[mlir][affine] Enable ConvertAffineToStandard pass to handle affine.delinearize_index Op. #82189
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
|
✅ With the latest revision this PR passed the C/C++ code formatter. |
Ris-Bali
changed the title
|
@llvm/pr-subscribers-mlir Author: Rishabh Bali (Ris-Bali) ChangesThis PR, aims to enable the Fixes #78458 Full diff: https://github.com/llvm/llvm-project/pull/82189.diff 2 Files Affected:
diff --git a/mlir/lib/Conversion/AffineToStandard/AffineToStandard.cpp b/mlir/lib/Conversion/AffineToStandard/AffineToStandard.cpp
index 15ad6d8cdf629d..3f86c2077e716b 100644
--- a/mlir/lib/Conversion/AffineToStandard/AffineToStandard.cpp
+++ b/mlir/lib/Conversion/AffineToStandard/AffineToStandard.cpp
@@ -15,6 +15,7 @@
#include "mlir/Dialect/Affine/IR/AffineOps.h"
#include "mlir/Dialect/Affine/Utils.h"
+#include "mlir/Dialect/Affine/Transforms/Transforms.h"
#include "mlir/Dialect/MemRef/IR/MemRef.h"
#include "mlir/Dialect/SCF/IR/SCF.h"
#include "mlir/Dialect/Vector/IR/VectorOps.h"
@@ -560,6 +561,7 @@ class LowerAffinePass
RewritePatternSet patterns(&getContext());
populateAffineToStdConversionPatterns(patterns);
populateAffineToVectorConversionPatterns(patterns);
+ populateAffineExpandIndexOpsPatterns(patterns);
ConversionTarget target(getContext());
target.addLegalDialect<arith::ArithDialect, memref::MemRefDialect,
scf::SCFDialect, VectorDialect>();
diff --git a/mlir/test/Conversion/AffineToStandard/lower-affine.mlir b/mlir/test/Conversion/AffineToStandard/lower-affine.mlir
index 92608135d24b08..1e6a8d454dd992 100644
--- a/mlir/test/Conversion/AffineToStandard/lower-affine.mlir
+++ b/mlir/test/Conversion/AffineToStandard/lower-affine.mlir
@@ -937,3 +937,58 @@ func.func @affine_parallel_with_reductions_i64(%arg0: memref<3x3xi64>, %arg1: me
// CHECK: scf.reduce.return %[[RES]] : i64
// CHECK: }
// CHECK: }
+
+
+///////////////////////////////////////////////////////////////////////
+
+func.func @test_dilinearize_index(%linear_index: index) -> (index, index, index) {
+ %b0 = arith.constant 16 : index
+ %b1 = arith.constant 224 : index
+ %b2 = arith.constant 224 : index
+ %1:3 = affine.delinearize_index %linear_index into (%b0, %b1, %b2) : index, index, index
+ return %1#0, %1#1, %1#2 : index, index, index
+}
+// CHECK-LABEL: func.func @test_dilinearize_index(
+// CHECK-SAME: %[[VAL_0:.*]]: index) -> (index, index, index) {
+// CHECK: %[[VAL_1:.*]] = arith.constant 16 : index
+// CHECK: %[[VAL_2:.*]] = arith.constant 224 : index
+// CHECK: %[[VAL_3:.*]] = arith.constant 224 : index
+// CHECK: %[[VAL_4:.*]] = arith.constant 50176 : index
+// CHECK: %[[VAL_5:.*]] = arith.constant 50176 : index
+// CHECK: %[[VAL_6:.*]] = arith.constant 0 : index
+// CHECK: %[[VAL_7:.*]] = arith.constant -1 : index
+// CHECK: %[[VAL_8:.*]] = arith.cmpi slt, %[[VAL_0]], %[[VAL_6]] : index
+// CHECK: %[[VAL_9:.*]] = arith.subi %[[VAL_7]], %[[VAL_0]] : index
+// CHECK: %[[VAL_10:.*]] = arith.select %[[VAL_8]], %[[VAL_9]], %[[VAL_0]] : index
+// CHECK: %[[VAL_11:.*]] = arith.divsi %[[VAL_10]], %[[VAL_5]] : index
+// CHECK: %[[VAL_12:.*]] = arith.subi %[[VAL_7]], %[[VAL_11]] : index
