From 89aa4eb56d56c81a9d53f94dffa5fa88742e986c Mon Sep 17 00:00:00 2001 From: ramelg01 Date: Tue, 8 Feb 2022 23:01:31 +0000 Subject: Improve start-up time for concatenation layers - pass tensor's dimensions at runtime rather than compile time - Add guard macro to compile only kernel of internest Resolves: COMPMID-5121 Signed-off-by: Ramy Elgammal Change-Id: I76b7c0cf56d803f58ebff5494c904ace2a86ef5a Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7097 Tested-by: Arm Jenkins Reviewed-by: Gian Marco Iodice Comments-Addressed: Arm Jenkins --- src/gpu/cl/kernels/ClWidthConcatenate4TensorsKernel.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'src/gpu/cl/kernels/ClWidthConcatenate4TensorsKernel.h') diff --git a/src/gpu/cl/kernels/ClWidthConcatenate4TensorsKernel.h b/src/gpu/cl/kernels/ClWidthConcatenate4TensorsKernel.h index 80afb3b85d..baf8d381be 100644 --- a/src/gpu/cl/kernels/ClWidthConcatenate4TensorsKernel.h +++ b/src/gpu/cl/kernels/ClWidthConcatenate4TensorsKernel.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2021 Arm Limited. + * Copyright (c) 2021-2022 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -63,6 +63,12 @@ public: // Inherited methods overridden: void run_op(ITensorPack &tensors, const Window &window, ::cl::CommandQueue &queue) override; + +private: + int32_t _depth{ 0 }; + int32_t _input1_width{ 0 }; + int32_t _input2_width{ 0 }; + int32_t _input3_width{ 0 }; }; } // namespace kernels } // namespace opencl -- cgit v1.2.1