[VAL_59:.*]] = addf %[[VAL_57]], %[[VAL_58]] : f32
// CHECK: store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
// CHECK: scf.if %[[VAL_60]] {
// CHECK: %[[VAL_61:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: store %[[VAL_61]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: %[[VAL_62:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
// CHECK: scf.if %[[VAL_62]] {
// CHECK: %[[VAL_63:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref<?xf32>
// CHECK: store %[[VAL_63]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_64:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
// CHECK: %[[VAL_65:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
// CHECK: %[[VAL_66:.*]] = select %[[VAL_64]], %[[VAL_65]], %[[VAL_48]] : index
// CHECK: %[[VAL_67:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
// CHECK: %[[VAL_68:.*]] = addi %[[VAL_49]], %[[VAL_4]] : index
// CHECK: %[[VAL_69:.*]] = select %[[VAL_67]], %[[VAL_68]], %[[VAL_49]] : index
// CHECK: scf.yield %[[VAL_66]], %[[VAL_69]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_70:.*]] = %[[VAL_71:.*]]#0 to %[[VAL_38]] step %[[VAL_4]] {
// CHECK: %[[VAL_72:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_70]]] : memref<?xindex>
// CHECK: %[[VAL_73:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_70]]] : memref<?xf32>
// CHECK: store %[[VAL_73]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_72]]] : memref<32x16xf32>
// CHECK: }
// CHECK: scf.for %[[VAL_74:.*]] = %[[VAL_75:.*]]#1 to %[[VAL_41]] step %[[VAL_4]] {
// CHECK: %[[VAL_76:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_74]]] : memref<?xindex>
// CHECK: %[[VAL_77:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_74]]] : memref<?xf32>
// CHECK: store %[[VAL_77]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_76]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: %[[VAL_78:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
// CHECK: scf.if %[[VAL_78]] {
// CHECK: %[[VAL_79:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_80:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_81:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_80]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_82:.*]] = %[[VAL_79]] to %[[VAL_81]] step %[[VAL_4]] {
// CHECK: %[[VAL_83:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_82]]] : memref<?xindex>
// CHECK: %[[VAL_84:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_82]]] : memref<?xf32>
// CHECK: store %[[VAL_84]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_83]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: %[[VAL_85:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
// CHECK: scf.if %[[VAL_85]] {
// CHECK: %[[VAL_86:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<?xindex>
// CHECK: %[[VAL_87:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index
// CHECK: %[[VAL_88:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_87]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_89:.*]] = %[[VAL_86]] to %[[VAL_88]] step %[[VAL_4]] {
// CHECK: %[[VAL_90:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_89]]] : memref<?xindex>
// CHECK: %[[VAL_91:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_89]]] : memref<?xf32>
// CHECK: store %[[VAL_91]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_90]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_92:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
// CHECK: %[[VAL_93:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_94:.*]] = select %[[VAL_92]], %[[VAL_93]], %[[VAL_27]] : index
// CHECK: %[[VAL_95:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
// CHECK: %[[VAL_96:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index
// CHECK: %[[VAL_97:.*]] = select %[[VAL_95]], %[[VAL_96]], %[[VAL_28]] : index
// CHECK: scf.yield %[[VAL_94]], %[[VAL_97]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_98:.*]] = %[[VAL_99:.*]]#0 to %[[VAL_18]] step %[[VAL_4]] {
// CHECK: %[[VAL_100:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_98]]] : memref<?xindex>
// CHECK: %[[VAL_101:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_98]]] : memref<?xindex>
// CHECK: %[[VAL_102:.*]] = addi %[[VAL_98]], %[[VAL_4]] : index
// CHECK: %[[VAL_103:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_102]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_104:.*]] = %[[VAL_101]] to %[[VAL_103]] step %[[VAL_4]] {
// CHECK: %[[VAL_105:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_104]]] : memref<?xindex>
// CHECK: %[[VAL_106:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_104]]] : memref<?xf32>
// CHECK: store %[[VAL_106]], %[[VAL_16]]{{\[}}%[[VAL_100]], %[[VAL_105]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: scf.for %[[VAL_107:.*]] = %[[VAL_108:.*]]#1 to %[[VAL_20]] step %[[VAL_4]] {
// CHECK: %[[VAL_109:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_107]]] : memref<?xindex>
// CHECK: %[[VAL_110:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_107]]] : memref<?xindex>
// CHECK: %[[VAL_111:.*]] = addi %[[VAL_107]], %[[VAL_4]] : index
// CHECK: %[[VAL_112:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_111]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_113:.*]] = %[[VAL_110]] to %[[VAL_112]] step %[[VAL_4]] {
// CHECK: %[[VAL_114:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_113]]] : memref<?xindex>
// CHECK: %[[VAL_115:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_113]]] : memref<?xf32>
// CHECK: store %[[VAL_115]], %[[VAL_16]]{{\[}}%[[VAL_109]], %[[VAL_114]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_116:.*]] = memref.tensor_load %[[VAL_16]] : memref<32x16xf32>
// CHECK: return %[[VAL_116]] : tensor<32x16xf32>
// CHECK: }
func @add_ss_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = addf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
