diff options
| author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2021-06-21 14:45:44 +0100 |
|---|---|---|
| committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2021-06-29 15:58:33 +0000 |
| commit | 53832b2bcce44c71fe31a618a81765294df55750 (patch) | |
| tree | 2165c4703891202186df55b772353bab8606315d /src/core/cpu/kernels/CpuGemmMatrixAdditionKernel.h | |
| parent | 72b56875b9bb30a9ed1d2ad38ec51fc88e435c35 (diff) | |
| download | ComputeLibrary-53832b2bcce44c71fe31a618a81765294df55750.tar.gz | |
Port NEGEMM to memory injecting interface (Part 2)
- Port NEGEMMMatrixMultiplyKernel to the new API
Partially resolves: COMPMID-4402
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Change-Id: I52b67055dc24bb3a417d6ec5aeeee86e21b74320
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5873
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/cpu/kernels/CpuGemmMatrixAdditionKernel.h')
| -rw-r--r-- | src/core/cpu/kernels/CpuGemmMatrixAdditionKernel.h | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/src/core/cpu/kernels/CpuGemmMatrixAdditionKernel.h b/src/core/cpu/kernels/CpuGemmMatrixAdditionKernel.h index 216e61b5d5..c8e6fa9589 100644 --- a/src/core/cpu/kernels/CpuGemmMatrixAdditionKernel.h +++ b/src/core/cpu/kernels/CpuGemmMatrixAdditionKernel.h @@ -38,7 +38,7 @@ namespace kernels * @note [ MTX_OUT = MTX_0 + beta * MTX_1 ] with MTX_0 and MTX_1 of the same size * * @note This stage is used to finalize the GEMM result and it is computed if and only if beta != 0.0. In case this kernel is used for finalizing GEMM result, we have: - * - MTX_0 = A * B * alpha, where MTX_0 is the output of @ref NEGEMMMatrixMultiplyKernel + * - MTX_0 = A * B * alpha, where MTX_0 is the output of @ref CpuGemmMatrixMultiplyKernel * - MTX_1 = C */ class CpuGemmMatrixAdditionKernel : public ICpuKernel @@ -52,7 +52,7 @@ public: * @note The input and output tensor must have the same dimensions * * @param[in] src Input tensor info (Matrix C). Data types supported: F16/F32 - * @param[in, out] dst Output tensor info. If this kernel is used to finalize the GEMM result, output contains the result obtained by the kernel @ref NEGEMMMatrixMultiplyKernel. Data type supported: the same as @p src. + * @param[in, out] dst Output tensor info. If this kernel is used to finalize the GEMM result, output contains the result obtained by the kernel @ref CpuGemmMatrixMultiplyKernel. Data type supported: the same as @p src. * @param[in] beta Weight of matrix C */ void configure(const ITensorInfo *src, ITensorInfo *dst, float beta); |