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/runtime/CL/functions/CLGEMM.h | |
| 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/runtime/CL/functions/CLGEMM.h')
| -rw-r--r-- | arm_compute/runtime/CL/functions/CLGEMM.h | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/arm_compute/runtime/CL/functions/CLGEMM.h b/arm_compute/runtime/CL/functions/CLGEMM.h index 043b2b8115..080f497b7b 100644 --- a/arm_compute/runtime/CL/functions/CLGEMM.h +++ b/arm_compute/runtime/CL/functions/CLGEMM.h @@ -36,7 +36,7 @@ namespace arm_compute { class ICLTensor; -/** Basic function to execute GEMM on OpenCL. Data types supported: F32, F16. This function calls the following OpenCL kernels: +/** Basic function to execute GEMM on OpenCL. This function calls the following OpenCL kernels: * * -# @ref CLGEMMInterleave4x4Kernel (if the output tensor is a matrix) * -# @ref CLGEMMTranspose1xWKernel (if the output tensor is a matrix) @@ -53,11 +53,11 @@ public: * * @note GEMM: General Matrix Multiply - [alpha * A * B + beta * C]. * - * @note All tensors must have the same data type. Data types supported: F32, F16 + * @note All tensors must have the same data type. * * @note Whilst the first input tensor can be a vector, the second input tensor must be at least a matrix * - * @param[in] a First input tensor (Matrix or Vector A). Data types supported: F32, F16 + * @param[in] a First input tensor (Matrix or Vector A). Data types supported: QS8/F16/F32 * @param[in] b Second input tensor (Matrix B). Data type supported: same as @p a. * @param[in] c Third input tensor (Matrix C). It can be a nullptr if just the multiplication between @p a and @p b is needed. Data type supported: same as @p a. * @param[out] output Output tensor. Data type supported: same as @p a |