// CHECK-LABEL: func @mul_ss_ss(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_6:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_7:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_8:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_9:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_10:.*]] = sparse_tensor.pointers %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_11:.*]] = sparse_tensor.indices %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_12:.*]] = sparse_tensor.pointers %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_13:.*]] = sparse_tensor.indices %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_14:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_15:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_16:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_15]], %[[VAL_16]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_19:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_20:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index
// CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index
// CHECK: %[[VAL_26:.*]] = and %[[VAL_24]], %[[VAL_25]] : i1
// CHECK: scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index):
// CHECK: %[[VAL_29:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_30:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref<?xindex>
// CHECK: %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index
// CHECK: %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index
// CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
// CHECK: %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
// CHECK: %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1
// CHECK: scf.if %[[VAL_35]] {
// CHECK: %[[VAL_36:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_38:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_37]]] : memref<?xindex>
// CHECK: %[[VAL_39:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<?xindex>
// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index
// CHECK: %[[VAL_41:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_40]]] : memref<?xindex>
// CHECK: %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index
// CHECK: %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index
// CHECK: %[[VAL_47:.*]] = and %[[VAL_45]], %[[VAL_46]] : i1
// CHECK: scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index):
// CHECK: %[[VAL_50:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_48]]] : memref<?xindex>
// CHECK: %[[VAL_51:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_49]]] : memref<?xindex>
// CHECK: %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index
// CHECK: %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index
// CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
// CHECK: %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
// CHECK: %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1
// CHECK: scf.if %[[VAL_56]] {
// CHECK: %[[VAL_57:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: %[[VAL_58:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref<?xf32>
// CHECK: %[[VAL_59:.*]] = mulf %[[VAL_57]], %[[VAL_58]] : f32
// CHECK: store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
// CHECK: %[[VAL_61:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
// CHECK: %[[VAL_62:.*]] = select %[[VAL_60]], %[[VAL_61]], %[[VAL_48]] : index
// CHECK: %[[VAL_63:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
// CHECK: %[[VAL_64:.*]] = addi %[[VAL_49]], %[[VAL_4]] : index
// CHECK: %[[VAL_65:.*]] = select %[[VAL_63]], %[[VAL_64]], %[[VAL_49]] : index
// CHECK: scf.yield %[[VAL_62]], %[[VAL_65]] : index, index
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: %[[VAL_66:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
// CHECK: %[[VAL_67:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_68:.*]] = select %[[VAL_66]], %[[VAL_67]], %[[VAL_27]] : index
// CHECK: %[[VAL_69:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
// CHECK: %[[VAL_70:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index
// CHECK: %[[VAL_71:.*]] = select %[[VAL_69]], %[[VAL_70]], %[[VAL_28]] : index
// CHECK: scf.yield %[[VAL_68]], %[[VAL_71]] : index, index
// CHECK: }
// CHECK: %[[VAL_72:.*]] = memref.tensor_load %[[VAL_16]] : memref<32x16xf32>
// CHECK: return %[[VAL_72]] : tensor<32x16xf32>
// CHECK: }
func @mul_ss_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = mulf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
#trait_sd_ds = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (i,j)>, // B
affine_map<(i,j) -> (i,j)> // X (out)
],
sparse = [
[ "S", "D" ], // A
[ "D", "S" ], // B
[ "D", "D" ] // X
],
iterator_types = ["parallel", "parallel"],
doc = "X(i,j) = A(i,j) OP B(i,j)"
}
// CHECK-LABEL: func @add_sd_ds(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_6:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_7:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_8:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_9:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_10:.*]] = sparse_tensor.pointers %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_11:.*]] = sparse_tensor.indices %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_12:.*]] = sparse_tensor.pointers %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_13:.*]] = sparse_tensor.indices %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_14:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_15:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_16:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_15]], %[[VAL_16]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_19:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_20:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index
// CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index
// CHECK: %[[VAL_26:.*]] = and %[[VAL_24]], %[[VAL_25]] : i1
// CHECK: scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index):
// CHECK: %[[VAL_29:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_30:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref<?xindex>
// CHECK: %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index
// CHECK: %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index
// CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
// CHECK: %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
// CHECK: %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1
// CHECK: scf.if %[[VAL_35]] {
// CHECK: %[[VAL_36:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_38:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_37]]] : memref<?xindex>
// CHECK: %[[VAL_39:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<?xindex>
// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index
