COMPMID-2805: Add QASYMM8_SIGNED support in NEGEMMLowpOutputStage
Add support from requantizing down from S32 to Int8 with fixed point
requantization. This involves the following:
- Compute fixed point multiplication between each entry of input by
result_fixedpoint_multiplier
- Add bias to final result if bias tensor is not a nullptr
- Round to nearest division by a power-of-two using result_shift
- Add offset to each result
- Clamp the value between the specified min and max bounds
- Cast to int8 data type
Change-Id: I641b3fac0833c568d8565ccb859bbc561a24c17d
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2340
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/utils/TypePrinter.h b/utils/TypePrinter.h
index ede2ea4..3f638d7 100644
--- a/utils/TypePrinter.h
+++ b/utils/TypePrinter.h
@@ -628,6 +628,9 @@
case DataType::QASYMM8:
os << "QASYMM8";
break;
+ case DataType::QASYMM8_SIGNED:
+ os << "QASYMM8_SIGNED";
+ break;
case DataType::QSYMM8_PER_CHANNEL:
os << "QSYMM8_PER_CHANNEL";
break;