diff options
| author | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2017-06-23 13:38:14 +0100 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-09-17 14:15:39 +0100 |
| commit | 3a3066bf2b35deee0f29403d1a1b15590e4860c5 (patch) | |
| tree | 814213532cb5b9bf90d427fb62d4860251bcfc1b /arm_compute/core/CL | |
| parent | 94450f1fc91a89778354c2e1c07a328ba86d9cfc (diff) | |
| download | ComputeLibrary-3a3066bf2b35deee0f29403d1a1b15590e4860c5.tar.gz | |
COMPMID-411 - Port CLGEMM to support 8 bit fixed point
Change-Id: I6c8bd69ae9715e4d83d128b2162fc15aa5561afb
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/78804
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Moritz Pflanzer <moritz.pflanzer@arm.com>
Diffstat (limited to 'arm_compute/core/CL')
| -rw-r--r-- | arm_compute/core/CL/kernels/CLGEMMMatrixAdditionKernel.h | 2 | ||||
| -rw-r--r-- | arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h | 2 |
2 files changed, 2 insertions, 2 deletions
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixAdditionKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixAdditionKernel.h index c808039567..b3a85a1706 100644 --- a/arm_compute/core/CL/kernels/CLGEMMMatrixAdditionKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMMatrixAdditionKernel.h @@ -52,7 +52,7 @@ public: * * @note The input and output tensors must have the same dimensions * - * @param[in] input Input tensor (Matrix C). Data types supported: F16/F32 + * @param[in] input Input tensor (Matrix C). Data types supported: QS8/F16/F32 * @param[in, out] output Output tensor. If this kernel is used to finalize the GEMM result (alpha * AB + beta * C), output must contain the result obtained by @ref CLGEMMMatrixMultiplyKernel. Data type supported: same as @p input * @param[in] beta Weight of matrix C */ diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h index 07ea3c12ac..7625358b8b 100644 --- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h @@ -53,7 +53,7 @@ public: CLGEMMMatrixMultiplyKernel &operator=(CLGEMMMatrixMultiplyKernel &&) = default; /** Initialise the kernel's input, output and alpha * - * @param[in] input0 Input tensor containing the interleaved Matrix A or the vector A. Data types supported: F16/F32 + * @param[in] input0 Input tensor containing the interleaved Matrix A or the vector A. Data types supported: QS8/F16/F32 * @param[in] input1 Input tensor containing the transposed Matrix B if the first input tensor A is not a vector. * If the output tensor is a vector, input1 must contain the matrix B not reshaped. 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 |