The advantages of SVM will be showcased with the help of samples.Ģ. There are number of new API calls added to OpenCL 2.0 specification, which were designed to support this new feature and to perform the above mentioned tasks. We will discuss ways of SVM buffer allocation, how SVM buffers interact with devices, synchronizations methods and ways to maintain memory consistency. SVM enhances programming experience and improves performance. Shared Virtual Memory provides the capability to create SVM buffers (coarse-grained and fine-grained) and sharing pointers between host and device without the need to create device memory objects and eliminating the need to perform data copying between the device and the host. We are going to cover the following features of OpenCL 2.0 supported in our released driver:ġ. We are going to talk about the things we have learned in the past year developing workloads for OpenCL 2.0 and speedups achieved over comparable OpenCL 1.2 implementations. To calculate the FPS, I measure only the time to process the image (without the time to acquire the image, without the time to display the image).OpenCL 2.0 is here, supported for the first time on the 5th Generation Intel ® Core Processors with Intel ® Processor Graphics. setUseOpenCL(true): ~200 FPS ~15% for CPU load ~setUseOpenCL(false): ~24 FPS ~8% for CPU load.I manage to have with this configuration coherent results: I retried with this time OpenCV 3.0.0 from master (as of ) and I built it with VS2010, 64 bits, release mode and without IPP. to set the GPU device: add the environment variable OPENCV_OPENCL_DEVICE with for example: :GPU:1.
#OPENCL BENCHMARK EXAMPLE WINDOWS#
Windows platform + Visual Studio 2010 + Release mode.Mine is about 7% when the program is running. GPU version=~70 FPS CPU load=~8% GPU load=~7%Īlso, you can use a program to monitor the GPU load (e.g.My result (pass as an argument 1 to use the OpenCL version, otherwise it is the CPU version): Std::cout << "Times passed in seconds: " << t << " FPS: " << (1/t) << " Average FPS=" << (cpt/total_time) << std::endl Ĭv::imshow("Sobel blurred Frame", blurredSobel) T = ((double) cv::getTickCount() - t) / cv::getTickFrequency() Std::cout << "Successfuly connected to camera " << std::endl Ĭv::ocl::oclMat frame_ocl, frameGray_ocl, frameSobelx_ocl, frameSobely_ocl, blurredSobel_ocl Ĭv::ocl::cvtColor(frame_ocl, frameGray_ocl, cv::COLOR_BGR2GRAY) Ĭv::ocl::Sobel(frameGray_ocl, frameSobelx_ocl, frameGray_ocl.depth(), 1, 0, 3) Ĭv::ocl::Sobel(frameGray_ocl, frameSobely_ocl, frameGray_ocl.depth(), 0, 1, 3) Ĭv::ocl::bitwise_or(frameSobelx_ocl, frameSobely_ocl, frameGray_ocl) Ĭv::ocl::blur(frameGray_ocl, blurredSobel_ocl, cv::Size(3,3)) Ĭv::cvtColor(frame, frameGray, cv::COLOR_BGR2GRAY) Ĭv::Sobel(frameGray, frameSobelx, pth(), 1, 0, 3) Ĭv::Sobel(frameGray, frameSobely, pth(), 0, 1, 3) Ĭv::bitwise_or(frameSobelx, frameSobely, frameGray) Ĭv::blur(frameGray, blurredSobel, cv::Size(3,3)) Std::cout << "Problem connecting to cam " << std::endl Std::cout << "use_opencl=" << use_opencl << std::endl
#OPENCL BENCHMARK EXAMPLE CODE#
This is the code I use to test OpenCL with OpenCV 2.4.10: #include I tested also with OpenCV 2.4.10 and it is possible to set the device for OpenCL. I did a quick test with OpenCV 3.0.0 beta and I realised that the OpenCL version used my Intel HD Graphics instead of my NVidia GPU (see my comments). Could anyone please compile and make this test? I'm trying to figure out if this is a hardware problem. how come that with OpenCL the GPU is working at 88% capacity and the CPU is at 150%? And, on top of that? It is slower than the non-GPU version? Without OpenCL: 26 FPS, 98% CPU usage and 5% GPU usage With OpenCL: 21 FPS, 180% CPU usage and 88% GPU usage
#OPENCL BENCHMARK EXAMPLE FREE#
I'm blurring the image multiple times to create a strain on the processor, but feel free to change that part of the code, what is important is the comparison between OpenCL and non-OpenCL versions.ĮDIT: Edited code to correct mistake in FPS calculationĬout << "Frames per second: " << frameCounter << endl I wrote an easy to compile simple code snippet that uses a webcam stream and finds Sobel edges and then blurs image some dozens of times. So I decided to ask you guys to help me benchmarking a piece of code. This is related to a previous question of mine, where I understood that there might not exist many answers about this topic just yet. I am trying to understand the potential of OpenCL module of OpenCV 3.0.0.
0 kommentar(er)
