Add post ops to ClGemmMatrixMultiplyReshapedOnlyRHSKernel and ClGemmMatrixMultiplyNativeKernel Part 3
Partially resolves: COMPMID-4435
Change-Id: Ifc5affa3a24a70942ca2d001380205df09b03ad7
Signed-off-by: SiCongLi <sicong.li@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6550
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/gpu/cl/kernels/ClGemmMatrixMultiplyNativeKernel.h b/src/gpu/cl/kernels/ClGemmMatrixMultiplyNativeKernel.h
index 89837cc..415eb7b 100644
--- a/src/gpu/cl/kernels/ClGemmMatrixMultiplyNativeKernel.h
+++ b/src/gpu/cl/kernels/ClGemmMatrixMultiplyNativeKernel.h
@@ -76,11 +76,12 @@
void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override;
private:
- bool _slide_matrix_b{ true };
- bool _reinterpret_input_as_3d{ false };
- bool _reinterpret_output_as_3d{ false };
- bool _use_dummy_work_items{ false };
- bool _add_bias{ false };
+ bool _slide_matrix_b{ true };
+ bool _reinterpret_input_as_3d{ false };
+ bool _reinterpret_output_as_3d{ false };
+ bool _use_dummy_work_items{ false };
+ bool _add_bias{ false };
+ unsigned int _num_post_op_args{ 0 }; // (EXPERIMENTAL_POST_OPS) total number of post op arguments
};
} // namespace kernels
} // namespace opencl