[Mlir-commits] [mlir] [mlir][nfc] Update vectorize-tensor-extract.mlir (2/N) (PR #119080)
Andrzej Warzyński
llvmlistbot at llvm.org
Tue Dec 10 23:52:10 PST 2024
https://github.com/banach-space updated https://github.com/llvm/llvm-project/pull/119080
>From 74135fa28523a4f76e166e30f5556c712e502050 Mon Sep 17 00:00:00 2001
From: Andrzej Warzynski <andrzej.warzynski at arm.com>
Date: Sat, 7 Dec 2024 14:21:48 +0000
Subject: [PATCH 1/2] [mlir][nfc] Update vectorize-tensor-extract.mlir (2/N)
Tests in "vectorize-tensor-extract.mlir" are inconsistent and would
benefit from refactoring to:
* Clearly categorize tests into "contiguous load," "gather load," and
"scalar load + broadcast" cases, reflecting the structure of
tensor.extract vectorization.
* Unify variable naming (both MLIR and FileCheck).
* Ensure all tests exercise unmasked vectorization (masked vectorization
is covered in "vectorize-tensor-extract-masked.mlir").
* Improve and standardize formatting.
These changes will make it easier to identify the test cases being
exercised and simplify future maintenance or refactoring.
This is patch 2/N in the series. Below is a summary of the changes in
this patch.
----------------------------------------------------------------------
Summary of patch 2/N
----------------------------------------------------------------------
Makes all tests re-use the same TD sequence. This TD sequence has been
extracted to a dedicted file:
* "td/vectorize-with-patterns.mlir".
----------------------------------------------------------------------
**DEPENDS ON**
* https://github.com/llvm/llvm-project/pull/118977
* https://github.com/llvm/llvm-project/pull/119079
Please only review the top commit
---
.../Linalg/td/vectorize-with-patterns.mlir | 10 +
.../Linalg/vectorize-tensor-extract.mlir | 218 ++----------------
2 files changed, 30 insertions(+), 198 deletions(-)
create mode 100644 mlir/test/Dialect/Linalg/td/vectorize-with-patterns.mlir
diff --git a/mlir/test/Dialect/Linalg/td/vectorize-with-patterns.mlir b/mlir/test/Dialect/Linalg/td/vectorize-with-patterns.mlir
new file mode 100644
index 00000000000000..f8d1a50d7430df
--- /dev/null
+++ b/mlir/test/Dialect/Linalg/td/vectorize-with-patterns.mlir
@@ -0,0 +1,10 @@
+module @transforms attributes { transform.with_named_sequence } {
+ transform.named_sequence @vectorize_with_patterns(%module: !transform.any_op {transform.readonly}) {
+
+ %0 = transform.structured.match ops{["linalg.generic"]} in %module : (!transform.any_op) -> !transform.any_op
+ %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
+ %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
+
+ transform.yield
+ }
+}
diff --git a/mlir/test/Dialect/Linalg/vectorize-tensor-extract.mlir b/mlir/test/Dialect/Linalg/vectorize-tensor-extract.mlir
index aa1e44166ec9d6..25fb7ed125f874 100644
--- a/mlir/test/Dialect/Linalg/vectorize-tensor-extract.mlir
+++ b/mlir/test/Dialect/Linalg/vectorize-tensor-extract.mlir
@@ -1,4 +1,6 @@
-// RUN: mlir-opt %s -transform-interpreter -split-input-file | FileCheck %s
+// RUN: mlir-opt -split-input-file \
+// RUN: -transform-preload-library='transform-library-paths=%p/td/vectorize-with-patterns.mlir' \
+// RUN: -transform-interpreter=entry-point=vectorize_with_patterns %s | FileCheck %s
#map0 = affine_map<(d0, d1, d2, d3) -> (d0, d2)>
#map1 = affine_map<(d0, d1, d2, d3) -> (d0, d1, d2, d3)>
@@ -27,15 +29,6 @@ func.func @vectorize_1d_tensor_extract(%arg0: tensor<3xf32>, %arg1: tensor<4x3xi
// CHECK: %[[GATHER:.*]] = vector.gather %[[ARG0]][%[[C0]]] [%[[INDICES]]], %[[MASK]], %[[PASSTHRU]]
