Improve start-up timer for GeMM (floating-point):

 - Pass M,N,K at runtime as kernel parameters
 - Add a guard macro to compile only kernel of interest
 - Move reshpaing kernels to gemm_utils.cl
 - Remove the fallback reshaping kernel with Y-Padding support

Resolves: COMPMID-4888
Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com>
Change-Id: Ida3851326f0b77e410633271de9ecca106e37931
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6662
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 0 insertions, 1 deletions

diff --git a/src/gpu/cl/operators/ClGemm.h b/src/gpu/cl/operators/ClGemm.h
index e084e53fe4..3c0cad3ca4 100644
--- a/src/gpu/cl/operators/ClGemm.h
+++ b/src/gpu/cl/operators/ClGemm.h
@@ -121,7 +121,6 @@ private:
     std::unique_ptr<kernels::ClGemmMatrixMultiplyNativeKernel>          _mm_native_kernel;
     std::unique_ptr<kernels::ClGemmMatrixMultiplyReshapedKernel>        _mm_reshaped_kernel;
     std::unique_ptr<kernels::ClGemmMatrixMultiplyReshapedOnlyRhsKernel> _mm_reshaped_only_rhs_kernel;
-    std::unique_ptr<kernels::ClGemmMatrixMultiplyReshapedOnlyRhsKernel> _mm_reshaped_only_rhs_fallback_kernel;
     TensorInfo                                                          _tmp_a;
     TensorInfo                                                          _tmp_b;
     bool                                                                _reshape_b_only_on_first_run;