Optimize CL and Neon Winograd tests

Several test optimizations have been introduced into Winograd tests for Gpu and Cpu backends. The testing strategy has been detailed as a comment header in the test design files.

In summary
    - Very large shapes in the nightly are made smaller
    - If the underlying kernel is the same for different data types, we only need to stress some key aspects of the kernels (e.g. read/write lengths in case of fp32/fp16).
    - In case the underlying kernel is the same (OpenCL), Fp16 is tested on a subset of the shapes
    - In Cpu, there is no need to test every combination for both NCHW and NHWC as we just permute the inputs and use NHWC kernels anyways
    - All activations does not need to be tested for each and every shape

Resolves: COMPMID-6464
Change-Id: Ie25fded85c65b9c7386dc21b23f9b695b1e77b07
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10393
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 146 insertions, 65 deletions

diff --git a/tests/datasets/LargeConvolutionLayerDataset.h b/tests/datasets/LargeConvolutionLayerDataset.h
index 1cffc9a221..72f73ba6d9 100644
--- a/tests/datasets/LargeConvolutionLayerDataset.h
+++ b/tests/datasets/LargeConvolutionLayerDataset.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2020 Arm Limited.
+ * Copyright (c) 2017-2020, 2023 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_TEST_LARGE_CONVOLUTION_LAYER_DATASET
-#define ARM_COMPUTE_TEST_LARGE_CONVOLUTION_LAYER_DATASET
+#ifndef ACL_TESTS_DATASETS_LARGECONVOLUTIONLAYERDATASET_H
+#define ACL_TESTS_DATASETS_LARGECONVOLUTIONLAYERDATASET_H
 
 #include "tests/datasets/ConvolutionLayerDataset.h"
 
