diff options
| author | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2019-09-24 12:05:06 +0100 |
|---|---|---|
| committer | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2019-09-26 11:44:34 +0000 |
| commit | 05639f6b1ee3dcdd2c7923d0cf3a5d4712bd0071 (patch) | |
| tree | 8bd2f0f2b874ac7347777b40d563506348fff754 /arm_compute | |
| parent | 1a569a30a2f456ff1a3e0a665201e1c3ab92df80 (diff) | |
| download | ComputeLibrary-05639f6b1ee3dcdd2c7923d0cf3a5d4712bd0071.tar.gz | |
COMPMID-2571: Add support for FP16 in CLGEMMReshaped - part 1
Change-Id: I8adb8850cc5ade49ebc1dbf63401f03d5ecad708
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1983
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/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.h | 2 | ||||
| -rw-r--r-- | arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h | 4 |
2 files changed, 4 insertions, 2 deletions
diff --git a/arm_compute/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.h b/arm_compute/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.h index a0aae190e8..3ce2776bce 100644 --- a/arm_compute/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.h +++ b/arm_compute/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.h @@ -54,6 +54,8 @@ public: private: std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G7x_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b); std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G76_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b); + std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G7x_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b); + std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G76_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b); std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G7x_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b); std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G76_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b); }; diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h index 2a76f44284..e6469f0370 100644 --- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h @@ -51,7 +51,7 @@ public: CLGEMMMatrixMultiplyReshapedKernel &operator=(CLGEMMMatrixMultiplyReshapedKernel &&) = default; /** Initialise the kernel's input and output. * - * @param[in] input0 Input tensor containing the LHS reshaped matrix. Data type supported: F32. The number of dimensions for the LHS matrix must be less or equal than 4 + * @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. * @param[out] output Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0 @@ -74,7 +74,7 @@ public: const GEMMKernelInfo &gemm_info); /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMMatrixMultiplyReshapedKernel * - * @param[in] input0 Input tensor containing the LHS reshaped matrix. Data type supported: F32. The number of dimensions for the LHS matrix must be less or equal than 4 + * @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 info containing the bias matrix. Data type supported: same as @p input0. * @param[in] output Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0 |