// CHECK: vector.transfer_write %[[GATHER]]
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
#map = affine_map<() -> ()>
@@ -59,15 +52,6 @@ func.func @extract_scalar_from_0d_into_0d(%src: tensor<f32>, %init: tensor<f32>)
// CHECK: %[[READ:.*]] = vector.transfer_read %[[SRC]][], %[[PAD]] : tensor<f32>, vector<f32>
// CHECK: vector.transfer_write %[[READ]], %[[INIT]][] : vector<f32>, tensor<f32>
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
#map = affine_map<(n) -> (n)>
@@ -92,51 +76,35 @@ func.func @extract_scalar_from_0d_into_1d(%src: tensor<f32>, %init: tensor<1xf32
// CHECK: %[[READ_BCAST:.*]] = vector.broadcast %[[READ]] : vector<f32> to vector<1xf32>
// CHECK: vector.transfer_write %[[READ_BCAST]], %[[INIT]][%[[C0]]] {in_bounds = [true]} : vector<1xf32>, tensor<1xf32>
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
#map = affine_map<(d0, d1, d2) -> (d0, d1, d2)>
-func.func @vectorize_nd_tensor_extract_scalar_broadcast(%arg0: tensor<3x3xf32>, %arg2: tensor<1x1x3xf32>) -> tensor<1x1x3xf32> {
+func.func @vectorize_nd_tensor_extract_scalar_broadcast(%src: tensor<3x3xf32>, %init: tensor<1x1x3xf32>) -> tensor<1x1x3xf32> {
%c0 = arith.constant 1 : index
%c1 = arith.constant 2 : index
- %2 = linalg.generic {
+
+ %res = linalg.generic {
indexing_maps = [#map],
iterator_types = ["parallel", "parallel", "parallel"]
- } outs(%arg2 : tensor<1x1x3xf32>) {
+ } outs(%init : tensor<1x1x3xf32>) {
^bb0(%arg4: f32):
- %7 = tensor.extract %arg0[%c0, %c1] : tensor<3x3xf32>
- linalg.yield %7 : f32
+ %1 = tensor.extract %src[%c0, %c1] : tensor<3x3xf32>
+ linalg.yield %1 : f32
} -> tensor<1x1x3xf32>
- return %2 : tensor<1x1x3xf32>
+
+ return %res : tensor<1x1x3xf32>
}
-// CHECK: #[[$MAP:.+]] = affine_map<(d0, d1) -> (0, 0, 0)>
// CHECK-LABEL: func.func @vectorize_nd_tensor_extract_scalar_broadcast(
-// CHECK-SAME: %[[ARG_0:.*]]: tensor<3x3xf32>,
-// CHECK-SAME: %[[ARG_1:.*]]: tensor<1x1x3xf32>) -> tensor<1x1x3xf32> {
-// CHECK-DAG: %[[C1:.*]] = arith.constant 1 : index
-// CHECK-DAG: %[[C2:.*]] = arith.constant 2 : index
-// CHECK-DAG: %[[C0:.*]] = arith.constant 0 : index
-// CHECK: %[[MASK:.*]] = vector.constant_mask [1] : vector<1xi1>
-// CHECK: %[[READ:.*]] = vector.mask %[[MASK]] { vector.transfer_read %[[ARG_0]][%[[C1]], %[[C2]]], {{.*}} {in_bounds = [true, true, true], permutation_map = #[[$MAP]]} : tensor<3x3xf32>, vector<1x1x3xf32> } : vector<1xi1> -> vector<1x1x3xf32>
-// CHECK: %[[C0_2:.*]] = arith.constant 0 : index
-// CHECK: vector.transfer_write %[[READ]], %[[ARG_1]]{{\[}}%[[C0_2]], %[[C0_2]], %[[C0_2]]] : vector<1x1x3xf32>, tensor<1x1x3xf32>
-
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- transform.structured.vectorize %0 { vectorize_nd_extract } : !transform.any_op
- transform.yield
- }
-}
+// CHECK-SAME: %[[SRC:.*]]: tensor<3x3xf32>,
+// CHECK-SAME: %[[INIT:.*]]: tensor<1x1x3xf32>) -> tensor<1x1x3xf32> {
+// CHECK: %[[C0:.*]] = arith.constant 0 : index
+// CHECK: %[[C1:.*]] = arith.constant 1 : index
+// CHECK: %[[C2:.*]] = arith.constant 2 : index
+// CHECK: %[[PAD:.*]] = arith.constant 0.000000e+00 : f32
+// CHECK: %[[READ:.*]] = vector.transfer_read %[[SRC]][%[[C1]], %[[C2]]], %[[PAD]] : tensor<3x3xf32>, vector<f32>
+// CHECK: %[[READ_BCAST:.*]] = vector.broadcast %[[READ]] : vector<f32> to vector<1x1x3xf32>
+// CHECK: vector.transfer_write %[[READ_BCAST]], %[[INIT]][%[[C0]], %[[C0]], %[[C0]]] {in_bounds = [true, true, true]} : vector<1x1x3xf32>, tensor<1x1x3xf32>
// -----
@@ -207,15 +175,6 @@ func.func @vectorize_nd_tensor_extract_transfer_read_basic_column(
