OPENCL BENCHMARK HEADLESS DRIVERS
Additionally make sure to download the latest drivers for NVIDIA CUDA and AMD OpenCL.
The Bonaire graphics processor is an average sized chip with a die area of 160 mm² and 2,080 million. Built on the 28 nm process, and based on the Bonaire graphics processor, in its Bonaire PRO GL variant, the card supports DirectX 12. Just add exclusions and extract the miner on to your desktop. The FirePro W5100 was a professional graphics card by AMD, launched on March 31st, 2014. Open-source OpenCL support still sucks for putting it bluntly. This happens with every other crypto currency mining software’s so it’s nothing to worry about. It will be nice dropping the X requirement for compute on Mesa drivers, but I don't think anyone will be running OpenCL compute farms with the open-source drivers in the near future.
OPENCL BENCHMARK HEADLESS PATCH
This patch series attempts to clear that up to work towards having OpenCL headless compute. Right now to gain access to the OpenCL/compute support with the open-source Mesa/Gallium3D drivers, the X.Org Server and XCB are required. The focus of these changes still being reviewed is to allow for headless OpenCL systems, such as common for compute/GPGPU farms. OpenCL is anecdotally much slower than CUDA. I also know that the middle-range GPUs cannot compete with high-range CPUs in double-precision computation - MKL on a 8-core Xeon will be faster than CULA or CUBLAS on an 300 GPU. If you have an OCL 1.2 or 2.x app, you don’t have to worry about OCL 3.0 impacting your backward compatibility.Mesa release manager Emil Velikov published a set of patches recently in what he's working on for render-node-only OpenCL and other code clean-ups. I've seen figures ranging from 2x to 400x. All OpenCL 1.2 apps will run perfectly on an OpenCL 3.0 device and OpenCL 2.x applications will run perfectly on OCL 3.0 devices so long as those devices support the features the app is using.
On the horizon, OpenCL and the 13 Dwarves will likely be released soon, which could be useful for benchmarking purposes. Notable examples include the SHOC benchmark suite and Rodinia. This new approach is modeled on the way Khronos rolled out Vulkan, and OCL 3.0 will be easy for developers to support. Currently there is no set performance benchmarks to test speeds of different frameworks. Each vendor will be able to support specific capabilities that make sense for their hardware, but there are no “one size fits all” restrictions of the sort that led vendors to walk away from the standard in the first place. Other than the core OCL 1.2 capabilities, everything introduced to the standard in OCL 2.x and 3.0 will be optional. The agreement is important in this case because Khronos is a consortium comprised of various member organizations, but it doesn’t wield any power of its own. The reason the new standard is based on OpenCL 1.2 is that this is the last version that everyone agrees contains absolutely necessary functions required to support the full sweep of use-cases for the standard.
OPENCL BENCHMARK HEADLESS DRIVER
All features introduced up to OpenCL 2.2 will remain available for any vendor that wants to write a driver to support them. To be clear, OCL 2.x code and capability won’t be stripped out of the standard, it’ll simply become an optional way to support OCL hardware.