diff options
author | Manuel Bottini <manuel.bottini@arm.com> | 2019-12-02 16:22:35 +0000 |
---|---|---|
committer | Manuel Bottini <manuel.bottini@arm.com> | 2020-01-14 13:15:11 +0000 |
commit | 959c26d0457deeebf7306b9e4317863f144415b5 (patch) | |
tree | 9a439d27b9985f21b3b1b27db519efe9e928954a /arm_compute/runtime/CL | |
parent | 6427c8233661f81053d1ad486b5914c612cef3d6 (diff) | |
download | ComputeLibrary-959c26d0457deeebf7306b9e4317863f144415b5.tar.gz |
COMPMID-2790: Add support for QASYMM8_SIGNED in CLGEMMLowpMatrixMultiplyCore
Change-Id: Ifdaeb53c512ba697f174649c026075010f54f628
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2472
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Diffstat (limited to 'arm_compute/runtime/CL')
-rw-r--r-- | arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h b/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h index 770ef0b287..66c5e9ee46 100644 --- a/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h +++ b/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2017-2019 ARM Limited. + * Copyright (c) 2017-2020 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -76,10 +76,10 @@ public: * -# Compute the matrix product of the resulting a * b in int32. * -# Quantize to uint8 if gemm_info.gemmlowp_output_stage != NONE * - * @param[in] a First input tensor (Matrix A). Data type supported: QASYMM8. + * @param[in] a First input tensor (Matrix A). Data type supported: QASYMM8/QASYMM8_SIGNED. * @param[in] b Second input tensor (Matrix B). Data type supported: same as @p a * @param[in] c Third input tensor (Matrix C). It can be a nullptr. Data type supported: S32 - * @param[out] output Output tensor. Data type supported: S32 or QASYMM8 if gemm_info.gemmlowp_output_stage != NONE + * @param[out] output Output tensor. Data type supported: S32 or QASYMM8/QASYMM8_SIGNED if gemm_info.gemmlowp_output_stage != NONE * @param[in] gemm_info (Optional) Specifies if the matrix A and/or matrix B have been reshaped and * if the reshape of matrix B should be executed only for the first run */ @@ -89,7 +89,7 @@ public: * @param[in] a First input tensor info (Matrix A). Data type supported: QASYMM8. * @param[in] b Second input tensor info (Matrix B). Data type supported: same as @p a * @param[in] c Third input tensor info (Matrix C). It can be a nullptr. Data type supported: S32 - * @param[in] output Output tensor info. Data type supported: S32 or QASYMM8 if gemm_info.gemmlowp_output_stage != NONE + * @param[in] output Output tensor info. Data type supported: S32 or QASYMM8/QASYMM8_SIGNED if gemm_info.gemmlowp_output_stage != NONE * @param[in] gemm_info (Optional) Specifies if the matrix A and/or matrix B have been reshaped and * if the reshape of matrix B should be executed only for the first run * |