Based on reader feedback, this weeks OpenCL News roundup now sees the news grouped into sections for easer reading. Thanks to everyone for their feedback. If we missed any news please contact us. News Intel TBB 4.4 (Threading Building Blocks) Update 2 introduces opencl_node which enables OpenCL powered devices to be utilized and coordinated by a flow graph. Video: [...]
This weeks OpenCL News included the following. If we missed anything please contact us. IWOCL 2015 Proceedings now online in the ACM digital Library Paper: Bridging OpenCL and CUDA: A Comparative Analysis and Translation Khronos uploaded the OpenCL ICD loader sources to GitHub to allow for external contributions Article: Using OpenCL 2.0 Read-Write Images from [...]
Advanced OpenCL Tutorial on May 11th at Stanford University to Kick-off IWOCL 2015 OpenCL Developer Conference Advanced Hands-On OpenCL tutorial helps developers discover the best ways to solving problems in heterogeneous parallel computing Stanford, CA – 21 April 2015. The organisers of IWOCL (“eye-wok-ul”), the International Workshop on OpenCL, today announced that AMD and HP [...]
In his talk at IWOCL 2015, JC Baratault AMD's Senior Business Development Manager - Globlal GPU Computing Code will present on the topic of "Heterogeneous Computing: the rise of open programming frameworks". Abstract: Heterogeneous Computing Code portability and scalability is the next big challenge on the road to Exascale computing. Despite the fact that GPU-based [...]
The Khronos Group, has announced the ratification and public release of the OpenCL 2.1 provisional specification. OpenCL 2.1 defines a new kernel language based on a subset of C++ for significantly enhanced programmer productivity, and support for the new Khronos SPIR-V cross-API shader program intermediate language now used by both OpenCL and the new Vulkan [...]
OpenCL provides an open, portable C-based programming model for highly parallel processors. In contrast to NVIDIA's proprietary programming API CUDA, a primary goal of OpenCL is portability across a diverse set of computing devices including CPUs, GPUs, and other accelerators. Topics covered will include: Introduction to vectorization Programming model OpenCL Datatypes and OpenCL vectorization features [...]
We recently spotted that the sessions for next years NVIDIA GPU Technology Conference are now being put online with several papers featuring OpenCL. The list of sessions is still being updated on the GTC website but so far we have seen the following 'explicitly' call out OpenCL. S5428: Adaptive OpenCL Libraries for Platform Portability (EM Photonics) S5488 [...]
In this paper we introduce IPMACC, a framework for translating OpenACC applications to CUDA or OpenCL. IPMACC is composed of set of translators translating OpenACC for C applications to CUDA or OpenCL. The framework uses the system compiler (e.g. nvcc) for generating final accelerator’s binary. The framework can be used for extending the OpenACC API, [...]
Heterogeneous computing has become a viable option in seeking computing performance, to the side of conventional homogeneous multi-/single-processor approaches. The advantage of heterogeneity is the possibility to choose the best device on the platform for different distinct workloads in the application to gain performance and/or to lower power consumption. The drawback of heterogeneity is the [...]
AMD have released their APP SDK v3.0 Beta for Windows 32/64-bit and Linux which adds support for OpenCL 2.0 and including twenty samples highlighting the new features. The release also includes accelerated libraries such as “Bolt” and the OpenCV (Open Computer Vision) library. This release supports the AMD Catalyst Omega 14.12 driver. For full release details visit: http://developer.amd.com/tools-and-sdks/opencl-zone/amd-accelerated-parallel-processing-app-sdk/ The release information confirms that [...]