// CHECK: %[[VAL_41:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_40]]] : memref<?xindex>
// CHECK: %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index
// CHECK: %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index
// CHECK: %[[VAL_47:.*]] = and %[[VAL_45]], %[[VAL_46]] : i1
// CHECK: scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index):
// CHECK: %[[VAL_50:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_48]]] : memref<?xindex>
// CHECK: %[[VAL_51:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_49]]] : memref<?xindex>
// CHECK: %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index
// CHECK: %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index
// CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
// CHECK: %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
// CHECK: %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1
// CHECK: scf.if %[[VAL_56]] {
// CHECK: %[[VAL_57:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: %[[VAL_58:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref<?xf32>
// CHECK: %[[VAL_59:.*]] = addf %[[VAL_57]], %[[VAL_58]] : f32
// CHECK: store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
// CHECK: scf.if %[[VAL_60]] {
// CHECK: %[[VAL_61:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: store %[[VAL_61]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: %[[VAL_62:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
// CHECK: scf.if %[[VAL_62]] {
// CHECK: %[[VAL_63:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref<?xf32>
// CHECK: store %[[VAL_63]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_64:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
// CHECK: %[[VAL_65:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
// CHECK: %[[VAL_66:.*]] = select %[[VAL_64]], %[[VAL_65]], %[[VAL_48]] : index
// CHECK: %[[VAL_67:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
// CHECK: %[[VAL_68:.*]] = addi %[[VAL_49]], %[[VAL_4]] : index
// CHECK: %[[VAL_69:.*]] = select %[[VAL_67]], %[[VAL_68]], %[[VAL_49]] : index
// CHECK: scf.yield %[[VAL_66]], %[[VAL_69]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_70:.*]] = %[[VAL_71:.*]]#0 to %[[VAL_38]] step %[[VAL_4]] {
// CHECK: %[[VAL_72:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_70]]] : memref<?xindex>
// CHECK: %[[VAL_73:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_70]]] : memref<?xf32>
// CHECK: store %[[VAL_73]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_72]]] : memref<32x16xf32>
// CHECK: }
// CHECK: scf.for %[[VAL_74:.*]] = %[[VAL_75:.*]]#1 to %[[VAL_41]] step %[[VAL_4]] {
// CHECK: %[[VAL_76:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_74]]] : memref<?xindex>
// CHECK: %[[VAL_77:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_74]]] : memref<?xf32>
// CHECK: store %[[VAL_77]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_76]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: %[[VAL_78:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
// CHECK: scf.if %[[VAL_78]] {
// CHECK: %[[VAL_79:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_80:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_81:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_80]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_82:.*]] = %[[VAL_79]] to %[[VAL_81]] step %[[VAL_4]] {
// CHECK: %[[VAL_83:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_82]]] : memref<?xindex>
// CHECK: %[[VAL_84:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_82]]] : memref<?xf32>
// CHECK: store %[[VAL_84]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_83]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: %[[VAL_85:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
// CHECK: scf.if %[[VAL_85]] {
// CHECK: %[[VAL_86:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<?xindex>
// CHECK: %[[VAL_87:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index
// CHECK: %[[VAL_88:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_87]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_89:.*]] = %[[VAL_86]] to %[[VAL_88]] step %[[VAL_4]] {
// CHECK: %[[VAL_90:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_89]]] : memref<?xindex>
// CHECK: %[[VAL_91:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_89]]] : memref<?xf32>
// CHECK: store %[[VAL_91]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_90]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_92:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
// CHECK: %[[VAL_93:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_94:.*]] = select %[[VAL_92]], %[[VAL_93]], %[[VAL_27]] : index
// CHECK: %[[VAL_95:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
// CHECK: %[[VAL_96:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index
// CHECK: %[[VAL_97:.*]] = select %[[VAL_95]], %[[VAL_96]], %[[VAL_28]] : index
// CHECK: scf.yield %[[VAL_94]], %[[VAL_97]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_98:.*]] = %[[VAL_99:.*]]#0 to %[[VAL_18]] step %[[VAL_4]] {
// CHECK: %[[VAL_100:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_98]]] : memref<?xindex>
// CHECK: %[[VAL_101:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_98]]] : memref<?xindex>
// CHECK: %[[VAL_102:.*]] = addi %[[VAL_98]], %[[VAL_4]] : index
// CHECK: %[[VAL_103:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_102]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_104:.*]] = %[[VAL_101]] to %[[VAL_103]] step %[[VAL_4]] {
// CHECK: %[[VAL_105:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_104]]] : memref<?xindex>
// CHECK: %[[VAL_106:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_104]]] : memref<?xf32>
// CHECK: store %[[VAL_106]], %[[VAL_16]]{{\[}}%[[VAL_100]], %[[VAL_105]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: scf.for %[[VAL_107:.*]] = %[[VAL_108:.*]]#1 to %[[VAL_20]] step %[[VAL_4]] {
// CHECK: %[[VAL_109:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_107]]] : memref<?xindex>
// CHECK: %[[VAL_110:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_107]]] : memref<?xindex>
// CHECK: %[[VAL_111:.*]] = addi %[[VAL_107]], %[[VAL_4]] : index
// CHECK: %[[VAL_112:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_111]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_113:.*]] = %[[VAL_110]] to %[[VAL_112]] step %[[VAL_4]] {