// CHECK: %[[RES:.*]] = vector.transfer_write %[[BCAST]], %[[OUTPUT]]{{\[}}%[[C0]], %[[C0]], %[[C0]]] {in_bounds = [true, true, true]} : vector<3x1x1xf32>, tensor<3x1x1xf32>
// CHECK: return %[[RES]] : tensor<3x1x1xf32>
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
func.func @vectorize_nd_tensor_extract_transfer_read_complex(%6: tensor<45x80x16xf32>, %arg0: index, %arg2: index, %arg1: index, %arg4: index, %extracted_slice : tensor<1x4xf32>) -> tensor<1x4xf32> {
@@ -259,15 +218,6 @@ func.func @vectorize_nd_tensor_extract_transfer_read_complex(%6: tensor<45x80x16
// CHECK: return %[[VAL_21]] : tensor<1x4xf32>
// CHECK: }
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
#map0 = affine_map<(d0, d1, d2, d3) -> (d0, d2)>
@@ -309,15 +259,6 @@ func.func @vectorize_nd_tensor_extract_index_from_tensor(%arg0: tensor<3x3xf32>,
// CHECK: %[[GATHER:.*]] = vector.gather %[[ARG0]][%[[C0]], %[[C0]]] [%[[T]]], %[[CST_1]], %[[PASSTHRU]] : tensor<3x3xf32>, vector<4x7x3x2xindex>, vector<4x7x3x2xi1>, vector<4x7x3x2xf32> into vector<4x7x3x2xf32>
// CHECK: vector.transfer_write %[[GATHER]], %[[ARG4]][%[[C0]], %[[C0]], %[[C0]], %[[C0]]] {in_bounds = [true, true, true, true]} : vector<4x7x3x2xf32>, tensor<4x7x3x2xf32>
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
#map = affine_map<(d0, d1) -> (d0, d1)>
@@ -339,15 +280,6 @@ func.func @vectorize_nd_tensor_extract_load_1d_column_vector_using_gather_load(%
return %1 : tensor<8x1xf32>
}
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg0: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg0 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 {vectorize_nd_extract} : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// CHECK-LABEL: func.func @vectorize_nd_tensor_extract_load_1d_column_vector_using_gather_load
// CHECK-SAME: %[[ARG0:.*]]: tensor<8x128x768xf32>
// CHECK-SAME: %[[ARG1:.*]]: index
@@ -390,15 +322,6 @@ func.func @index_from_output_column_vector_gather_load(%src: tensor<8x128xf32>)
return %res : tensor<8x1xf32>
}
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg2: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg2 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 {vectorize_nd_extract} : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// CHECK-LABEL: func.func @index_from_output_column_vector_gather_load(
// CHECK-SAME: %[[SRC:.*]]: tensor<8x128xf32>) -> tensor<8x1xf32> {
// CHECK: %[[C128:.*]] = arith.constant dense<128> : vector<1x8xindex>
@@ -437,15 +360,6 @@ func.func @index_from_output_column_vector_contiguous_load(%src: tensor<8x128xf3
return %res : tensor<8x1xf32>
}
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg2: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg2 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 {vectorize_nd_extract} : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// CHECK-LABEL: func.func @index_from_output_column_vector_contiguous_load(
// CHECK-SAME: %[[SRC:.*]]: tensor<8x128xf32>) -> tensor<8x1xf32> {
// CHECK: %[[C0:.*]] = arith.constant 0 : index
@@ -497,15 +411,6 @@ func.func @vectorize_nd_tensor_extract_contiguous_and_gather(%arg0: tensor<6xf32
// CHECK: %[[VAL_14:.*]] = vector.transfer_write %[[VAL_13]], %[[VAL_8]]{{\[}}%[[VAL_2]]] {in_bounds = [true]} : vector<5xf32>, tensor<5xf32>
// CHECK: return %[[VAL_14]] : tensor<5xf32>
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
// The vectorizer converts `affine.apply` so that the subsequent Ops can be vectorised based on the converted ops. Contiguous load.
