commit 538a076aae14dbc1940c52057e135f8a1872aa11
author Giorgio Arena <giorgio.arena@arm.com> Fri May 14 16:38:43 2021 +0100
committer Georgios Pinitas <georgios.pinitas@arm.com> Mon May 17 09:05:30 2021 +0000
tree 3eadacd0beb21d39eed87c18d4f63f255c785ae2
parent ed4b8a07e67c7802207c8954a88ad7a91aec79e0

Fix oclgrind error on CLGEMMLowp reshaped only RHS quantized per channel

Fix corner case in which the quantization is per channel and OFM == 1
The function can safely set the per_channel quantization flag to false since there is only one output channel
This way, the kernel will avoid adding useless padding to the output multipliers and shifts

Resolve COMPMID-4384

Change-Id: Ic03452bfaf52d1be536cd371721adedd2e580a08
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5648
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>

src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp

diff --git a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp
index d39900a..37c1100 100644
--- a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp
@@ -256,7 +256,7 @@
             window_changed = window_changed || update_window_and_padding(win_out, bias_access);
         }
 
-        if(output_multipliers != nullptr && output_multipliers->dimension(0) > 1)
+        if(output_multipliers != nullptr && output_stage.is_quantized_per_channel)
         {
             AccessWindowHorizontal output_multipliers_access(output_multipliers, 0, num_elems_processed_per_iteration_x);
             AccessWindowHorizontal output_shifts_access(output_shifts, 0, num_elems_processed_per_iteration_x);