[mlir][vector] Add tests for xfer-flatten patterns #102210
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-mlir-vector Author: Andrzej Warzyński (banach-space) ChangesAdds tests for scalable vectors in:
This is rather straightfoward as the tested patterns (*) do not support (*) Full diff: https://github.com/llvm/llvm-project/pull/102210.diff 1 Files Affected:
diff --git a/mlir/test/Dialect/Vector/vector-transfer-flatten.mlir b/mlir/test/Dialect/Vector/vector-transfer-flatten.mlir
index 9d16aa46a9f2ad..fb8dad02dfda6b 100644
--- a/mlir/test/Dialect/Vector/vector-transfer-flatten.mlir
+++ b/mlir/test/Dialect/Vector/vector-transfer-flatten.mlir
@@ -6,6 +6,8 @@
///----------------------------------------------------------------------------------------
/// vector.transfer_read
/// [Pattern: FlattenContiguousRowMajorTransferReadPattern]
+///
+/// NOTE: Scalable vectors are not supported
///----------------------------------------------------------------------------------------
func.func @transfer_read_dims_match_contiguous(
@@ -28,6 +30,22 @@ func.func @transfer_read_dims_match_contiguous(
// CHECK-128B-LABEL: func @transfer_read_dims_match_contiguous
// CHECK-128B: memref.collapse_shape
+func.func @transfer_read_dims_match_contiguous_scalable(
+ %mem : memref<5x4x3x2xi8, strided<[24, 6, 2, 1], offset: ?>>) -> vector<5x4x3x[2]xi8> {
+
+ %c0 = arith.constant 0 : index
+ %cst = arith.constant 0 : i8
+ %res = vector.transfer_read %mem[%c0, %c0, %c0, %c0], %cst :
+ memref<5x4x3x2xi8, strided<[24, 6, 2, 1], offset: ?>>, vector<5x4x3x[2]xi8>
+ return %res : vector<5x4x3x[2]xi8>
+}
+
+// CHECK-LABEL: func @transfer_read_dims_match_contiguous_scalable
+// CHECK-NOT: memref.collapse_shape
+
+// CHECK-128B-LABEL: func @transfer_read_dims_match_contiguous_scalable
+// CHECK-128B: memref.collapse_shape
+
// -----
func.func @transfer_read_dims_match_contiguous_empty_stride(
@@ -259,6 +277,8 @@ func.func @transfer_read_non_contiguous_src(
///----------------------------------------------------------------------------------------
/// vector.transfer_write
/// [Pattern: FlattenContiguousRowMajorTransferWritePattern]
+///
+/// NOTE: Scalable vectors are not supported
///----------------------------------------------------------------------------------------
func.func @transfer_write_dims_match_contiguous(
@@ -281,6 +301,22 @@ func.func @transfer_write_dims_match_contiguous(
// CHECK-128B-LABEL: func @transfer_write_dims_match_contiguous(
// CHECK-128B: memref.collapse_shape
+func.func @transfer_write_dims_match_contiguous_scalable(
+ %mem : memref<5x4x3x2xi8, strided<[24, 6, 2, 1], offset: ?>>,
+ %vec : vector<5x4x3x[2]xi8>) {
+
+ %c0 = arith.constant 0 : index
+ vector.transfer_write %vec, %mem [%c0, %c0, %c0, %c0] :
+ vector<5x4x3x[2]xi8>, memref<5x4x3x2xi8, strided<[24, 6, 2, 1], offset: ?>>
+ return
+}
+
+// CHECK-LABEL: func @transfer_write_dims_match_contiguous_scalable(
+// CHECK-NOT: memref.collapse_shape
+
+// CHECK-128B-LABEL: func @transfer_write_dims_match_contiguous_scalable
+// CHECK-128B-NOT: memref.collapse_shape
+
// -----
func.func @transfer_write_dims_match_contiguous_empty_stride(
@@ -504,7 +540,11 @@ func.func @transfer_write_non_contiguous_src(
///----------------------------------------------------------------------------------------
/// [Pattern: DropUnitDimFromElementwiseOps]
+///
/// TODO: Move to a dedicated file - there's no "flattening" in the following tests
+/// TODO: Potential duplication with tests from:
+/// * "vector-dropleadunitdim-transforms.mlir"
+/// * "vector-transfer-drop-unit-dims-patterns.mlir"
///----------------------------------------------------------------------------------------
func.func @fold_unit_dim_add_basic(%vec : vector<1x8xi32>) -> vector<1x8xi32> {
|
|
@llvm/pr-subscribers-mlir Author: Andrzej Warzyński (banach-space) ChangesAdds tests for scalable vectors in:
This is rather straightfoward as the tested patterns (*) do not support (*) Full diff: https://github.com/llvm/llvm-project/pull/102210.diff 1 Files Affected:
