Update GEMM assembly kernels

- Introduce Fp32 kernels with internal calculations in Bfloat16 when
fast_mode is enabled
- Improve kernel selection heuristics

Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I68a9e7e862b6fd2721b46e0d7cc791091c4ab279
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5965
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 1 insertions, 1 deletions

diff --git a/src/runtime/NEON/functions/NEConvolutionLayer.cpp b/src/runtime/NEON/functions/NEConvolutionLayer.cpp
index 1022e397d0..e88bd3b5d4 100644
--- a/src/runtime/NEON/functions/NEConvolutionLayer.cpp
+++ b/src/runtime/NEON/functions/NEConvolutionLayer.cpp
@@ -67,7 +67,7 @@ void NEConvolutionLayer::configure(ITensor *input, const ITensor *weights, const
         case ConvolutionMethod::GEMM:
         {
             auto f = std::make_unique<NEGEMMConvolutionLayer>(_memory_manager);
-            f->configure(input, weights, biases, output, conv_info, weights_info, dilation, act_info);
+            f->configure(input, weights, biases, output, conv_info, weights_info, dilation, act_info, enable_fast_math);
             _function = std::move(f);
             break;
         }