Tools
OpenCL
AMD CodeXL is a comprehensive tool suite that enables developers to harness the benefits of AMD CPUs, GPUs and APUs.
OpenCL
APP KernelAnalyzer is a static analysis tool used to compile, analyze and disassemble an OpenCL™ kernel for AMD Radeon™ GPUs.
Direct Compute | OpenCL
APP Profiler is a performance analysis tool that gathers data from the OpenCL™ run-time and AMD Radeon™ GPUs during the execution of an OpenCL™ application. You can use this data to discover bottlenecks and find ways to optimize the application’s performance for AMD platforms.
C/C++ | Fortran | Java | OpenCL | .Net
CodeAnalyst is a profiling tool that improves the performance of games and media-oriented applications, transaction processing, and high performance scientific/engineering computation on AMD & Intel processors.
OpenCL | OpenGL
gDEBugger is an OpenCL™ and OpenGL debugger and memory analyzer. This tool collects information about OpenCL™ & OpenGL API usage and allows OpenCL™ kernel debugging by stepping through the source code and setting source code breakpoints. For API-level debugging and memory analysis, gDEBuggers works with any CPU, GPU or APU (including non-AMD hardware). For OpenCL(TM) kernel debugging, this tool supports Radeon(TM) HD 5xxx or newer AMD GPUs while any AMD APUs are supported as long as the debugging is done on the GPU device in the APU.
SDKs
OpenCL | Visual Studio
The APP SDK is a complete development platform to allow you to quickly and easily develop applications that are accelerated using OpenCL™. This SDK works with AMD heterogeneous computing technologies (AMD APUs or GPUs).
Libraries
Java | OpenCL
This API converts Java bytecode to OpenCL at runtime and executes it on the GPU. If Aparapi can’t execute on the GPU, it will execute in a Java thread pool.
OpenCL
These math libraries contain FFT and BLAS functions. They primarily target AMD GPUs & APUs but support CPUs as well to facilitate debugging and heterogeneous programming.
OpenCL | C++ AMP
Bolt provides an STL compatible library of high level constructs for creating accelerated data parallel applications. The Bolt Beta includes an array of Bolt capabilities by including support for common compute-optimized routines including sort, scan, transform, and reduce operations. In its open-source debut, Bolt supports C++ AMP in addition to OpenCL™ as underlying supported compute technologies.
DirectX | OpenGL | OpenCL
GPUPerfAPI is a library that can be integrated directly into your own graphics or compute application for accessing GPU performance counters. It requires AMD Radeon™ HDseries graphic cards.
So all in all the announcement of AMD’s CodeXL tool is a major step forward for AMD’s software developer initiatives. CodeXL brings the CPU side andGPU side of AMD hardware base under the same roof for the purposes of code profiling and debugging, anddoes it in a multi-platform conscious manner. To AMD’s credit, in the year since the inaugural AFDS,they’ve really started to build a truly meaningful software ecosystem around their APUs; and CodeXL isanother integral part of that initiative.
– Thomas Ryan
SemiAccurate
