Google Git
Sign in
llvm / llvm-project / 15d1ee36720ff24323f55452ae3cfb63f318c3f3 / . / mlir / test / Dialect / Linalg / sparse_2d.mlir
blob: 957c3b6e1589d961161f924b56c03e37fc8e6490 [file] [log] [blame]
// NOTE: Assertions have been autogenerated by utils/generate-test-checks.py
// RUN: mlir-opt %s -test-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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 32 : index
// CHECK: %[[VAL_3:.*]] = constant 16 : index
// CHECK: %[[VAL_4:.*]] = constant 0 : index
// CHECK: %[[VAL_5:.*]] = constant 1 : index
// CHECK: %[[VAL_6:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_7:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_8:.*]] = alloca() : memref<32x16xf32>
// CHECK: scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_2]] step %[[VAL_5]] {
// CHECK: scf.for %[[VAL_10:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
// CHECK: %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
// CHECK: %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
// CHECK: %[[VAL_13:.*]] = addf %[[VAL_11]], %[[VAL_12]] : f32
// CHECK: store %[[VAL_13]], %[[VAL_8]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_14:.*]] = tensor_load %[[VAL_8]] : memref<32x16xf32>
// CHECK: return %[[VAL_14]] : tensor<32x16xf32>
// CHECK: }
func @add_dd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_dd
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga: tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 32 : index
// CHECK: %[[VAL_3:.*]] = constant 16 : index
// CHECK: %[[VAL_4:.*]] = constant 0 : index
// CHECK: %[[VAL_5:.*]] = constant 1 : index
// CHECK: %[[VAL_6:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_7:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_8:.*]] = alloca() : memref<32x16xf32>
// CHECK: scf.for %[[VAL_9:.*]] = %[[VAL_4]] to %[[VAL_2]] step %[[VAL_5]] {
// CHECK: scf.for %[[VAL_10:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
// CHECK: %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
// CHECK: %[[VAL_12:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
// CHECK: %[[VAL_13:.*]] = mulf %[[VAL_11]], %[[VAL_12]] : f32
// CHECK: store %[[VAL_13]], %[[VAL_8]]{{\[}}%[[VAL_9]], %[[VAL_10]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_14:.*]] = tensor_load %[[VAL_8]] : memref<32x16xf32>
// CHECK: return %[[VAL_14]] : tensor<32x16xf32>
// CHECK: }
func @mul_dd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_dd
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga : tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 999 : index
// 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:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_11:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_12:.*]] = alloca() : memref<32x16xf32>
// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_5]] to %[[VAL_3]] step %[[VAL_7]] {
// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_13]]] : memref<?xindex>
// CHECK: %[[VAL_15:.*]] = addi %[[VAL_13]], %[[VAL_7]] : index
// CHECK: %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref<?xindex>
// CHECK: %[[VAL_17:.*]]:2 = scf.while (%[[VAL_18:.*]] = %[[VAL_14]], %[[VAL_19:.*]] = %[[VAL_5]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_16]] : index
// CHECK: scf.condition(%[[VAL_20]]) %[[VAL_18]], %[[VAL_19]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_21:.*]]: index, %[[VAL_22:.*]]: index):
// CHECK: %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref<?xindex>
// CHECK: %[[VAL_24:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index
// CHECK: scf.if %[[VAL_24]] {
// CHECK: %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref<?xf32>
// CHECK: %[[VAL_26:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]], %[[VAL_22]]] : memref<32x16xf32>
// CHECK: %[[VAL_27:.*]] = addf %[[VAL_25]], %[[VAL_26]] : f32
// CHECK: store %[[VAL_27]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_22]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: scf.if %[[VAL_6]] {
// CHECK: %[[VAL_28:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]], %[[VAL_22]]] : memref<32x16xf32>
// CHECK: store %[[VAL_28]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_22]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_29:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index
// CHECK: %[[VAL_30:.*]] = addi %[[VAL_21]], %[[VAL_7]] : index
// CHECK: %[[VAL_31:.*]] = select %[[VAL_29]], %[[VAL_30]], %[[VAL_21]] : index
// CHECK: %[[VAL_32:.*]] = addi %[[VAL_22]], %[[VAL_7]] : index
// CHECK: scf.yield %[[VAL_31]], %[[VAL_32]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_33:.*]] = %[[VAL_34:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_35:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_13]], %[[VAL_33]]] : memref<32x16xf32>
// CHECK: store %[[VAL_35]], %[[VAL_12]]{{\[}}%[[VAL_13]], %[[VAL_33]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_36:.*]] = tensor_load %[[VAL_12]] : memref<32x16xf32>
// CHECK: return %[[VAL_36]] : tensor<32x16xf32>
// CHECK: }
func @add_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ds
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga : tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 999 : index
// CHECK: %[[VAL_3:.*]] = constant 32 : index
// CHECK: %[[VAL_4:.*]] = constant 0 : index
// CHECK: %[[VAL_5:.*]] = constant 1 : index
// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_9:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_10:.*]] = alloca() : memref<32x16xf32>
// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
// CHECK: %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_11]]] : memref<?xindex>
// CHECK: %[[VAL_13:.*]] = addi %[[VAL_11]], %[[VAL_5]] : index
// CHECK: %[[VAL_14:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_13]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_12]] to %[[VAL_14]] step %[[VAL_5]] {
// CHECK: %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xindex>
// CHECK: %[[VAL_17:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_15]]] : memref<?xf32>
// CHECK: %[[VAL_18:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_11]], %[[VAL_16]]] : memref<32x16xf32>
// CHECK: %[[VAL_19:.*]] = mulf %[[VAL_17]], %[[VAL_18]] : f32
// CHECK: store %[[VAL_19]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_16]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_20:.*]] = tensor_load %[[VAL_10]] : memref<32x16xf32>
// CHECK: return %[[VAL_20]] : tensor<32x16xf32>
// CHECK: }
func @mul_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ds
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga : tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 999 : index
// 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:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_11:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_12:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_13:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref<?xindex>
// CHECK: %[[VAL_15:.*]]:2 = scf.while (%[[VAL_16:.*]] = %[[VAL_13]], %[[VAL_17:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_18:.*]] = cmpi ult, %[[VAL_16]], %[[VAL_14]] : index
// CHECK: scf.condition(%[[VAL_18]]) %[[VAL_16]], %[[VAL_17]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_19:.*]]: index, %[[VAL_20:.*]]: index):
// CHECK: %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref<?xindex>
// CHECK: %[[VAL_22:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index
// CHECK: scf.if %[[VAL_22]] {
// CHECK: scf.for %[[VAL_23:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_24:.*]] = muli %[[VAL_19]], %[[VAL_4]] : index
// CHECK: %[[VAL_25:.*]] = addi %[[VAL_24]], %[[VAL_23]] : index
// CHECK: %[[VAL_26:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_25]]] : memref<?xf32>
