AMD today released its first drivers to implement Microsoft's DirectX Agility SDK version 1.613, which introduces the new DirectX 12 Work Graphs 1.0 API. AMD has extensively worked on implementing the new technology, which among other things, significantly reduces the CPU's role in most common shader graphics workloads, and improve GPU shader thread saturation, as the GPU waits less on the CPU's share of shader workloads. The new AMD Software Adrenalin 23.40.14.01 drivers are off the main driver update channel, and is intended for developers and enthusiasts to start exploring GPU Work Graphs. GPU Upload Heaps, and certain features of Shader Model 6.8 on supported AMD Radeon GPUs. There are some known issues with the driver specific to AMD's implementation of GPU Work Graphs, and the latest version of the Agility SDK in general, which are listed below.

DOWNLOAD: AMD Software Adrenalin 23.40.14.01 for Agility SDK Support

Microsoft has implemented two new features into its DirectX 12 API - GPU Upload Heaps and Non-Normalized sampling have been added via the latest Agility SDK 1.710.0 preview, and the former looks to be the more intriguing of the pair. The SDK preview is only accessible to developers at the present time, since its official introduction on Friday 31 March. Support has also been initiated via the latest graphics drivers issued by NVIDIA, Intel, and AMD. The Microsoft team has this to say about the preview version of GPU upload heaps feature in DirectX 12: "Historically a GPU's VRAM was inaccessible to the CPU, forcing programs to have to copy large amounts of data to the GPU via the PCI bus. Most modern GPUs have introduced VRAM resizable base address register (BAR) enabling Windows to manage the GPU VRAM in WDDM 2.0 or later."

They continue to describe how the update allows the CPU to gain access to the pool of VRAM on the connected graphics card: "With the VRAM being managed by Windows, D3D now exposes the heap memory access directly to the CPU! This allows both the CPU and GPU to directly access the memory simultaneously, removing the need to copy data from the CPU to the GPU increasing performance in certain scenarios." This GPU optimization could offer many benefits in the context of computer games, since memory requirements continue to grow in line with an increase in visual sophistication and complexity.