aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.h
diff options
context:
space:
mode:
authorManuel Bottini <manuel.bottini@arm.com>2020-04-08 10:15:51 +0100
committerManuel Bottini <manuel.bottini@arm.com>2020-04-17 14:10:38 +0000
commit4c6bd514a8d424a29b776754f1b3426fa3a8c339 (patch)
treeed20ea238ae069ab138b62ea6879e0c1b955b606 /arm_compute/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.h
parentd2f6d96cdc2ad2169c4abd0a8c4884f61ed6d186 (diff)
downloadComputeLibrary-4c6bd514a8d424a29b776754f1b3426fa3a8c339.tar.gz
COMPMID-3280: Make all ML primitives for CL use the new interface - Part 1
- Only CLKernels have been updated Change-Id: Ife55b847c2e39e712a186eb6ca452503d5b66937 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3001 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.h')
-rw-r--r--arm_compute/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.h23
1 files changed, 23 insertions, 0 deletions
diff --git a/arm_compute/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.h b/arm_compute/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.h
index 4094bc681e..02ed20e5af 100644
--- a/arm_compute/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.h
@@ -71,6 +71,29 @@ public:
*/
void configure(const ICLTensor *mm_result, const ICLTensor *vector_sum_col, const ICLTensor *vector_sum_row, const ICLTensor *bias, ICLTensor *output, int32_t k, int32_t a_offset, int32_t b_offset,
const GEMMLowpOutputStageInfo &output_stage, const ICLTensor *output_multipliers, const ICLTensor *output_shifts);
+ /** Initialise the kernel's input and output.
+ *
+ * @param[in] compile_context The compile context to be used.
+ * @param[in] mm_result Input tensor containing the result of @ref CLGEMMLowpMatrixMultiplyKernel. Data type supported: S32
+ * @param[in] vector_sum_col Input row-vector of sums of all the entries in each column of matrix B.
+ * Note: vector_sum_col can be a nullptr in case a_offset = 0. Data type supported: same as @p mm_result
+ * @param[in] vector_sum_row Input row-vector of sums of all the entries in each row of matrix A.
+ * Note: vector_sum_row can be a nullptr in case b_offset = 0. Data type supported: same as @p mm_result
+ * @param[in] bias Biases tensor. Only shared biases supported and it can be a nullptr if the addition of biases is not required.
+ * Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p input.
+ * @param[out] output Output tensor. Data type supported: QASYMM8/QASYMM8_SIGNED.
+ * @param[in] k Number of matrix A columns or Matrix B rows
+ * @param[in] a_offset Offset to be added to each element of the matrix A.
+ * @param[in] b_offset Offset to be added to each element of the matrix B.
+ * @param[in] output_stage GEMMLowp output stage info
+ * @param[in] output_multipliers Output multipliers tensor. In case of per-channel quantization, the number of multipliers must be equal to the number of filters (OFM).
+ * Supported data types: S32
+ * @param[in] output_shifts Output shifts tensor. In case of per-channel quantization, the number of multipliers must be equal to the number of filters (OFM).
+ * Supported data types: S32
+ */
+ void configure(CLCompileContext &compile_context, const ICLTensor *mm_result, const ICLTensor *vector_sum_col, const ICLTensor *vector_sum_row, const ICLTensor *bias, ICLTensor *output, int32_t k,
+ int32_t a_offset, int32_t b_offset,
+ const GEMMLowpOutputStageInfo &output_stage, const ICLTensor *output_multipliers, const ICLTensor *output_shifts);
/** Static function to check if given info will lead to a valid configuration of @ref CLGEMMLowpOffsetContributionKernel
*
* @param[in] mm_result Input tensor containing the result of @ref CLGEMMLowpOffsetContributionKernel. Data type supported: S32