diff options
author | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2019-09-27 09:23:15 +0100 |
---|---|---|
committer | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2019-09-30 08:28:43 +0000 |
commit | 0c17aa25a4f7bc812707150b91930f0cf8e75294 (patch) | |
tree | 29088e00bd7ba443dc122ad3436b0a4ef369a102 /arm_compute | |
parent | 40958adf8bad8fd9fefe591ee55a381f7bbb6fea (diff) | |
download | ComputeLibrary-0c17aa25a4f7bc812707150b91930f0cf8e75294.tar.gz |
COMPMID-2571: Add mixed-precision support in CLGEMMReshaped for FP16
Change-Id: I5ba90d4de4594ed784c7230aa6b10503be67c001
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1991
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute')
-rw-r--r-- | arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h index e6469f0370..d3c54a76c8 100644 --- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h @@ -51,6 +51,10 @@ public: CLGEMMMatrixMultiplyReshapedKernel &operator=(CLGEMMMatrixMultiplyReshapedKernel &&) = default; /** Initialise the kernel's input and output. * + * @note The F16 computation also supports mixed precision through the gemm_info.fp_mixed_precision flag. + * Mixed precision combines different floating precisions during the computation, in particular, F32 for the accumulations and F16 for the + * multiplications. i.e. float c = (half)a * (half)b + * * @param[in] input0 Input tensor containing the LHS reshaped matrix. Data type supported: F16/F32. The number of dimensions for the LHS matrix must be less or equal than 4 * @param[in] input1 Input tensor containing the RHS reshaped matrix. Data type supported: same as @p input0. The number of dimensions for the RHS matrix must be less or equal than 3 * @param[in] input2 Input tensor containing the bias matrix. Data type supported: same as @p input0. |