@@ -44,18 +44,31 @@ public:
     {
         // Kernel size 3
         // Batch size 1
-        add_config(TensorShape(224U, 222U, 64U), TensorShape(3U, 3U, 64U, 64U), TensorShape(64U), TensorShape(224U, 222U, 64U), PadStrideInfo(1, 1, 1, 1));
-        add_config(TensorShape(112U, 113U, 64U), TensorShape(3U, 3U, 64U, 128U), TensorShape(128U), TensorShape(112U, 113U, 128U), PadStrideInfo(1, 1, 1, 1));
-        add_config(TensorShape(112U, 112U, 128U), TensorShape(3U, 3U, 128U, 129U), TensorShape(129U), TensorShape(112U, 112U, 129U), PadStrideInfo(1, 1, 1, 1));
-        add_config(TensorShape(53U, 56U, 125U), TensorShape(3U, 3U, 125U, 256U), TensorShape(256U), TensorShape(51U, 54U, 256U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(56U, 56U, 256U), TensorShape(3U, 3U, 256U, 256U), TensorShape(256U), TensorShape(54U, 54U, 256U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(28U, 28U, 257U), TensorShape(3U, 3U, 257U, 512U), TensorShape(512U), TensorShape(28U, 28U, 512U), PadStrideInfo(1, 1, 1, 1));
-        add_config(TensorShape(28U, 28U, 512U), TensorShape(3U, 3U, 512U, 512U), TensorShape(512U), TensorShape(28U, 28U, 512U), PadStrideInfo(1, 1, 1, 1));
-        add_config(TensorShape(14U, 14U, 512U), TensorShape(3U, 3U, 512U, 512U), TensorShape(512U), TensorShape(12U, 12U, 512U), PadStrideInfo(1, 1, 0, 0));
-        // Batch size 3, 2 and 4
-        add_config(TensorShape(224U, 222U, 64U, 3U), TensorShape(3U, 3U, 64U, 64U), TensorShape(64U), TensorShape(224U, 222U, 64U, 3U), PadStrideInfo(1, 1, 1, 1));
-        add_config(TensorShape(112U, 113U, 64U, 2U), TensorShape(3U, 3U, 64U, 128U), TensorShape(128U), TensorShape(110U, 111U, 128U, 2U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(111U, 112U, 127U, 4U), TensorShape(3U, 3U, 127U, 128U), TensorShape(128U), TensorShape(111U, 112U, 128U, 4U), PadStrideInfo(1, 1, 1, 1));
+        add_config(TensorShape(224U, 222U, 32U), TensorShape(3U, 3U, 32U, 32U), TensorShape(32U), TensorShape(224U, 222U, 32U), PadStrideInfo(1, 1, 1, 1));
+        add_config(TensorShape(112U, 113U, 32U), TensorShape(3U, 3U, 32U, 64U), TensorShape(64U), TensorShape(112U, 113U, 64U), PadStrideInfo(1, 1, 1, 1));
+        add_config(TensorShape(112U, 112U, 64U), TensorShape(3U, 3U, 64U, 129U), TensorShape(129U), TensorShape(112U, 112U, 129U), PadStrideInfo(1, 1, 1, 1));
+        add_config(TensorShape(53U, 56U, 125U), TensorShape(3U, 3U, 125U, 128U), TensorShape(128U), TensorShape(51U, 54U, 128U), PadStrideInfo(1, 1, 0, 0));
+        add_config(TensorShape(56U, 56U, 128U), TensorShape(3U, 3U, 128U, 128U), TensorShape(128U), TensorShape(54U, 54U, 128U), PadStrideInfo(1, 1, 0, 0));
+        add_config(TensorShape(28U, 28U, 257U), TensorShape(3U, 3U, 257U, 128U), TensorShape(128U), TensorShape(28U, 28U, 128U), PadStrideInfo(1, 1, 1, 1));
+
+        // Batch > 1
+        add_config(TensorShape(111U, 112U, 127U, 4U), TensorShape(3U, 3U, 127U, 64U), TensorShape(64U), TensorShape(111U, 112U, 64U, 4U), PadStrideInfo(1, 1, 1, 1));
+    }
+};
+
+class LargeWinogradConvolutionLayer3x3DatasetFp16Subset final : public ConvolutionLayerDataset
+{
+public:
+    LargeWinogradConvolutionLayer3x3DatasetFp16Subset()
+    {
+        // Kernel size 3
+        // Batch size 1
+        add_config(TensorShape(224U, 222U, 32U), TensorShape(3U, 3U, 32U, 32U), TensorShape(32U), TensorShape(224U, 222U, 32U), PadStrideInfo(1, 1, 1, 1));
+        add_config(TensorShape(112U, 112U, 64U), TensorShape(3U, 3U, 64U, 129U), TensorShape(129U), TensorShape(112U, 112U, 129U), PadStrideInfo(1, 1, 1, 1));
+        add_config(TensorShape(56U, 56U, 128U), TensorShape(3U, 3U, 128U, 128U), TensorShape(128U), TensorShape(54U, 54U, 128U), PadStrideInfo(1, 1, 0, 0));
+
+        // Batch > 1
+        add_config(TensorShape(111U, 112U, 127U, 4U), TensorShape(3U, 3U, 127U, 64U), TensorShape(64U), TensorShape(111U, 112U, 64U, 4U), PadStrideInfo(1, 1, 1, 1));
     }
 };
 
