COMPMID-706 - Add GEMMLowp output stage for scaling by a fixed point number

DoD:
- Implement NEON kernel for quantizing down the gemmlowp result. The
  result should be scaled by a fixedpoint number
- Implement OpenCL kernel for quantizing down the gemmlowp result. The
  result should be scaled by a fixedpoint number
- Add test for validating the result

Required for:
- Integration of GEMMLowp in Android NN
- Convolution quantized
- Fully connected quantized

Change-Id: Ia963d25d695471e963961fb49a5600e78374ac4f
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/110981
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>

1 files changed, 14 insertions, 0 deletions

diff --git a/src/runtime/NEON/functions/NEGEMMLowpOutputStage.cpp b/src/runtime/NEON/functions/NEGEMMLowpOutputStage.cpp
index ed51291e95..53e5ae2f5a 100644
--- a/src/runtime/NEON/functions/NEGEMMLowpOutputStage.cpp
+++ b/src/runtime/NEON/functions/NEGEMMLowpOutputStage.cpp
@@ -24,6 +24,7 @@
 #include "arm_compute/runtime/NEON/functions/NEGEMMLowpOutputStage.h"
 
 #include "arm_compute/core/ITensor.h"
+#include "arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h"
 #include "arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleKernel.h"
 #include "support/ToolchainSupport.h"
 
@@ -39,4 +40,17 @@ void NEGEMMLowpQuantizeDownInt32ToUint8Scale::configure(const ITensor *input, co
 Error NEGEMMLowpQuantizeDownInt32ToUint8Scale::validate(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, int min, int max)
 {
     return NEGEMMLowpQuantizeDownInt32ToUint8ScaleKernel::validate(input, bias, output, min, max);
+}
+
+void NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint::configure(const ITensor *input, const ITensor *bias, ITensor *output, int result_fixedpoint_multiplier, int result_shift,
+                                                                    int result_offset_after_shift, int min, int max)
+{
+    auto k = arm_compute::support::cpp14::make_unique<NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel>();
+    k->configure(input, bias, output, result_fixedpoint_multiplier, result_shift, result_offset_after_shift, min, max);
+    _kernel = std::move(k);
+}
+
+Error NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint::validate(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, int min, int max)
+{
+    return NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel::validate(input, bias, output, min, max);
 }
\ No newline at end of file