// CHECK: %[[VAL_27:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_20]], %[[VAL_23]]] : memref<32x16xf32>
// CHECK: %[[VAL_28:.*]] = addf %[[VAL_26]], %[[VAL_27]] : f32
// CHECK: store %[[VAL_28]], %[[VAL_12]]{{\[}}%[[VAL_20]], %[[VAL_23]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: scf.if %[[VAL_5]] {
// CHECK: scf.for %[[VAL_29:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_30:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_20]], %[[VAL_29]]] : memref<32x16xf32>
// CHECK: store %[[VAL_30]], %[[VAL_12]]{{\[}}%[[VAL_20]], %[[VAL_29]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_31:.*]] = cmpi eq, %[[VAL_21]], %[[VAL_20]] : index
// CHECK: %[[VAL_32:.*]] = addi %[[VAL_19]], %[[VAL_7]] : index
// CHECK: %[[VAL_33:.*]] = select %[[VAL_31]], %[[VAL_32]], %[[VAL_19]] : index
// CHECK: %[[VAL_34:.*]] = addi %[[VAL_20]], %[[VAL_7]] : index
// CHECK: scf.yield %[[VAL_33]], %[[VAL_34]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_35:.*]] = %[[VAL_36:.*]]#1 to %[[VAL_3]] step %[[VAL_7]] {
// CHECK: scf.for %[[VAL_37:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_38:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_35]], %[[VAL_37]]] : memref<32x16xf32>
// CHECK: store %[[VAL_38]], %[[VAL_12]]{{\[}}%[[VAL_35]], %[[VAL_37]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_39:.*]] = tensor_load %[[VAL_12]] : memref<32x16xf32>
// CHECK: return %[[VAL_39]] : tensor<32x16xf32>
// CHECK: }
func @add_sd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_sd
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga : tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 999 : index
// CHECK: %[[VAL_3:.*]] = constant 16 : index
// CHECK: %[[VAL_4:.*]] = constant 0 : index
// CHECK: %[[VAL_5:.*]] = constant 1 : index
// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_9:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_10:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_12:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_13:.*]] = %[[VAL_11]] to %[[VAL_12]] step %[[VAL_5]] {
// CHECK: %[[VAL_14:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_13]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
// CHECK: %[[VAL_16:.*]] = muli %[[VAL_13]], %[[VAL_3]] : index
// CHECK: %[[VAL_17:.*]] = addi %[[VAL_16]], %[[VAL_15]] : index
// CHECK: %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_17]]] : memref<?xf32>
// CHECK: %[[VAL_19:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_14]], %[[VAL_15]]] : memref<32x16xf32>
// CHECK: %[[VAL_20:.*]] = mulf %[[VAL_18]], %[[VAL_19]] : f32
// CHECK: store %[[VAL_20]], %[[VAL_10]]{{\[}}%[[VAL_14]], %[[VAL_15]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_21:.*]] = tensor_load %[[VAL_10]] : memref<32x16xf32>
// CHECK: return %[[VAL_21]] : tensor<32x16xf32>
// CHECK: }
func @mul_sd(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_sd
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga : tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 999 : index
// 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:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_13:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_14:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_15:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_6]]] : memref<?xindex>
// CHECK: %[[VAL_16:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_7]]] : memref<?xindex>
// CHECK: %[[VAL_17:.*]]:2 = scf.while (%[[VAL_18:.*]] = %[[VAL_15]], %[[VAL_19:.*]] = %[[VAL_6]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_20:.*]] = cmpi ult, %[[VAL_18]], %[[VAL_16]] : index
// CHECK: scf.condition(%[[VAL_20]]) %[[VAL_18]], %[[VAL_19]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_21:.*]]: index, %[[VAL_22:.*]]: index):
// CHECK: %[[VAL_23:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_21]]] : memref<?xindex>
// CHECK: %[[VAL_24:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index
// CHECK: scf.if %[[VAL_24]] {
// CHECK: %[[VAL_25:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_21]]] : memref<?xindex>
// CHECK: %[[VAL_26:.*]] = addi %[[VAL_21]], %[[VAL_7]] : index
// CHECK: %[[VAL_27:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_26]]] : memref<?xindex>
// CHECK: %[[VAL_28:.*]]:2 = scf.while (%[[VAL_29:.*]] = %[[VAL_25]], %[[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:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_32]]] : memref<?xindex>
// CHECK: %[[VAL_35:.*]] = cmpi eq, %[[VAL_34]], %[[VAL_33]] : index
// CHECK: scf.if %[[VAL_35]] {
// CHECK: %[[VAL_36:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_32]]] : memref<?xf32>
// CHECK: %[[VAL_37:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_33]]] : memref<32x16xf32>
// CHECK: %[[VAL_38:.*]] = addf %[[VAL_36]], %[[VAL_37]] : f32
// CHECK: store %[[VAL_38]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_33]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: scf.if %[[VAL_5]] {
// CHECK: %[[VAL_39:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_33]]] : memref<32x16xf32>
// CHECK: store %[[VAL_39]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_33]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_40:.*]] = cmpi eq, %[[VAL_34]], %[[VAL_33]] : index
// CHECK: %[[VAL_41:.*]] = addi %[[VAL_32]], %[[VAL_7]] : index
// CHECK: %[[VAL_42:.*]] = select %[[VAL_40]], %[[VAL_41]], %[[VAL_32]] : index
// CHECK: %[[VAL_43:.*]] = addi %[[VAL_33]], %[[VAL_7]] : index
// CHECK: scf.yield %[[VAL_42]], %[[VAL_43]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_44:.*]] = %[[VAL_45:.*]]#1 to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_46:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_44]]] : memref<32x16xf32>
// CHECK: store %[[VAL_46]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_44]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: scf.if %[[VAL_5]] {
// CHECK: scf.for %[[VAL_47:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_48:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_22]], %[[VAL_47]]] : memref<32x16xf32>
// CHECK: store %[[VAL_48]], %[[VAL_14]]{{\[}}%[[VAL_22]], %[[VAL_47]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_49:.*]] = cmpi eq, %[[VAL_23]], %[[VAL_22]] : index
// CHECK: %[[VAL_50:.*]] = addi %[[VAL_21]], %[[VAL_7]] : index
// CHECK: %[[VAL_51:.*]] = select %[[VAL_49]], %[[VAL_50]], %[[VAL_21]] : index
// CHECK: %[[VAL_52:.*]] = addi %[[VAL_22]], %[[VAL_7]] : index
// CHECK: scf.yield %[[VAL_51]], %[[VAL_52]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_53:.*]] = %[[VAL_54:.*]]#1 to %[[VAL_3]] step %[[VAL_7]] {
// CHECK: scf.for %[[VAL_55:.*]] = %[[VAL_6]] to %[[VAL_4]] step %[[VAL_7]] {
// CHECK: %[[VAL_56:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_53]], %[[VAL_55]]] : memref<32x16xf32>
// CHECK: store %[[VAL_56]], %[[VAL_14]]{{\[}}%[[VAL_53]], %[[VAL_55]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_57:.*]] = tensor_load %[[VAL_14]] : memref<32x16xf32>
// CHECK: return %[[VAL_57]] : tensor<32x16xf32>
// CHECK: }
func @add_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga : tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 999 : index
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_10:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_11:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_12:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_13:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_14:.*]] = %[[VAL_12]] to %[[VAL_13]] step %[[VAL_4]] {
// CHECK: %[[VAL_15:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_14]]] : memref<?xindex>
// CHECK: %[[VAL_16:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref<?xindex>
// CHECK: %[[VAL_17:.*]] = addi %[[VAL_14]], %[[VAL_4]] : index
