The Khronos OpenCL working group recently created a new Tooling Subgroup with the aim of improving the tools ecosystem for this widely-used open standard for heterogeneous computation—in particular, boosting the development of tooling components that can be shared by multiple vendors. Subgroup members have been meeting regularly to coordinate the overall direction for OpenCL tools, with an emphasis on strengthening the development of tools in open source, particularly by encouraging collaboration between the OpenCL and LLVM communities.
The 2018 X.Org Developer’s Conference (XDC2018) videos have now been posted online. XCD 2018 saw many Khronos members sponsor this conference, including Igalia, AMD, Arm, COLLABORA, Google, NVIDIA, Intel and Valve. The talks covered Vulkan, OpenGL, OpenGL ES, OpenCL, SPIR-V, GLSL and OpenXR. We’ve compiled a list of all the videos discussing these Khronos standards here, or you can watch all the videos from the conference on the X.Org Foundation YouTube channel.
Khronos has released a provisional Vulkan Memory Model Specification that includes extensions for Vulkan, SPIR-V, and GLSL and gives Vulkan developers additional control over how their shaders synchronize access to should cooperate safely over memory operations in a parallel execution environment. In tandem with the extension specification, Khronos has released memory model extension conformance tests to enable implementers to do early tests on their shader compilers to ensure that the specified memory synchronization is implemented correctly. The memory model will have an Alloy description of the extension functionality to enable formal modeling and experimentation.
LunarG has updated its white paper that describes using spirv-opt to reduce SPIR-V size. New discussions include using spirv-opt to “legalize” SPIR-V when generated from HLSL; SPIR-V integration with the glslang and dxc frontends; description of new size reduction passes available in spirv-opt; and updates to the recommended recipe for those who wish to customize their optimization.