diff options
author | Vidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com> | 2019-11-04 14:42:08 +0000 |
---|---|---|
committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2019-11-14 16:25:06 +0000 |
commit | 951b8a4c01de2810349b6f16cf9bbba7578484fa (patch) | |
tree | 8b3ab1c04279da7be3afd6632a9894b6197c1e1b /arm_compute/core/Types.h | |
parent | cd4e9abf7a165f15ccd10ac4541365d4f8a6db19 (diff) | |
download | ComputeLibrary-951b8a4c01de2810349b6f16cf9bbba7578484fa.tar.gz |
COMPMID-2309 : CLConvolutionLayer: support QUANT8_SYMM_PER_CHANNEL filters
Change-Id: I16f6758b768ede404a064db057302ded706e1e8a
Signed-off-by: Vidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com>
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2215
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/Types.h')
-rw-r--r-- | arm_compute/core/Types.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/arm_compute/core/Types.h b/arm_compute/core/Types.h index 851292f1e1..38d78971ef 100644 --- a/arm_compute/core/Types.h +++ b/arm_compute/core/Types.h @@ -1883,6 +1883,7 @@ struct GEMMLowpOutputStageInfo int gemmlowp_max_bound{ 0 }; /**< GEMMLowp max value used to saturate down the output result before converting back to QASYMM8 */ std::vector<int32_t> gemmlowp_multipliers{}; /**< GEMMLowp output stage multiplier used for quantizing to QASYMM8 */ std::vector<int32_t> gemmlowp_shifts{}; /**< GEMMLowp output stage multiplier used for quantizing to QASYMM8 */ + bool is_quantized_per_channel{ false }; /**< GEMMLowp quantized per-channel flag */ }; /** GEMM LHS (Left Hand Side) matrix information */ |