// CHECK: %[[VAL_18:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_17]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_19:.*]] = %[[VAL_16]] to %[[VAL_18]] step %[[VAL_4]] {
// CHECK: %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_19]]] : memref<?xindex>
// CHECK: %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_19]]] : memref<?xf32>
// CHECK: %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_15]], %[[VAL_20]]] : memref<32x16xf32>
// CHECK: %[[VAL_23:.*]] = mulf %[[VAL_21]], %[[VAL_22]] : f32
// CHECK: store %[[VAL_23]], %[[VAL_11]]{{\[}}%[[VAL_15]], %[[VAL_20]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_24:.*]] = tensor_load %[[VAL_11]] : memref<32x16xf32>
// CHECK: return %[[VAL_24]] : tensor<32x16xf32>
// CHECK: }
func @mul_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga : tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 999 : index
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_15:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_16:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_20:.*]]:2 = scf.while (%[[VAL_21:.*]] = %[[VAL_16]], %[[VAL_22:.*]] = %[[VAL_18]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_23:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_17]] : index
// CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_19]] : index
// CHECK: %[[VAL_25:.*]] = and %[[VAL_23]], %[[VAL_24]] : i1
// CHECK: scf.condition(%[[VAL_25]]) %[[VAL_21]], %[[VAL_22]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index):
// CHECK: %[[VAL_28:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_26]]] : memref<?xindex>
// CHECK: %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_30:.*]] = cmpi ult, %[[VAL_29]], %[[VAL_28]] : index
// CHECK: %[[VAL_31:.*]] = select %[[VAL_30]], %[[VAL_29]], %[[VAL_28]] : index
// CHECK: %[[VAL_32:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
// CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
// CHECK: %[[VAL_34:.*]] = and %[[VAL_32]], %[[VAL_33]] : i1
// CHECK: scf.if %[[VAL_34]] {
// CHECK: %[[VAL_35:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
// CHECK: %[[VAL_36:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
// CHECK: %[[VAL_37:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_36]]] : memref<?xindex>
// CHECK: %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_39:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_40:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_39]]] : memref<?xindex>
// CHECK: %[[VAL_41:.*]]:2 = scf.while (%[[VAL_42:.*]] = %[[VAL_35]], %[[VAL_43:.*]] = %[[VAL_38]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_44:.*]] = cmpi ult, %[[VAL_42]], %[[VAL_37]] : index
// CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_40]] : index
// CHECK: %[[VAL_46:.*]] = and %[[VAL_44]], %[[VAL_45]] : i1
// CHECK: scf.condition(%[[VAL_46]]) %[[VAL_42]], %[[VAL_43]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_47:.*]]: index, %[[VAL_48:.*]]: index):
// CHECK: %[[VAL_49:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_47]]] : memref<?xindex>
// CHECK: %[[VAL_50:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_48]]] : memref<?xindex>
// CHECK: %[[VAL_51:.*]] = cmpi ult, %[[VAL_50]], %[[VAL_49]] : index
// CHECK: %[[VAL_52:.*]] = select %[[VAL_51]], %[[VAL_50]], %[[VAL_49]] : index
// CHECK: %[[VAL_53:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
// CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
// CHECK: %[[VAL_55:.*]] = and %[[VAL_53]], %[[VAL_54]] : i1
// CHECK: scf.if %[[VAL_55]] {
// CHECK: %[[VAL_56:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
// CHECK: %[[VAL_57:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: %[[VAL_58:.*]] = addf %[[VAL_56]], %[[VAL_57]] : f32
// CHECK: store %[[VAL_58]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: %[[VAL_59:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
// CHECK: scf.if %[[VAL_59]] {
// CHECK: %[[VAL_60:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
// CHECK: store %[[VAL_60]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: %[[VAL_61:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
// CHECK: scf.if %[[VAL_61]] {
// CHECK: %[[VAL_62:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: store %[[VAL_62]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_63:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
// CHECK: %[[VAL_64:.*]] = addi %[[VAL_47]], %[[VAL_4]] : index
// CHECK: %[[VAL_65:.*]] = select %[[VAL_63]], %[[VAL_64]], %[[VAL_47]] : index
// CHECK: %[[VAL_66:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
// CHECK: %[[VAL_67:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
// CHECK: %[[VAL_68:.*]] = select %[[VAL_66]], %[[VAL_67]], %[[VAL_48]] : index
// CHECK: scf.yield %[[VAL_65]], %[[VAL_68]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_69:.*]] = %[[VAL_70:.*]]#0 to %[[VAL_37]] step %[[VAL_4]] {
// CHECK: %[[VAL_71:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_69]]] : memref<?xindex>
// CHECK: %[[VAL_72:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_69]]] : memref<?xf32>
// CHECK: store %[[VAL_72]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_71]]] : memref<32x16xf32>
// CHECK: }
// CHECK: scf.for %[[VAL_73:.*]] = %[[VAL_74:.*]]#1 to %[[VAL_40]] step %[[VAL_4]] {
// CHECK: %[[VAL_75:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_73]]] : memref<?xindex>
// CHECK: %[[VAL_76:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_73]]] : memref<?xf32>
// CHECK: store %[[VAL_76]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_75]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: %[[VAL_77:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
// CHECK: scf.if %[[VAL_77]] {
// CHECK: %[[VAL_78:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
// CHECK: %[[VAL_79:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
// CHECK: %[[VAL_80:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_79]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_81:.*]] = %[[VAL_78]] to %[[VAL_80]] step %[[VAL_4]] {
// CHECK: %[[VAL_82:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_81]]] : memref<?xindex>
// CHECK: %[[VAL_83:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_81]]] : memref<?xf32>
// CHECK: store %[[VAL_83]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_82]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: %[[VAL_84:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
// CHECK: scf.if %[[VAL_84]] {
// CHECK: %[[VAL_85:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_86:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_87:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_86]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_88:.*]] = %[[VAL_85]] to %[[VAL_87]] step %[[VAL_4]] {
// CHECK: %[[VAL_89:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_88]]] : memref<?xindex>
// CHECK: %[[VAL_90:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_88]]] : memref<?xf32>
// CHECK: store %[[VAL_90]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_89]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_91:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
// CHECK: %[[VAL_92:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
// CHECK: %[[VAL_93:.*]] = select %[[VAL_91]], %[[VAL_92]], %[[VAL_26]] : index
// CHECK: %[[VAL_94:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
// CHECK: %[[VAL_95:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_96:.*]] = select %[[VAL_94]], %[[VAL_95]], %[[VAL_27]] : index
// CHECK: scf.yield %[[VAL_93]], %[[VAL_96]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_97:.*]] = %[[VAL_98:.*]]#0 to %[[VAL_17]] step %[[VAL_4]] {
