The Khronos Group has loaded some of the slide set from the GDC 2014 sessions online. Included in this uploaded are slides from OpenCL, OpenGL ES, OpenGL Efficiency, OpenGL, OpenVX, SYCL for OpenCL, Volumerics OpenCL RT Graphics and the Khronos Press Briefing. All presentations are also available via Slideshare.
CEVA announced that it has enriched its CEVA-CV computer vision real-time library to include more than 750 functions. New functions added in the latest CEVA-CV release include feature detection kernels and object recognition algorithms such as Harris Corner, Hough Transform, Integral Sum, Fast, LBP, SURF, HOG, SVM, and ORB detection and matching. CEVA-CV now also includes kernels required by The Khronos Group's OpenVX 1.0 specification, which is set to become the key standard for cross-platform acceleration of computer vision applications and libraries.
OpenCL Integrated Performance Primitives (OpenCLIPP) is a library providing processing primitives (image processing primitives in the first version) implemented with OpenCL for fast execution on dedicated computing devices like GPUs. It was designed to be simple to use and to have low overhead. Two interfaces are provided: C Interface similar to the Intel IPP and NVIDIA NPP libraries and C++ Interface. An OpenCL SDK is required to build the library.
OpenCL.NET is a .NET library, providing full API bindings for the OpenCL standard. Using GPU acceleration and OpenCL.NET, it is possible to achieve great performance in .NET based applications. CLFORTRAN aims to simplify integration of GPU resources for scientific computing in various fields of science that heavily relies on Fortran codes.
BuildAR announced their latest release that shows a rich location based Augmented Reality application running in a standard mobile web browser using WebGL. This is built using the open source awe.js library.
OpenTK is a fast, low-level C# library that wraps OpenGL, OpenCL. The latest version adds strongly-typed enums for OpenGL 4.4 and OpenGL ES 3.0, and improves platform support via a brand-new SDL2 backend. Use it standalone or inside a UI on every major platform.
The AMD CodeXL 1.3 release which includes many updates including remote GPU profiling and debugging. Bolt, an STL compatible C++ template library for creating data-parallel applications using C++ (no C++ AMP / OpenCL code required) has also been updated. AMD APP SDK has also been updated to v2.9. APP SDK 2.9 now includes 2 new features which are currently in Beta.
PoCL is aiming at becoming an efficient open source (MIT-licensed) implementation of the OpenCL 1.2 (and soon OpenCL 2.0) standard. This release adds support for LLVM/Clang 3.3, employs inner loop parallelization in the kernel compiler, uses Vecmathlib for inlineable efficient math library implementations, contains plenty of bug fixes, and provides several new OpenCL API implementations.
The AMD library team has spent the last three years working on APPML – the Accelerated Parallel Processing Math Library. APPML contains an OpenCL implementation of BLAS and FFT routines. The library enables developers to accelerate common scientific and engineering computations on APUs and discrete graphics accelerators.
Version 2 adds support for ETC2 and EAC textures and conversion of legacy LUMINANCE* and INTENSITY* formats when loading in an OpenGL core context. It includes KTX loader tests for OpenGL ES 3.0 and OpenGL 3.3. In addition a couple of nasty bugs have been fixed including one in the KTX writer where image rows were not padded to 4 bytes as required by the spec. Complete details of the changes are located in the OpenGL ES SDK. A new version of toktx has also been released. New features are ability to create KTX files with textures in sized internal formats and defaulting to RED and RG formats for 1 and 2 channel textures. Naturally it incorporates the bug-fixed writer from libktx. Visit the KTX home page to download these tools.
Virtual OpenCL (VCL) is a cluster platform that allows unmodified OpenCL applications to transparently utilize many OpenCL devices in a cluster, as if all the devices are on the local computer. The latest update includes one security fix, bug fixes and the addition of SuperCL special registry, allowing SuperCL programs to read the time in nano-seconds.
JavaCL 1.0.0-RC3 was just released and brings lots of bugfixes, massive performance improvements and preliminary OSGi support. This BSD-licensed library gives Java developer all the power of OpenCL, with just a single cross-platform JAR to put in their classpath (no native libraries headache). The release notes and JavaCL download are available online.