@@ -66,18 +79,31 @@ public:
     {
         // Kernel size 3
         // Batch size 1
-        add_config(TensorShape(224U, 222U, 64U), TensorShape(3U, 1U, 64U, 64U), TensorShape(64U), TensorShape(224U, 222U, 64U), PadStrideInfo(1, 1, 1, 0));
-        add_config(TensorShape(112U, 113U, 64U), TensorShape(3U, 1U, 64U, 128U), TensorShape(128U), TensorShape(112U, 113U, 128U), PadStrideInfo(1, 1, 1, 0));
-        add_config(TensorShape(112U, 112U, 128U), TensorShape(3U, 1U, 128U, 129U), TensorShape(129U), TensorShape(112U, 112U, 129U), PadStrideInfo(1, 1, 1, 0));
-        add_config(TensorShape(53U, 56U, 125U), TensorShape(3U, 1U, 125U, 256U), TensorShape(256U), TensorShape(51U, 56U, 256U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(56U, 56U, 256U), TensorShape(3U, 1U, 256U, 256U), TensorShape(256U), TensorShape(56U, 56U, 256U), PadStrideInfo(1, 1, 1, 0));
-        add_config(TensorShape(28U, 28U, 257U), TensorShape(3U, 1U, 257U, 512U), TensorShape(512U), TensorShape(26U, 28U, 512U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(28U, 28U, 512U), TensorShape(3U, 1U, 512U, 512U), TensorShape(512U), TensorShape(28U, 28U, 512U), PadStrideInfo(1, 1, 1, 0));
-        add_config(TensorShape(14U, 14U, 512U), TensorShape(3U, 1U, 512U, 512U), TensorShape(512U), TensorShape(12U, 14U, 512U), PadStrideInfo(1, 1, 0, 0));
-        // Batch size 3, 2 and 4
-        add_config(TensorShape(224U, 222U, 64U, 3U), TensorShape(3U, 1U, 64U, 64U), TensorShape(64U), TensorShape(224U, 222U, 64U, 3U), PadStrideInfo(1, 1, 1, 0));
-        add_config(TensorShape(112U, 113U, 64U, 2U), TensorShape(3U, 1U, 64U, 128U), TensorShape(128U), TensorShape(110U, 113U, 128U, 2U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(111U, 112U, 127U, 4U), TensorShape(3U, 1U, 127U, 128U), TensorShape(128U), TensorShape(111U, 112U, 128U, 4U), PadStrideInfo(1, 1, 1, 0));
+        add_config(TensorShape(224U, 222U, 32U), TensorShape(3U, 1U, 32U, 32U), TensorShape(32U), TensorShape(224U, 222U, 32U), PadStrideInfo(1, 1, 1, 0));
+        add_config(TensorShape(112U, 113U, 32U), TensorShape(3U, 1U, 32U, 64U), TensorShape(64U), TensorShape(112U, 113U, 64U), PadStrideInfo(1, 1, 1, 0));
+        add_config(TensorShape(112U, 112U, 64U), TensorShape(3U, 1U, 64U, 129U), TensorShape(129U), TensorShape(112U, 112U, 129U), PadStrideInfo(1, 1, 1, 0));
+        add_config(TensorShape(53U, 56U, 125U), TensorShape(3U, 1U, 125U, 128U), TensorShape(128U), TensorShape(51U, 56U, 128U), PadStrideInfo(1, 1, 0, 0));
+        add_config(TensorShape(56U, 56U, 128U), TensorShape(3U, 1U, 128U, 128U), TensorShape(128U), TensorShape(56U, 56U, 128U), PadStrideInfo(1, 1, 1, 0));
+        add_config(TensorShape(28U, 28U, 257U), TensorShape(3U, 1U, 257U, 128U), TensorShape(128U), TensorShape(26U, 28U, 128U), PadStrideInfo(1, 1, 0, 0));
+
+        // Batch > 1
+        add_config(TensorShape(111U, 112U, 127U, 4U), TensorShape(3U, 1U, 127U, 64U), TensorShape(64U), TensorShape(111U, 112U, 64U, 4U), PadStrideInfo(1, 1, 1, 0));
+    }
+};
+
+class LargeWinogradConvolutionLayer3x1DatasetFp16Subset final : public ConvolutionLayerDataset
+{
+public:
+    LargeWinogradConvolutionLayer3x1DatasetFp16Subset()
+    {
+        // Kernel size 3
+        // Batch size 1
+        add_config(TensorShape(112U, 113U, 32U), TensorShape(3U, 1U, 32U, 64U), TensorShape(64U), TensorShape(112U, 113U, 64U), PadStrideInfo(1, 1, 1, 0));
+        add_config(TensorShape(53U, 56U, 125U), TensorShape(3U, 1U, 125U, 128U), TensorShape(128U), TensorShape(51U, 56U, 128U), PadStrideInfo(1, 1, 0, 0));
+        add_config(TensorShape(28U, 28U, 257U), TensorShape(3U, 1U, 257U, 128U), TensorShape(128U), TensorShape(26U, 28U, 128U), PadStrideInfo(1, 1, 0, 0));
+
+        // Batch > 1
+        add_config(TensorShape(111U, 112U, 127U, 4U), TensorShape(3U, 1U, 127U, 64U), TensorShape(64U), TensorShape(111U, 112U, 64U, 4U), PadStrideInfo(1, 1, 1, 0));
     }
 };
 