+// CHECK: %[[VAL_13:.*]] = arith.select %[[VAL_8]], %[[VAL_12]], %[[VAL_11]] : index
+// CHECK: %[[VAL_14:.*]] = arith.constant 50176 : index
+// CHECK: %[[VAL_15:.*]] = arith.remsi %[[VAL_0]], %[[VAL_14]] : index
+// CHECK: %[[VAL_16:.*]] = arith.constant 0 : index
+// CHECK: %[[VAL_17:.*]] = arith.cmpi slt, %[[VAL_15]], %[[VAL_16]] : index
+// CHECK: %[[VAL_18:.*]] = arith.addi %[[VAL_15]], %[[VAL_14]] : index
+// CHECK: %[[VAL_19:.*]] = arith.select %[[VAL_17]], %[[VAL_18]], %[[VAL_15]] : index
+// CHECK: %[[VAL_20:.*]] = arith.constant 50176 : index
+// CHECK: %[[VAL_21:.*]] = arith.remsi %[[VAL_0]], %[[VAL_20]] : index
+// CHECK: %[[VAL_22:.*]] = arith.constant 0 : index
+// CHECK: %[[VAL_23:.*]] = arith.cmpi slt, %[[VAL_21]], %[[VAL_22]] : index
+// CHECK: %[[VAL_24:.*]] = arith.addi %[[VAL_21]], %[[VAL_20]] : index
+// CHECK: %[[VAL_25:.*]] = arith.select %[[VAL_23]], %[[VAL_24]], %[[VAL_21]] : index
+// CHECK: %[[VAL_26:.*]] = arith.constant 224 : index
+// CHECK: %[[VAL_27:.*]] = arith.constant 0 : index
+// CHECK: %[[VAL_28:.*]] = arith.constant -1 : index
+// CHECK: %[[VAL_29:.*]] = arith.cmpi slt, %[[VAL_25]], %[[VAL_27]] : index
+// CHECK: %[[VAL_30:.*]] = arith.subi %[[VAL_28]], %[[VAL_25]] : index
+// CHECK: %[[VAL_31:.*]] = arith.select %[[VAL_29]], %[[VAL_30]], %[[VAL_25]] : index
+// CHECK: %[[VAL_32:.*]] = arith.divsi %[[VAL_31]], %[[VAL_26]] : index
+// CHECK: %[[VAL_33:.*]] = arith.subi %[[VAL_28]], %[[VAL_32]] : index
+// CHECK: %[[VAL_34:.*]] = arith.select %[[VAL_29]], %[[VAL_33]], %[[VAL_32]] : index
+// CHECK: %[[VAL_35:.*]] = arith.constant 224 : index
+// CHECK: %[[VAL_36:.*]] = arith.remsi %[[VAL_0]], %[[VAL_35]] : index
+// CHECK: %[[VAL_37:.*]] = arith.constant 0 : index
+// CHECK: %[[VAL_38:.*]] = arith.cmpi slt, %[[VAL_36]], %[[VAL_37]] : index
+// CHECK: %[[VAL_39:.*]] = arith.addi %[[VAL_36]], %[[VAL_35]] : index
+// CHECK: %[[VAL_40:.*]] = arith.select %[[VAL_38]], %[[VAL_39]], %[[VAL_36]] : index
+// CHECK: return %[[VAL_13]], %[[VAL_34]], %[[VAL_40]] : index, index, index
+// CHECK: }
|
ftynse
approved these changes
Feb 22, 2024
|
Please run clang-format on your code. |
Ris-Bali
force-pushed
the
add_affineexpandindex_to_affine_lower
branch
from
e7e36ef to
957bb48
Compare
Done!! Although the windows tests are failing now because of configuration error. Linux tests are passing. |
Ris-Bali
force-pushed
the
add_affineexpandindex_to_affine_lower
branch
from
957bb48 to
c203ff9
Compare
Ris-Bali
force-pushed
the
add_affineexpandindex_to_affine_lower
branch
from
c203ff9 to
9415f1b
Compare
ingomueller-net
added a commit
that referenced
this pull request
Feb 28, 2024
That commit (from #82189) introduces a new dependency but does not declare it in the BUILD files.
mylai-mtk
pushed a commit
to mylai-mtk/llvm-project
that referenced
this pull request
Jul 12, 2024
That commit (from llvm#82189) introduces a new dependency but does not declare it in the BUILD files.
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.
This PR, aims to enable the
ConvertAffineToStandardto handleaffine.dilinearize_indexOperation.Fixes #78458