An executive from Advanced Micro Devices said that while both ATI, graphics product group of AMD, as well as Nvidia Corp. have been talking about general purpose computing on graphics processing units (GPGPU) for years, the capability will only become popular sometime after 2010, when more advanced compilers become available and after Microsoft releases its DirectX 11 in 2009.
Even though graphics processing units (GPUs) pack much more computing power than traditional central processing units (CPUs), in order to take advantage that performance, software must be specifically tailored for GPUs. As a result, only some programs can benefit from increased processing horse power of GPUs now due to the virtual absence of tools that help software developers to create programs that rely on GPUs. However, this is going to change in three years, said Giuseppe Amato, sales & marketing technical director at AMD in EMEA region. In fact, besides tools that help to develop GPGPU software, the world"s second largest maker of x86 processors also expects the emerge of special real-time compilers (akin to those used in drivers for GPUs nowadays) that will be able to choose whether to compute on a CPU or a GPU cores.