@@ -88,18 +114,31 @@ public:
     {
         // Kernel size 3
         // Batch size 1
-        add_config(TensorShape(224U, 222U, 64U), TensorShape(1U, 3U, 64U, 64U), TensorShape(64U), TensorShape(224U, 222U, 64U), PadStrideInfo(1, 1, 0, 1));
-        add_config(TensorShape(112U, 113U, 64U), TensorShape(1U, 3U, 64U, 128U), TensorShape(128U), TensorShape(112U, 113U, 128U), PadStrideInfo(1, 1, 0, 1));
-        add_config(TensorShape(112U, 112U, 128U), TensorShape(1U, 3U, 128U, 129U), TensorShape(129U), TensorShape(112U, 110U, 129U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(53U, 56U, 125U), TensorShape(1U, 3U, 125U, 256U), TensorShape(256U), TensorShape(53U, 56U, 256U), PadStrideInfo(1, 1, 0, 1));
-        add_config(TensorShape(56U, 56U, 256U), TensorShape(1U, 3U, 256U, 256U), TensorShape(256U), TensorShape(56U, 54U, 256U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(28U, 28U, 257U), TensorShape(1U, 3U, 257U, 512U), TensorShape(512U), TensorShape(28U, 28U, 512U), PadStrideInfo(1, 1, 0, 1));
-        add_config(TensorShape(28U, 28U, 512U), TensorShape(1U, 3U, 512U, 512U), TensorShape(512U), TensorShape(28U, 28U, 512U), PadStrideInfo(1, 1, 0, 1));
-        add_config(TensorShape(14U, 14U, 512U), TensorShape(1U, 3U, 512U, 512U), TensorShape(512U), TensorShape(14U, 12U, 512U), PadStrideInfo(1, 1, 0, 0));
-        // Batch size 3, 2 and 4
-        add_config(TensorShape(224U, 222U, 64U, 3U), TensorShape(1U, 3U, 64U, 64U), TensorShape(64U), TensorShape(224U, 222U, 64U, 3U), PadStrideInfo(1, 1, 0, 1));
-        add_config(TensorShape(112U, 113U, 64U, 2U), TensorShape(1U, 3U, 64U, 128U), TensorShape(128U), TensorShape(112U, 113U, 128U, 2U), PadStrideInfo(1, 1, 0, 1));
-        add_config(TensorShape(111U, 112U, 127U, 4U), TensorShape(1U, 3U, 127U, 128U), TensorShape(128U), TensorShape(111U, 112U, 128U, 4U), PadStrideInfo(1, 1, 0, 1));
+        add_config(TensorShape(224U, 222U, 32U), TensorShape(1U, 3U, 32U, 32U), TensorShape(32U), TensorShape(224U, 222U, 32U), PadStrideInfo(1, 1, 0, 1));
+        add_config(TensorShape(112U, 113U, 32U), TensorShape(1U, 3U, 32U, 64U), TensorShape(64U), TensorShape(112U, 113U, 64U), PadStrideInfo(1, 1, 0, 1));
+        add_config(TensorShape(112U, 112U, 64U), TensorShape(1U, 3U, 64U, 129U), TensorShape(129U), TensorShape(112U, 110U, 129U), PadStrideInfo(1, 1, 0, 0));
+        add_config(TensorShape(53U, 56U, 125U), TensorShape(1U, 3U, 125U, 128U), TensorShape(128U), TensorShape(53U, 56U, 128U), PadStrideInfo(1, 1, 0, 1));
+        add_config(TensorShape(56U, 56U, 128U), TensorShape(1U, 3U, 128U, 128U), TensorShape(128U), TensorShape(56U, 54U, 128U), PadStrideInfo(1, 1, 0, 0));
+        add_config(TensorShape(28U, 28U, 257U), TensorShape(1U, 3U, 257U, 128U), TensorShape(128U), TensorShape(28U, 28U, 128U), PadStrideInfo(1, 1, 0, 1));
+
+        // Batch > 1
+        add_config(TensorShape(111U, 112U, 127U, 4U), TensorShape(1U, 3U, 127U, 64U), TensorShape(64U), TensorShape(111U, 112U, 64U, 4U), PadStrideInfo(1, 1, 0, 1));
+    }
+};
+
+class LargeWinogradConvolutionLayer1x3DatasetFp16Subset final : public ConvolutionLayerDataset
+{
+public:
+    LargeWinogradConvolutionLayer1x3DatasetFp16Subset()
+    {
+        // Kernel size 3
+        // Batch size 1
+        add_config(TensorShape(112U, 112U, 64U), TensorShape(1U, 3U, 64U, 129U), TensorShape(129U), TensorShape(112U, 110U, 129U), PadStrideInfo(1, 1, 0, 0));
+        add_config(TensorShape(53U, 56U, 125U), TensorShape(1U, 3U, 125U, 128U), TensorShape(128U), TensorShape(53U, 56U, 128U), PadStrideInfo(1, 1, 0, 1));
+        add_config(TensorShape(28U, 28U, 257U), TensorShape(1U, 3U, 257U, 128U), TensorShape(128U), TensorShape(28U, 28U, 128U), PadStrideInfo(1, 1, 0, 1));
+
+        // Batch > 1
+        add_config(TensorShape(111U, 112U, 127U, 4U), TensorShape(1U, 3U, 127U, 64U), TensorShape(64U), TensorShape(111U, 112U, 64U, 4U), PadStrideInfo(1, 1, 0, 1));
     }
 };
 
