COMPMID-665 - NEON: Add QASYMM8 in place Activation layer

- Added min and max arguments for QuantizeDownInt32ToUint8Scale in order
  to apply bounded relu

- Added support for int32_t biases

- Extended tests

Change-Id: I015dae17faa7284766b5435ca33bcf593c1b2b69
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/96512
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>

1 files changed, 7 insertions, 0 deletions

diff --git a/arm_compute/core/NEON/kernels/NEGEMMLowpOffsetContributionKernel.h b/arm_compute/core/NEON/kernels/NEGEMMLowpOffsetContributionKernel.h
index 04b84339b0..8c1bae9396 100644
--- a/arm_compute/core/NEON/kernels/NEGEMMLowpOffsetContributionKernel.h
+++ b/arm_compute/core/NEON/kernels/NEGEMMLowpOffsetContributionKernel.h
@@ -35,6 +35,13 @@ class ITensor;
  * This kernel takes a final int32 accumulator value (the output of @NEGEMMLowpMatrixMultiplyKernel),
  * and adds to it the offset contribution of matrix A and matrix B in-place.
  *
+ * The final result is:
+ *
+ * mm_result[i][k] = mm_result[i][k] +
+ *                   (vector_sum_col[k] * a_offset) +
+ *                   (vector_sum_row[i] * b_offset) +
+ *                   (a_offset * b_offset * k)
+ *
  */
 class NEGEMMLowpOffsetContributionKernel : public INEKernel
 {