From 0c17aa25a4f7bc812707150b91930f0cf8e75294 Mon Sep 17 00:00:00 2001 From: Gian Marco Iodice Date: Fri, 27 Sep 2019 09:23:15 +0100 Subject: COMPMID-2571: Add mixed-precision support in CLGEMMReshaped for FP16 Change-Id: I5ba90d4de4594ed784c7230aa6b10503be67c001 Signed-off-by: Gian Marco Iodice Reviewed-on: https://review.mlplatform.org/c/1991 Tested-by: Arm Jenkins Reviewed-by: Georgios Pinitas Comments-Addressed: Arm Jenkins --- arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arm_compute') 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 @@ -50,6 +50,10 @@ public: /** Allow instances of this class to be moved */ 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 -- cgit v1.2.1