@@ -110,15 +149,27 @@ public:
     {
         // Kernel size 5
         // Batch size 1
-        add_config(TensorShape(224U, 224U, 3U), TensorShape(5U, 5U, 3U, 64U), TensorShape(64U), TensorShape(220U, 220U, 64U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(123U, 134U, 16U), TensorShape(5U, 5U, 16U, 7U), TensorShape(7U), TensorShape(123U, 134U, 7U), PadStrideInfo(1, 1, 2, 2));
+        add_config(TensorShape(224U, 224U, 3U), TensorShape(5U, 5U, 3U, 32U), TensorShape(32U), TensorShape(220U, 220U, 32U), PadStrideInfo(1, 1, 0, 0));
         add_config(TensorShape(181U, 152U, 42U), TensorShape(5U, 5U, 42U, 100U), TensorShape(100U), TensorShape(177U, 148U, 100U), PadStrideInfo(1, 1, 0, 0));
         add_config(TensorShape(200U, 201U, 24U), TensorShape(5U, 5U, 24U, 61), TensorShape(61U), TensorShape(200U, 201U, 61), PadStrideInfo(1, 1, 2, 2));
 
-        // Batch size 2, 3 and 4
-        add_config(TensorShape(224U, 224U, 3U, 2U), TensorShape(5U, 5U, 3U, 64U), TensorShape(64U), TensorShape(220U, 220U, 64U, 2U), PadStrideInfo(1, 1, 0, 0));
+        // Batch > 1
+        add_config(TensorShape(123U, 134U, 16U, 3U), TensorShape(5U, 5U, 16U, 7U), TensorShape(7U), TensorShape(123U, 134U, 7U, 3U), PadStrideInfo(1, 1, 2, 2));
+    }
+};
+
+class LargeWinogradConvolutionLayer5x5DatasetFp16Subset final : public ConvolutionLayerDataset
+{
+public:
+    LargeWinogradConvolutionLayer5x5DatasetFp16Subset()
+    {
+        // Kernel size 5
+        // Batch size 1
+        add_config(TensorShape(181U, 152U, 42U), TensorShape(5U, 5U, 42U, 100U), TensorShape(100U), TensorShape(177U, 148U, 100U), PadStrideInfo(1, 1, 0, 0));
+        add_config(TensorShape(200U, 201U, 24U), TensorShape(5U, 5U, 24U, 61), TensorShape(61U), TensorShape(200U, 201U, 61), PadStrideInfo(1, 1, 2, 2));
+
+        // Batch > 1
         add_config(TensorShape(123U, 134U, 16U, 3U), TensorShape(5U, 5U, 16U, 7U), TensorShape(7U), TensorShape(123U, 134U, 7U, 3U), PadStrideInfo(1, 1, 2, 2));
-        add_config(TensorShape(181U, 152U, 42U, 4U), TensorShape(5U, 5U, 42U, 100U), TensorShape(100U), TensorShape(177U, 148U, 100U, 4U), PadStrideInfo(1, 1, 0, 0));
     }
 };
 