// CHECK: %[[VAL_114:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_113]]] : memref<?xindex>
// CHECK: %[[VAL_115:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_113]]] : memref<?xf32>
// CHECK: store %[[VAL_115]], %[[VAL_16]]{{\[}}%[[VAL_109]], %[[VAL_114]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_116:.*]] = memref.tensor_load %[[VAL_16]] : memref<32x16xf32>
// CHECK: return %[[VAL_116]] : tensor<32x16xf32>
// CHECK: }
func @add_sd_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = addf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
// CHECK-LABEL: func @mul_sd_ds(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_6:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_7:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_8:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_9:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_10:.*]] = sparse_tensor.pointers %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_11:.*]] = sparse_tensor.indices %[[VAL_1]], %[[VAL_3]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_12:.*]] = sparse_tensor.pointers %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_13:.*]] = sparse_tensor.indices %[[VAL_1]], %[[VAL_4]] : tensor<32x16xf32> to memref<?xindex>
// CHECK: %[[VAL_14:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<32x16xf32> to memref<?xf32>
// CHECK: %[[VAL_15:.*]] = memref.buffer_cast %[[VAL_2]] : memref<32x16xf32>
// CHECK: %[[VAL_16:.*]] = memref.alloc() : memref<32x16xf32>
// CHECK: linalg.copy(%[[VAL_15]], %[[VAL_16]]) : memref<32x16xf32>, memref<32x16xf32>
// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_19:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_20:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_21:.*]]:2 = scf.while (%[[VAL_22:.*]] = %[[VAL_17]], %[[VAL_23:.*]] = %[[VAL_19]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_18]] : index
// CHECK: %[[VAL_25:.*]] = cmpi ult, %[[VAL_23]], %[[VAL_20]] : index
// CHECK: %[[VAL_26:.*]] = and %[[VAL_24]], %[[VAL_25]] : i1
// CHECK: scf.condition(%[[VAL_26]]) %[[VAL_22]], %[[VAL_23]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_27:.*]]: index, %[[VAL_28:.*]]: index):
// CHECK: %[[VAL_29:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_30:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_28]]] : memref<?xindex>
// CHECK: %[[VAL_31:.*]] = cmpi ult, %[[VAL_30]], %[[VAL_29]] : index
// CHECK: %[[VAL_32:.*]] = select %[[VAL_31]], %[[VAL_30]], %[[VAL_29]] : index
// CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
// CHECK: %[[VAL_34:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
// CHECK: %[[VAL_35:.*]] = and %[[VAL_33]], %[[VAL_34]] : i1
// CHECK: scf.if %[[VAL_35]] {
// CHECK: %[[VAL_36:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_37:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_38:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_37]]] : memref<?xindex>
// CHECK: %[[VAL_39:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_28]]] : memref<?xindex>
// CHECK: %[[VAL_40:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index
// CHECK: %[[VAL_41:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_40]]] : memref<?xindex>
// CHECK: %[[VAL_42:.*]]:2 = scf.while (%[[VAL_43:.*]] = %[[VAL_36]], %[[VAL_44:.*]] = %[[VAL_39]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_38]] : index
// CHECK: %[[VAL_46:.*]] = cmpi ult, %[[VAL_44]], %[[VAL_41]] : index
// CHECK: %[[VAL_47:.*]] = and %[[VAL_45]], %[[VAL_46]] : i1
// CHECK: scf.condition(%[[VAL_47]]) %[[VAL_43]], %[[VAL_44]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_48:.*]]: index, %[[VAL_49:.*]]: index):
// CHECK: %[[VAL_50:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_48]]] : memref<?xindex>
// CHECK: %[[VAL_51:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_49]]] : memref<?xindex>
// CHECK: %[[VAL_52:.*]] = cmpi ult, %[[VAL_51]], %[[VAL_50]] : index
// CHECK: %[[VAL_53:.*]] = select %[[VAL_52]], %[[VAL_51]], %[[VAL_50]] : index
// CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
// CHECK: %[[VAL_55:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
// CHECK: %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1
// CHECK: scf.if %[[VAL_56]] {
// CHECK: %[[VAL_57:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: %[[VAL_58:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_49]]] : memref<?xf32>
// CHECK: %[[VAL_59:.*]] = mulf %[[VAL_57]], %[[VAL_58]] : f32
// CHECK: store %[[VAL_59]], %[[VAL_16]]{{\[}}%[[VAL_32]], %[[VAL_53]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: %[[VAL_60:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_53]] : index
// CHECK: %[[VAL_61:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
// CHECK: %[[VAL_62:.*]] = select %[[VAL_60]], %[[VAL_61]], %[[VAL_48]] : index
// CHECK: %[[VAL_63:.*]] = cmpi eq, %[[VAL_51]], %[[VAL_53]] : index
// CHECK: %[[VAL_64:.*]] = addi %[[VAL_49]], %[[VAL_4]] : index
// CHECK: %[[VAL_65:.*]] = select %[[VAL_63]], %[[VAL_64]], %[[VAL_49]] : index
// CHECK: scf.yield %[[VAL_62]], %[[VAL_65]] : index, index
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: %[[VAL_66:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_32]] : index
// CHECK: %[[VAL_67:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_68:.*]] = select %[[VAL_66]], %[[VAL_67]], %[[VAL_27]] : index
// CHECK: %[[VAL_69:.*]] = cmpi eq, %[[VAL_30]], %[[VAL_32]] : index
// CHECK: %[[VAL_70:.*]] = addi %[[VAL_28]], %[[VAL_4]] : index
// CHECK: %[[VAL_71:.*]] = select %[[VAL_69]], %[[VAL_70]], %[[VAL_28]] : index
// CHECK: scf.yield %[[VAL_68]], %[[VAL_71]] : index, index
// CHECK: }
// CHECK: %[[VAL_72:.*]] = memref.tensor_load %[[VAL_16]] : memref<32x16xf32>
// CHECK: return %[[VAL_72]] : tensor<32x16xf32>
// CHECK: }
func @mul_sd_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>, %argx: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%argx: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %x: f32):
%0 = mulf %a, %b : f32
linalg.yield %0 : f32
} -> tensor<32x16xf32>
return %0 : tensor<32x16xf32>
}
#trait_matvec = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (j)>, // b
affine_map<(i,j) -> (i)> // x (out)
],
sparse = [
[ "D", "S" ], // A
[ "D" ], // b
[ "D" ] // x
],