// CHECK: %[[VAL_99:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_97]]] : memref<?xindex>
// CHECK: %[[VAL_100:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_97]]] : memref<?xindex>
// CHECK: %[[VAL_101:.*]] = addi %[[VAL_97]], %[[VAL_4]] : index
// CHECK: %[[VAL_102:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_101]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_103:.*]] = %[[VAL_100]] to %[[VAL_102]] step %[[VAL_4]] {
// CHECK: %[[VAL_104:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_103]]] : memref<?xindex>
// CHECK: %[[VAL_105:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_103]]] : memref<?xf32>
// CHECK: store %[[VAL_105]], %[[VAL_15]]{{\[}}%[[VAL_99]], %[[VAL_104]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: scf.for %[[VAL_106:.*]] = %[[VAL_107:.*]]#1 to %[[VAL_19]] step %[[VAL_4]] {
// CHECK: %[[VAL_108:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_106]]] : memref<?xindex>
// CHECK: %[[VAL_109:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_106]]] : memref<?xindex>
// CHECK: %[[VAL_110:.*]] = addi %[[VAL_106]], %[[VAL_4]] : index
// CHECK: %[[VAL_111:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_110]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_112:.*]] = %[[VAL_109]] to %[[VAL_111]] step %[[VAL_4]] {
// CHECK: %[[VAL_113:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_112]]] : memref<?xindex>
// CHECK: %[[VAL_114:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_112]]] : memref<?xf32>
// CHECK: store %[[VAL_114]], %[[VAL_15]]{{\[}}%[[VAL_108]], %[[VAL_113]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_115:.*]] = tensor_load %[[VAL_15]] : memref<32x16xf32>
// CHECK: return %[[VAL_115]] : tensor<32x16xf32>
// CHECK: }
func @add_ss_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga : tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 999 : index
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_15:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_16:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_20:.*]]:2 = scf.while (%[[VAL_21:.*]] = %[[VAL_16]], %[[VAL_22:.*]] = %[[VAL_18]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_23:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_17]] : index
// CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_19]] : index
// CHECK: %[[VAL_25:.*]] = and %[[VAL_23]], %[[VAL_24]] : i1
// CHECK: scf.condition(%[[VAL_25]]) %[[VAL_21]], %[[VAL_22]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index):
// CHECK: %[[VAL_28:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_26]]] : memref<?xindex>
// CHECK: %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_30:.*]] = cmpi ult, %[[VAL_29]], %[[VAL_28]] : index
// CHECK: %[[VAL_31:.*]] = select %[[VAL_30]], %[[VAL_29]], %[[VAL_28]] : index
// CHECK: %[[VAL_32:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
// CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
// CHECK: %[[VAL_34:.*]] = and %[[VAL_32]], %[[VAL_33]] : i1
// CHECK: scf.if %[[VAL_34]] {
// CHECK: %[[VAL_35:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
// CHECK: %[[VAL_36:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
// CHECK: %[[VAL_37:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_36]]] : memref<?xindex>
// CHECK: %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_39:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_40:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_39]]] : memref<?xindex>
// CHECK: %[[VAL_41:.*]]:2 = scf.while (%[[VAL_42:.*]] = %[[VAL_35]], %[[VAL_43:.*]] = %[[VAL_38]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_44:.*]] = cmpi ult, %[[VAL_42]], %[[VAL_37]] : index
// CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_40]] : index
// CHECK: %[[VAL_46:.*]] = and %[[VAL_44]], %[[VAL_45]] : i1
// CHECK: scf.condition(%[[VAL_46]]) %[[VAL_42]], %[[VAL_43]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_47:.*]]: index, %[[VAL_48:.*]]: index):
// CHECK: %[[VAL_49:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_47]]] : memref<?xindex>
// CHECK: %[[VAL_50:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_48]]] : memref<?xindex>
// CHECK: %[[VAL_51:.*]] = cmpi ult, %[[VAL_50]], %[[VAL_49]] : index
// CHECK: %[[VAL_52:.*]] = select %[[VAL_51]], %[[VAL_50]], %[[VAL_49]] : index
// CHECK: %[[VAL_53:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
// CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
// CHECK: %[[VAL_55:.*]] = and %[[VAL_53]], %[[VAL_54]] : i1
// CHECK: scf.if %[[VAL_55]] {
// CHECK: %[[VAL_56:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
// CHECK: %[[VAL_57:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: %[[VAL_58:.*]] = mulf %[[VAL_56]], %[[VAL_57]] : f32
// CHECK: store %[[VAL_58]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: %[[VAL_59:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
// CHECK: %[[VAL_60:.*]] = addi %[[VAL_47]], %[[VAL_4]] : index
// CHECK: %[[VAL_61:.*]] = select %[[VAL_59]], %[[VAL_60]], %[[VAL_47]] : index
// CHECK: %[[VAL_62:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
// CHECK: %[[VAL_63:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
// CHECK: %[[VAL_64:.*]] = select %[[VAL_62]], %[[VAL_63]], %[[VAL_48]] : index
// CHECK: scf.yield %[[VAL_61]], %[[VAL_64]] : index, index
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: %[[VAL_65:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
// CHECK: %[[VAL_66:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
// CHECK: %[[VAL_67:.*]] = select %[[VAL_65]], %[[VAL_66]], %[[VAL_26]] : index
// CHECK: %[[VAL_68:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
// CHECK: %[[VAL_69:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_70:.*]] = select %[[VAL_68]], %[[VAL_69]], %[[VAL_27]] : index
// CHECK: scf.yield %[[VAL_67]], %[[VAL_70]] : index, index
// CHECK: }
// CHECK: %[[VAL_71:.*]] = tensor_load %[[VAL_15]] : memref<32x16xf32>
// CHECK: return %[[VAL_71]] : tensor<32x16xf32>
// CHECK: }
func @mul_ss_ss(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga : tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 999 : index
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_15:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_16:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_20:.*]]:2 = scf.while (%[[VAL_21:.*]] = %[[VAL_16]], %[[VAL_22:.*]] = %[[VAL_18]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_23:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_17]] : index
// CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_19]] : index
// CHECK: %[[VAL_25:.*]] = and %[[VAL_23]], %[[VAL_24]] : i1
// CHECK: scf.condition(%[[VAL_25]]) %[[VAL_21]], %[[VAL_22]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index):
// CHECK: %[[VAL_28:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_26]]] : memref<?xindex>
// CHECK: %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_30:.*]] = cmpi ult, %[[VAL_29]], %[[VAL_28]] : index
// CHECK: %[[VAL_31:.*]] = select %[[VAL_30]], %[[VAL_29]], %[[VAL_28]] : index
// CHECK: %[[VAL_32:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
// CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
// CHECK: %[[VAL_34:.*]] = and %[[VAL_32]], %[[VAL_33]] : i1
// CHECK: scf.if %[[VAL_34]] {
// CHECK: %[[VAL_35:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
// CHECK: %[[VAL_36:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
// CHECK: %[[VAL_37:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_36]]] : memref<?xindex>
// CHECK: %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_39:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_40:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_39]]] : memref<?xindex>
