[Mlir-commits] [mlir] 3f59734 - [mlir][aarch64] Disable bf16 tests on AArch64

[Andrzej Warzynski]

Author: Andrzej Warzynski
Date: 2022-10-20T07:11:05Z
New Revision: 3f59734e0c25ffcd8b522d2ccd8484941a819fca

URL: https://github.com/llvm/llvm-project/commit/3f59734e0c25ffcd8b522d2ccd8484941a819fca
DIFF: https://github.com/llvm/llvm-project/commit/3f59734e0c25ffcd8b522d2ccd8484941a819fca.diff

LOG: [mlir][aarch64] Disable bf16 tests on AArch64

This patch disables 2 bf16 tests that are currently not supported on
AArch64. I've triaged these failures and opened [1] to track this. I
don't have a simple reproducer for dense_output_bf16.mlir, but it's
rather clear that both tests fail due to missing support for `bfloat`
operations in the AArch64 backend.

I'm not sure what the path forward to enable these tests on AArch64
should be. I think that there are two options:
  * AArch64 backened gains capability to legalize these nodes containing
    `bfloat` operands, or
  * MLIR (similarly to Clang) is taught not to emit such nodes in the
    first place.

[1] https://github.com/llvm/llvm-project/issues/58465

Differential Revision: https://reviews.llvm.org/D136273

Added: 
    

Modified: 
    mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir
    mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_bf16.mlir

Removed: 
    


################################################################################
diff  --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir
index e96295b5e092a..c608590c7962e 100644
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir
@@ -4,6 +4,8 @@
 // RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // RUN: FileCheck %s
 
+// UNSUPPORTED: aarch64
+
 #SparseVector = #sparse_tensor.encoding<{dimLevelType = ["compressed"]}>
 #DenseVector = #sparse_tensor.encoding<{dimLevelType = ["dense"]}>
 

diff  --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_bf16.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_bf16.mlir
index 9d05359e96f70..47be829e87555 100644
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_bf16.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_sum_bf16.mlir
@@ -4,6 +4,8 @@
 // RUN:  -shared-libs=%mlir_lib_dir/libmlir_c_runner_utils%shlibext | \
 // RUN: FileCheck %s
 
+// UNSUPPORTED: aarch64
+
 !Filename = !llvm.ptr<i8>
 
 #SparseMatrix = #sparse_tensor.encoding<{