iterator_types = ["parallel", "reduction"],
doc = "x(i) += SUM_j A(i,j) * b(j)"
}
// CHECK-LABEL: func @matvec(
// CHECK-SAME: %[[VAL_0:.*]]: tensor<16x32xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32xf32>,
// CHECK-SAME: %[[VAL_2:.*]]: tensor<16xf32>) -> tensor<16xf32> {
// CHECK: %[[VAL_3:.*]] = constant 16 : index
// CHECK: %[[VAL_4:.*]] = constant 0 : index
// CHECK: %[[VAL_5:.*]] = constant 1 : index
// CHECK: %[[VAL_6:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_5]] : tensor<16x32xf32> to memref<?xindex>
// CHECK: %[[VAL_7:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_5]] : tensor<16x32xf32> to memref<?xindex>
// CHECK: %[[VAL_8:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<16x32xf32> to memref<?xf32>
// CHECK: %[[VAL_9:.*]] = memref.buffer_cast %[[VAL_1]] : memref<32xf32>
// CHECK: %[[VAL_10:.*]] = memref.buffer_cast %[[VAL_2]] : memref<16xf32>
// CHECK: %[[VAL_11:.*]] = memref.alloc() : memref<16xf32>
// CHECK: linalg.copy(%[[VAL_10]], %[[VAL_11]]) : memref<16xf32>, memref<16xf32>
// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
// CHECK: %[[VAL_13:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_5]] : index
// CHECK: %[[VAL_15:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref<?xindex>
// CHECK: %[[VAL_16:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_12]]] : memref<16xf32>
// CHECK: %[[VAL_17:.*]] = scf.for %[[VAL_18:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_5]] iter_args(%[[VAL_19:.*]] = %[[VAL_16]]) -> (f32) {
// CHECK: %[[VAL_20:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_18]]] : memref<?xindex>
// CHECK: %[[VAL_21:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref<?xf32>
// CHECK: %[[VAL_22:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_20]]] : memref<32xf32>
// CHECK: %[[VAL_23:.*]] = mulf %[[VAL_21]], %[[VAL_22]] : f32
// CHECK: %[[VAL_24:.*]] = addf %[[VAL_23]], %[[VAL_19]] : f32
// CHECK: scf.yield %[[VAL_24]] : f32
// CHECK: }
// CHECK: store %[[VAL_25:.*]], %[[VAL_11]]{{\[}}%[[VAL_12]]] : memref<16xf32>
// CHECK: }
// CHECK: %[[VAL_26:.*]] = memref.tensor_load %[[VAL_11]] : memref<16xf32>
// CHECK: return %[[VAL_26]] : tensor<16xf32>
// CHECK: }
func @matvec(%argA: tensor<16x32xf32>, %argb: tensor<32xf32>, %argx: tensor<16xf32>) -> tensor<16xf32> {
%0 = linalg.generic #trait_matvec
ins(%argA, %argb: tensor<16x32xf32>, tensor<32xf32>)
outs(%argx: tensor<16xf32>) {
^bb(%A: f32, %b: f32, %x: f32):
%0 = mulf %A, %b : f32
%1 = addf %0, %x : f32
linalg.yield %1 : f32
} -> tensor<16xf32>
return %0 : tensor<16xf32>
}
#trait_sum_reduction = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> ()> // x (scalar out)
],
sparse = [
[ "D", "S" ], // A
[ ] // x
],
iterator_types = ["reduction", "reduction"],
doc = "x += SUM_ij A(i,j)"
}
// CHECK-LABEL: func @sum_reduction(
// CHECK-SAME: %[[VAL_0:.*]]: tensor<10x20xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<f32>) -> tensor<f32> {
// CHECK: %[[VAL_2:.*]] = constant 10 : index
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_4]] : tensor<10x20xf32> to memref<?xindex>
// CHECK: %[[VAL_6:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<10x20xf32> to memref<?xf32>
// CHECK: %[[VAL_7:.*]] = memref.buffer_cast %[[VAL_1]] : memref<f32>
// CHECK: %[[VAL_8:.*]] = memref.alloc() : memref<f32>
// CHECK: linalg.copy(%[[VAL_7]], %[[VAL_8]]) : memref<f32>, memref<f32>
// CHECK: scf.for %[[VAL_9:.*]] = %[[VAL_3]] to %[[VAL_2]] step %[[VAL_4]] {
// CHECK: %[[VAL_10:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_9]]] : memref<?xindex>
// CHECK: %[[VAL_11:.*]] = addi %[[VAL_9]], %[[VAL_4]] : index
// CHECK: %[[VAL_12:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref<?xindex>
// CHECK: %[[VAL_13:.*]] = memref.load %[[VAL_8]][] : memref<f32>
// CHECK: %[[VAL_14:.*]] = scf.for %[[VAL_15:.*]] = %[[VAL_10]] to %[[VAL_12]] step %[[VAL_4]] iter_args(%[[VAL_16:.*]] = %[[VAL_13]]) -> (f32) {
// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_15]]] : memref<?xf32>
// CHECK: %[[VAL_18:.*]] = addf %[[VAL_16]], %[[VAL_17]] : f32
// CHECK: scf.yield %[[VAL_18]] : f32
// CHECK: }
// CHECK: store %[[VAL_19:.*]], %[[VAL_8]][] : memref<f32>
// CHECK: }
// CHECK: %[[VAL_20:.*]] = memref.tensor_load %[[VAL_8]] : memref<f32>
// CHECK: return %[[VAL_20]] : tensor<f32>
// CHECK: }
func @sum_reduction(%arga: tensor<10x20xf32>, %argx: tensor<f32>) -> tensor<f32> {
%0 = linalg.generic #trait_sum_reduction
ins(%arga: tensor<10x20xf32>)
outs(%argx: tensor<f32>) {
^bb(%a: f32, %x: f32):
%0 = addf %x, %a : f32
linalg.yield %0 : f32
} -> tensor<f32>
return %0 : tensor<f32>
}
#trait_scale = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (i,j)> // X (out)
],
sparse = [
[ "D", "S" ], // A
[ "D", "D" ] // X
],
iterator_types = ["parallel", "parallel"],
doc = "X(i,j) = A(i,j) * SCALE"
}
// CHECK-LABEL: func @scale(
// CHECK-SAME: %[[VAL_0:.*]]: tensor<?x?xf64>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<?x?xf64>) -> tensor<?x?xf64> {
// CHECK-DAG: %[[VAL_3:.*]] = constant 0 : index
// CHECK-DAG: %[[VAL_4:.*]] = constant 1 : index
// CHECK-DAG: %[[VAL_2:.*]] = constant 2.000000e+00 : f64
// CHECK: %[[VAL_5:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_4]] : tensor<?x?xf64> to memref<?xindex>
// CHECK: %[[VAL_6:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_4]] : tensor<?x?xf64> to memref<?xindex>
// CHECK: %[[VAL_7:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<?x?xf64> to memref<?xf64>
// CHECK: %[[VAL_8:.*]] = memref.dim %[[VAL_1]], %[[VAL_3]] : tensor<?x?xf64>
// CHECK: %[[VAL_9:.*]] = memref.dim %[[VAL_1]], %[[VAL_4]] : tensor<?x?xf64>
// CHECK: %[[VAL_10:.*]] = memref.buffer_cast %[[VAL_1]] : memref<?x?xf64>
// CHECK: %[[VAL_11:.*]] = memref.alloc(%[[VAL_8]], %[[VAL_9]]) : memref<?x?xf64>
// CHECK: linalg.copy(%[[VAL_10]], %[[VAL_11]]) : memref<?x?xf64>, memref<?x?xf64>
// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_3]] to %[[VAL_8]] step %[[VAL_4]] {
// CHECK: %[[VAL_13:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_12]]] : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_4]] : index
// CHECK: %[[VAL_15:.*]] = memref.load %[[VAL_5]]{{\[}}%[[VAL_14]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_16:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_4]] {
