COMPMID-792 - Re-enabled Winograd on NEON in all graph examples.

Since now the input transform can be multi-threaded, I re-ebaled Winograd in all graph examples

Change-Id: I39ef78243bb47fdae135e18dcae2102af0675b3b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/131048
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>

7 files changed, 19 insertions, 32 deletions

diff --git a/examples/graph_alexnet.cpp b/examples/graph_alexnet.cpp
index b97ca54c78..ffcd8b8411 100644
--- a/examples/graph_alexnet.cpp
+++ b/examples/graph_alexnet.cpp
@@ -56,10 +56,9 @@ public:
         const int target      = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
         Target    target_hint = set_target_hint(target);
 
-        // TODO (geopin01) : Get GPU target somehow and set gemm also for midgard ?
         const bool        is_neon              = (target_hint == Target::NEON);
         ConvolutionMethod convolution_5x5_hint = is_neon ? ConvolutionMethod::GEMM : ConvolutionMethod::DIRECT;
-        ConvolutionMethod convolution_3x3_hint = is_neon ? ConvolutionMethod::GEMM : ConvolutionMethod::DEFAULT;
+        ConvolutionMethod convolution_3x3_hint = ConvolutionMethod::DEFAULT;
         FastMathHint      fast_math_hint       = FastMathHint::DISABLED;
 
         // Parse arguments
diff --git a/examples/graph_googlenet.cpp b/examples/graph_googlenet.cpp
index bac3c7c6d5..a47fc9d588 100644
--- a/examples/graph_googlenet.cpp
+++ b/examples/graph_googlenet.cpp
@@ -52,10 +52,9 @@ public:
         std::unique_ptr<IPreprocessor> preprocessor = arm_compute::support::cpp14::make_unique<CaffePreproccessor>(mean_rgb);
 
         // Set target. 0 (NEON), 1 (OpenCL), 2 (OpenCL with Tuner). By default it is NEON
-        const int         target           = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
-        Target            target_hint      = set_target_hint(target);
-        ConvolutionMethod convolution_hint = target_hint == Target::NEON ? ConvolutionMethod::GEMM : ConvolutionMethod::DEFAULT;
-        FastMathHint      fast_math_hint   = FastMathHint::DISABLED;
+        const int    target         = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
+        Target       target_hint    = set_target_hint(target);
+        FastMathHint fast_math_hint = FastMathHint::DISABLED;
 
         // Parse arguments
         if(argc < 2)
@@ -107,7 +106,6 @@ public:
                   get_weights_accessor(data_path, "/cnn_data/googlenet_model/conv1/conv1_7x7_s2_w.npy"),
                   get_weights_accessor(data_path, "/cnn_data/googlenet_model/conv1/conv1_7x7_s2_b.npy"),
                   PadStrideInfo(2, 2, 3, 3))
-              << convolution_hint
               << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
               << PoolingLayer(PoolingLayerInfo(PoolingType::MAX, 3, PadStrideInfo(2, 2, 0, 0, DimensionRoundingType::CEIL)))
               << NormalizationLayer(NormalizationLayerInfo(NormType::CROSS_MAP, 5, 0.0001f, 0.75f))
diff --git a/examples/graph_inception_v3.cpp b/examples/graph_inception_v3.cpp
index 8e30fd97f2..1d4eb53233 100644
--- a/examples/graph_inception_v3.cpp
+++ b/examples/graph_inception_v3.cpp
@@ -51,10 +51,9 @@ public:
         std::unique_ptr<IPreprocessor> preprocessor = arm_compute::support::cpp14::make_unique<TFPreproccessor>();
 
         // Set target. 0 (NEON), 1 (OpenCL), 2 (OpenCL with Tuner). By default it is NEON
-        const int         target           = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
-        Target            target_hint      = set_target_hint(target);
-        ConvolutionMethod convolution_hint = target_hint == Target::NEON ? ConvolutionMethod::GEMM : ConvolutionMethod::DEFAULT;
-        FastMathHint      fast_math_hint   = FastMathHint::DISABLED;
+        const int    target         = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
+        Target       target_hint    = set_target_hint(target);
+        FastMathHint fast_math_hint = FastMathHint::DISABLED;
 
         // Parse arguments
         if(argc < 2)
@@ -111,7 +110,6 @@ public:
                                          get_random_accessor(1.f, 1.f), get_weights_accessor(data_path,
                                                                                              "/cnn_data/inceptionv3_model/Conv2d_1a_3x3_BatchNorm_beta.npy"),
                                          0.001f)
-              << convolution_hint
               << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
               << ConvolutionLayer(3U, 3U, 32U,
                                   get_weights_accessor(data_path, "/cnn_data/inceptionv3_model/Conv2d_2a_3x3_weights.npy"),
diff --git a/examples/graph_inception_v4.cpp b/examples/graph_inception_v4.cpp
index 827370ec5e..ed95baa99e 100644
--- a/examples/graph_inception_v4.cpp
+++ b/examples/graph_inception_v4.cpp
@@ -54,10 +54,9 @@ public:
         std::unique_ptr<IPreprocessor> preprocessor = arm_compute::support::cpp14::make_unique<TFPreproccessor>();
 
         // Set target. 0 (NEON), 1 (OpenCL). By default it is NEON
-        const int         target           = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
-        Target            target_hint      = set_target_hint(target);
-        ConvolutionMethod convolution_hint = target_hint == Target::NEON ? ConvolutionMethod::GEMM : ConvolutionMethod::DEFAULT;
-        FastMathHint      fast_math_hint   = FastMathHint::DISABLED;
+        const int    target         = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
+        Target       target_hint    = set_target_hint(target);
+        FastMathHint fast_math_hint = FastMathHint::DISABLED;
 
