COMPMID-2452: Dot product optimizations on merge/transforms

-Adds optimized gemm transforms for AArch64.
-Optimized gemm merger to only support alpha==1 and (beta==0 || beta=1) cases

Change-Id: I55793b12a0381f4fd53f521d0e57416809904d96
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2003
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>

1 files changed, 0 insertions, 2 deletions

diff --git a/src/core/NEON/kernels/arm_gemm/gemm_hybrid_quantized.hpp b/src/core/NEON/kernels/arm_gemm/gemm_hybrid_quantized.hpp
index 1bd9126da9..b4edece8d5 100644
--- a/src/core/NEON/kernels/arm_gemm/gemm_hybrid_quantized.hpp
+++ b/src/core/NEON/kernels/arm_gemm/gemm_hybrid_quantized.hpp
@@ -221,7 +221,6 @@ public:
                     compute_row_sums(_qp, _Ksize, (m_end - m_start),
                                      this->_Aptr + (multi * this->_A_multi_stride) + (batch * this->_A_batch_stride) + (m_start * this->_lda), this->_lda,
                                      local_row_sums);
-//                                     row_bias + (multi * _nbatches * _Msize) + (batch * _Msize) + m_start);
                 }
 
                 {
@@ -231,7 +230,6 @@ public:
 
                     requantize_block_32(_qp, (nmax - n0), (m_end - m_start), result_buffer, (nmax - n0),
                                         this->_Cptr + (multi * this->_C_multi_stride) + (batch * this->_C_batch_stride) + (m_start * this->_ldc) + n0, this->_ldc,
-//                                        row_bias + (multi * _nbatches * _Msize) + (batch * _Msize) + m_start, col_bias);
                                         local_row_sums, col_bias + (multi * _Nsize) + n0);
                 }
             } while (p.next_dim0());