COMPMID-1413 - Improve the performance of GEMMLowp with 8 bit dot product on OpenCL

COMPMID-1424 - Add dot product support for CLDepthwise QASYMM8 3x3 NHWC non-unit stride

With this patch we are able to improve the performance of MobileNet v1-qasymm8 by 37 %
Tried to use the dot product instruction in CLDepthwise QASYMM8 3x3 NHWC non-unit stride
but I have not seen any benefit (maybe because we have few arithemtic operation and we
do not have more load instructions). However Depthwise convolution has been improved by
30%

Change-Id: Id768a99c2e53a04276707e427af5d0ec93419ada
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/155082
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>

1 files changed, 4 insertions, 4 deletions

diff --git a/src/runtime/CL/functions/CLGEMMLowpOutputStage.cpp b/src/runtime/CL/functions/CLGEMMLowpOutputStage.cpp
index f5dc655776..f1c24626dc 100644
--- a/src/runtime/CL/functions/CLGEMMLowpOutputStage.cpp
+++ b/src/runtime/CL/functions/CLGEMMLowpOutputStage.cpp
@@ -45,17 +45,17 @@ Status CLGEMMLowpQuantizeDownInt32ToUint8Scale::validate(const ITensorInfo *inpu
 
 void CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint::configure(const ICLTensor *input, const ICLTensor *bias, ICLTensor *output,
                                                                     int result_fixedpoint_multiplier, int result_shift, int result_offset_after_shift,
-                                                                    int min, int max, unsigned int output_3d_depth)
+                                                                    int min, int max)
 {
     auto k = arm_compute::support::cpp14::make_unique<CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel>();
-    k->configure(input, bias, output, result_fixedpoint_multiplier, result_shift, result_offset_after_shift, min, max, output_3d_depth);
+    k->configure(input, bias, output, result_fixedpoint_multiplier, result_shift, result_offset_after_shift, min, max);
     _kernel = std::move(k);
 }
 
 Status CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint::validate(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output,
-                                                                     int min, int max, unsigned int output_3d_depth)
+                                                                     int min, int max)
 {
-    return CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::validate(input, bias, output, min, max, output_3d_depth);
+    return CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::validate(input, bias, output, min, max);
 }
 
 void CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFloat::configure(const ICLTensor *input, const ICLTensor *bias, ICLTensor *output,