COMPMID-713: Address failures in OCLGrind for CLDirectConvolution

-Changes way of clamping in the kernel side.
-Fills padding with quantized values

Change-Id: I94d17c341fd637fbb24390722162b551b62d16cb
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/111114
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>

1 files changed, 1 insertions, 2 deletions

diff --git a/tests/validation/CPP/ConvolutionLayer.cpp b/tests/validation/CPP/ConvolutionLayer.cpp
index a767912879..3884a930a2 100644
--- a/tests/validation/CPP/ConvolutionLayer.cpp
+++ b/tests/validation/CPP/ConvolutionLayer.cpp
@@ -210,8 +210,7 @@ void convolution3d(const SimpleTensor<uint8_t> &in, const SimpleTensor<uint8_t>
 
     acc = asymm_rounding_divide_by_pow2(asymm_int_mult(acc, output_multiplier), output_shift);
     acc += output_offset;
-    acc = std::max<int32_t>(acc, 0);
-    acc = std::min<int32_t>(acc, 255);
+    acc = clamp<int32_t>(acc, 0, 255);
 
     // Store the result
     *out_ptr = acc;