         // Parse arguments
         if(argc < 2)
@@ -114,7 +113,6 @@ public:
                                          get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_1a_3x3_BatchNorm_beta.npy"),
                                          0.001f)
               << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
-              << convolution_hint
               // Conv2d_2a_3x3
               << ConvolutionLayer(3U, 3U, 32U,
                                   get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_2a_3x3_weights.npy"),
diff --git a/examples/graph_resnet50.cpp b/examples/graph_resnet50.cpp
index 6fac372550..7332bb8b15 100644
--- a/examples/graph_resnet50.cpp
+++ b/examples/graph_resnet50.cpp
@@ -52,10 +52,9 @@ public:
                                                                                                                    false /* Do not convert to BGR */);
 
         // Set target. 0 (NEON), 1 (OpenCL), 2 (OpenCL with Tuner). By default it is NEON
-        const int         target           = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
-        Target            target_hint      = set_target_hint(target);
-        ConvolutionMethod convolution_hint = target_hint == Target::NEON ? ConvolutionMethod::GEMM : ConvolutionMethod::DEFAULT;
-        FastMathHint      fast_math_hint   = FastMathHint::DISABLED;
+        const int    target         = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
+        Target       target_hint    = set_target_hint(target);
+        FastMathHint fast_math_hint = FastMathHint::DISABLED;
 
         // Parse arguments
         if(argc < 2)
@@ -108,7 +107,6 @@ public:
                   std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr),
                   PadStrideInfo(2, 2, 3, 3))
               .set_name("conv1/convolution")
-              << convolution_hint
               << BatchNormalizationLayer(
                   get_weights_accessor(data_path, "/cnn_data/resnet50_model/conv1_BatchNorm_moving_mean.npy"),
                   get_weights_accessor(data_path, "/cnn_data/resnet50_model/conv1_BatchNorm_moving_variance.npy"),
diff --git a/examples/graph_squeezenet.cpp b/examples/graph_squeezenet.cpp
index 2627c96774..4d7bcf1ca8 100644
--- a/examples/graph_squeezenet.cpp
+++ b/examples/graph_squeezenet.cpp
@@ -53,10 +53,9 @@ public:
         std::unique_ptr<IPreprocessor> preprocessor = arm_compute::support::cpp14::make_unique<CaffePreproccessor>(mean_rgb);
 
         // Set target. 0 (NEON), 1 (OpenCL), 2 (OpenCL with Tuner). By default it is NEON
-        const int         target           = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
-        Target            target_hint      = set_target_hint(target);
-        ConvolutionMethod convolution_hint = target_hint == Target::NEON ? ConvolutionMethod::GEMM : ConvolutionMethod::DEFAULT;
-        FastMathHint      fast_math_hint   = FastMathHint::DISABLED;
+        const int    target         = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
+        Target       target_hint    = set_target_hint(target);
+        FastMathHint fast_math_hint = FastMathHint::DISABLED;
 
         // Parse arguments
         if(argc < 2)
@@ -110,7 +109,6 @@ public:
                   PadStrideInfo(2, 2, 0, 0))
               << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
               << PoolingLayer(PoolingLayerInfo(PoolingType::MAX, 3, PadStrideInfo(2, 2, 0, 0, DimensionRoundingType::CEIL)))
-              << convolution_hint
               << ConvolutionLayer(
                   1U, 1U, 16U,
                   get_weights_accessor(data_path, "/cnn_data/squeezenet_v1.0_model/fire2_squeeze1x1_w.npy"),
diff --git a/examples/graph_squeezenet_v1_1.cpp b/examples/graph_squeezenet_v1_1.cpp
index c4a5433352..f5fede2f70 100644
--- a/examples/graph_squeezenet_v1_1.cpp
+++ b/examples/graph_squeezenet_v1_1.cpp
@@ -56,10 +56,9 @@ public:
         std::unique_ptr<IPreprocessor> preprocessor = arm_compute::support::cpp14::make_unique<CaffePreproccessor>(mean_rgb);
 
         // Set target. 0 (NEON), 1 (OpenCL), 2 (OpenCL with Tuner). By default it is NEON
-        const int         target           = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
-        Target            target_hint      = set_target_hint(target);
-        ConvolutionMethod convolution_hint = target_hint == Target::NEON ? ConvolutionMethod::GEMM : ConvolutionMethod::DEFAULT;
-        FastMathHint      fast_math_hint   = FastMathHint::DISABLED;
+        const int    target         = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
+        Target       target_hint    = set_target_hint(target);
+        FastMathHint fast_math_hint = FastMathHint::DISABLED;
 
         // Parse arguments
         if(argc < 2)
@@ -112,7 +111,6 @@ public:
                   get_weights_accessor(data_path, "/cnn_data/squeezenet_v1_1_model/conv1_w.npy"),
                   get_weights_accessor(data_path, "/cnn_data/squeezenet_v1_1_model/conv1_b.npy"),
                   PadStrideInfo(2, 2, 0, 0))
-              << convolution_hint
               << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
               << PoolingLayer(PoolingLayerInfo(PoolingType::MAX, 3, PadStrideInfo(2, 2, 0, 0, DimensionRoundingType::CEIL)))
               << ConvolutionMethod::DEFAULT