diff --git a/mlir/test/Dialect/Vector/vector-transfer-flatten.mlir b/mlir/test/Dialect/Vector/vector-transfer-flatten.mlir
index 9d16aa46a9f2a..fb8dad02dfda6 100644
--- a/mlir/test/Dialect/Vector/vector-transfer-flatten.mlir
+++ b/mlir/test/Dialect/Vector/vector-transfer-flatten.mlir
@@ -6,6 +6,8 @@
///----------------------------------------------------------------------------------------
/// vector.transfer_read
/// [Pattern: FlattenContiguousRowMajorTransferReadPattern]
+///
+/// NOTE: Scalable vectors are not supported
///----------------------------------------------------------------------------------------
func.func @transfer_read_dims_match_contiguous(
@@ -28,6 +30,22 @@ func.func @transfer_read_dims_match_contiguous(
// CHECK-128B-LABEL: func @transfer_read_dims_match_contiguous
// CHECK-128B: memref.collapse_shape
+func.func @transfer_read_dims_match_contiguous_scalable(
+ %mem : memref<5x4x3x2xi8, strided<[24, 6, 2, 1], offset: ?>>) -> vector<5x4x3x[2]xi8> {
+
+ %c0 = arith.constant 0 : index
+ %cst = arith.constant 0 : i8
+ %res = vector.transfer_read %mem[%c0, %c0, %c0, %c0], %cst :
+ memref<5x4x3x2xi8, strided<[24, 6, 2, 1], offset: ?>>, vector<5x4x3x[2]xi8>
+ return %res : vector<5x4x3x[2]xi8>
+}
+
+// CHECK-LABEL: func @transfer_read_dims_match_contiguous_scalable
+// CHECK-NOT: memref.collapse_shape
+
+// CHECK-128B-LABEL: func @transfer_read_dims_match_contiguous_scalable
+// CHECK-128B: memref.collapse_shape
+
// -----
func.func @transfer_read_dims_match_contiguous_empty_stride(
@@ -259,6 +277,8 @@ func.func @transfer_read_non_contiguous_src(
///----------------------------------------------------------------------------------------
/// vector.transfer_write
/// [Pattern: FlattenContiguousRowMajorTransferWritePattern]
+///
+/// NOTE: Scalable vectors are not supported
///----------------------------------------------------------------------------------------
func.func @transfer_write_dims_match_contiguous(
@@ -281,6 +301,22 @@ func.func @transfer_write_dims_match_contiguous(
// CHECK-128B-LABEL: func @transfer_write_dims_match_contiguous(
// CHECK-128B: memref.collapse_shape
+func.func @transfer_write_dims_match_contiguous_scalable(
+ %mem : memref<5x4x3x2xi8, strided<[24, 6, 2, 1], offset: ?>>,
+ %vec : vector<5x4x3x[2]xi8>) {
+
+ %c0 = arith.constant 0 : index
+ vector.transfer_write %vec, %mem [%c0, %c0, %c0, %c0] :
+ vector<5x4x3x[2]xi8>, memref<5x4x3x2xi8, strided<[24, 6, 2, 1], offset: ?>>
+ return
+}
+
+// CHECK-LABEL: func @transfer_write_dims_match_contiguous_scalable(
+// CHECK-NOT: memref.collapse_shape
+
+// CHECK-128B-LABEL: func @transfer_write_dims_match_contiguous_scalable
+// CHECK-128B-NOT: memref.collapse_shape
+
// -----
func.func @transfer_write_dims_match_contiguous_empty_stride(
@@ -504,7 +540,11 @@ func.func @transfer_write_non_contiguous_src(
///----------------------------------------------------------------------------------------
/// [Pattern: DropUnitDimFromElementwiseOps]
+///
/// TODO: Move to a dedicated file - there's no "flattening" in the following tests
+/// TODO: Potential duplication with tests from:
+/// * "vector-dropleadunitdim-transforms.mlir"
+/// * "vector-transfer-drop-unit-dims-patterns.mlir"
///----------------------------------------------------------------------------------------
func.func @fold_unit_dim_add_basic(%vec : vector<1x8xi32>) -> vector<1x8xi32> {
|
Adds tests for scalable vectors in: * vector-transfer-flatten.mlir This is rather straightfoward as the tested patterns (*) do not support scalable vectors. (*) `FlattenContiguousRowMajorTransferReadPattern` and `FlattenContiguousRowMajorTransferWritePattern`
banach-space
force-pushed
the
andrzej/xfer_flatten_scalable_tests
branch
from
ef72b6f to
371f811
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds tests for scalable vectors in:
This is rather straightfoward as the tested patterns (*) do not support
scalable vectors.
(*)
FlattenContiguousRowMajorTransferReadPatternandFlattenContiguousRowMajorTransferWritePattern