// CHECK: %[[VAL_17:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_16]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_16]]] : memref<?xf64>
// CHECK: %[[VAL_19:.*]] = mulf %[[VAL_18]], %[[VAL_2]] : f64
// CHECK: store %[[VAL_19]], %[[VAL_11]]{{\[}}%[[VAL_12]], %[[VAL_17]]] : memref<?x?xf64>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_20:.*]] = memref.tensor_load %[[VAL_11]] : memref<?x?xf64>
// CHECK: return %[[VAL_20]] : tensor<?x?xf64>
// CHECK: }
func @scale(%arga: tensor<?x?xf64>, %argx: tensor<?x?xf64>) -> tensor<?x?xf64> {
%0 = constant 2.0 : f64
%1 = linalg.generic #trait_scale
ins(%arga: tensor<?x?xf64>)
outs(%argx: tensor<?x?xf64>) {
^bb(%a: f64, %x: f64):
%2 = mulf %a, %0 : f64
linalg.yield %2 : f64
} -> tensor<?x?xf64>
return %1 : tensor<?x?xf64>
}
#trait_sampled_dense_dense = {
indexing_maps = [
affine_map<(i,j,k) -> (i,j)>, // S
affine_map<(i,j,k) -> (i,k)>, // A
affine_map<(i,j,k) -> (k,j)>, // B
affine_map<(i,j,k) -> (i,j)> // X (out)
],
sparse = [
[ "S", "S" ], // S
[ "D", "D" ], // A
[ "D", "D" ], // B
[ "D", "D" ] // X
],
iterator_types = ["parallel", "parallel", "reduction"],
doc = "X(i,j) += S(i,j) SUM_k A(i,k) B(k,j)"
}
// CHECK-LABEL: func @sampled_dense_dense(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<?x?xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<?x?xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<?x?xf32>,
// CHECK-SAME: %[[VAL_3:.*3]]: tensor<?x?xf32>) -> tensor<?x?xf32> {
// CHECK: %[[VAL_4:.*]] = constant 0 : index
// CHECK: %[[VAL_5:.*]] = constant 1 : index
// CHECK: %[[VAL_6:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_4]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_7:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_4]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_8:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_5]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_9:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_5]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_10:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<?x?xf32> to memref<?xf32>
// CHECK: %[[VAL_11:.*]] = memref.buffer_cast %[[VAL_1]] : memref<?x?xf32>
// CHECK: %[[VAL_12:.*]] = memref.dim %[[VAL_2]], %[[VAL_4]] : tensor<?x?xf32>
// CHECK: %[[VAL_13:.*]] = memref.buffer_cast %[[VAL_2]] : memref<?x?xf32>
// CHECK: %[[VAL_14:.*]] = memref.dim %[[VAL_3]], %[[VAL_4]] : tensor<?x?xf32>
// CHECK: %[[VAL_15:.*]] = memref.dim %[[VAL_3]], %[[VAL_5]] : tensor<?x?xf32>
// CHECK: %[[VAL_16:.*]] = memref.buffer_cast %[[VAL_3]] : memref<?x?xf32>
// CHECK: %[[VAL_17:.*]] = memref.alloc(%[[VAL_14]], %[[VAL_15]]) : memref<?x?xf32>
// CHECK: linalg.copy(%[[VAL_16]], %[[VAL_17]]) : memref<?x?xf32>, memref<?x?xf32>
// CHECK: %[[VAL_18:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_19:.*]] = memref.load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_20:.*]] = %[[VAL_18]] to %[[VAL_19]] step %[[VAL_5]] {
// CHECK: %[[VAL_21:.*]] = memref.load %[[VAL_7]]{{\[}}%[[VAL_20]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_22:.*]] = %[[VAL_4]] to %[[VAL_12]] step %[[VAL_5]] {
// CHECK: %[[VAL_23:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_21]], %[[VAL_22]]] : memref<?x?xf32>
// CHECK: %[[VAL_24:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_20]]] : memref<?xindex>
// CHECK: %[[VAL_25:.*]] = addi %[[VAL_20]], %[[VAL_5]] : index
// CHECK: %[[VAL_26:.*]] = memref.load %[[VAL_8]]{{\[}}%[[VAL_25]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_27:.*]] = %[[VAL_24]] to %[[VAL_26]] step %[[VAL_5]] {
// CHECK: %[[VAL_28:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_29:.*]] = memref.load %[[VAL_17]]{{\[}}%[[VAL_21]], %[[VAL_28]]] : memref<?x?xf32>
// CHECK: %[[VAL_30:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_27]]] : memref<?xf32>
// CHECK: %[[VAL_31:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_28]]] : memref<?x?xf32>
// CHECK: %[[VAL_32:.*]] = mulf %[[VAL_23]], %[[VAL_31]] : f32
// CHECK: %[[VAL_33:.*]] = mulf %[[VAL_30]], %[[VAL_32]] : f32
// CHECK: %[[VAL_34:.*]] = addf %[[VAL_29]], %[[VAL_33]] : f32
// CHECK: store %[[VAL_34]], %[[VAL_17]]{{\[}}%[[VAL_21]], %[[VAL_28]]] : memref<?x?xf32>
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_35:.*]] = memref.tensor_load %[[VAL_17]] : memref<?x?xf32>
// CHECK: return %[[VAL_35]] : tensor<?x?xf32>
// CHECK: }
func @sampled_dense_dense(%args: tensor<?x?xf32>,
%arga: tensor<?x?xf32>,
%argb: tensor<?x?xf32>,
%argx: tensor<?x?xf32>) -> tensor<?x?xf32> {
%0 = linalg.generic #trait_sampled_dense_dense
ins(%args, %arga, %argb: tensor<?x?xf32>, tensor<?x?xf32>, tensor<?x?xf32>)
outs(%argx: tensor<?x?xf32>) {
^bb(%s: f32, %a: f32, %b: f32, %x: f32):
%0 = mulf %a, %b : f32
%1 = mulf %s, %0 : f32
%2 = addf %x, %1 : f32
linalg.yield %2 : f32
} -> tensor<?x?xf32>
return %0 : tensor<?x?xf32>
}
#trait_sum_kernel_with_inv = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (i,j)>, // B
affine_map<(i,j) -> (i,j)>, // C
affine_map<(i,j) -> (i)>, // d
affine_map<(i,j) -> ()>, // e
affine_map<(i,j) -> (i)> // x (out)
],
sparse = [
[ "S", "S" ], // A
[ "D", "S" ], // B
[ "D", "S" ], // C
[ "D" ], // d
[ ], // e
[ "D" ] // x
],
iterator_types = ["parallel", "reduction"],
doc = "x(i) = SUM_j A(i,j) * B(i,j) * d(i) * e + C(i,j)"
}
// CHECK-LABEL: func @sum_kernel_with_inv(
// CHECK-SAME: %[[VAL_0:.*0]]: tensor<?x?xf32>,
// CHECK-SAME: %[[VAL_1:.*1]]: tensor<?x?xf32>,
// CHECK-SAME: %[[VAL_2:.*2]]: tensor<?x?xf32>,
// CHECK-SAME: %[[VAL_3:.*3]]: tensor<?xf32>,
// CHECK-SAME: %[[VAL_4:.*4]]: tensor<f32>,
// CHECK-SAME: %[[VAL_5:.*5]]: tensor<?xf32>) -> tensor<?xf32> {
// CHECK: %[[VAL_6:.*]] = constant 0 : index
// CHECK: %[[VAL_7:.*]] = constant true
// CHECK: %[[VAL_8:.*]] = constant 1 : index
// CHECK: %[[VAL_9:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_6]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_10:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_6]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_11:.*]] = sparse_tensor.pointers %[[VAL_0]], %[[VAL_8]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_12:.*]] = sparse_tensor.indices %[[VAL_0]], %[[VAL_8]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_13:.*]] = sparse_tensor.values %[[VAL_0]] : tensor<?x?xf32> to memref<?xf32>