@@ -128,15 +179,26 @@ public:
     LargeWinogradConvolutionLayer5x1Dataset()
     {
         // Batch size 1
-        add_config(TensorShape(224U, 224U, 3U), TensorShape(5U, 1U, 3U, 64U), TensorShape(64U), TensorShape(224U, 224U, 64U), PadStrideInfo(1, 1, 2, 0));
-        add_config(TensorShape(123U, 134U, 16U), TensorShape(5U, 1U, 16U, 7U), TensorShape(7U), TensorShape(123U, 134U, 7U), PadStrideInfo(1, 1, 2, 0));
+        add_config(TensorShape(224U, 224U, 3U), TensorShape(5U, 1U, 3U, 32U), TensorShape(32U), TensorShape(224U, 224U, 32U), PadStrideInfo(1, 1, 2, 0));
         add_config(TensorShape(181U, 152U, 42U), TensorShape(5U, 1U, 42U, 100U), TensorShape(100U), TensorShape(177U, 152U, 100U), PadStrideInfo(1, 1, 0, 0));
         add_config(TensorShape(200U, 201U, 24U), TensorShape(5U, 1U, 24U, 61), TensorShape(61U), TensorShape(200U, 201U, 61), PadStrideInfo(1, 1, 2, 0));
 
-        // Batch size 2, 3 and 4
-        add_config(TensorShape(224U, 224U, 3U, 2U), TensorShape(5U, 1U, 3U, 64U), TensorShape(64U), TensorShape(224U, 224U, 64U, 2U), PadStrideInfo(1, 1, 2, 0));
+        // Batch > 1
+        add_config(TensorShape(123U, 134U, 16U, 3U), TensorShape(5U, 1U, 16U, 7U), TensorShape(7U), TensorShape(123U, 134U, 7U, 3U), PadStrideInfo(1, 1, 2, 0));
+    }
+};
+
+class LargeWinogradConvolutionLayer5x1DatasetFp16Subset final : public ConvolutionLayerDataset
+{
+public:
+    LargeWinogradConvolutionLayer5x1DatasetFp16Subset()
+    {
+        // Batch size 1
+        add_config(TensorShape(224U, 224U, 3U), TensorShape(5U, 1U, 3U, 32U), TensorShape(32U), TensorShape(224U, 224U, 32U), PadStrideInfo(1, 1, 2, 0));
+        add_config(TensorShape(200U, 201U, 24U), TensorShape(5U, 1U, 24U, 61), TensorShape(61U), TensorShape(200U, 201U, 61), PadStrideInfo(1, 1, 2, 0));
+
+        // Batch > 1
         add_config(TensorShape(123U, 134U, 16U, 3U), TensorShape(5U, 1U, 16U, 7U), TensorShape(7U), TensorShape(123U, 134U, 7U, 3U), PadStrideInfo(1, 1, 2, 0));
-        add_config(TensorShape(181U, 152U, 42U, 4U), TensorShape(5U, 1U, 42U, 100U), TensorShape(100U), TensorShape(177U, 152U, 100U, 4U), PadStrideInfo(1, 1, 0, 0));
     }
 };
 