@@ -540,15 +445,6 @@ func.func @vectorize_nd_tensor_extract_with_affine_apply_contiguous(%6: tensor<8
// CHECK: return %[[VAL_12]] : tensor<1x4xf32>
// CHECK: }
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
func.func @vectorize_nd_tensor_extract_with_tensor_extract(%input_1: tensor<1x20xi32>, %input_2: tensor<257x24xf32>, %arg0 : index, %arg1 : index, %arg2 : index, %arg3 : index) -> tensor<1x1x4xf32> {
@@ -585,16 +481,6 @@ func.func @vectorize_nd_tensor_extract_with_tensor_extract(%input_1: tensor<1x20
// for address calculation also satisfy the required conditions).
// CHECK: vector.transfer_read %[[INPUT_2]][%{{.*}}, %{{.*}}, %{{.*}} {in_bounds = [true, true]} : tensor<257x24xf32>, vector<1x4xf32>
-
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
// The vectorizer converts `affine.apply` so that the subsequent Ops can be vectorised based on the converted ops. Gather load.
@@ -632,15 +518,6 @@ func.func @vectorize_nd_tensor_extract_with_affine_apply_gather(%6: tensor<80x16
// CHECK: return %[[VAL_14]] : tensor<1x4xf32>
// CHECK: }
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
// Make sure that non-linear arithmetic operations (e.g. arith.maxsi) are allowed when calculating indices for load operations. Gather load.
@@ -674,15 +551,6 @@ func.func @vectorize_nd_tensor_extract_with_maxsi_gather(%arg0: tensor<80x16xf32
// CHECK: return %[[VAL_10]] : tensor<1x4xf32>
// CHECK: }
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
// Make sure that non-linear arithmetic operations (e.g. arith.maxsi) are allowed when calculating indices for load operations. Contiguous load.
@@ -718,15 +586,6 @@ func.func @vectorize_nd_tensor_extract_with_maxsi_contiguous(%arg0: tensor<80x16
// CHECK: return %[[VAL_9]] : tensor<1x4xf32>
// CHECK: }
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
// The vectorizer assumes it's a gather load whenever using a block argument to calculate an index.
