Getting Started – Software and Hardware
If you are interested in getting started with OpenCL™ and heterogeneous computing but are wondering what kind of hardware and software you need, here are our couple of suggestions to help get you started.
The following list describes software tools we suggest to help you get started with heterogeneous programming.
AMD APP SDK
The AMD APP SDK includes almost 60 OpenCL™ sample applications to help demonstrate how to implement various popular algorithms in OpenCL™. It also includes the AMD APP Profiler, which is a Microsoft® Visual Studio® integrated runtime profiler that gathers performance data from the GPU as your application runs. This information can then be used by developers to discover where the bottlenecks are in their OpenCL™ application and find ways to optimize their application’s performance.
AMD APP KernelAnalyzer
The AMD APP KernelAnalyzer (SKA) which is a tool for statically analyzing the performance of OpenCL™ C kernels. SKA will compile down your OpenCL™ C kernels into the actual instructions used to program the GPU. It then performs a static analysis of the instruction stream and is able to report back to the developer a variety of information, including register usage, ALU utilization and memory contention, all without having to run the application on actual hardware.
AMD CodeAnalyst Performance Analyzer with OpenCL Support
AMD CodeAnalyst for Windows now has OpenCL support. Collect and analyze the OpenCL™ API execution performance from both CPUs and GPUs. Use the detailed lists to find calls of interest and use the timeline to understand the entire execution or drill down to the smallest API call details.
AMD gDebugger is an OpenCL™ and OpenGL debugger and memory analyzer integrated into Microsoft® Visual Studio®. gDEBugger offers real-time OpenCL kernel debugging, which allows developers to step into the kernel execution directly from the API call that issues it, debug inside the kernel, view all variable values across the different work groups and work items – and all this on a single computer with a single GPU.
We suggest the following minimal AMD hardware configurations.