@@ -146,15 +208,12 @@ public:
     LargeWinogradConvolutionLayer7x1Dataset()
     {
         // Batch size 1
-        add_config(TensorShape(224U, 224U, 3U), TensorShape(7U, 1U, 3U, 64U), TensorShape(64U), TensorShape(218U, 224U, 64U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(123U, 134U, 16U), TensorShape(7U, 1U, 16U, 7U), TensorShape(7U), TensorShape(123U, 134U, 7U), PadStrideInfo(1, 1, 3, 0));
+        add_config(TensorShape(224U, 224U, 3U), TensorShape(7U, 1U, 3U, 32U), TensorShape(32U), TensorShape(218U, 224U, 32U), PadStrideInfo(1, 1, 0, 0));
         add_config(TensorShape(181U, 152U, 42U), TensorShape(7U, 1U, 42U, 100U), TensorShape(100U), TensorShape(175U, 152U, 100U), PadStrideInfo(1, 1, 0, 0));
         add_config(TensorShape(200U, 201U, 24U), TensorShape(7U, 1U, 24U, 61), TensorShape(61U), TensorShape(200U, 201U, 61), PadStrideInfo(1, 1, 3, 0));
 
-        // Batch size 2, 3 and 4
-        add_config(TensorShape(224U, 224U, 3U, 2U), TensorShape(7U, 1U, 3U, 64U), TensorShape(64U), TensorShape(224U, 224U, 64U, 2U), PadStrideInfo(1, 1, 3, 0));
+        // Batch > 1
         add_config(TensorShape(123U, 134U, 16U, 3U), TensorShape(7U, 1U, 16U, 7U), TensorShape(7U), TensorShape(123U, 134U, 7U, 3U), PadStrideInfo(1, 1, 3, 0));
-        add_config(TensorShape(181U, 152U, 42U, 4U), TensorShape(7U, 1U, 42U, 100U), TensorShape(100U), TensorShape(175U, 152U, 100U, 4U), PadStrideInfo(1, 1, 0, 0));
     }
 };
 
@@ -164,15 +223,26 @@ public:
     LargeWinogradConvolutionLayer1x7Dataset()
     {
         // Batch size 1
-        add_config(TensorShape(224U, 224U, 3U), TensorShape(1U, 7U, 3U, 64U), TensorShape(64U), TensorShape(224U, 218U, 64U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(123U, 134U, 16U), TensorShape(1U, 7U, 16U, 7U), TensorShape(7U), TensorShape(123U, 134U, 7U), PadStrideInfo(1, 1, 0, 3));
+        add_config(TensorShape(224U, 224U, 3U), TensorShape(1U, 7U, 3U, 32U), TensorShape(32U), TensorShape(224U, 218U, 32U), PadStrideInfo(1, 1, 0, 0));
+        add_config(TensorShape(181U, 152U, 42U), TensorShape(1U, 7U, 42U, 100U), TensorShape(100U), TensorShape(181U, 146U, 100U), PadStrideInfo(1, 1, 0, 0));
+        add_config(TensorShape(200U, 201U, 24U), TensorShape(1U, 7U, 24U, 61), TensorShape(61U), TensorShape(200U, 201U, 61), PadStrideInfo(1, 1, 0, 3));
+
+        // Batch > 1
+        add_config(TensorShape(123U, 134U, 16U, 3U), TensorShape(1U, 7U, 16U, 7U), TensorShape(7U), TensorShape(123U, 134U, 7U, 3U), PadStrideInfo(1, 1, 0, 3));
+    }
+};
+
+class LargeWinogradConvolutionLayer1x7DatasetFp16Subset final : public ConvolutionLayerDataset
+{
+public:
+    LargeWinogradConvolutionLayer1x7DatasetFp16Subset()
+    {
+        // Batch size 1
         add_config(TensorShape(181U, 152U, 42U), TensorShape(1U, 7U, 42U, 100U), TensorShape(100U), TensorShape(181U, 146U, 100U), PadStrideInfo(1, 1, 0, 0));
         add_config(TensorShape(200U, 201U, 24U), TensorShape(1U, 7U, 24U, 61), TensorShape(61U), TensorShape(200U, 201U, 61), PadStrideInfo(1, 1, 0, 3));
 