// CHECK: %[[VAL_41:.*]]:2 = scf.while (%[[VAL_42:.*]] = %[[VAL_35]], %[[VAL_43:.*]] = %[[VAL_38]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_44:.*]] = cmpi ult, %[[VAL_42]], %[[VAL_37]] : index
// CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_40]] : index
// CHECK: %[[VAL_46:.*]] = and %[[VAL_44]], %[[VAL_45]] : i1
// CHECK: scf.condition(%[[VAL_46]]) %[[VAL_42]], %[[VAL_43]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_47:.*]]: index, %[[VAL_48:.*]]: index):
// CHECK: %[[VAL_49:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_47]]] : memref<?xindex>
// CHECK: %[[VAL_50:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_48]]] : memref<?xindex>
// CHECK: %[[VAL_51:.*]] = cmpi ult, %[[VAL_50]], %[[VAL_49]] : index
// CHECK: %[[VAL_52:.*]] = select %[[VAL_51]], %[[VAL_50]], %[[VAL_49]] : index
// CHECK: %[[VAL_53:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
// CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
// CHECK: %[[VAL_55:.*]] = and %[[VAL_53]], %[[VAL_54]] : i1
// CHECK: scf.if %[[VAL_55]] {
// CHECK: %[[VAL_56:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
// CHECK: %[[VAL_57:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: %[[VAL_58:.*]] = addf %[[VAL_56]], %[[VAL_57]] : f32
// CHECK: store %[[VAL_58]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: %[[VAL_59:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
// CHECK: scf.if %[[VAL_59]] {
// CHECK: %[[VAL_60:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
// CHECK: store %[[VAL_60]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: %[[VAL_61:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
// CHECK: scf.if %[[VAL_61]] {
// CHECK: %[[VAL_62:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: store %[[VAL_62]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_63:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
// CHECK: %[[VAL_64:.*]] = addi %[[VAL_47]], %[[VAL_4]] : index
// CHECK: %[[VAL_65:.*]] = select %[[VAL_63]], %[[VAL_64]], %[[VAL_47]] : index
// CHECK: %[[VAL_66:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
// CHECK: %[[VAL_67:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
// CHECK: %[[VAL_68:.*]] = select %[[VAL_66]], %[[VAL_67]], %[[VAL_48]] : index
// CHECK: scf.yield %[[VAL_65]], %[[VAL_68]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_69:.*]] = %[[VAL_70:.*]]#0 to %[[VAL_37]] step %[[VAL_4]] {
// CHECK: %[[VAL_71:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_69]]] : memref<?xindex>
// CHECK: %[[VAL_72:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_69]]] : memref<?xf32>
// CHECK: store %[[VAL_72]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_71]]] : memref<32x16xf32>
// CHECK: }
// CHECK: scf.for %[[VAL_73:.*]] = %[[VAL_74:.*]]#1 to %[[VAL_40]] step %[[VAL_4]] {
// CHECK: %[[VAL_75:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_73]]] : memref<?xindex>
// CHECK: %[[VAL_76:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_73]]] : memref<?xf32>
// CHECK: store %[[VAL_76]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_75]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: %[[VAL_77:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
// CHECK: scf.if %[[VAL_77]] {
// CHECK: %[[VAL_78:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
// CHECK: %[[VAL_79:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
// CHECK: %[[VAL_80:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_79]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_81:.*]] = %[[VAL_78]] to %[[VAL_80]] step %[[VAL_4]] {
// CHECK: %[[VAL_82:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_81]]] : memref<?xindex>
// CHECK: %[[VAL_83:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_81]]] : memref<?xf32>
// CHECK: store %[[VAL_83]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_82]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: %[[VAL_84:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
// CHECK: scf.if %[[VAL_84]] {
// CHECK: %[[VAL_85:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_86:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_87:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_86]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_88:.*]] = %[[VAL_85]] to %[[VAL_87]] step %[[VAL_4]] {
// CHECK: %[[VAL_89:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_88]]] : memref<?xindex>
// CHECK: %[[VAL_90:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_88]]] : memref<?xf32>
// CHECK: store %[[VAL_90]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_89]]] : memref<32x16xf32>
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_91:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
// CHECK: %[[VAL_92:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
// CHECK: %[[VAL_93:.*]] = select %[[VAL_91]], %[[VAL_92]], %[[VAL_26]] : index
// CHECK: %[[VAL_94:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
// CHECK: %[[VAL_95:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_96:.*]] = select %[[VAL_94]], %[[VAL_95]], %[[VAL_27]] : index
// CHECK: scf.yield %[[VAL_93]], %[[VAL_96]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_97:.*]] = %[[VAL_98:.*]]#0 to %[[VAL_17]] step %[[VAL_4]] {
// CHECK: %[[VAL_99:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_97]]] : memref<?xindex>
// CHECK: %[[VAL_100:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_97]]] : memref<?xindex>
// CHECK: %[[VAL_101:.*]] = addi %[[VAL_97]], %[[VAL_4]] : index
// CHECK: %[[VAL_102:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_101]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_103:.*]] = %[[VAL_100]] to %[[VAL_102]] step %[[VAL_4]] {
// CHECK: %[[VAL_104:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_103]]] : memref<?xindex>
// CHECK: %[[VAL_105:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_103]]] : memref<?xf32>
// CHECK: store %[[VAL_105]], %[[VAL_15]]{{\[}}%[[VAL_99]], %[[VAL_104]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: scf.for %[[VAL_106:.*]] = %[[VAL_107:.*]]#1 to %[[VAL_19]] step %[[VAL_4]] {
// CHECK: %[[VAL_108:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_106]]] : memref<?xindex>
// CHECK: %[[VAL_109:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_106]]] : memref<?xindex>
// CHECK: %[[VAL_110:.*]] = addi %[[VAL_106]], %[[VAL_4]] : index
// CHECK: %[[VAL_111:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_110]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_112:.*]] = %[[VAL_109]] to %[[VAL_111]] step %[[VAL_4]] {
// CHECK: %[[VAL_113:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_112]]] : memref<?xindex>
// CHECK: %[[VAL_114:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_112]]] : memref<?xf32>
// CHECK: store %[[VAL_114]], %[[VAL_15]]{{\[}}%[[VAL_108]], %[[VAL_113]]] : memref<32x16xf32>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_115:.*]] = tensor_load %[[VAL_15]] : memref<32x16xf32>
// CHECK: return %[[VAL_115]] : tensor<32x16xf32>
// CHECK: }
func @add_sd_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga : tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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:.*]]: tensor<32x16xf32>,
// CHECK-SAME: %[[VAL_1:.*]]: tensor<32x16xf32>) -> tensor<32x16xf32> {
// CHECK: %[[VAL_2:.*]] = constant 999 : index
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_15:.*]] = alloca() : memref<32x16xf32>
// CHECK: %[[VAL_16:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_17:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_18:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_3]]] : memref<?xindex>
// CHECK: %[[VAL_19:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_4]]] : memref<?xindex>