// CHECK: %[[VAL_14:.*]] = sparse_tensor.pointers %[[VAL_1]], %[[VAL_8]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_15:.*]] = sparse_tensor.indices %[[VAL_1]], %[[VAL_8]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_16:.*]] = sparse_tensor.values %[[VAL_1]] : tensor<?x?xf32> to memref<?xf32>
// CHECK: %[[VAL_17:.*]] = sparse_tensor.pointers %[[VAL_2]], %[[VAL_8]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_18:.*]] = sparse_tensor.indices %[[VAL_2]], %[[VAL_8]] : tensor<?x?xf32> to memref<?xindex>
// CHECK: %[[VAL_19:.*]] = sparse_tensor.values %[[VAL_2]] : tensor<?x?xf32> to memref<?xf32>
// CHECK: %[[VAL_20:.*]] = memref.buffer_cast %[[VAL_3]] : memref<?xf32>
// CHECK: %[[VAL_21:.*]] = memref.buffer_cast %[[VAL_4]] : memref<f32>
// CHECK: %[[VAL_22:.*]] = memref.dim %[[VAL_5]], %[[VAL_6]] : tensor<?xf32>
// CHECK: %[[VAL_23:.*]] = memref.buffer_cast %[[VAL_5]] : memref<?xf32>
// CHECK: %[[VAL_24:.*]] = memref.alloc(%[[VAL_22]]) : memref<?xf32>
// CHECK: linalg.copy(%[[VAL_23]], %[[VAL_24]]) : memref<?xf32>, memref<?xf32>
// CHECK: %[[VAL_25:.*]] = memref.load %[[VAL_21]][] : memref<f32>
// CHECK: %[[VAL_26:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_6]]] : memref<?xindex>
// CHECK: %[[VAL_27:.*]] = memref.load %[[VAL_9]]{{\[}}%[[VAL_8]]] : memref<?xindex>
// CHECK: %[[VAL_28:.*]]:2 = scf.while (%[[VAL_29:.*]] = %[[VAL_26]], %[[VAL_30:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_31:.*]] = cmpi ult, %[[VAL_29]], %[[VAL_27]] : index
// CHECK: scf.condition(%[[VAL_31]]) %[[VAL_29]], %[[VAL_30]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_32:.*]]: index, %[[VAL_33:.*]]: index):
// CHECK: %[[VAL_34:.*]] = memref.load %[[VAL_10]]{{\[}}%[[VAL_32]]] : memref<?xindex>
// CHECK: %[[VAL_35:.*]] = cmpi eq, %[[VAL_34]], %[[VAL_33]] : index
// CHECK: scf.if %[[VAL_35]] {
// CHECK: %[[VAL_36:.*]] = memref.load %[[VAL_20]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: %[[VAL_37:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_32]]] : memref<?xindex>
// CHECK: %[[VAL_38:.*]] = addi %[[VAL_32]], %[[VAL_8]] : index
// CHECK: %[[VAL_39:.*]] = memref.load %[[VAL_11]]{{\[}}%[[VAL_38]]] : memref<?xindex>
// CHECK: %[[VAL_40:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_33]]] : memref<?xindex>
// CHECK: %[[VAL_41:.*]] = addi %[[VAL_33]], %[[VAL_8]] : index
// CHECK: %[[VAL_42:.*]] = memref.load %[[VAL_14]]{{\[}}%[[VAL_41]]] : memref<?xindex>
// CHECK: %[[VAL_43:.*]] = memref.load %[[VAL_17]]{{\[}}%[[VAL_33]]] : memref<?xindex>
// CHECK: %[[VAL_44:.*]] = addi %[[VAL_33]], %[[VAL_8]] : index
// CHECK: %[[VAL_45:.*]] = memref.load %[[VAL_17]]{{\[}}%[[VAL_44]]] : memref<?xindex>
// CHECK: %[[VAL_46:.*]]:3 = scf.while (%[[VAL_47:.*]] = %[[VAL_37]], %[[VAL_48:.*]] = %[[VAL_40]], %[[VAL_49:.*]] = %[[VAL_43]]) : (index, index, index) -> (index, index, index) {
// CHECK: %[[VAL_50:.*]] = cmpi ult, %[[VAL_47]], %[[VAL_39]] : index
// CHECK: %[[VAL_51:.*]] = cmpi ult, %[[VAL_48]], %[[VAL_42]] : index
// CHECK: %[[VAL_52:.*]] = and %[[VAL_50]], %[[VAL_51]] : i1
// CHECK: %[[VAL_53:.*]] = cmpi ult, %[[VAL_49]], %[[VAL_45]] : index
// CHECK: %[[VAL_54:.*]] = and %[[VAL_52]], %[[VAL_53]] : i1
// CHECK: scf.condition(%[[VAL_54]]) %[[VAL_47]], %[[VAL_48]], %[[VAL_49]] : index, index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_55:.*]]: index, %[[VAL_56:.*]]: index, %[[VAL_57:.*]]: index):
// CHECK: %[[VAL_58:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_55]]] : memref<?xindex>
// CHECK: %[[VAL_59:.*]] = memref.load %[[VAL_15]]{{\[}}%[[VAL_56]]] : memref<?xindex>
// CHECK: %[[VAL_60:.*]] = cmpi ult, %[[VAL_59]], %[[VAL_58]] : index
// CHECK: %[[VAL_61:.*]] = select %[[VAL_60]], %[[VAL_59]], %[[VAL_58]] : index
// CHECK: %[[VAL_62:.*]] = memref.load %[[VAL_18]]{{\[}}%[[VAL_57]]] : memref<?xindex>
// CHECK: %[[VAL_63:.*]] = cmpi ult, %[[VAL_62]], %[[VAL_61]] : index
// CHECK: %[[VAL_64:.*]] = select %[[VAL_63]], %[[VAL_62]], %[[VAL_61]] : index
// CHECK: %[[VAL_65:.*]] = cmpi eq, %[[VAL_58]], %[[VAL_64]] : index
// CHECK: %[[VAL_66:.*]] = cmpi eq, %[[VAL_59]], %[[VAL_64]] : index
// CHECK: %[[VAL_67:.*]] = and %[[VAL_65]], %[[VAL_66]] : i1
// CHECK: %[[VAL_68:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_64]] : index
// CHECK: %[[VAL_69:.*]] = and %[[VAL_67]], %[[VAL_68]] : i1
// CHECK: scf.if %[[VAL_69]] {
// CHECK: %[[VAL_70:.*]] = memref.load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: %[[VAL_71:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_55]]] : memref<?xf32>
// CHECK: %[[VAL_72:.*]] = memref.load %[[VAL_16]]{{\[}}%[[VAL_56]]] : memref<?xf32>
// CHECK: %[[VAL_73:.*]] = mulf %[[VAL_71]], %[[VAL_72]] : f32
// CHECK: %[[VAL_74:.*]] = mulf %[[VAL_73]], %[[VAL_36]] : f32
// CHECK: %[[VAL_75:.*]] = mulf %[[VAL_74]], %[[VAL_25]] : f32
// CHECK: %[[VAL_76:.*]] = memref.load %[[VAL_19]]{{\[}}%[[VAL_57]]] : memref<?xf32>
// CHECK: %[[VAL_77:.*]] = addf %[[VAL_75]], %[[VAL_76]] : f32
// CHECK: %[[VAL_78:.*]] = addf %[[VAL_70]], %[[VAL_77]] : f32
// CHECK: store %[[VAL_78]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: } else {
// CHECK: %[[VAL_79:.*]] = cmpi eq, %[[VAL_58]], %[[VAL_64]] : index
// CHECK: %[[VAL_80:.*]] = cmpi eq, %[[VAL_59]], %[[VAL_64]] : index
// CHECK: %[[VAL_81:.*]] = and %[[VAL_79]], %[[VAL_80]] : i1
// CHECK: scf.if %[[VAL_81]] {
// CHECK: %[[VAL_82:.*]] = memref.load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: %[[VAL_83:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_55]]] : memref<?xf32>
// CHECK: %[[VAL_84:.*]] = memref.load %[[VAL_16]]{{\[}}%[[VAL_56]]] : memref<?xf32>
// CHECK: %[[VAL_85:.*]] = mulf %[[VAL_83]], %[[VAL_84]] : f32
// CHECK: %[[VAL_86:.*]] = mulf %[[VAL_85]], %[[VAL_36]] : f32
// CHECK: %[[VAL_87:.*]] = mulf %[[VAL_86]], %[[VAL_25]] : f32
// CHECK: %[[VAL_88:.*]] = addf %[[VAL_82]], %[[VAL_87]] : f32
// CHECK: store %[[VAL_88]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: } else {
// CHECK: %[[VAL_89:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_64]] : index
// CHECK: scf.if %[[VAL_89]] {
// CHECK: %[[VAL_90:.*]] = memref.load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: %[[VAL_91:.*]] = memref.load %[[VAL_19]]{{\[}}%[[VAL_57]]] : memref<?xf32>
// CHECK: %[[VAL_92:.*]] = addf %[[VAL_90]], %[[VAL_91]] : f32
// CHECK: store %[[VAL_92]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_93:.*]] = cmpi eq, %[[VAL_58]], %[[VAL_64]] : index