-        // Batch size 2, 3 and 4
-        add_config(TensorShape(224U, 224U, 3U, 2U), TensorShape(1U, 7U, 3U, 64U), TensorShape(64U), TensorShape(224U, 224U, 64U, 2U), PadStrideInfo(1, 1, 0, 3));
+        // Batch > 1
         add_config(TensorShape(123U, 134U, 16U, 3U), TensorShape(1U, 7U, 16U, 7U), TensorShape(7U), TensorShape(123U, 134U, 7U, 3U), PadStrideInfo(1, 1, 0, 3));
-        add_config(TensorShape(181U, 152U, 42U, 4U), TensorShape(1U, 7U, 42U, 100U), TensorShape(100U), TensorShape(181U, 146U, 100U, 4U), PadStrideInfo(1, 1, 0, 0));
     }
 };
 
@@ -182,15 +252,26 @@ public:
     LargeWinogradConvolutionLayer1x5Dataset()
     {
         // Batch size 1
-        add_config(TensorShape(224U, 224U, 3U), TensorShape(1U, 5U, 3U, 64U), TensorShape(64U), TensorShape(224U, 224U, 64U), PadStrideInfo(1, 1, 0, 2));
-        add_config(TensorShape(123U, 134U, 16U), TensorShape(1U, 5U, 16U, 7U), TensorShape(7U), TensorShape(123U, 130U, 7U), PadStrideInfo(1, 1, 0, 0));
+        add_config(TensorShape(224U, 224U, 3U), TensorShape(1U, 5U, 3U, 32U), TensorShape(32U), TensorShape(224U, 224U, 32U), PadStrideInfo(1, 1, 0, 2));
         add_config(TensorShape(181U, 152U, 42U), TensorShape(1U, 5U, 42U, 100U), TensorShape(100U), TensorShape(181U, 148U, 100U), PadStrideInfo(1, 1, 0, 0));
         add_config(TensorShape(200U, 201U, 24U), TensorShape(1U, 5U, 24U, 61), TensorShape(61U), TensorShape(200U, 201U, 61), PadStrideInfo(1, 1, 0, 2));
 
-        // Batch size 2, 3 and 4
-        add_config(TensorShape(224U, 224U, 3U, 2U), TensorShape(1U, 5U, 3U, 64U), TensorShape(64U), TensorShape(224U, 224U, 64U, 2U), PadStrideInfo(1, 1, 0, 2));
+        // Batch size > 1
+        add_config(TensorShape(123U, 134U, 16U, 3U), TensorShape(1U, 5U, 16U, 7U), TensorShape(7U), TensorShape(123U, 130U, 7U, 3U), PadStrideInfo(1, 1, 0, 0));
+    }
+};
+
+class LargeWinogradConvolutionLayer1x5DatasetFp16Subset final : public ConvolutionLayerDataset
+{
+public:
+    LargeWinogradConvolutionLayer1x5DatasetFp16Subset()
+    {
+        // Batch size 1
+        add_config(TensorShape(224U, 224U, 3U), TensorShape(1U, 5U, 3U, 32U), TensorShape(32U), TensorShape(224U, 224U, 32U), PadStrideInfo(1, 1, 0, 2));
+        add_config(TensorShape(181U, 152U, 42U), TensorShape(1U, 5U, 42U, 100U), TensorShape(100U), TensorShape(181U, 148U, 100U), PadStrideInfo(1, 1, 0, 0));
+
+        // Batch size > 1
         add_config(TensorShape(123U, 134U, 16U, 3U), TensorShape(1U, 5U, 16U, 7U), TensorShape(7U), TensorShape(123U, 130U, 7U, 3U), PadStrideInfo(1, 1, 0, 0));
-        add_config(TensorShape(181U, 152U, 42U, 4U), TensorShape(1U, 5U, 42U, 100U), TensorShape(100U), TensorShape(181U, 148U, 100U, 4U), PadStrideInfo(1, 1, 0, 0));
     }
 };
 
@@ -233,4 +314,4 @@ public:
 } // namespace datasets
 } // namespace test
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_TEST_LARGE_CONVOLUTION_LAYER_DATASET */
+#endif // ACL_TESTS_DATASETS_LARGECONVOLUTIONLAYERDATASET_H