COMPMID-3784 Add broadcast support to S32 NEPixelwiseMultiplication
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: Ifae31c74eb46c561225394a387fc15332423bfa9
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4030
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
diff --git a/arm_compute/runtime/NEON/functions/NEPixelWiseMultiplication.h b/arm_compute/runtime/NEON/functions/NEPixelWiseMultiplication.h
index 4ff7f1d..e107298 100644
--- a/arm_compute/runtime/NEON/functions/NEPixelWiseMultiplication.h
+++ b/arm_compute/runtime/NEON/functions/NEPixelWiseMultiplication.h
@@ -42,16 +42,17 @@
*
* Valid configurations (Input1,Input2) -> Output :
*
- * - (U8,U8) -> U8, S16
- * - (U8,S16) -> S16
- * - (S16,U8) -> S16
- * - (S16,S16) -> S16
- * - (S32,S32) -> S32
- * - (F16,F16) -> F16
- * - (F32,F32) -> F32
- * - (QASYMM8,QASYMM8) -> QASYMM8
- * - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
- * - (QSYMM16,QSYMM16) -> QSYMM16, S32
+ * Support: Broadcast? Scale=1/255?
+ * - (U8,U8) -> U8, S16 N Y
+ * - (U8,S16) -> S16 N Y
+ * - (S16,U8) -> S16 N Y
+ * - (S16,S16) -> S16 N Y
+ * - (S32,S32) -> S32 Y N
+ * - (F16,F16) -> F16 N Y
+ * - (F32,F32) -> F32 Y Y
+ * - (QASYMM8,QASYMM8) -> QASYMM8 Y Y
+ * - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED Y Y
+ * - (QSYMM16,QSYMM16) -> QSYMM16, S32 N Y
*
* @note For @p scale equal to 1/255 only round to nearest even (implemented as round half up) is supported.
* For all other scale values only round to zero (implemented as round towards minus infinity) is supported.
@@ -74,16 +75,17 @@
*
* Valid configurations (Input1,Input2) -> Output :
*
- * - (U8,U8) -> U8, S16
- * - (U8,S16) -> S16
- * - (S16,U8) -> S16
- * - (S16,S16) -> S16
- * - (S32,S32) -> S32
- * - (F16,F16) -> F16
- * - (F32,F32) -> F32
- * - (QASYMM8,QASYMM8) -> QASYMM8
- * - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
- * - (QSYMM16,QSYMM16) -> QSYMM16, S32
+ * Support: Broadcast? Scale=1/255?
+ * - (U8,U8) -> U8, S16 N Y
+ * - (U8,S16) -> S16 N Y
+ * - (S16,U8) -> S16 N Y
+ * - (S16,S16) -> S16 N Y
+ * - (S32,S32) -> S32 Y N
+ * - (F16,F16) -> F16 N Y
+ * - (F32,F32) -> F32 Y Y
+ * - (QASYMM8,QASYMM8) -> QASYMM8 Y Y
+ * - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED Y Y
+ * - (QSYMM16,QSYMM16) -> QSYMM16, S32 N Y
*
* @note For @p scale equal to 1/255 only round to nearest even (implemented as round half up) is supported.
* For all other scale values only round to zero (implemented as round towards minus infinity) is supported.