@@ -759,15 +618,6 @@ func.func @vectorize_nd_tensor_extract_block_arg(%arg0: tensor<5x6xf32>, %arg1:
// CHECK: return %[[VAL_12]] : tensor<5xf32>
// CHECK: }
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
#map1 = affine_map<(d0, d1, d2) -> (d0, d1, d2)>
@@ -788,15 +638,6 @@ func.func @vectorize_0d_tensor_extract(%arg0: tensor<f32>, %arg2: tensor<1x1x3xf
// CHECK: %[[EXTRACT:.*]] = vector.transfer_read %[[ARG_0]][], %{{.+}} : tensor<f32>
// CHECK: vector.broadcast %[[EXTRACT]] : vector<f32> to vector<1x1x3xf32>
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
// -----
#map = affine_map<(d0, d1, d2) -> (d0, d1, d2)>
@@ -833,16 +674,6 @@ func.func @vectorize_reverse_like_tensor_extract(%arg0: tensor<1x2x3xf32>, %arg1
// CHECK: %[[GATHER:.*]] = vector.gather %[[ARG0]][%[[C0]], %[[C0]], %[[C0]]] [%[[T3]]], %[[MASK]], %[[PASSTHRU]]
// CHECK: vector.transfer_write %[[GATHER]]
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
-
-
// -----
func.func @vectorize_scalar_read_with_broadcast_from_column_tensor(%init: tensor<1x1x4xi32>) -> tensor<1x1x4xi32> {
@@ -874,12 +705,3 @@ func.func @vectorize_scalar_read_with_broadcast_from_column_tensor(%init: tensor
// CHECK: %[[READ:.*]] = vector.transfer_read %[[SRC]]{{\[}}%[[IDX_ELT]], %[[C0]]], %[[PAD]] : tensor<15x1xi32>, vector<i32>
// CHECK: %[[READ_BCAST:.*]] = vector.broadcast %[[READ]] : vector<i32> to vector<1x1x4xi32>
// CHECK: %[[RES:.*]] = vector.transfer_write %[[READ_BCAST]], %[[INIT]][%[[C0]], %[[C0]], %[[C0]]] {in_bounds = [true, true, true]} : vector<1x1x4xi32>, tensor<1x1x4xi32>
-
-module attributes {transform.with_named_sequence} {
- transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
- %0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
- %1 = transform.get_parent_op %0 {isolated_from_above} : (!transform.any_op) -> !transform.any_op
- %2 = transform.structured.vectorize_children_and_apply_patterns %1 { vectorize_nd_extract } : (!transform.any_op) -> !transform.any_op
- transform.yield
- }
-}
>From 90552889dc4b39eee2682c161646824445e08f74 Mon Sep 17 00:00:00 2001
From: Andrzej Warzynski <andrzej.warzynski at arm.com>
Date: Tue, 10 Dec 2024 18:17:00 +0000
Subject: [PATCH 2/2] fixup! [mlir][nfc] Update vectorize-tensor-extract.mlir
(2/N)
Restore CHECK-DAG
---
mlir/test/Dialect/Linalg/vectorize-tensor-extract.mlir | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/mlir/test/Dialect/Linalg/vectorize-tensor-extract.mlir b/mlir/test/Dialect/Linalg/vectorize-tensor-extract.mlir
index 25fb7ed125f874..25435cf51a6156 100644
--- a/mlir/test/Dialect/Linalg/vectorize-tensor-extract.mlir
+++ b/mlir/test/Dialect/Linalg/vectorize-tensor-extract.mlir
@@ -98,10 +98,10 @@ func.func @vectorize_nd_tensor_extract_scalar_broadcast(%src: tensor<3x3xf32>, %
// CHECK-LABEL: func.func @vectorize_nd_tensor_extract_scalar_broadcast(
// CHECK-SAME: %[[SRC:.*]]: tensor<3x3xf32>,
// CHECK-SAME: %[[INIT:.*]]: tensor<1x1x3xf32>) -> tensor<1x1x3xf32> {
-// CHECK: %[[C0:.*]] = arith.constant 0 : index
-// CHECK: %[[C1:.*]] = arith.constant 1 : index
-// CHECK: %[[C2:.*]] = arith.constant 2 : index
-// CHECK: %[[PAD:.*]] = arith.constant 0.000000e+00 : f32
+// CHECK-DAG: %[[C0:.*]] = arith.constant 0 : index
+// CHECK-DAG: %[[C1:.*]] = arith.constant 1 : index
+// CHECK-DAG: %[[C2:.*]] = arith.constant 2 : index
+// CHECK-DAG: %[[PAD:.*]] = arith.constant 0.000000e+00 : f32
// CHECK: %[[READ:.*]] = vector.transfer_read %[[SRC]][%[[C1]], %[[C2]]], %[[PAD]] : tensor<3x3xf32>, vector<f32>
// CHECK: %[[READ_BCAST:.*]] = vector.broadcast %[[READ]] : vector<f32> to vector<1x1x3xf32>
// CHECK: vector.transfer_write %[[READ_BCAST]], %[[INIT]][%[[C0]], %[[C0]], %[[C0]]] {in_bounds = [true, true, true]} : vector<1x1x3xf32>, tensor<1x1x3xf32>
More information about the Mlir-commits
mailing list