From b0c5037d94ba7073ccabb0ebaff54db320f184c4 Mon Sep 17 00:00:00 2001 From: Gian Marco Iodice Date: Fri, 15 Mar 2019 10:13:05 +0000 Subject: COMPMID-2043: Add support for "dummy threads" in CLGEMMReshaped Change-Id: I89403b97503fbb99f6a32f5d62b8c535ab26a7be Signed-off-by: Gian Marco Iodice Reviewed-on: https://review.mlplatform.org/c/877 Reviewed-by: Michele Di Giorgio Tested-by: Arm Jenkins Reviewed-by: Georgios Pinitas Comments-Addressed: Arm Jenkins --- arm_compute/core/CL/ICLKernel.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'arm_compute/core/CL/ICLKernel.h') diff --git a/arm_compute/core/CL/ICLKernel.h b/arm_compute/core/CL/ICLKernel.h index f5423584e1..590f8929cb 100644 --- a/arm_compute/core/CL/ICLKernel.h +++ b/arm_compute/core/CL/ICLKernel.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2016-2018 ARM Limited. + * Copyright (c) 2016-2019 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -308,14 +308,16 @@ private: * * @note If kernel->kernel() is empty then the function will return without adding anything to the queue. * - * @param[in,out] queue OpenCL command queue. - * @param[in] kernel Kernel to enqueue - * @param[in] window Window the kernel has to process. - * @param[in] lws_hint Local workgroup size requested. Default is based on the device target. + * @param[in,out] queue OpenCL command queue. + * @param[in] kernel Kernel to enqueue + * @param[in] window Window the kernel has to process. + * @param[in] lws_hint (Optional) Local workgroup size requested. Default is based on the device target. + * @param[in] use_dummy_work_items (Optional) Use dummy work items in order to have two dimensional power of two NDRange. Default is false + * Note: it is kernel responsibility to check if the work-item is out-of-range * * @note If any dimension of the lws is greater than the global workgroup size then no lws will be passed. */ -void enqueue(cl::CommandQueue &queue, ICLKernel &kernel, const Window &window, const cl::NDRange &lws_hint = CLKernelLibrary::get().default_ndrange()); +void enqueue(cl::CommandQueue &queue, ICLKernel &kernel, const Window &window, const cl::NDRange &lws_hint = CLKernelLibrary::get().default_ndrange(), bool use_dummy_work_items = false); /** Add the passed array's parameters to the object's kernel's arguments starting from the index idx. * -- cgit v1.2.1