// CHECK: %[[VAL_20:.*]]:2 = scf.while (%[[VAL_21:.*]] = %[[VAL_16]], %[[VAL_22:.*]] = %[[VAL_18]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_23:.*]] = cmpi ult, %[[VAL_21]], %[[VAL_17]] : index
// CHECK: %[[VAL_24:.*]] = cmpi ult, %[[VAL_22]], %[[VAL_19]] : index
// CHECK: %[[VAL_25:.*]] = and %[[VAL_23]], %[[VAL_24]] : i1
// CHECK: scf.condition(%[[VAL_25]]) %[[VAL_21]], %[[VAL_22]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_26:.*]]: index, %[[VAL_27:.*]]: index):
// CHECK: %[[VAL_28:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_26]]] : memref<?xindex>
// CHECK: %[[VAL_29:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_30:.*]] = cmpi ult, %[[VAL_29]], %[[VAL_28]] : index
// CHECK: %[[VAL_31:.*]] = select %[[VAL_30]], %[[VAL_29]], %[[VAL_28]] : index
// CHECK: %[[VAL_32:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
// CHECK: %[[VAL_33:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
// CHECK: %[[VAL_34:.*]] = and %[[VAL_32]], %[[VAL_33]] : i1
// CHECK: scf.if %[[VAL_34]] {
// CHECK: %[[VAL_35:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_26]]] : memref<?xindex>
// CHECK: %[[VAL_36:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
// CHECK: %[[VAL_37:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_36]]] : memref<?xindex>
// CHECK: %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_27]]] : memref<?xindex>
// CHECK: %[[VAL_39:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_40:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_39]]] : memref<?xindex>
// CHECK: %[[VAL_41:.*]]:2 = scf.while (%[[VAL_42:.*]] = %[[VAL_35]], %[[VAL_43:.*]] = %[[VAL_38]]) : (index, index) -> (index, index) {
// CHECK: %[[VAL_44:.*]] = cmpi ult, %[[VAL_42]], %[[VAL_37]] : index
// CHECK: %[[VAL_45:.*]] = cmpi ult, %[[VAL_43]], %[[VAL_40]] : index
// CHECK: %[[VAL_46:.*]] = and %[[VAL_44]], %[[VAL_45]] : i1
// CHECK: scf.condition(%[[VAL_46]]) %[[VAL_42]], %[[VAL_43]] : index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_47:.*]]: index, %[[VAL_48:.*]]: index):
// CHECK: %[[VAL_49:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_47]]] : memref<?xindex>
// CHECK: %[[VAL_50:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_48]]] : memref<?xindex>
// CHECK: %[[VAL_51:.*]] = cmpi ult, %[[VAL_50]], %[[VAL_49]] : index
// CHECK: %[[VAL_52:.*]] = select %[[VAL_51]], %[[VAL_50]], %[[VAL_49]] : index
// CHECK: %[[VAL_53:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
// CHECK: %[[VAL_54:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
// CHECK: %[[VAL_55:.*]] = and %[[VAL_53]], %[[VAL_54]] : i1
// CHECK: scf.if %[[VAL_55]] {
// CHECK: %[[VAL_56:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_47]]] : memref<?xf32>
// CHECK: %[[VAL_57:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_48]]] : memref<?xf32>
// CHECK: %[[VAL_58:.*]] = mulf %[[VAL_56]], %[[VAL_57]] : f32
// CHECK: store %[[VAL_58]], %[[VAL_15]]{{\[}}%[[VAL_31]], %[[VAL_52]]] : memref<32x16xf32>
// CHECK: } else {
// CHECK: }
// CHECK: %[[VAL_59:.*]] = cmpi eq, %[[VAL_49]], %[[VAL_52]] : index
// CHECK: %[[VAL_60:.*]] = addi %[[VAL_47]], %[[VAL_4]] : index
// CHECK: %[[VAL_61:.*]] = select %[[VAL_59]], %[[VAL_60]], %[[VAL_47]] : index
// CHECK: %[[VAL_62:.*]] = cmpi eq, %[[VAL_50]], %[[VAL_52]] : index
// CHECK: %[[VAL_63:.*]] = addi %[[VAL_48]], %[[VAL_4]] : index
// CHECK: %[[VAL_64:.*]] = select %[[VAL_62]], %[[VAL_63]], %[[VAL_48]] : index
// CHECK: scf.yield %[[VAL_61]], %[[VAL_64]] : index, index
// CHECK: }
// CHECK: } else {
// CHECK: }
// CHECK: %[[VAL_65:.*]] = cmpi eq, %[[VAL_28]], %[[VAL_31]] : index
// CHECK: %[[VAL_66:.*]] = addi %[[VAL_26]], %[[VAL_4]] : index
// CHECK: %[[VAL_67:.*]] = select %[[VAL_65]], %[[VAL_66]], %[[VAL_26]] : index
// CHECK: %[[VAL_68:.*]] = cmpi eq, %[[VAL_29]], %[[VAL_31]] : index
// CHECK: %[[VAL_69:.*]] = addi %[[VAL_27]], %[[VAL_4]] : index
// CHECK: %[[VAL_70:.*]] = select %[[VAL_68]], %[[VAL_69]], %[[VAL_27]] : index
// CHECK: scf.yield %[[VAL_67]], %[[VAL_70]] : index, index
// CHECK: }
// CHECK: %[[VAL_71:.*]] = tensor_load %[[VAL_15]] : memref<32x16xf32>
// CHECK: return %[[VAL_71]] : tensor<32x16xf32>
// CHECK: }
func @mul_sd_ds(%arga: tensor<32x16xf32>, %argb: tensor<32x16xf32>) -> tensor<32x16xf32> {
%0 = linalg.generic #trait_ss_ss
ins(%arga, %argb: tensor<32x16xf32>, tensor<32x16xf32>)
outs(%arga : tensor<32x16xf32>) {
^bb(%a: f32, %b: f32, %s: 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 999 : index
// CHECK: %[[VAL_4:.*]] = constant 16 : index
// CHECK: %[[VAL_5:.*]] = constant 0 : index
// CHECK: %[[VAL_6:.*]] = constant 1 : index
// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_3]]) : memref<?xindex>
// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_3]]) : memref<?xf32>
// CHECK: %[[VAL_10:.*]] = alloca() : memref<32xf32>
// CHECK: %[[VAL_11:.*]] = alloca() : memref<16xf32>
// CHECK: scf.for %[[VAL_12:.*]] = %[[VAL_5]] to %[[VAL_4]] step %[[VAL_6]] {
// CHECK: %[[VAL_13:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_12]]] : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = addi %[[VAL_12]], %[[VAL_6]] : index
// CHECK: %[[VAL_15:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_14]]] : memref<?xindex>
// CHECK: %[[VAL_16:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_12]]] : memref<16xf32>
// CHECK: %[[VAL_17:.*]] = scf.for %[[VAL_18:.*]] = %[[VAL_13]] to %[[VAL_15]] step %[[VAL_6]] iter_args(%[[VAL_19:.*]] = %[[VAL_16]]) -> (f32) {
// CHECK: %[[VAL_20:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_18]]] : memref<?xindex>
// CHECK: %[[VAL_21:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_18]]] : memref<?xf32>
// CHECK: %[[VAL_22:.*]] = load %[[VAL_10]]{{\[}}%[[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:.*]] = 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 999 : index
// CHECK: %[[VAL_3:.*]] = constant 10 : index
// CHECK: %[[VAL_4:.*]] = constant 0 : index
// CHECK: %[[VAL_5:.*]] = constant 1 : index
// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_2]]) : memref<?xf32>
// CHECK: %[[VAL_9:.*]] = alloca() : memref<f32>
// CHECK: scf.for %[[VAL_10:.*]] = %[[VAL_4]] to %[[VAL_3]] step %[[VAL_5]] {
// CHECK: %[[VAL_11:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_10]]] : memref<?xindex>
// CHECK: %[[VAL_12:.*]] = addi %[[VAL_10]], %[[VAL_5]] : index
// CHECK: %[[VAL_13:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_12]]] : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = load %[[VAL_9]][] : memref<f32>
// CHECK: %[[VAL_15:.*]] = scf.for %[[VAL_16:.*]] = %[[VAL_11]] to %[[VAL_13]] step %[[VAL_5]] iter_args(%[[VAL_17:.*]] = %[[VAL_14]]) -> (f32) {
// CHECK: %[[VAL_18:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_16]]] : memref<?xf32>
// CHECK: %[[VAL_19:.*]] = addf %[[VAL_17]], %[[VAL_18]] : f32
// CHECK: scf.yield %[[VAL_19]] : f32
// CHECK: }
// CHECK: store %[[VAL_20:.*]], %[[VAL_9]][] : memref<f32>
// CHECK: }
// CHECK: %[[VAL_21:.*]] = tensor_load %[[VAL_9]] : memref<f32>
// CHECK: return %[[VAL_21]] : 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>) -> tensor<?x?xf64> {
// CHECK: %[[VAL_1:.*]] = constant 2.000000e+00 : f64
// CHECK: %[[VAL_2:.*]] = constant 999 : index
// CHECK: %[[VAL_3:.*]] = constant 0 : index
// CHECK: %[[VAL_4:.*]] = constant 1 : index
// CHECK: %[[VAL_5:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_6:.*]] = alloca(%[[VAL_2]]) : memref<?xindex>
// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_2]]) : memref<?xf64>
// CHECK: %[[VAL_8:.*]] = dim %[[VAL_0]], %[[VAL_3]] : tensor<?x?xf64>
// CHECK: %[[VAL_9:.*]] = dim %[[VAL_0]], %[[VAL_4]] : tensor<?x?xf64>
// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_8]], %[[VAL_9]]) : memref<?x?xf64>
// CHECK: scf.for %[[VAL_11:.*]] = %[[VAL_3]] to %[[VAL_8]] step %[[VAL_4]] {
