diff options
author | Pablo Tello <pablo.tello@arm.com> | 2017-11-02 16:09:35 +0000 |
---|---|---|
committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:35:24 +0000 |
commit | 6ff12a0f7765f62b8d0fa8554021e1cac2789f19 (patch) | |
tree | 9338db697789106b49ea391634be8b3c08ef9f97 /arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h | |
parent | 97988a4b3ef0f840432daf95b6e4b2ad7e5feefd (diff) | |
download | ComputeLibrary-6ff12a0f7765f62b8d0fa8554021e1cac2789f19.tar.gz |
COMPMID-662: Integrated the new a64_s8_gemm_12x8 + dot product kernel into ACL.
Change-Id: Id8f919e486a132fc58346c9f84fccbeeb83d19b3
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/94233
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Diffstat (limited to 'arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h')
-rw-r--r-- | arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h b/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h index 670274b8f3..f145eb6ca3 100644 --- a/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h +++ b/arm_compute/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.h @@ -35,8 +35,8 @@ class ITensor; * @note @ref NEGEMMLowpMatrixMultiplyKernel low precision matrix product kernel * This kernel performs the following computation: * - * -# Convert a values from uint8 to int32 - * -# Convert b values from uint8 to int32 + * -# Convert a values from int8 to int32 + * -# Convert b values from int8 to int32 * -# Compute the int32 matrix product of the resulting a * b and store the result as int32 * */ @@ -58,7 +58,7 @@ public: * The input matrices @p input0 and @p input1 must be the output of the kernels: @ref NEGEMMInterleave4x4Kernel and @ref NEGEMMTranspose1xWKernel. These two * kernels change the layout of the original matrices to be more cache-friendly. * - * @param[in] input0 Input tensor containing the interleaved Matrix A. Data type supported: U8 + * @param[in] input0 Input tensor containing the interleaved Matrix A. Data type supported: S8 * @param[in] input1 Input tensor containing the transposed Matrix B. Data type supported: same as @p input0 * @param[out] output Output tensor to store the result of matrix multiplication. Data type supported: S32 */ @@ -74,4 +74,4 @@ private: bool _slide_matrix_b; }; } // namespace arm_compute -#endif /*__ARM_COMPUTE_NEGEMMLOWPMATRIXMULTIPLYKERNEL_H__*/
\ No newline at end of file +#endif /*__ARM_COMPUTE_NEGEMMLOWPMATRIXMULTIPLYKERNEL_H__*/ |