// CHECK: %[[VAL_94:.*]] = addi %[[VAL_55]], %[[VAL_8]] : index
// CHECK: %[[VAL_95:.*]] = select %[[VAL_93]], %[[VAL_94]], %[[VAL_55]] : index
// CHECK: %[[VAL_96:.*]] = cmpi eq, %[[VAL_59]], %[[VAL_64]] : index
// CHECK: %[[VAL_97:.*]] = addi %[[VAL_56]], %[[VAL_8]] : index
// CHECK: %[[VAL_98:.*]] = select %[[VAL_96]], %[[VAL_97]], %[[VAL_56]] : index
// CHECK: %[[VAL_99:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_64]] : index
// CHECK: %[[VAL_100:.*]] = addi %[[VAL_57]], %[[VAL_8]] : index
// CHECK: %[[VAL_101:.*]] = select %[[VAL_99]], %[[VAL_100]], %[[VAL_57]] : index
// CHECK: scf.yield %[[VAL_95]], %[[VAL_98]], %[[VAL_101]] : index, index, index
// CHECK: }
// CHECK: %[[VAL_102:.*]]:2 = scf.while (%[[VAL_103:.*]] = %[[VAL_104:.*]]#0, %[[VAL_105:.*]] = %[[VAL_104]]#1) : (index, index) -> (index, index) {
// CHECK: %[[VAL_106:.*]] = cmpi ult, %[[VAL_103]], %[[VAL_39]] : index
// CHECK: %[[VAL_107:.*]] = cmpi ult, %[[VAL_105]], %[[VAL_42]] : index
// CHECK: %[[VAL_108:.*]] = and %[[VAL_106]], %[[VAL_107]] : i1
// CHECK: scf.condition(%[[VAL_108]]) %[[VAL_103]], %[[VAL_105]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_109:.*]]: index, %[[VAL_110:.*]]: index):
// CHECK: %[[VAL_111:.*]] = memref.load %[[VAL_12]]{{\[}}%[[VAL_109]]] : memref<?xindex>
// CHECK: %[[VAL_112:.*]] = memref.load %[[VAL_15]]{{\[}}%[[VAL_110]]] : memref<?xindex>
// CHECK: %[[VAL_113:.*]] = cmpi ult, %[[VAL_112]], %[[VAL_111]] : index
// CHECK: %[[VAL_114:.*]] = select %[[VAL_113]], %[[VAL_112]], %[[VAL_111]] : index
// CHECK: %[[VAL_115:.*]] = cmpi eq, %[[VAL_111]], %[[VAL_114]] : index
// CHECK: %[[VAL_116:.*]] = cmpi eq, %[[VAL_112]], %[[VAL_114]] : index
// CHECK: %[[VAL_117:.*]] = and %[[VAL_115]], %[[VAL_116]] : i1
// CHECK: scf.if %[[VAL_117]] {
// CHECK: %[[VAL_118:.*]] = memref.load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: %[[VAL_119:.*]] = memref.load %[[VAL_13]]{{\[}}%[[VAL_109]]] : memref<?xf32>
// CHECK: %[[VAL_120:.*]] = memref.load %[[VAL_16]]{{\[}}%[[VAL_110]]] : memref<?xf32>
// CHECK: %[[VAL_121:.*]] = mulf %[[VAL_119]], %[[VAL_120]] : f32
// CHECK: %[[VAL_122:.*]] = mulf %[[VAL_121]], %[[VAL_36]] : f32
// CHECK: %[[VAL_123:.*]] = mulf %[[VAL_122]], %[[VAL_25]] : f32
// CHECK: %[[VAL_124:.*]] = addf %[[VAL_118]], %[[VAL_123]] : f32
// CHECK: store %[[VAL_124]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: } else {
// CHECK: }
// CHECK: %[[VAL_125:.*]] = cmpi eq, %[[VAL_111]], %[[VAL_114]] : index
// CHECK: %[[VAL_126:.*]] = addi %[[VAL_109]], %[[VAL_8]] : index
// CHECK: %[[VAL_127:.*]] = select %[[VAL_125]], %[[VAL_126]], %[[VAL_109]] : index
// CHECK: %[[VAL_128:.*]] = cmpi eq, %[[VAL_112]], %[[VAL_114]] : index
// CHECK: %[[VAL_129:.*]] = addi %[[VAL_110]], %[[VAL_8]] : index
// CHECK: %[[VAL_130:.*]] = select %[[VAL_128]], %[[VAL_129]], %[[VAL_110]] : index
// CHECK: scf.yield %[[VAL_127]], %[[VAL_130]] : index, index
// CHECK: }
// CHECK: %[[VAL_131:.*]] = memref.load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: %[[VAL_132:.*]] = scf.for %[[VAL_133:.*]] = %[[VAL_134:.*]]#2 to %[[VAL_45]] step %[[VAL_8]] iter_args(%[[VAL_135:.*]] = %[[VAL_131]]) -> (f32) {
// CHECK: %[[VAL_136:.*]] = memref.load %[[VAL_19]]{{\[}}%[[VAL_133]]] : memref<?xf32>
// CHECK: %[[VAL_137:.*]] = addf %[[VAL_135]], %[[VAL_136]] : f32
// CHECK: scf.yield %[[VAL_137]] : f32
// CHECK: }
// CHECK: store %[[VAL_138:.*]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: } else {
// CHECK: scf.if %[[VAL_7]] {
// CHECK: %[[VAL_139:.*]] = memref.load %[[VAL_17]]{{\[}}%[[VAL_33]]] : memref<?xindex>
// CHECK: %[[VAL_140:.*]] = addi %[[VAL_33]], %[[VAL_8]] : index
// CHECK: %[[VAL_141:.*]] = memref.load %[[VAL_17]]{{\[}}%[[VAL_140]]] : memref<?xindex>
// CHECK: %[[VAL_142:.*]] = memref.load %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: %[[VAL_143:.*]] = scf.for %[[VAL_144:.*]] = %[[VAL_139]] to %[[VAL_141]] step %[[VAL_8]] iter_args(%[[VAL_145:.*]] = %[[VAL_142]]) -> (f32) {
// CHECK: %[[VAL_146:.*]] = memref.load %[[VAL_19]]{{\[}}%[[VAL_144]]] : memref<?xf32>
// CHECK: %[[VAL_147:.*]] = addf %[[VAL_145]], %[[VAL_146]] : f32
// CHECK: scf.yield %[[VAL_147]] : f32
// CHECK: }
// CHECK: store %[[VAL_148:.*]], %[[VAL_24]]{{\[}}%[[VAL_33]]] : memref<?xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_149:.*]] = cmpi eq, %[[VAL_34]], %[[VAL_33]] : index
// CHECK: %[[VAL_150:.*]] = addi %[[VAL_32]], %[[VAL_8]] : index
// CHECK: %[[VAL_151:.*]] = select %[[VAL_149]], %[[VAL_150]], %[[VAL_32]] : index
// CHECK: %[[VAL_152:.*]] = addi %[[VAL_33]], %[[VAL_8]] : index
// CHECK: scf.yield %[[VAL_151]], %[[VAL_152]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_153:.*]] = %[[VAL_154:.*]]#1 to %[[VAL_22]] step %[[VAL_8]] {
// CHECK: %[[VAL_155:.*]] = memref.load %[[VAL_17]]{{\[}}%[[VAL_153]]] : memref<?xindex>
// CHECK: %[[VAL_156:.*]] = addi %[[VAL_153]], %[[VAL_8]] : index
// CHECK: %[[VAL_157:.*]] = memref.load %[[VAL_17]]{{\[}}%[[VAL_156]]] : memref<?xindex>
// CHECK: %[[VAL_158:.*]] = memref.load %[[VAL_24]]{{\[}}%[[VAL_153]]] : memref<?xf32>
// CHECK: %[[VAL_159:.*]] = scf.for %[[VAL_160:.*]] = %[[VAL_155]] to %[[VAL_157]] step %[[VAL_8]] iter_args(%[[VAL_161:.*]] = %[[VAL_158]]) -> (f32) {
// CHECK: %[[VAL_162:.*]] = memref.load %[[VAL_19]]{{\[}}%[[VAL_160]]] : memref<?xf32>
// CHECK: %[[VAL_163:.*]] = addf %[[VAL_161]], %[[VAL_162]] : f32
// CHECK: scf.yield %[[VAL_163]] : f32
// CHECK: }
// CHECK: store %[[VAL_164:.*]], %[[VAL_24]]{{\[}}%[[VAL_153]]] : memref<?xf32>
// CHECK: }
// CHECK: %[[VAL_165:.*]] = memref.tensor_load %[[VAL_24]] : memref<?xf32>
// CHECK: return %[[VAL_165]] : tensor<?xf32>
// CHECK: }
func @sum_kernel_with_inv(%arga: tensor<?x?xf32>,
%argb: tensor<?x?xf32>,
%argc: tensor<?x?xf32>,
%argd: tensor<?xf32>,
%arge: tensor<f32>,
%argx: tensor<?xf32>) -> tensor<?xf32> {
%0 = linalg.generic #trait_sum_kernel_with_inv
ins(%arga, %argb, %argc, %argd, %arge : tensor<?x?xf32>,
tensor<?x?xf32>,
tensor<?x?xf32>,
tensor<?xf32>,
tensor<f32>)
outs(%argx: tensor<?xf32>) {
^bb(%a: f32, %b: f32, %c: f32, %d: f32, %e: f32, %x: f32):
%0 = mulf %a, %b : f32
%1 = mulf %0, %d : f32
%2 = mulf %1, %e : f32
%3 = addf %2, %c : f32
%4 = addf %x, %3 : f32
linalg.yield %4 : f32
} -> tensor<?xf32>
return %0 : tensor<?xf32>
}