// CHECK: %[[VAL_12:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_11]]] : memref<?xindex>
// CHECK: %[[VAL_13:.*]] = addi %[[VAL_11]], %[[VAL_4]] : index
// CHECK: %[[VAL_14:.*]] = load %[[VAL_5]]{{\[}}%[[VAL_13]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_15:.*]] = %[[VAL_12]] to %[[VAL_14]] step %[[VAL_4]] {
// CHECK: %[[VAL_16:.*]] = load %[[VAL_6]]{{\[}}%[[VAL_15]]] : memref<?xindex>
// CHECK: %[[VAL_17:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_15]]] : memref<?xf64>
// CHECK: %[[VAL_18:.*]] = mulf %[[VAL_17]], %[[VAL_1]] : f64
// CHECK: store %[[VAL_18]], %[[VAL_10]]{{\[}}%[[VAL_11]], %[[VAL_16]]] : memref<?x?xf64>
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_19:.*]] = tensor_load %[[VAL_10]] : memref<?x?xf64>
// CHECK: return %[[VAL_19]] : tensor<?x?xf64>
// CHECK: }
func @scale(%arga: tensor<?x?xf64>) -> tensor<?x?xf64> {
%0 = constant 2.0 : f64
%1 = linalg.generic #trait_scale
ins(%arga: tensor<?x?xf64>)
outs(%arga: tensor<?x?xf64>) {
^bb(%a: f64, %s: 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 999 : index
// CHECK: %[[VAL_5:.*]] = constant 0 : index
// CHECK: %[[VAL_6:.*]] = constant 1 : index
// CHECK: %[[VAL_7:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
// CHECK: %[[VAL_8:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
// CHECK: %[[VAL_9:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_4]]) : memref<?xindex>
// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_4]]) : memref<?xf32>
// CHECK: %[[VAL_12:.*]] = dim %[[VAL_1]], %[[VAL_5]] : tensor<?x?xf32>
// CHECK: %[[VAL_13:.*]] = dim %[[VAL_1]], %[[VAL_6]] : tensor<?x?xf32>
// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_12]], %[[VAL_13]]) : memref<?x?xf32>
// CHECK: %[[VAL_15:.*]] = dim %[[VAL_2]], %[[VAL_5]] : tensor<?x?xf32>
// CHECK: %[[VAL_16:.*]] = dim %[[VAL_2]], %[[VAL_6]] : tensor<?x?xf32>
// CHECK: %[[VAL_17:.*]] = alloca(%[[VAL_15]], %[[VAL_16]]) : memref<?x?xf32>
// CHECK: %[[VAL_18:.*]] = dim %[[VAL_3]], %[[VAL_5]] : tensor<?x?xf32>
// CHECK: %[[VAL_19:.*]] = dim %[[VAL_3]], %[[VAL_6]] : tensor<?x?xf32>
// CHECK: %[[VAL_20:.*]] = alloca(%[[VAL_18]], %[[VAL_19]]) : memref<?x?xf32>
// CHECK: %[[VAL_21:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_5]]] : memref<?xindex>
// CHECK: %[[VAL_22:.*]] = load %[[VAL_7]]{{\[}}%[[VAL_6]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_23:.*]] = %[[VAL_21]] to %[[VAL_22]] step %[[VAL_6]] {
// CHECK: %[[VAL_24:.*]] = load %[[VAL_8]]{{\[}}%[[VAL_23]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_25:.*]] = %[[VAL_5]] to %[[VAL_15]] step %[[VAL_6]] {
// CHECK: %[[VAL_26:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_24]], %[[VAL_25]]] : memref<?x?xf32>
// CHECK: %[[VAL_27:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_23]]] : memref<?xindex>
// CHECK: %[[VAL_28:.*]] = addi %[[VAL_23]], %[[VAL_6]] : index
// CHECK: %[[VAL_29:.*]] = load %[[VAL_9]]{{\[}}%[[VAL_28]]] : memref<?xindex>
// CHECK: scf.for %[[VAL_30:.*]] = %[[VAL_27]] to %[[VAL_29]] step %[[VAL_6]] {
// CHECK: %[[VAL_31:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_30]]] : memref<?xindex>
// CHECK: %[[VAL_32:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_24]], %[[VAL_31]]] : memref<?x?xf32>
// CHECK: %[[VAL_33:.*]] = load %[[VAL_11]]{{\[}}%[[VAL_30]]] : memref<?xf32>
// CHECK: %[[VAL_34:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_25]], %[[VAL_31]]] : memref<?x?xf32>
// CHECK: %[[VAL_35:.*]] = mulf %[[VAL_26]], %[[VAL_34]] : f32
// CHECK: %[[VAL_36:.*]] = mulf %[[VAL_33]], %[[VAL_35]] : f32
// CHECK: %[[VAL_37:.*]] = addf %[[VAL_32]], %[[VAL_36]] : f32
// CHECK: store %[[VAL_37]], %[[VAL_20]]{{\[}}%[[VAL_24]], %[[VAL_31]]] : memref<?x?xf32>
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_38:.*]] = tensor_load %[[VAL_20]] : memref<?x?xf32>
// CHECK: return %[[VAL_38]] : 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 999 : index
// CHECK: %[[VAL_7:.*]] = constant 0 : index
// CHECK: %[[VAL_8:.*]] = constant true
// CHECK: %[[VAL_9:.*]] = constant 1 : index
// CHECK: %[[VAL_10:.*]] = alloca(%[[VAL_6]]) : memref<?xindex>
// CHECK: %[[VAL_11:.*]] = alloca(%[[VAL_6]]) : memref<?xindex>
// CHECK: %[[VAL_12:.*]] = alloca(%[[VAL_6]]) : memref<?xindex>
// CHECK: %[[VAL_13:.*]] = alloca(%[[VAL_6]]) : memref<?xindex>
// CHECK: %[[VAL_14:.*]] = alloca(%[[VAL_6]]) : memref<?xf32>
// CHECK: %[[VAL_15:.*]] = alloca(%[[VAL_6]]) : memref<?xindex>
// CHECK: %[[VAL_16:.*]] = alloca(%[[VAL_6]]) : memref<?xindex>
// CHECK: %[[VAL_17:.*]] = alloca(%[[VAL_6]]) : memref<?xf32>
// CHECK: %[[VAL_18:.*]] = alloca(%[[VAL_6]]) : memref<?xindex>
// CHECK: %[[VAL_19:.*]] = alloca(%[[VAL_6]]) : memref<?xindex>
// CHECK: %[[VAL_20:.*]] = alloca(%[[VAL_6]]) : memref<?xf32>
// CHECK: %[[VAL_21:.*]] = dim %[[VAL_3]], %[[VAL_7]] : tensor<?xf32>
// CHECK: %[[VAL_22:.*]] = alloca(%[[VAL_21]]) : memref<?xf32>
// CHECK: %[[VAL_23:.*]] = alloca() : memref<f32>
// CHECK: %[[VAL_24:.*]] = dim %[[VAL_5]], %[[VAL_7]] : tensor<?xf32>
// CHECK: %[[VAL_25:.*]] = alloca(%[[VAL_24]]) : memref<?xf32>
// CHECK: %[[VAL_26:.*]] = load %[[VAL_23]][] : memref<f32>
// CHECK: %[[VAL_27:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_7]]] : memref<?xindex>
// CHECK: %[[VAL_28:.*]] = load %[[VAL_10]]{{\[}}%[[VAL_9]]] : memref<?xindex>
// CHECK: %[[VAL_29:.*]]:2 = scf.while (%[[VAL_30:.*]] = %[[VAL_27]], %[[VAL_31:.*]] = %[[VAL_7]]) : (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:.*]] = 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:.*]] = load %[[VAL_22]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: %[[VAL_38:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_33]]] : memref<?xindex>
// CHECK: %[[VAL_39:.*]] = addi %[[VAL_33]], %[[VAL_9]] : index
// CHECK: %[[VAL_40:.*]] = load %[[VAL_12]]{{\[}}%[[VAL_39]]] : memref<?xindex>
// CHECK: %[[VAL_41:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_34]]] : memref<?xindex>
// CHECK: %[[VAL_42:.*]] = addi %[[VAL_34]], %[[VAL_9]] : index
// CHECK: %[[VAL_43:.*]] = load %[[VAL_15]]{{\[}}%[[VAL_42]]] : memref<?xindex>
// CHECK: %[[VAL_44:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_34]]] : memref<?xindex>
// CHECK: %[[VAL_45:.*]] = addi %[[VAL_34]], %[[VAL_9]] : index
// CHECK: %[[VAL_46:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_45]]] : memref<?xindex>
// CHECK: %[[VAL_47:.*]]:4 = scf.while (%[[VAL_48:.*]] = %[[VAL_38]], %[[VAL_49:.*]] = %[[VAL_41]], %[[VAL_50:.*]] = %[[VAL_44]], %[[VAL_51:.*]] = %[[VAL_7]]) : (index, index, index, index) -> (index, index, index, index) {
// CHECK: %[[VAL_52:.*]] = cmpi ult, %[[VAL_48]], %[[VAL_40]] : index
// CHECK: %[[VAL_53:.*]] = cmpi ult, %[[VAL_49]], %[[VAL_43]] : index
// CHECK: %[[VAL_54:.*]] = and %[[VAL_52]], %[[VAL_53]] : i1
// CHECK: %[[VAL_55:.*]] = cmpi ult, %[[VAL_50]], %[[VAL_46]] : index
// CHECK: %[[VAL_56:.*]] = and %[[VAL_54]], %[[VAL_55]] : i1
// CHECK: scf.condition(%[[VAL_56]]) %[[VAL_48]], %[[VAL_49]], %[[VAL_50]], %[[VAL_51]] : index, index, index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_57:.*]]: index, %[[VAL_58:.*]]: index, %[[VAL_59:.*]]: index, %[[VAL_60:.*]]: index):
// CHECK: %[[VAL_61:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_57]]] : memref<?xindex>
// CHECK: %[[VAL_62:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_58]]] : memref<?xindex>
// CHECK: %[[VAL_63:.*]] = load %[[VAL_19]]{{\[}}%[[VAL_59]]] : memref<?xindex>
// CHECK: %[[VAL_64:.*]] = cmpi eq, %[[VAL_61]], %[[VAL_60]] : index
// CHECK: %[[VAL_65:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_60]] : index
// CHECK: %[[VAL_66:.*]] = and %[[VAL_64]], %[[VAL_65]] : i1
// CHECK: %[[VAL_67:.*]] = cmpi eq, %[[VAL_63]], %[[VAL_60]] : index
// CHECK: %[[VAL_68:.*]] = and %[[VAL_66]], %[[VAL_67]] : i1
// CHECK: scf.if %[[VAL_68]] {
