commit 296580423e262c8914ebf50b378730ed47c0b323
author Sadik Armagan <sadik.armagan@arm.com> Mon May 11 10:35:08 2020 +0100
committer Michele Di Giorgio <michele.digiorgio@arm.com> Tue May 12 11:31:16 2020 +0000
tree 564f236fcf183c46c21aa02f3e6b047710fa8aed
parent 6e10aa395e81b83edb3437191acd7abe1639c7dc

IVGCVSW-4744 CTS: RandomGraphTest LargeGraph failures in CpuAcc HAL 1.2 and 1.3

* Retain data layout for SpaceToBatchLayerKernel and BatchToSpaceLayerKernel

Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I5bd0c3ca90a4964eda9f838c97c784aced0f4579
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3166
Reviewed-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

arm_compute/core/NEON/kernels/NEBatchToSpaceLayerKernel.h

diff --git a/arm_compute/core/NEON/kernels/NEBatchToSpaceLayerKernel.h b/arm_compute/core/NEON/kernels/NEBatchToSpaceLayerKernel.h
index e9bbf4e..61e47b0 100644
--- a/arm_compute/core/NEON/kernels/NEBatchToSpaceLayerKernel.h
+++ b/arm_compute/core/NEON/kernels/NEBatchToSpaceLayerKernel.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019 ARM Limited.
+ * Copyright (c) 2019-2020 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -92,6 +92,7 @@
     const ITensor *_input;       /**< Source tensor */
     const ITensor *_block_shape; /**< Block shape tensor */
     ITensor       *_output;      /**< Destination tensor */
+    DataLayout     _data_layout; /**< Data layout to  be used at run-time */
 
     int32_t _block_shape_x;
     int32_t _block_shape_y;