// CHECK: %[[VAL_69:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: %[[VAL_70:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_57]]] : memref<?xf32>
// CHECK: %[[VAL_71:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_58]]] : memref<?xf32>
// CHECK: %[[VAL_72:.*]] = mulf %[[VAL_70]], %[[VAL_71]] : f32
// CHECK: %[[VAL_73:.*]] = mulf %[[VAL_72]], %[[VAL_37]] : f32
// CHECK: %[[VAL_74:.*]] = mulf %[[VAL_73]], %[[VAL_26]] : f32
// CHECK: %[[VAL_75:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_59]]] : memref<?xf32>
// CHECK: %[[VAL_76:.*]] = addf %[[VAL_74]], %[[VAL_75]] : f32
// CHECK: %[[VAL_77:.*]] = addf %[[VAL_69]], %[[VAL_76]] : f32
// CHECK: store %[[VAL_77]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: } else {
// CHECK: %[[VAL_78:.*]] = cmpi eq, %[[VAL_61]], %[[VAL_60]] : index
// CHECK: %[[VAL_79:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_60]] : index
// CHECK: %[[VAL_80:.*]] = and %[[VAL_78]], %[[VAL_79]] : i1
// CHECK: scf.if %[[VAL_80]] {
// CHECK: %[[VAL_81:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: %[[VAL_82:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_57]]] : memref<?xf32>
// CHECK: %[[VAL_83:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_58]]] : memref<?xf32>
// CHECK: %[[VAL_84:.*]] = mulf %[[VAL_82]], %[[VAL_83]] : f32
// CHECK: %[[VAL_85:.*]] = mulf %[[VAL_84]], %[[VAL_37]] : f32
// CHECK: %[[VAL_86:.*]] = mulf %[[VAL_85]], %[[VAL_26]] : f32
// CHECK: %[[VAL_87:.*]] = addf %[[VAL_81]], %[[VAL_86]] : f32
// CHECK: store %[[VAL_87]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: } else {
// CHECK: %[[VAL_88:.*]] = cmpi eq, %[[VAL_63]], %[[VAL_60]] : index
// CHECK: scf.if %[[VAL_88]] {
// CHECK: %[[VAL_89:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: %[[VAL_90:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_59]]] : memref<?xf32>
// CHECK: %[[VAL_91:.*]] = addf %[[VAL_89]], %[[VAL_90]] : f32
// CHECK: store %[[VAL_91]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_92:.*]] = cmpi eq, %[[VAL_61]], %[[VAL_60]] : index
// CHECK: %[[VAL_93:.*]] = addi %[[VAL_57]], %[[VAL_9]] : index
// CHECK: %[[VAL_94:.*]] = select %[[VAL_92]], %[[VAL_93]], %[[VAL_57]] : index
// CHECK: %[[VAL_95:.*]] = cmpi eq, %[[VAL_62]], %[[VAL_60]] : index
// CHECK: %[[VAL_96:.*]] = addi %[[VAL_58]], %[[VAL_9]] : index
// CHECK: %[[VAL_97:.*]] = select %[[VAL_95]], %[[VAL_96]], %[[VAL_58]] : index
// CHECK: %[[VAL_98:.*]] = cmpi eq, %[[VAL_63]], %[[VAL_60]] : index
// CHECK: %[[VAL_99:.*]] = addi %[[VAL_59]], %[[VAL_9]] : index
// CHECK: %[[VAL_100:.*]] = select %[[VAL_98]], %[[VAL_99]], %[[VAL_59]] : index
// CHECK: %[[VAL_101:.*]] = addi %[[VAL_60]], %[[VAL_9]] : index
// CHECK: scf.yield %[[VAL_94]], %[[VAL_97]], %[[VAL_100]], %[[VAL_101]] : index, index, index, index
// CHECK: }
// CHECK: %[[VAL_102:.*]]:3 = scf.while (%[[VAL_103:.*]] = %[[VAL_104:.*]]#0, %[[VAL_105:.*]] = %[[VAL_104]]#1, %[[VAL_106:.*]] = %[[VAL_104]]#3) : (index, index, index) -> (index, index, index) {
// CHECK: %[[VAL_107:.*]] = cmpi ult, %[[VAL_103]], %[[VAL_40]] : index
// CHECK: %[[VAL_108:.*]] = cmpi ult, %[[VAL_105]], %[[VAL_43]] : index
// CHECK: %[[VAL_109:.*]] = and %[[VAL_107]], %[[VAL_108]] : i1
// CHECK: scf.condition(%[[VAL_109]]) %[[VAL_103]], %[[VAL_105]], %[[VAL_106]] : index, index, index
// CHECK: } do {
// CHECK: ^bb0(%[[VAL_110:.*]]: index, %[[VAL_111:.*]]: index, %[[VAL_112:.*]]: index):
// CHECK: %[[VAL_113:.*]] = load %[[VAL_13]]{{\[}}%[[VAL_110]]] : memref<?xindex>
// CHECK: %[[VAL_114:.*]] = load %[[VAL_16]]{{\[}}%[[VAL_111]]] : memref<?xindex>
// CHECK: %[[VAL_115:.*]] = cmpi eq, %[[VAL_113]], %[[VAL_112]] : index
// CHECK: %[[VAL_116:.*]] = cmpi eq, %[[VAL_114]], %[[VAL_112]] : index
// CHECK: %[[VAL_117:.*]] = and %[[VAL_115]], %[[VAL_116]] : i1
// CHECK: scf.if %[[VAL_117]] {
// CHECK: %[[VAL_118:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: %[[VAL_119:.*]] = load %[[VAL_14]]{{\[}}%[[VAL_110]]] : memref<?xf32>
// CHECK: %[[VAL_120:.*]] = load %[[VAL_17]]{{\[}}%[[VAL_111]]] : memref<?xf32>
// CHECK: %[[VAL_121:.*]] = mulf %[[VAL_119]], %[[VAL_120]] : f32
// CHECK: %[[VAL_122:.*]] = mulf %[[VAL_121]], %[[VAL_37]] : f32
// CHECK: %[[VAL_123:.*]] = mulf %[[VAL_122]], %[[VAL_26]] : f32
// CHECK: %[[VAL_124:.*]] = addf %[[VAL_118]], %[[VAL_123]] : f32
// CHECK: store %[[VAL_124]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: } else {
// CHECK: }
// CHECK: %[[VAL_125:.*]] = cmpi eq, %[[VAL_113]], %[[VAL_112]] : index
// CHECK: %[[VAL_126:.*]] = addi %[[VAL_110]], %[[VAL_9]] : index
// CHECK: %[[VAL_127:.*]] = select %[[VAL_125]], %[[VAL_126]], %[[VAL_110]] : index
// CHECK: %[[VAL_128:.*]] = cmpi eq, %[[VAL_114]], %[[VAL_112]] : index
// CHECK: %[[VAL_129:.*]] = addi %[[VAL_111]], %[[VAL_9]] : index
// CHECK: %[[VAL_130:.*]] = select %[[VAL_128]], %[[VAL_129]], %[[VAL_111]] : index
// CHECK: %[[VAL_131:.*]] = addi %[[VAL_112]], %[[VAL_9]] : index
// CHECK: scf.yield %[[VAL_127]], %[[VAL_130]], %[[VAL_131]] : index, index, index
// CHECK: }
// CHECK: %[[VAL_132:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: %[[VAL_133:.*]] = scf.for %[[VAL_134:.*]] = %[[VAL_135:.*]]#2 to %[[VAL_46]] step %[[VAL_9]] iter_args(%[[VAL_136:.*]] = %[[VAL_132]]) -> (f32) {
// CHECK: %[[VAL_137:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_134]]] : memref<?xf32>
// CHECK: %[[VAL_138:.*]] = addf %[[VAL_136]], %[[VAL_137]] : f32
// CHECK: scf.yield %[[VAL_138]] : f32
// CHECK: }
// CHECK: store %[[VAL_139:.*]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: } else {
// CHECK: scf.if %[[VAL_8]] {
// CHECK: %[[VAL_140:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_34]]] : memref<?xindex>
// CHECK: %[[VAL_141:.*]] = addi %[[VAL_34]], %[[VAL_9]] : index
// CHECK: %[[VAL_142:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_141]]] : memref<?xindex>
// CHECK: %[[VAL_143:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: %[[VAL_144:.*]] = scf.for %[[VAL_145:.*]] = %[[VAL_140]] to %[[VAL_142]] step %[[VAL_9]] iter_args(%[[VAL_146:.*]] = %[[VAL_143]]) -> (f32) {
// CHECK: %[[VAL_147:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_145]]] : memref<?xf32>
// CHECK: %[[VAL_148:.*]] = addf %[[VAL_146]], %[[VAL_147]] : f32
// CHECK: scf.yield %[[VAL_148]] : f32
// CHECK: }
// CHECK: store %[[VAL_149:.*]], %[[VAL_25]]{{\[}}%[[VAL_34]]] : memref<?xf32>
// CHECK: } else {
// CHECK: }
// CHECK: }
// CHECK: %[[VAL_150:.*]] = cmpi eq, %[[VAL_35]], %[[VAL_34]] : index
// CHECK: %[[VAL_151:.*]] = addi %[[VAL_33]], %[[VAL_9]] : index
// CHECK: %[[VAL_152:.*]] = select %[[VAL_150]], %[[VAL_151]], %[[VAL_33]] : index
// CHECK: %[[VAL_153:.*]] = addi %[[VAL_34]], %[[VAL_9]] : index
// CHECK: scf.yield %[[VAL_152]], %[[VAL_153]] : index, index
// CHECK: }
// CHECK: scf.for %[[VAL_154:.*]] = %[[VAL_155:.*]]#1 to %[[VAL_24]] step %[[VAL_9]] {
// CHECK: %[[VAL_156:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_154]]] : memref<?xindex>
// CHECK: %[[VAL_157:.*]] = addi %[[VAL_154]], %[[VAL_9]] : index
// CHECK: %[[VAL_158:.*]] = load %[[VAL_18]]{{\[}}%[[VAL_157]]] : memref<?xindex>
// CHECK: %[[VAL_159:.*]] = load %[[VAL_25]]{{\[}}%[[VAL_154]]] : memref<?xf32>
// CHECK: %[[VAL_160:.*]] = scf.for %[[VAL_161:.*]] = %[[VAL_156]] to %[[VAL_158]] step %[[VAL_9]] iter_args(%[[VAL_162:.*]] = %[[VAL_159]]) -> (f32) {
// CHECK: %[[VAL_163:.*]] = load %[[VAL_20]]{{\[}}%[[VAL_161]]] : memref<?xf32>
// CHECK: %[[VAL_164:.*]] = addf %[[VAL_162]], %[[VAL_163]] : f32
// CHECK: scf.yield %[[VAL_164]] : f32
// CHECK: }
// CHECK: store %[[VAL_165:.*]], %[[VAL_25]]{{\[}}%[[VAL_154]]] : memref<?xf32>
// CHECK: }
// CHECK: %[[VAL_166:.*]] = tensor_load %[[VAL_25]] : memref<?xf32>
// CHECK: return %[[VAL_166]] : 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>
}